Maintworld Magazine 2/2025

2/2025 www.maintworld.com
maintenance & asset management
Coaching the Future
of Maintenance p 10
A LONGSTANDING EFNMS PARTNER AND LEADER IN MAINTENANCE INNOVATION page 22 HANNOVER MESSE page 32

EDITORIAL
Maintenance
Has Magnetism!
AS THE NEW EDITOR-IN-
CHIEF, I’ve spent this
spring getting to know the
world of maintenance.
And it’s truly fascinating.
Everyday professionals
ensure that operations
run smoothly in production
plants, on roads, railways,
in ports, and shopping
centres. In factories,
production lines are maintained
and deliver on their
targets without dramatic
interruptions. Roads and
transport routes are functional
and safe, allowing
goods and people to move
reliably. Homes and public spaces are refurbished and maintained to ensure
they remain good places to live and operate.
Ports, rail transport, depots, and airports – the very foundations of our
society – must serve their users 24/7, come calm or storm. Maintenance
stands guard and keeps everything running. It is a cornerstone of supply
security – often invisible, but vital for life and its ongoing pulse.
Maintenance is a critical part of industry, infrastructure, and services.
The expertise of professionals in our field will become even more essential
as new technologies and artificial intelligence become part of everyday life.
These tools will not replace people – on the contrary, they empower us to
do our work better, more efficiently, and more safely.
Today, there are unprecedented opportunities for skilled maintenance
professionals. Demand for our know-how is growing, and the future looks
bright.
There is work in this field – plenty of it, all around the world. Maintenance
never ends: equipment, structures, and processes require constant
care and development. As a field, maintenance is a major employer, offering
diverse career paths for a wide range of talent.
I look forward to inspiring encounters with experts and readers in our
field. Together, we can raise maintenance to the position it deserves and
ensure the sector remains attractive and vibrant well into the future.
The future of maintenance is built on competence – let’s make sure,
together, that the availability of skilled professionals doesn’t become a barrier
to progress. Let’s invest in education in every country – education that
inspires, evolves, and continues to produce highly motivated top talent for
the industry!
Jari Kostiainen
Editor-in-Chief, Maintworld
4 maintworld 2/2025
24
Nordzucker
AG, one of
Europe’s leading sugar
producers, is undergoing a
major digital and cultural
transformation inmaintenance
operations across its
13 European factories.

IN THIS ISSUE 2/2025
10
Maria
Ryytty is not just
managing the future of
industrial maintenance, she’s
coaching it, nurturing it, and
pushing to ensure it serves
both business and humanity.
=
32
Generative
AI is emerging as more than
a technological trend—it’s fast becoming
a strategy for turning the sector’s
fortunes around. This became evident
in a study, conducted by Strategy&
in partnership with VDMA Software
and Digitalization, and presented at
Hannover Messe in March 2025.
4 Editorial
6 News
20
8 Trump’s 360° Trade War
22
10 Coaching the Future of Maintenance
14 The Human Algorithm
24
Building the smart, resource-
16
efficient factories of the future 28
Predictive Maintenance and the Rise
of the Self- Healing Factory
NVDO: A Longstanding
EFNMS Partner and Leader
in Maintenance Innovation
Enhancing Predictive
Maintenance at Nordic Sugar
Rapid Growth in the
Global Industry 5.0 Market
32
Hannover Messe
36
40
42
44
46
50
Kemira's Revolutionary
Approach to Asset Management
The future of rail freight
Industrial Robotics: Trends Defining
the Next Generation
AI-Based Predictive Maintenance
Set to Hit $1.69 Billion by 2030
The Digital Twin Paradox
How Industry 4.0 Revolutionized
Manufacturing and Maintenance
Issued by Finnish Maintenance Society, Promaint, Messuaukio 1, 00520 Helsinki, Finland, tel. +358 50 441 8915, Editor-in-chief
Jari Kostiainen, jari.kostiainen@kunnossapito.fi Advertisements Mika Säilä, +358 50 352 3277, mika.saila@totalmarketing.fi
Layout Sirli Siniväli, sirli.fotod@gmail.com Printed by Savion Kirjapaino Oy Frequency 4 issues per year, ISSN L 1798-7024 (print),
ISSN 1799-8670 (online) Cover photo Stegra.
2/2025 maintworld 5

NEWS
From Confusion to Innovation:
How GreaseTech is Transforming Lubrication
Maintenance in Corrugating Plants
Jesh Ramesh realised during his Master's degree studies that the
tools available to maintenance teams were outdated and inadequate.
He was determined to find a better way.
JESH RAMESH
The Co-Founder and CEO of GreaseTech
Where he combines his deep industry experience with a passion
for innovation to improve plant maintenance processes.
AS A YOUNG engineer at Packaging Corporation of America
(PCA) in Jackson, TN, I was eager to make an impact. One of
my earliest challenges was tackling lubrication Preventative
Maintenance (PM) processes—a critical yet often overlooked
aspect of plant operations. It didn’t take long to realize just how
overwhelming this task was for maintenance teams and how
much room there was for improvement. This experience planted
the seed for what would eventually become GreaseTech.
The Problem: Complexity and Chaos in Lubrication PMs
In the corrugating industry, production often takes priority
over everything else, and PM downtime is consistently
squeezed. This creates significant challenges for maintenance
teams, especially when it comes to lubrication. As I
observed technicians attempting to grease hundreds of bearings
during limited windows of time,
I saw how difficult it was for them to:
• Track every bearing and ensure none were missed.
• Identify the correct lubricant for each specific point.
• Apply the precise amount needed, avoiding under-greasing
or over-greasing.
The situation wasn’t any easier for maintenance managers.
They had no visibility into what work had been completed,
what was skipped, or whether the lubrication was done correctly.
Improper lubrication—a key contributor to nearly 70%
of mechanical failures—was wreaking havoc on operations.
It was clear to me that something had to change.
The Spark of Innovation
Years later, while pursuing my Master’s in Business, Entrepreneurship,
and Technology at the University of Waterloo,
this problem kept nagging at me. I realized that the tools
available to maintenance teams were outdated and inadequate,
and I was determined to find a better way.
That’s when I met Nathan Wong, a brilliant computer science
student at the University of Waterloo. Nathan had been
coding since the age of 11, and his technical expertise was the
Jesurun Ramesh standing with GreaseTech’s smart grease gun.
perfect complement to my industry knowledge. We quickly
realized we shared a passion for solving real-world problems
and started brainstorming how technology could transform
lubrication maintenance. Together, we began developing what
would become GreaseTech.
The GreaseTech Solution
GreaseTech combines cutting-edge hardware and intuitive software
to address the challenges I saw firsthand in the corrugating
industry. Here’s how it works:
1. Automated Tracking: Every lubrication point in the
plant is digitally mapped and tagged. Technicians use a
smart grease gun equipped with sensors to track which
6 maintworld 2/2025

NEWS
points have been serviced, ensuring nothing is overlooked.
2. Lubricant Matching: GreaseTech’s system stores detailed
specifications for every bearing, including the exact
type and amount of lubricant required. This eliminates
the guesswork and reduces mismatches that lead to
equipment failures.
3. Real-Time Visibility: Maintenance managers can access
a centralized dashboard to monitor progress, identify
skipped tasks, and ensure compliance with schedules—all
in real time.
4. Data-Driven Maintenance: Digital records allow plants
to analyze lubrication trends, address recurring issues,
and optimize their PM schedules.
Why It Matters for Corrugating Plants
Corrugating plants operate in high-pressure environments
where unplanned downtime directly impacts production and
profitability. Lubrication PMs, while essential, often take a
backseat to immediate production needs.
GreaseTech bridges this gap by empowering maintenance
teams with tools that ensure efficiency and accuracy.
Bearings are no longer over-greased or under-greased, and
managers gain the insights they need to optimize their operations.
The result? Reduced downtime, fewer equipment
failures, and greater overall reliability.
Building a Vision for the Future
The journey from identifying a problem at PCA to building
a solution at Waterloo has been one of collaboration and
innovation. Nathan and I poured countless hours into understanding
the needs of maintenance teams and designing
a system that truly addresses their pain points. Today, GreaseTech
is helping corrugating plants across North America
improve reliability and simplify lubrication processes.
At GreaseTech, we believe that innovation starts on the
plant floor. My experience at PCA and Nathan’s technical
expertise have allowed us to create a solution that’s not only
practical but transformative. Together, we’re committed to
making the lives of maintenance technicians, planners, and
managers easier—one bearing at a time.
To learn more about GreaseTech and how it can improve
your plant’s lubrication PMs, visit our website or contact us
directly. Let’s redefine reliability, together.
Website and demo video: https://www.greasetech.ca/product
The Forgotten Crisis: Why Industry
and Technical Services Must Act Now
WHILE GLOBAL attention is focused on the conflicts in
Ukraine and Gaza, and the changes in international trade
rules, a crisis is unfolding in the background—one that threatens
the very foundations of our economy and civilization: the
climate crisis.
And this warning no longer comes only from climate activists,
scientists, or politicians. Increasingly, it’s being echoed by
top figures in the financial sector itself. Günther Thallinger,
Chair of the Investment Management Board at Allianz, recently
warned: “The climate crisis is destroying capital and
assets in real time. Entire regions risk becoming uninsurable.
This is a systemic risk that fundamentally threatens our market
economy.”
The increasing frequency of extreme weather, soaring damage
costs, and declining asset values are putting structural pressure
on how markets and businesses operate. Thallinger notes
that many solutions are already available—but they are not being
implemented quickly enough or at a large enough scale.
Untapped Potential for Improvement
Fortunately, change is on the horizon. The shipping industry,
whose global emissions rival those of industrial giants like
Germany or Japan, agreed on April 11 under the IMO Net-Zero
Framework to cut CO₂ emissions by 65% by 2040. Concrete
measures are being introduced, such as a CO₂ tax for those
who fail to meet the targets.
In the industrial sector as well, frontrunners are proving
that major progress is possible. The MORE4Sustainability
project benchmark shows that early adopters have achieved
up to 31% improvement in energy efficiency and 28%
emissions reduction within just a few years.
BEMAS, the Belgian Maintenance Association, recently
awarded the Maintenance & Facility team of Safran Aero
Boosters in Herstal as “Technical Team of the Year” in Wallonia.
Over the past five years, they managed to cut energy use
by 15%—not just through major investments, but also through
smart technical measures. One example: eliminating standby
consumption from idle machines, which used to consume
up to 80% of their energy even when not in use. Today, those
machines are completely shut off at night and on weekends,
resulting in significant ecological and economic gains.
What About Your Technical Team?
Within your own organization, there are huge opportunities
to improve energy efficiency and reduce emissions with relatively
simple actions. Not just to help fight climate change, but
also to stay competitive and financially sound. Be honest: can
your company really afford to consume—and pay for—30%
more energy than your competitors?
The technology exists. The methodology is available. The
best practices are proven. All that’s missing is rapid and widespread
adoption.
The choice is yours. But the time to act is now.
Wim Vancauwenberghe
Maintenance Evangelist and Director of BEMAS
2/2025 maintworld 7

NEWS
Trump’s 360° Trade War:
What Industrial Leaders Need to Know
Uncertainty is the new normal. President Trump’s aggressive tariff strategy is not just
a trade policy—it’s a global shockwave. Companies that move quickly to understand
and manage the macroeconomic impacts will be better prepared to weather the
volatility and protect competitiveness. Those that wait for clarity may fall behind.
ON APRIL 2, 2025 President Trump
enacted a sweeping tariff hike, catapulting
the U.S. average effective
tariff rate to around 23%—a tenfold
increase from the previous
year. The move rattled markets
and injected deep uncertainty
into global trade. For executives
in the industrial sectors,
this shift demands more than
a reactive shrug. It calls for a
strategic rethink of risk, supply
chains, and long-term positioning.
Despite the temporary 90-day
pause on retaliatory tariffs for most
countries, the signal is clear: we’ve
entered a new era of unpredictable trade
policy—what economists from Boston Consulting
Group call a regime of “deliberate uncertainty.”
This isn’t a bilateral dispute—it’s a one-versus-all trade
war. The U.S. has applied tariffs broadly, without targeting specific
countries or industries. In contrast, other nations are only
engaging the U.S. The asymmetry is important: while the U.S.
risks global blowback, its trade partners face disruption only in
their U.S. business. This weakens the U.S.’s negotiating position
and complicates outcomes for global companies trying to plan.
First-Order Effects: Supply and Demand Shocks
1. SUPPLY SHOCKS – MOSTLY SELF-INFLICTED FOR THE U.S.
Tariffs act as a tax on imports, and those costs pass through
to businesses and consumers. For U.S. manufacturers, this
means costlier inputs and squeezed margins. The expected
result: higher inflation, reduced real incomes, slower consumption,
and weaker GDP growth—projected to drop by 1.4%
in 2025.
2. RETALIATORY PAIN – LIMITED BUT REAL FOR OTHERS
If other nations impose counter-tariffs, they too face inflation
and slower growth, though the effect is
smaller—around 0.1 % to 0.3 % GDP
impact—because they’re targeting
only U.S. goods.
3. DEMAND SHOCKS – TRADE
PARTNERS HIT HARDER
Higher U.S. tariffs make it
harder for foreign producers
to sell into the U.S. market.
The impact depends on how
sensitive demand is to price
changes. For most countries, the
hit could range from -0.2 % to -0.6
% of GDP. But for highly exposed
economies like Vietnam, losses may
top 6 %.
4. U.S. EXPORTS FACE HEADWINDS
As other countries respond, American exports
decline. Though the U.S. is less reliant on exports than, say,
Germany or China, the widespread nature of retaliation could
shrink GDP by another 0.5 %.
Trump’s tariff policy seeks to reshore production and
revive U.S. manufacturing. But tariffs are a blunt instrument.
Unlike targeted incentives like the CHIPS Act, which spurred
strategic investments in semiconductors, tariffs affect all
goods, regardless of their economic or strategic value.
The risk? Misallocating resources to low-productivity sectors
like furniture or apparel, which may cannibalize labor
and capital from more advanced industries. With unemployment
already low, the economy doesn't have surplus workers
to absorb new, labor-intensive production. This could drag
down average productivity and hinder long-term growth—a
net loss for the economy.
Trade policy isn’t just a Washington game anymore, it’s a
frontline issue for global business. Managing macro risk, once
a niche skill, is fast becoming essential. Industrial leaders who
invest now in analytical capacity, scenario planning, and supply
chain intelligence will not only endure the current turbulence—
they’ll gain a competitive edge for whatever comes next.
8 maintworld 2/2025

NEWS
Five Hidden Undercurrents Leaders Can’t Ignore
Beyond the immediate economic drag, industrial leaders
should watch for five secondary effects—less predictable, but
equally important.
• Confidence erosion
Consumers and businesses lose faith. Even if confidence metrics
don’t always predict outcomes (as seen in recent years),
they remain a bellwether worth monitoring.
• Wealth effects
Markets have already taken a hit. Lower equity valuations
translate to lower consumer spending and tighter capital for
firms.
• Policy missteps
The Federal Reserve is stuck between battling inflation and
supporting growth. Tariffs complicate their dual mandate and
raise the odds of miscalculation.
• Competitiveness loss
Around 50% of U.S. imports are intermediate goods—raw materials,
tools, components. Tariffs increase production costs
and erode the competitive edge, especially in capital-intensive
industries.
• Compounding shocks
When an economy is weakened, it becomes more vulnerable.
A financial mishap, cyberattack, geopolitical event, or even
natural disaster could hit harder and last longer under these
conditions.
INDUSTRIAL MANAGER’S CHECKLIST: HOW
TO NAVIGATE THE TRADE SHOCK
BUILD ANALYTICAL CAPABILITIES, NOT RIGID PLANS
Tariffs are now a moving target. Create flexible tools and
teams to assess policy shifts in real time and act accordingly.
REVISIT YOUR ASSUMPTIONS
Today’s trade dynamics may evolve rapidly. A broader
global response—or major shifts in sourcing and export
patterns—can quickly change exposure.
THINK IN CYCLES AND DECADES
Balance short-term operational tweaks with longer-term
strategic moves. Don’t let today’s noise distract from
tomorrow’s risk—or opportunity.
QUANTIFY EXPOSURE TO SUPPLY SHOCKS
Understand where you rely on foreign inputs. Map your
supply chains and model cost and productivity impacts
from tariff-related inflation.
PREPARE FOR GEOPOLITICAL SPILLOVERS
What starts as a trade policy can trigger regulation, retaliation,
or realignment in allied economies. Think beyond
borders and stay ahead of potential domino effects.
Based on an article by Philipp Carlsson-Szlezak, Paul
Swartz, and Martin Reeves, originally published in Harvard
Business Review. Edited by Mia Heiskanen
Further reading:
THE EXECUTION PREMIUM: LINKING
STRATEGY TO OPERATIONS FOR
COMPETITIVE ADVANTAGE
In a world of stiffening competition,
business strategy is more crucial than
ever. Building on their breakthrough
works on strategy-focused
organizations, the authors Robert
S.Kaplan and David P. Norton describe
a multistage system that enables you
to gain measurable benefits from your
carefully formulated business strategy.
THE THREE-BOX SOLUTION: A
STRATEGY FOR LEADING INNOVATION
Leaders already know that innovation
calls for a different set of activities,
skills, methods, metrics, mind-sets, and
leadership approaches. Innovation guru
Vijay Govindarajan expands the leader’s
innovation tool kit with a simple
and proven method for allocating
the organization’s energy, time, and
resources--in balanced measure--across
what he calls “the three boxes”.
2/2025 maintworld 9

LEADERSHIP
Text: MIA HEISKANEN
Photos: STEGRA
Coaching the Future
of Maintenance
Maria Ryytty is redefining what leadership in maintenance and automation looks
like—one system, one team, and one conversation at a time. And while her EFNMS
Manager Award may sit quietly on a shelf, its real value is in the signal it sends.
Excellence in maintenance management doesn’t look one way, and it certainly
doesn’t belong to just one kind of person.
10 maintworld 2/2025
SHE’S NOT JUST MANAGING the future
of industrial maintenance, she’s
coaching it, nurturing it, and pushing
to ensure it serves both business and
humanity. From her new role at Stegra
at the heart of one of Europe’s most
ambitious industrial projects, she’s
showing that technical leadership can
be both rigorous and deeply human.
When Maria Ryytty was announced
as the recipient of the EFNMS
European Maintenance Manager Award
2024, it wasn’t just a personal win—it
was a milestone. The honor, presented
by the European Federation of National
Maintenance Societies, recognized not
only her leadership but her trailblazing
role in reshaping how industrial maintenance
teams operate and thrive.
Now, as the newly appointed Asset
Manager at the Stegra facility in
Boden, Sweden, Ryytty is proving why
she earned it. She’s not just managing
assets—she’s building a new standard
for the future.
Ryytty is still visibly moved when
talking about the award. “I’m shivering
just remembering it,” she says.
“Out of 24 European countries, I—a
Swedish woman in heavy industry—
was chosen. That’s huge. It’s proof
that everything I’ve worked toward for
nearly two decades has mattered.”
For her, the EFNMS Award is more
than a plaque. It’s recognition of a longstanding
mission: to raise the standard
of leadership in technical environments
through team empowerment,
diversity, and data-driven strategy.
In the male-dominated world of
industrial maintenance and automation,
Ryytty stands out—not just as a
woman in leadership, but as a transformative
force changing how technical
teams work, grow, and succeed.
EFNMS MANAGER
AWARD 2024
Maria Ryytty was awarded European
Maintenance Manager of the
Year by the European Federation
of National Maintenance Societies
(EFNMS) in 2024.
This prestigious honor, awarded
every other year, recognizes outstanding
leadership in maintenance
across 24 European countries.
Ryytty’s win marked a turning
point—not only in her career but in
the visibility and value of diverse
leadership in industrial management.
"This award reflects everything
I’ve trained for—not just professionally,
but personally. It’s about people,
growth, and performance." - Maria
Ryytty
Ryytty’s management journey
didn’t start in a boardroom—it started
on a basketball court. Having coached
youth and adult teams for years, she
brings that same philosophy into the
factory. “Just like athletes train, I’ve
been training to lead teams,” she says.
Her new challenge? Being part of
the team building an entire asset management
organization from scratch at
one of Europe’s most climate-forward
industrial sites. The Stegra plant in
Boden will be home to over 200,000
assets across three vertically integrated
green facilities: hydrogen, iron, and
steel production.
With 11 new hires on her immediate
radar and 1,500 personnel expected
to join the total plant when up and
running in its first phase, Ryytty is
laying the groundwork for something
far beyond routine maintenance.
“We’re designing how this plant
thinks,” she says. “From governance
to escalation paths to safety culture,
it all begins now.”
A calling, not just a job. This mission
brought her to Stegra’s project
in northern Sweden. Still under construction,
the facility promises to be a
milestone in industrial climate action,
producing steel with up to 95 % lower
CO2 emissions than steel made with
coke-fired blast furnaces. Ryytty’s role
is central to its success.

LEADERSHIP
2/2025 maintworld 11

LEADERSHIP
Joining Stegra wasn’t just a career
move, it was personal. “This project
has meaning. We’re creating climatepositive
steel. That matters. My grandchildren’s
children deserve a future,
and I can help build it.”
She describes it as a “window
opportunity”—a chance to help shape
a greenfield site from the beginning.
“We’re not fixing legacy systems here.
We’re creating something new. It’s
a once-in-a-lifetime opportunity. A
blank slate.”
A manager who coaches, not
commands. Ryytty’s management
style is rooted in coaching, not command
and control. While her sports
background shaped her, she’s adjusted
her language over time. “Not everyone
connects with sports. I realized
I needed to meet my team where
they are, not where I come from.”
She describes her approach as
“coaching both the team and the individual.”
It’s about recognizing that
not everyone starts from the same
place—and that great teams are built
through individual growth. Her team
in Boden will reflect her values: diversity,
respect, and emotional intelligence.
“I’m building the team from
scratch,” she says. “I want diversity
in age, gender, background, and
thinking. And I want everyone to feel
seen.”
Ryytty is no stranger to being
the first. She earned her engineering
degree in 2005 and stepped into
management by 2009—an early
leap in a male-dominated field. “Of
course, it’s been tough,” she says.
“But I’ve always focused on the business.
I do not enter the room as a
woman. I enter as a leader.”
Her resilience has helped her
open doors that were once closed.
Now, she’s holding those doors open
for others. “I’ve taken the hits, so
others don’t have to. When I meet
young women entering technical
management, I say: you are welcome.
You are needed.”
From reactive to predictive. As
industries pivot toward smarter, more
sustainable operations, Ryytty sees
predictive maintenance as the new
baseline. “We can’t be stuck in a 1960s
mentality where something breaks
and we fix it,” she says. “We need to
build a predictive culture.”
“OUT OF 24 COUNTRIES I
WAS SELECTED FOR MY
SKILLS AND EXPERIENCE
A SWEDISH WOMAN IN
HEAVY INDUSTRY.”
– MARIA RYYTTY, ON
RECEIVING THE EFNMS
MANAGER AWARD
At Stegra, she and her team will be
implementing Industry 5.0 principles
from the beginning: leveraging smart
systems and real-time data to create
an intelligent, interconnected maintenance
ecosystem.
“We’re moving toward a future
where machines generate their own
work orders and schedule their own
maintenance,” she explains. “The
human role will be to guide and verify—not
chase problems after they’ve
happened.”
This isn’t an abstract theory, it’s
being built now. “Imagine a machine
that listens to itself and knows it will
fail in three months—so it books the
12 maintworld 2/2025

LEADERSHIP
right technician in advance. That’s
where we’re going and it´s exciting to
be building it.”
Finding balance in the fast
lane. Ryytty’s leadership doesn’t
end at the office door. A long-time
volunteer in youth sports, she finds
energy outside of work that fuels
her performance inside it. “Work is
part of life, not the whole thing,” she
says. “You need to shut off to show
up fully.”
It wasn’t always this way. “At first, I
struggled. But now I’ve learned: sometimes
you work late, sometimes you
leave early. What matters is knowing
where your edge is.”
She emphasizes the same lesson to
her team. “Especially for young professionals,
it’s easy to burn out. I tell
them: don’t try to be perfect. Just be
present. Build a life around your work,
not just inside it.”
What comes next. As she recruits
her core team and establishes Stegra’s
asset management foundations, Ryytty
knows the biggest challenge ahead
is talent. “The hardest part is finding
competence. But I trust my instinct. I
can feel when someone’s right. It’s not
about attitude, it’s about presence.”
Her advice to future leaders is clear:
start by knowing yourself. “I’ve done
the internal work. I know my values.
That’s what gives me the strength to
lead others.”
Her leadership philosophy is simple
but powerful:
“Develop yourself, so you can develop
your team. Build trust. Build
systems. And always keep moving forward.”
ABOUT STEGRA
Stegra is an industrial impact scaleup
in the process of building its
first plant for large-scale production
of green hydrogen, green iron
and green steel. The company
was founded in 2020 as H2 Green
Steel and changed name to Stegra
in 2024 to reflect its purpose to
decarbonize hard-to-abate industry,
starting with steel. Stegra’s flagship
plant is being built in Boden, northern
Sweden, and its headquarters
are in Stockholm.
2/2025 maintworld 13

ARTIFICIAL INTELLIGENCE IN MAINTENANCE
Text: MIA HEISKANEN
Photo: AI, Photo of Gianpiero MIA HEISKANEN
The Human Algorithm:
Leading Maintenance Teams in the AI Era
As artificial intelligence reshapes maintenance operations, the greatest challenge for
leaders isn't technological, but cultural. INSEAD Professor Gianpiero Petriglieri reveals
how maintenance leaders can preserve humanity while embracing automation.
GIANPIERO PETRIGLIERI
is Associate Professor of Organizational
Behaviour at INSEAD and an
expert on leadership and learning
in the workplace. His award-winning
research and teaching focus on
what it means, and what it takes,
to become a leader. This work has
earned him a spot among the 50
most influential management thinkers
in the world.
In an era where predictive maintenance algorithms and
AI-driven decision-making tools are becoming standard,
maintenance leaders face a crucial question: How do we
maintain our organizational culture's vitality while leveraging
technological advancement?
"The moment even leaders are suffocated by 'ought,' the
culture begins to lose its humanity. It becomes mechanical,"
warns Professor Gianpiero Petriglieri, addressing a
crucial challenge in today's management landscape. This
insight becomes particularly relevant as maintenance
organizations globally navigate the integration of AI and
automation systems.
14 maintworld 2/2025

Just as equipment requires preventive maintenance,
organizational culture demands intentional care. Petriglieri
identifies three critical "cultural malfunctions" that leaders
must monitor:
1. Cultural Diffusion: When rapid technological implementation
leads to losing sight of core organizational values
2. Cultural Stagnation: When successful maintenance
practices become unquestionable, blocking innovation
3. Cultural Fragmentation: When maintenance, operations,
and engineering teams work in silos, breaking down
the essential communication channels needed for integrated
operations
These cultural issues manifest through three workplace
symptoms: distraction, distress, and disconnection – what
Petriglieri calls "the 3Ds of workplace despair."
Petriglieri reinforces this perspective, citing that organizations
can achieve a 20-25 % performance improvement
by properly integrating AI with human capabilities. "It's not
going to be a human-only workforce of the future. It's also
not going to be only an AI-driven workforce. It is going to be
humans augmented by AI."
For maintenance leaders, Petriglieri suggests a threepart
approach to keeping organizational culture alive:
1. Investment in Principles: Define and reinforce what
your maintenance organization truly values beyond efficiency
metrics
2. Practice Enhancement: Regularly update procedures
while preserving essential human judgment
3. People Development: Foster connections between technical
teams and across organizational levels
"Learning is the oxygen of culture," Petriglieri states, emphasizing
that continuous learning should be viewed not as operational
overhead but as essential cultural maintenance.
The Human-Data Interface. In an industry increasingly
driven by condition monitoring and predictive analytics,
Petriglieri challenges the notion of being "data driven." Instead,
he advocates for being "data-informed" – using technical
data to enhance, not replace, human judgment and experience.
"Machines can be data driven. Humans are not data driven.
We will never be," Petriglieri asserts. "Humans are driven
by duties and desires." This distinction is crucial for leaders
managing the integration of e.g. AI-powered maintenance
systems while preserving team engagement and expertise.
Future-Proofing Leadership. The key to successful
leadership lies in maintaining what Petriglieri calls
"the courage to act and the courage to ask." Leaders must
have the confidence to implement new technologies while
maintaining the wisdom to question their impact on team
dynamics and organizational culture.
For maintenance organizations navigating digital transformation,
the message is clear: technical excellence and
human connection aren't opposing forces – they're complementary
strengths. The most successful leaders will be those
who can harness both, creating cultures that are as reliable as
their equipment and as adaptable as their teams.
This article is based on insights from the Nordic Business
Forum webinar "Humanizing Leadership – How to Keep
Culture Alive in the Age of AI" featuring Professor Gianpiero
Petriglieri, Associate Professor of Organizational Behaviour
at INSEAD, May 2025.
GIS
Next
Generation
EAM
BIM
PdM
AI
Mobile
APM
AIP
BI
PPM
Many companies use their Enterprise Asset Management
(EAM) system mainly as an electronic card index or a
digital work order system, unaware of the possibilities it
has for Asset Management. EAM Systems like Maximo,
IFS Ultimo, HxGN EAM and SAP EAM have evolved
tremendously. They now offer functionalities for Asset
Investment Planning, Project Portfolio Management,
Asset Performance Management, Business Intelligence
and Predictive Maintenance. Major steps have also been
taken in the field of Mobile, GIS and BIM integration.
Are you ready for Next Generation EAM?
Our VDM XL experts can assist you with further
professionalisation and automation of your Maintenance
& Asset Management organisation.
www.mainnovation.com

INDUSTRY
Text: GIANLUCA CASSANOVA
Photo: ABB
Building the smart,
resource-efficient
factories of the future
Global manufacturers are meeting the dual challenges of decarbonisation and
increased demand by transforming their sites using smart energy management,
circular practices and renewable energy solutions. Gianluca Cassanova, Procurement
& Operations Excellence at ABB’s Smart Buildings Division, explains.
16 maintworld 2/2025

INDUSTRY
WITH MANUFACTURING and production
responsible for 20 percent of
global carbon emissions¹, the pressure
is rising on industries to decarbonize.
At the same time, demand for manufactured
goods continues to grow – the
global electrical enclosures market,
for example, is expected to grow by
around 67 percent by 2032². Futureproofing
factory operations is therefore
more critical than ever.
Factory buildings themselves are
part of the equation, yet 80 percent lack
the automation or digitization needed
to drive meaningful improvements3.
Smart, modular and easy to implement
web-based platforms now enable
systems like heating, ventilation, air
conditioning, and energy management to
integrate seamlessly, generating a single,
unified view of how efficiently and effectively
a building operates. Building Management
Systems are not only measuring
and monitoring but also allowing control
and smart automation to drive efficiency
and energy consumption reduction.
Armed with this granular data, facility
managers can then take proactive steps
to reduce energy usage, greenhouse gas
(GHG) emissions and costs.
In this article, we will discuss how
industry 4.0 innovations like AI and
machine learning, combined with circular
economy models and the integration
of renewables, are empowering
manufacturers to reduce factory greenhouse
gas emissions while maximizing
production and profits. We also share
CUSTOMERS ARE LOOKING
FOR PRODUCTS AND
SOLUTIONS DESIGNED
WITH SUSTAINABILITY,
DURABILITY, AND
RECYCLABILITY IN MIND.
how ABB’s Mission to Zero program
is shaping the factories of the future
by combining digital technologies and
renewable energy into scalable and replicable
solutions.
Smart energy management as
a strategic advantage
With energy costs rising and sustainability
regulations tightening, real-time
energy management systems help manufacturers
monitor, control, optimize
and reduce consumption, forecast demand,
hedging from energy costs variation
and prevent waste. These systems
not only unlock operational savings but
also offer resilience against volatile energy
markets.
Visibility into energy performance
is also vital for both internal sustainability
KPIs and external reporting
obligations. As supply chains become
more focused on environmental performance,
working with partners that
demonstrate credible sustainability
credentials is becoming a strategic differentiator
and competitive advantage.
Digital tools such as ABB’s InSite
energy management system enable
manufacturers to monitor, analyse,
control and optimize their energy usage
in real time. Designed specifically for
electrical distribution systems in commercial
and industrial buildings, InSite
offers actionable insights into energy
consumption and system performance.
By visualizing load profiles, detecting
anomalies and supporting remote diagnostics,
it empowers facility managers
to make informed decisions that reduce
energy waste, lower costs and support
emissions targets.
Circular manufacturing and
integrating renewables
Customers are looking for products and
solutions designed with sustainability,
durability, and recyclability in mind. Incorporating
circular principles like material
recovery, design for disassembly,
and waste minimization helps manufacturers
meet these expectations while
reducing their environmental impact.
Unfortunately, global material extraction
continues to rise, and circularity has
dropped from 9.1 percent in 2018 to just
7.2 percent in 2023⁴. Moving away from
the “take-make-dispose” model toward
2/2025 maintworld 17

INDUSTRY
a “reduce-reuse-recycle” approach allows
manufacturers to cut waste and preserve
resources, while supporting longer
product life cycles and innovation.
In parallel, many industrial operators
are introducing on-site renewable
generation, including solar and wind,
to reduce reliance on fossil-fuel grids.
When paired with smart systems, these
sources provide a cleaner, more selfsufficient
energy base. Geothermic heating
systems could be as well considered
a kind of energy generation or 'closed
cycle’ circular model, considering that
heating waste from production process
in warm seasons is stored to be then reused
for heating during cold months.
As part of ABB’s Mission to Zero
program – a global initiative to decarbonize
operations using digital and renewable
technologies – the company’s
flagship site in Lüdenscheid, Germany,
has reduced its annual CO₂ emissions
by 750 tons through a combination of
solar energy, digital optimization and
energy-efficient systems⁵.
Customer trust and employee
engagement
Technology is only part of the story.
People – employees, customers, and
communities – are essential to delivering
and sustaining meaningful climate
action.
Just as customers, from public infrastructure
bodies to Original Equipment
Manufacturers (OEMs), demand
demonstrable action from suppliers,
employees increasingly want to work for
companies that share their values and
are actively addressing sustainability.
Empowering people with data and purpose
helps build stronger stakeholder relationships
and makes progress tangible.
That’s why ABB’s Mission to Zero is
more than a set of technologies; it’s a scalable
blueprint and suite of proven solutions
for manufacturing sites to reduce emissions
and boost energy efficiency. Built
on ABB digital platforms and renewable
energy, it provides a replicable roadmap
for factories worldwide, particularly in
energy-intensive or fast-growing markets.
EMPLOYEES INCREASINGLY
WANT TO WORK FOR
COMPANIES THAT SHARE
THEIR VALUES AND ARE
ACTIVELY ADDRESSING
SUSTAINABILITY.
Case study: people power in
Santa Palomba
To date, 25 manufacturing facilities
have led the way in cutting emissions
and energy use based upon this model.
One of these, a production site for
ABB residual current devices and energy
meters in Santa Palomba, Italy,
has reduced its CO2 emissions by 675
tons a year. In addition to its existing
renewable sources, a new photovoltaic
system supplies a quarter of the
site’s energy⁵.
The Santa Palomba site has also
achieved UL Certified Zero Waste to
Landfill Platinum status – the highest
level of a globally recognized benchmark
for waste diversion. 100 percent of the
site's waste is now reused, recycled, or
recovered, with nothing sent to landfill.
This milestone reflects ABB’s commitment
to circular manufacturing and
resource efficiency, with several other
sites worldwide also progressing toward
or achieving the same certification.
The team at Santa Palomba collaborated
with a logistics partner to
implement an innovative smart grid
project within an Energy Community
concept. More than 3,000 PV panels
installed on the company’s warehouses
next door to the ABB site now
provide a peak power of 1.52MW. In
the spirit of joint action, PV shelters
in the car park help power 17 electric
charging stations for the fleet of electric
and plug-in hybrid company cars.
To monitor and optimize energy
consumption, ABB AbilityTM building
management software tracks
energy consumption in real-time and
helps the site manage efficiency on
the most energy-intensive systems
such as air conditioning, the compressed
air system, air intake and
lighting (already 100 percent LED).
By the end of this year, Santa Palomba
plans to replace its boilers with
high-efficiency heat pumps.
Creating local value and
greener communities
The digitalized, decarbonized factories
of the future promise more than
emissions reductions. They bring
healthier environments, skilled ‘green’
jobs, and stronger local energy resilience.
When combined, Industry
4.0 tools, processes, circularity, and
renewable energy provide the capabilities
manufacturers need today,
to transform operations and support
thriving, sustainable communities.
The question is – what role will your
factory play in the sustainable transformation?
SOURCES:
¹ Buildings - Energy System - IEA
² Electrical Enclosure Market Size, Trends | Industry Outlook, 2032
³ https://new.abb.com/news/detail/119399/5-ways-to-make-your-operations-more-sustainable
⁴ https://www.circularity-gap.world/2023
⁵ https://new.abb.com/news/detail/114480/abb-manufacturing-site-in-santa-palomba-reducing-carbon-emissions-by-675-tons-a-year
18 maintworld 2/2025

WIND ENERGY
Text: NINA GARLO
Europe Reinforces Wind Energy
Security Amid Geopolitical Tensions
Since Russia’s invasion of Ukraine in 2022, Europe has re-evaluated its overall security
strategy—including how it sources and protects its energy. To reduce dependence on
imported fossil fuels, the continent is rapidly expanding domestic renewable energy,
particularly wind power. However, this transition brings new vulnerabilities, such as
physical sabotage and cyberattacks targeting critical infrastructure.
WITHIN this context, the role of maintenance
becomes increasingly vital—not
just to ensure operational efficiency,
but also to safeguard energy assets
against evolving threats.
“Europe is not only building more
wind farms—it’s also making sure they’re
secure,” says WindEurope. As risks increase,
the wind sector is strengthening
its collaboration with defence and cybersecurity
experts to better protect energy
infrastructure.
Infrastructure Under Threat
Attacks on Europe’s energy infrastructure
are no longer hypothetical. The sabotage
of the Nord Stream 2 pipeline in 2022
served as a stark warning, undermining
gas security and causing widespread
economic consequences. According to
POLITICO, Global Energy Monitor, and
TeleGeography, there have been at least
six suspected sabotage incidents in the
Baltic Sea alone since then, targeting subsea
electricity and internet cables—11 of
which have been disabled since 2023.
Such cables are critical, linking electricity
markets and connecting offshore wind
power to the mainland. As reliance on offshore
renewables grows, so does the need
to fortify these assets.
WindEurope Steps Up
WindEurope is stepping up its role in securing
Europe’s energy. Its 2025 Annual
Event in Copenhagen saw record participation
from NATO, the European Defence
Agency (EDA), and national defence bodies—signalling
closer cooperation with the
military.
“We’re working on practical solutions,”
says WindEurope, highlighting the EUfunded
SYMBIOSIS project, which aligns
offshore wind development with defence
needs. The project explores how wind
farms, equipped with sensors and radar,
could act as “eyes and ears” at sea to boost
maritime security.
Securing the Digital Frontier
Modern wind turbines are sophisticated
machines filled with electronics, sensors,
and control systems—making them vulnerable
to cyberattacks. To tackle this, the
EU’s updated Network and Information
Systems Directive (NIS2) now includes
energy among the critical sectors that
must comply with stringent cybersecurity
standards.
Upcoming policies, such as a dedicated
cybersecurity code for the electricity sector,
will further bolster Europe’s defences.
WindEurope is urging governments to
make cybersecurity and data protection
mandatory criteria in renewable energy
auctions and public procurement.
Laying the Groundwork for
Secure Expansion
WindEurope advocates for integrating security
measures from the earliest stages of
wind farm planning. Their recommendations
include:
• Proactive security planning at
the project design phase
• Regular dialogue between policymakers,
the defence sector, and
energy developers
• Rapid response protocols, including
a dedicated emergency
hotline for offshore wind incidents
• Ongoing training and simulation
drills for emergency preparedness
Though enhanced security entails added
costs, WindEurope stresses that these
remain marginal compared to overall offshore
wind investments.
MAINTENANCE: A
STRATEGIC PRIORITY
As wind power becomes embedded
in national defence strategies,
maintaining critical infrastructure
also becomes increasingly essential.
Industrial maintenance ensures the
reliability, efficiency, and longevity
of both energy and military systems.
WIND ENERGY MAINTENANCE
Predictive Maintenance: AI and
IoT sensors monitor turbine performance
in real time, identifying
issues before failures occur.
Drone Inspections: Drones
equipped with high-resolution
cameras inspect turbine blades
and towers, improving safety and
reducing downtime.
Offshore Challenges: Harsh marine
conditions demand specialised
coatings and regular preventive
maintenance to prevent corrosion
and weather damage.
Remote Monitoring: Centralised
systems enable real-time tracking
of turbine health and optimisation
of performance.
DEFENCE MAINTENANCE
Radar & Surveillance Systems: Regular
calibration and maintenance
ensure accuracy and prevent radar
disruption.
Military Equipment: Aircraft, ships,
and armoured vehicles rely on
consistent upkeep to remain combat
ready.
Energy Security: Military bases
using renewable energy require
preventive maintenance to avoid
power interruptions, especially in
remote or conflict-prone areas.
2/2025 maintworld 19

TECHNOLOGY
Text: NINA GARLO
Photo: SHUTTERSTOCK
From Breakdowns to Brainpower
Predictive Maintenance and the
Rise of the Self-Healing Factory
A decade ago, the key question in a maintenance shop was simple: How fast can we
fix the breakdown? Today, the most competitive plants flip that question around:
How rarely do we experience an unexpected breakdown?
THANKS TO CHEAP SENSORS, edge
gateways, and machine-learning (ML)
toolkits, maintenance is shifting from
a reactive cost centre to a strategic
advantage.
“Maintenance is no longer just
about wrench time,” says Christos
Tsallis, an industrial analytics specialist.
“It’s about insight time. The smart
factories predict failures - and sometimes
prevent them entirely.”
The Digital Pulse of Machines
Modern assets already bristle with
measurement points-velocity pickups
on bearings, current transformers
around motor leads, embedded infrared
spot sensors inside switchgear,
and more. What has changed is the
ability to act on that torrent of data in
real time.
Small edge devices stream or preprocess
high-frequency signals on the
plant floor, forwarding summaries to
the cloud for heavy analytics: training
models, correlating cross-asset anomalies,
and spotting slow-burn wear pat-
20 maintworld 2/2025

TECHNOLOGY
terns. Where the data stack has been
fully integrated with a computerised
maintenance-management system
(CMMS), ML-generated health scores
can automatically open work orders,
though only in highly instrumented
plants with robust change-management
processes.
Inside the Machine-Learning
Toolbox
Tree-based ensembles such as random
forests and gradient-boosted trees excel
when you have only a modest record of
past failures and well-structured tabular
data. However, their effectiveness can
wobble under severe class imbalance,
hence the common practice of pairing
them with anomaly-detection tools like
Isolation Forest. Deep-learning models
for temporal signals – CNNs, LSTMs,
and auto-encoders-deliver impressive
accuracy on data-rich fleets (turbine
arrays, accelerated test benches), but
they demand rigorous validation to
keep false positives in check. Hybrid
or physics-informed models come into
their own on assets whose behaviour is
tightly ruled by first principles - rotordynamic
or thermodynamic systems –
because the embedded physics helps the
algorithm extrapolate safely outside its
training envelope. In compliance-heavy
arenas such as aerospace and med-tech,
federated or other privacy-preserving
approaches allow plants to train models
without exporting raw logs; their chief
caveats are bandwidth overhead and
the governance required to coordinate
model updates across sites.
Cross-Industry Snapshots
• Discrete manufacturing – Published
trials in automotive plants
show up to 30 % downtime reduction
when fog-level ensemble models
alert crews ahead of the following
natural changeover.
• Process & heavy industry –
Hybrid twins help hot-rolling
mills and crushers survive dusty,
high-temperature environments
by simulating physical stress scenarios
that would be impossible (or
unsafe) to create physically.
• Power generation – Utilities
experimenting with deep autoencoders
on generator statorwinding
data have reported forcedoutage
cuts of as much as 40 % in
pilot seasons.
CHRISTOS
TSALLIS
is an Electrical
and Electronics
Engineer with
international
academic and
research experience
in Industry
4.0 and maintenance strategies.
He has worked in heavy industry and
conducted research in France, Finland,
and Portugal through competitive
scholarship programs. He is pursuing
a Ph.D. focused on the mathematical
modelling of complex systems.
• Wind turbines – ML models that
fuse SCADA and high-speed vibration
data trim false alarms during
yaw transitions while detecting
blade-root cracks earlier.
• Commercial buildings – Hospitals
now flag HVAC drift in real
time; out-of-spec chillers waste energy
and threaten medicine spoilage.
• Transportation & logistics – Decision-tree
models built on brakecycle
counts and engine acoustics
outperform mileage-only schedules,
delaying overhauls without
extra sensors on every component.
• Semiconductors – Wafer fabs
embed tool-health scores in yield
forecasts, using dimensionalityreduction
techniques to spot the
slightest drift.
What Works-and What Still
Gets in the Way
Metrics. Classic accuracy can be misleading
when failures are rare. Practitioners
track precision and recall (classification),
the F-score or AUC-ROC
(threshold robustness), and remaining
useful life (RUL) for regression-style
predictions. Mixing the two families
without context confuses non-data scientists,
so reports should call out which
metric serves which decision.
Data scarcity & imbalance. Oversampling,
simulated failures, and anomaly
detection help, but subject-matter
experts must vet every loop.
People & trust. No one will idle a
€3 million line on a black-box warning.
Transparent feature importance, clear
alert thresholds, and regular model reviews
build credibility.
Cybersecurity. Edge gateways increase
the attack surface; IEC 62443
compliance and zero-trust network design
are becoming table stakes.
ROI variability. Gains rise with asset
criticality, data quality, and changemanagement
maturity. Plants should
benchmark pilot projects before rolling
out at scale.
Towards the
Self-Healing Factory
Four innovations are converging:
• Lifelong learning models self-update
as conditions shift.
• Immersive digital twins – 3-D, physics-based
replicas ingest live data to
test “what-ifs” without risking production.
• Autonomous workflows – where
CMMS platforms know crew skills,
spare-part lead times, and asset criticality,
they can reprioritise tasks on
the fly.
• Sustainability wins – extending equipment
life and avoiding scrap align
directly with CO₂-reduction targets.
Predictive maintenance has left the
R&D lab and entered daily operations.
“We’re not just preventing breakdowns,”
says Tsallis. “We’re weaving
intelligence into the fabric of the plant,”
Tsallis highlights.
The journey, however, is as cultural as
it is technical: from reactive firefighting
to strategic foresight, from static manuals
to learning systems, and from viewing
maintenance as a cost to recognising
it as a multiplier of value and resilience,
he concludes.
2/2025 maintworld 21

MAINTENANCE SOCIETY
NVDO: A Longstanding
EFNMS Partner and Leader
in Maintenance Innovation
The Dutch Maintenance Society (NVDO), a founding member of the European
Federation of National Maintenance Societies (EFNMS), has been a key force in
shaping the European maintenance industry for 50 years. As an active member
of three EFNMS committees and the General Assembly, NVDO leads efforts
that promote innovation and professional growth throughout the sector.
Text: NINA GARLO Photos: NVDO
THE DUTCH maintenance market keeps
growing, even with global economic
challenges. It now makes up 4.1% of the
country’s GDP and provides jobs for
around 326,500 people—representing a
3.7% rise in 2024 from the year before,
according to NVDO’s annual survey
with universities and industry partners.
After slowing down in 2023, the
sector bounced back in 2024, but the
shortage of skilled technical workers
remains a major challenge.
NVDO General Manager Ellen den
Broeder notes that more than twothirds
of job openings over the past
year were for technical positions, and
companies are finding it increasingly
difficult to attract qualified candidates.
“The tight labour market remains a
major issue, especially in technical and
technological roles,” den Broeder explains.
“On a positive note, the proportion
of women working in maintenance has
risen to a record 9.9% this year—the highest
level in at least eight years,” she adds.
Turnover and Talent Retention
Under Pressure
According to Den Broeder, the absenteeism
rate in the Dutch maintenance
sector is 5.4%, closely aligned with the
national average of 5.3%, reflecting stable
attendance levels. Meanwhile, the
NVDO Maintenance Compass report
“Tackling the shortage of skilled technical workers is a shared European challenge.
NVDO is keen to explore European solutions that could add significant value to our
members.” – NVDO General Manager Ellen den Broeder
reveals a rising staff turnover rate in the
sector. This is largely driven by retirements
and employee dissatisfaction.
Furthermore, more professionals are
leaving the maintenance field altogether,
with the percentage of industry exits increasing
from 28% to 39% in just one year.
“This poses challenges for the sector
when it comes to training talent.
With the rise of advanced technologies
and the use of complex digital
systems, the demand for well-trained
and certified maintenance professionals
is growing,” Den Broeder
says.
Den Broeder emphasizes that addressing
the labour shortage requires
a collaborative effort:
22 maintworld 2/2025

MAINTENANCE SOCIETY
DUTCH MAINTENANCE
SOCIETY (NVDO)
• NVDO represents 326.500
maintenance professionals in
the Netherlands.
• The Dutch maintenance sector
has an estimated value of €30-
35 billion, accounting for about
4% of the country's GDP.
• NVDO serves as Europe’s largest
maintenance platform, supporting
businesses and professionals
in Asset Management.
• The organization promotes
knowledge transfer, advocacy,
and networking to enhance
maintenance efficiency.
• NVDO works closely with various
stakeholders (fe: the government)
to drive innovation
and best practices.
The proportion of women working in maintenance in the Netherlands has risen to a
record 9.9% this year—the highest level in at least eight years.
“No single organization can solve
this challenge alone. Public-private
partnerships between government,
businesses, and educational institutions
are essential. NVDO is encouraged
by the increasing number of such
collaborations.”
Cybersecurity – a Core Priority
Den Broeder emphasizes the growing
importance of training and retaining
skilled professionals in the
face of rapid technological change.
As operational technology becomes
increasingly integrated with IT systems,
cybersecurity has emerged
as a critical concern. Inadequate
data protection can result in severe
consequences, including the loss
of sensitive business information,
underscoring the need for proactive
and robust security strategies.
She further notes that upcoming
European regulations will compel
companies to strengthen their cybersecurity
posture. Among these is
the Cyber Solidarity Act (Regulation
EU 2025/38), a key legislative measure
designed to bolster cybersecurity
resilience across the EU. It introduces
enhanced threat detection
capabilities, improved coordination
of incident response among member
states, a unified risk management
framework for EU institutions, and
the creation of an Interinstitutional
Cybersecurity Board to oversee implementation.
The regulation will
also introduce mandatory cybersecurity
standards that companies
must comply with.
Building a Resilient, Skilled
Workforce Together
In response to these emerging challenges,
NVDO is intensifying its support
for the maintenance sector. The
organization offers targeted training
programmes, upholds certification
standards, and promotes lifelong
learning to ensure professionals stay
current with technological advancements.
In parallel, NVDO actively collaborates
with industry stakeholders
to raise cybersecurity awareness and
develop practical frameworks to help
companies protect their digital infrastructure
and meet evolving regulatory
requirements.
Den Broeder hopes that the EFNMS
with its committees and partnerships
can contribute to the common European-wide
problem in the maintenance
industry: “Tackling the shortage of
skilled technical workers is a shared
European challenge. NVDO is keen to
explore European solutions that could
add significant value to our members.”
DUTCH INDUSTRIAL
MAINTENANCE MARKET
SET TO REACH $9.97 BILLION
BY 2032, POWERED BY
INNOVATION AND STEADY
GROWTH
The Netherlands' industrial maintenance
market is on a steady
growth trajectory, projected to
reach nearly USD 10 billion by
2032, with a compound annual
growth rate of 2.7%. Despite challenges
like high labour costs, the
market continues to grow as companies
embrace the benefits of
digitization and automation.
Key trends include the rise of
predictive maintenance using IoT
for real-time monitoring, as well
as targeted workforce upskilling
initiatives to meet demand for
specialized MRO (Maintenance,
Repair, and Operations) services.
The Dutch government actively
supports this shift through strategic
policies and investments:
• Green Deal Industrial Plan: Part
of the EU’s broader green strategy,
it promotes clean tech and
reduced carbon emissions in
which NVDO contributes
• Industrial Decarbonization
Scheme: A €750 million EUbacked
initiative encouraging
fossil-free industrial processes.
• Vision on Industry Policy:
A long-term focus on digital
transformation and sustainability
to boost competitiveness.
Sources: Polaris Market
Research, www.eerstekamer.nl
2/2025 maintworld 23

CASE STORY
Enhancing Predictive
Maintenance at Nordic Sugar:
Lessons from Nakskov’s
Steam Dryer Project
Text NINA GARLO Photos: NORDIC SUGAR
Head of Plant Projects at Nakskov, Anders Jørgensen-Juu, infront of the evaporator station.
24 maintworld 2/2025

CASE STORY
Nordzucker AG, one of
Europe’s leading sugar
producers, is undergoing
a major digital and cultural
transformation in
maintenance operations
across its 13 European
factories—with Nordic
Sugar Nakskov, member
of Nordzucker Group
in Denmark leading the
charge.
WITH 4,000 employees and 16 production
sites globally (including three in
Australia), the company is building a
unified strategy to achieve maintenance
excellence—combining predictive technologies,
structured planning, and mobile
tools to maximize uptime and asset
performance.
At the centre of this change is a smart
approach toward predictive maintenance,
exemplified by the work done at Nakskov
around a notoriously unreliable piece of
equipment: the steam dryer. Modern dryers
such as the one at Naskov use hot air
from primary steam to dry pulp more efficiently.
They also recover and reuse secondary
steam, making the process more
energy-efficient and sustainable.
“Maintaining the pressure inside the
dryer is crucial,” explains Head of Plant
Projects at Nakskov, Anders Jørgensen-
Juul. “We typically have about 2,5 to 3
bars inside, while the ambient pressure
outside is much lower. Our challenge
was with the outlet valve, which suffered
from multiple breakdowns.”
To address this challenge, Nordic
Sugar implemented a predictive maintenance
system at its Nakskov plant powered
by machine learning. By collecting
and analyzing sensor and historical failure
data, they trained a model to predict
component breakdowns and estimate
the remaining useful life (RUL) of parts.
According to Jørgensen-Juul, the
initial results were encouraging—predictions
were accurate within 13 days
in the first year, enabling smarter
maintenance scheduling and reducing
unnecessary part replacements. Challenges
arose in 2023 when needed but
unplanned equipment modifications affected
model accuracy, highlighting the
Dashboard for monitoring RUL development for the outlet rotary valve for the steamdrier.
Outlet rotary valve for the steamdrier.
importance of system stability and data
consistency.
“Despite setbacks, the initiative has
proven valuable both operationally and
environmentally. Predictive maintenance
has given more insight for future
possibilities to extend equipment life,
minimize downtime, and align with
Nordzucker’s sustainability goals,” continues
Jørgensen-Juul. Going forward,
the company plans to cautiously expand
machine learning use for high-impact
components.
From Reactive to Predictive:
Why the Steam Dryer Was
the Perfect Test Case
“The steam dryer in Nakskov had a very
unpredictable failure pattern, disturbing
our seasonal production cycles,”
explains Jørgensen-Juul.
“Existing diagnostic tools were not
accurate enough, and this made it the
perfect case to test predictive maintenance
driven by machine learning.”
The plant’s challenge was clear: break
free from unplanned shutdowns and lev-
2/2025 maintworld 25

CASE STORY
erage data to predict failures before they
occur. However, integrating machine
learning into their distributed control
system (DCS) and existing sensor infrastructure
revealed a key insight early on.
“We assumed we had 'big data' from
years of collection, but in reality, very
little of it was usable. This forced us to
shift our mindset from ‘more data’ to
‘right data.’ Now, we’re strict about what
we collect and why.”
Beep reception in Nakskov.
Building the Business
Case: Scheduling, RUL, and
Seasonal Strategy
For a seasonal industry where sugar beet
campaigns only run for four months per
year, timing is everything, notes Jørgensen-
Juul. The goal of predictive maintenance
wasn’t just to avoid unexpected breakdowns—it
was to optimize inspections and
bundle repairs during the narrow maintenance
windows during campaigns.
“Being able to estimate Remaining
Useful Lifetime (RUL) is incredibly
valuable to us. If we can trust a machine
learning model to give an accurate RUL,
we might skip unnecessary inspections
altogether between seasons.”
While early machine learning trials
showed promising direction, they also
highlighted the complexity of modelling
failure. After reaching a prediction accuracy
of ±13 days over a 120-day period—
short of their ±5-day goal—the hydraulic
system was rebuilt, rendering the previous
training data obsolete.
“We’re now back to collecting data for
three more production periods before
relaunching the model.”
“WE ASSUMED WE HAD
'BIG DATA' FROM YEARS OF
COLLECTION, BUT IN REALITY,
VERY LITTLE OF IT WAS USABLE.
THIS FORCED US TO SHIFT OUR
MINDSET FROM ‘MORE DATA’
TO ‘RIGHT DATA.’ NOW, WE’RE
STRICT ABOUT WHAT WE
COLLECT AND WHY.”
Operator-Driven Maintenance
and Mobile Digitalization
“Predictive analytics is only one part of
the bigger picture,” Jørgensen-Juul says.
“Nordic Sugar has restructured its entire
maintenance framework.”
He adds that the company has restructured
its entire approach, starting
with the implementation of a unified
SAP-based digital maintenance system.
All 13 European factories now use SAP
PM for work orders and failure tracking,
which supports critical metrics like
mean time between failures (MTBF)
and helps prioritize tasks effectively.
Since 2022, every maintenance employee
has been equipped with a smartphone
running the Mobile Work Order
(MWO) system by 2BM Software. This
digital tool allows staff to report faults using
images and receive real-time updates,
improving responsiveness and clarity.
“Scheduled maintenance has also
become more efficient, with around
60% of planned work now automated
via SAP. This shift reduces reliance on
manual memory and coordination,
while also ensuring compliance with legal
inspection requirements,” highlights
Jørgensen-Juul.
According to Jørgensen-Juul, a notable
innovation is the pilot program
in Nakskov focused on operator-driven
maintenance. Here, technicians
who operate the equipment during
production are also responsible for
26 maintworld 2/2025

CASE STORY
FAST FACTS –
NORDIC SUGAR’S
MAINTENANCE
TRANSFORMATION
• 13 European factories + 3 in
Australia
• Full SAP PM integration across
Europe
• Mobile maintenance with MWO
since 2022
• Criticality classification of all
assets (A-B-C)
• 60% of scheduled maintenance
now automated
• Pilot site for predictive maintenance:
Nakskov, Denmark.
its upkeep. This dual role enhances
their understanding of operational
conditions and leads to faster, higherquality
maintenance outcomes.
To further streamline efforts, Nordic
Sugar has introduced a criticality classification
system for all assets. Equipment
is ranked A, B, or C based on its business
impact, allowing teams to allocate time
and resources where they matter most,
and deprioritize less critical assets.
Underlying these technical changes
is a cultural transformation led by
strong leadership: “Reaching 60–70%
maintenance efficiency is possible
with relatively little effort. But 90%?
That takes leadership, attention to detail,
and a shift in workplace culture,”
Jørgensen-Juul emphasizes.
Maintenance managers must clearly
communicate why predictive tools are
being adopted and what value they bring.
“Clear communication from leaders
about the reasons for adopting predictive
tools—and their value—is crucial,”
he stresses. Furthermore, maintenance
staff must be trained to interpret predictive
data accurately. Skilled technicians
play a key role in defining true
equipment failure, providing the essential
feedback needed to refine and train
predictive models effectively.
Scaling Up—and Knowing
When Not To
Interestingly, Nakskov remains the
only site currently applying machine
learning to RUL estimation. The reason?
“The business case only makes
sense for equipment with unpredictable
failures, short mean time between
failures, and where low-cost methods
don’t suffice.”
Machine learning projects are currently
limited in number due to resource
constraints and the parallel push for
green transformation. “We're prioritizing
cases in process optimization for now,
which are more straightforward. But we
believe predictive maintenance will scale
across the industry as tools mature.”
For companies just starting their predictive
maintenance journey, Jørgensen-Juul’s
message is clear:
“Start small. Choose equipment
that’s critical, already monitored, and
breaks down 2–3 times per year. If you
can nearly solve the issue without AI,
you’ll better understand how complex
data preparation really is. Don’t overreach
early—build confidence first.”
Over the next five years, Jørgensen-
Juul sees a split trajectory in the sugar
industry: some companies will try to
scale too fast and fail, while others will
build step by step from early successes.
The company hopes to play an active
role in knowledge sharing.
“In the end, all companies benefit
when we share what works. Predictive
maintenance can’t be scaled alone—it
takes community, leadership, and practical
wisdom.”
2/2025 maintworld 27

MARKET REPORT
Text: VAULA AUNOLA
Photos: SHUTTERSTOCK
Rapid Growth
in the Global
Industry 5.0 Market
The increasing usage of advanced automation technology and artificial
intelligence is a primary driver of this sector’s growth.
ACCORDING to Verified Market Research,
the revenue of the Industry 5.0
market will exceed 64.79 billion USD
in 2024 and is projected to reach approximately
76.7 billion USD by 2032.
The market will grow at a CAGR of
3.5% from 2025 to 2032.
Strong Manufacturing Base
Drives Europe’s Market
Many innovative industries exist in
Europe, particularly in the automotive,
aerospace, and machinery sectors,
which have long been at the forefront
of technical innovation.
According to the European Commission’s
2023 Industrial Policy Report,
manufacturing contributes 20%
of Europe’s overall GDP, with over €2.1
trillion in yearly production value.
The European Union’s Digital Economy
and Society Index (DESI) predicts
that 68% of EU manufacturing enterprises
have integrated sophisticated
digital technology, with Industry 5.0
usage reaching 45% in 2023.
According to the German Federal
Ministry for Economic Affairs, industries
that implemented Industry 5.0
technology increased productivity by
34% and improved resource efficiency
by 52%.
Eurostat figures show that European
manufacturers will invest €98
billion in Industry 5.0 technologies
in 2023, with 73% of large industrial
businesses already using humancentric
automation and sustainable
manufacturing methods.
Fastest Growth in the
Asia-Pacific Region
Asia-Pacific is the fastest-growing
region in the Industry 5.0 market.
Countries such as China, Japan, and
28 maintworld 2/2025

MARKET REPORT
India are adopting sophisticated
manufacturing technologies to boost
productivity and remain competitive
on a global scale, thanks to increasing
industrialization and a strong focus on
automation, AI, and IoT.
Japan’s Ministry of Economy, Trade
and Industry (METI) reported an 85%
rise in manufacturing facilities utilizing
Industry 5.0 technology in 2023,
with investments topping ¥2.5 trillion.
According to the South Korean Ministry
of Trade, Industry, and Energy,
62% of its smart factories have integrated
human-machine collaborative
systems, increasing productivity by 45%.
According to data from China’s Ministry
of Industry and Information Technology
(MIIT), manufacturers who
adopted Industry 5.0 technology saved
56% on operational expenses while improving
product quality by 38%.
Singapore’s Economic Development
Board states that 70% of its industrial
sector has adopted advanced
automation and AI technologies, with
“THE EXPANDING
TECHNOLOGICAL
IMPROVEMENTS IN
ASIA-PACIFIC WILL HAVE
A SIGNIFICANT IMPACT
ON THE INDUSTRY 5.0
MARKET.”
Industry 5.0 investments increasing at
a 28% annual pace.
AI in the Manufacturing
segment
As manufacturing evolves, there is a
major emphasis on automation to increase
productivity, eliminate human
error, and cut costs. AI plays an important
part in this by allowing robots
to learn from data, adapt to changing
conditions, and optimize production
in real-time. Manufacturers may use
AI to automate difficult activities,
foresee maintenance needs, and improve
quality control, thereby increasing
operational efficiency and agility.
The demand for AI-driven manufacturing
solutions is projected to
skyrocket as businesses realize the
2/2025 maintworld 29

MARKET REPORT
The Global Industry 5.0 Market will grow at
a CAGR of 3.5% from 2025 to 2032. Source:
Verified Market Research
The Automotive Industry
Leads the Way
With the fast incorporation of modern
technologies such as artificial
intelligence, robots, augmented reality,
and digital twins, the automotive
sector is becoming more efficient,
versatile, and innovative. These
developments allow manufacturers
to construct highly customized automobiles,
increase manufacturing
rates, and lower operating costs.
Furthermore, the inclusion of
smart technologies into automobiles
improves safety, performance, and
sustainability, which aligns with rising
consumer desire for smarter, more environmentally
friendly vehicles.
benefits of adopting modern technologies
into their operations.
Meeting Sustainability
Requirements
Companies are under increasing
pressure to meet stricter environmental
requirements and minimize
their carbon footprint, making the
inclusion of sustainable practices
and green technologies into production
processes even more important.
Developing smart factories and innovative
manufacturing procedures
that optimize resource consumption
while minimizing waste is consistent
with these goals, pushing additional
investment.
New Technologies
Enhancing Safety
As companies incorporate new technology
such as robots, artificial intelligence,
and automation, there is a heavy emphasis
on establishing work environments
in which humans and machines
complement rather than replace one
another. Furthermore, implementing
smart safety systems, real-time monitoring,
and AI-driven decision-making
tools will increase worker safety while
decreasing risks and increasing operational
efficiency.
According to the European Commission’s
2023 Industry 5.0 report,
workplace accidents in manufacturing
were reduced by 65% in facilities that
utilized human-machine collaborative
systems.
The U.S. Bureau of Labor Statistics
says that industries implementing
Industry 5.0 technologies showed
a 42% improvement in worker safety
measures in 2023, with collaborative
robots (cobots) contributing to
a 38% reduction in repetitive strain
injuries.
High Implementation Costs
According to the report the significant
implementation costs involved with
implementing Industry 5.0 technologies
may stifle market growth, particularly
for small and medium-sized businesses
(SMEs).
As technology improves and becomes
more widely used, costs are likely to fall,
making it more affordable for a broader
spectrum of businesses. Government
incentives, subsidies, and collaborations
with technology suppliers may also help
to alleviate financial pressures.
Source: Verified Market Research –
Industry 5.0 Market Valuation (2025-
2032)
30 maintworld 2/2025

EXHIBITION REPORT
Rewiring Industry: How GenAI Can
Pull Manufacturing Back Into Profit
Europe’s industrial manufacturers are caught in a bind. Profitability is slipping,
productivity has plateaued, and traditional cost-saving levers have lost their
edge. But now, Generative AI is emerging as more than a technological trend—it’s
fast becoming a strategy for turning the sector’s fortunes around. This became
evident in a study, conducted by Strategy& in partnership with VDMA Software
and Digitalization, and presented at Hannover Messe in March 2025.
Compiled by MIA HEISKANEN
Photos: HANNOVER MESSE
INDUSTRIAL manufacturing in Europe
is under pressure. For decades, productivity
and profits grew hand in
hand, fueled by waves of innovation
from lean manufacturing to automation.
But since 2010, something
has shifted. Productivity growth has
nearly flatlined—rising just five percent
in the last 15 years—while costs,
especially labor, have surged. The
result is a profitability squeeze that
spans the sector, from machinery and
equipment makers to automation
technology suppliers.
This new normal is pushing companies
to ask hard questions about where
the next wave of value will come from.
And increasingly, eyes are turning to
Generative AI. Once seen as a futuristic
concept or niche software feature, GenAI
is now being recognized for what it
could truly be: a tool to reshape how industrial
manufacturers design, produce,
and compete.
32 maintworld 2/2025

EXHIBITION REPORT
A new joint study from Strategy&
and VDMA Software and Digitalization
makes the case. Surveying 247 companies
and evaluating 45 practical GenAI
applications, the study finds clear,
quantifiable opportunities to improve
operating margins—up to 10.7 percentage
points across the sector. That
equates to a €28 billion profit boost for
Germany’s manufacturing industry
alone, if executed effectively.
“GENERATIVE AI ISN’T JUST
ABOUT AUTOMATION—
IT’S ABOUT COMPETITIVE
SURVIVAL IN A HIGH-
COST, LOW-GROWTH
ENVIRONMENT.”
Yet that “if” looms large.
So far, most manufacturers have
treated GenAI as an IT or support
function play—rolling out chatbots,
automating documentation, or experimenting
with software tools.
These initiatives are valuable but
limited. They don’t hit the real profit
drivers. As the study shows, the biggest
financial impact from GenAI
comes when it’s applied directly to
core business functions—think R&D,
sales, production planning, or supply
chain management.
In sales, for instance, GenAI can
personalize offers, anticipate market
demand, and dynamically adjust pricing,
unlocking real revenue growth. In
R&D, it can accelerate prototyping and
design, shorten time-to-market, and
reduce material waste. Even in areas
like production and logistics, predictive
capabilities and data-driven recommendations
can streamline workflows,
reduce downtime, and shrink costs.
Despite this, only 7% of surveyed
companies have implemented GenAI
company-wide, and fewer than one in
three have even deployed a single use
case in a real-world setting. There’s a
disconnect between potential and practice—and
it’s costing the industry.
What holds manufacturers back
isn’t just technical complexity. According
to the study, the biggest hurdles are
FOUR FOUNDATIONS
FOR A WINNING
GENAI STRATEGY
poor 1. data Strategic quality, Focus: a lack Prioritize of skilled highimpact
core over functions where over to invest. sup-
talent,
and uncertainty
Many companies port use cases. are still waiting for
2. Data Quality: Clean, connected
clearer use cases or broader industry
data is non-negotiable.
adoption before making bold moves.
3. Organizational Readiness: Create
that an wait-and-see incubator team strategy with comes
But
with a decision risk. As more rights. companies adopt
GenAI, 4. Execution the competitive Discipline: advantage Track use it
offers will cases narrow. against The real early financial adopters—those
who embed GenAI into
KPIs.
core
processes now—are likely to capture the
greatest gains in both profit and market
share. Later movers may find themselves
catching up, not leading.
That’s why the report argues for a deliberate,
top-down GenAI strategy. Not
every business process needs GenAI—
but the ones that do must be prioritized,
tested, and scaled. This means identifying
high-impact opportunities, setting
clear objectives, and creating internal
“incubators” that can move fast, free
from legacy roadblocks.
GenAI also opens the door to something
more profound than operational
tweaks. It invites a rethink of how
2/2025 maintworld 33

EXHIBITION REPORT
industrial companies structure their
business models altogether. New ways
of designing products, serving customers,
and optimizing workflows become
possible when GenAI is integrated
deeply, not just layered on top.
For example, automatically generated
product designs based on customer
input could radically shorten
design cycles. Predictive insights about
supply chain disruptions—drawn from
unstructured global data—can help
firms act before problems hit. Even the
onboarding of new employees or the
customization of marketing campaigns
can be done at a scale and precision
that simply wasn’t possible before.
These aren’t futuristic concepts.
They’re already being piloted by leading
firms—and they work. But the shift
from pilot to scale requires executive
commitment, not just experimentation.
The message is clear: the promise of
GenAI in industrial manufacturing is no
longer hypothetical. The tools exist, the
use cases are proven, and the economic
upside is compelling. What’s missing is
bold execution.
For companies willing to act now, the
opportunity is twofold. They can claw
back lost productivity and profit—and
just as crucially, they can secure a leadership
position in the next chapter of
industrial innovation.
“COMPANIES THAT TREAT
GENAI AS A BOLT-ON
FEATURE WILL FALL BEHIND.
THOSE THAT TREAT IT AS
A CORE CAPABILITY WILL
PULL AHEAD.”
Delay too long, and that window
closes. As GenAI matures and becomes
commonplace, its ability to
differentiate will diminish. Those
who wait will inherit a commoditized
tool. Those who lead will build
the future.
Presented at Hannover
Messe 2025
This landmark study, conducted by Strategy&
in partnership with VDMA Software
and Digitalization, was officially presented
at Hannover Messe in March 2025. The
event marked a turning point in how the
industry views GenAI—not as an experiment,
but as a new operating paradigm for
Europe’s manufacturing core. The message
from Hannover is loud and clear: the
GenAI moment is here. Those who lead
now will define the next era of industrial
competitiveness.
You can download the study at
GenAI in industrial manufacturing |
Strategy&
34 maintworld 2/2025

EXHIBITION REPORT
KEY INTAKES FROM HANNOVER MESSE 2025
Tech show, business exhibition and platform for economic
policy dialog between partners: that was HANNOVER
MESSE 2025. The world's most important industrial trade
fair has been emanating positive signals this year: artificial
intelligence (AI), automation, digitalization, and electrification
are driving quantum leaps in industry efficiency.
More than 123,000 visitors from 150 countries
exchanged ideas with the 4,000 exhibiting companies on
how they can use AI profitably, automate their factories,
or become more energy efficient. More than 40 percent of
visitors came from abroad.
Dr. Gunther Kegel, President of the German Electrical
and Electronic Manufacturers' Association (ZVEI) and
Chairman of the HANNOVER MESSE Exhibitors’ Advisory
Board:
“HANNOVER MESSE has once again shown that it is
the most important platform for industrial innovation.
AI in industrial applications was of particular interest to
visitors, especially those from abroad. This shows that
German industry can continue to offer a global orientation
in times of technological change. Our companies are
leaders in Industrie 4.0, and we are convinced that we can
further expand this very good starting position. Industrial
AI is a new growth area that will continue to drive the
automation and digitalization of industry."
The number one topic at this year's trade fair
concerned AI applications for industry.
“AI has the potential to change industry more in just a
few years than it has changed in the entire past decade,”
says Köckler. The exhibiting companies used specific
examples to show how manufacturing companies can
benefit from artificial intelligence. “Through the targeted
use of these technologies, small and medium-sized
enterprises can also increase their efficiency, reduce costs,
and significantly increase their competitiveness,” said Dr.
Jochen Köckler, CEO of Deutsche Messe AG.
Source: Hannover Messe
2/2025 maintworld 35

INDUSTRY
From Healthcare to Industrial Care:
Kemira's Revolutionary Approach
to Asset Management
Just as modern healthcare has shifted from treating illnesses to preventing them,
Kemira is revolutionizing industrial maintenance by treating its rotating assets like
a population of patients. The secret? Treating equipment failure is not as inevitable,
but as entirely preventable.
Text: MIA HEISKANEN, AKI KARUVEHA
Images: ASENSIOT LTD.
THROUGH an innovative partnership
with Asensiot Oy, the global chemical
company has developed a groundbreaking
preventive approach that's already
delivered a sevenfold return on investment
across ten production sites.
“In safety, every accident is preventable.
Yet, when it comes to rotating assets,
we still accept failures as inevitable.
Why are we willing to tolerate risks that
we know can be eliminated? OEE (Overall
Equipment Efficiency) can track performance
but misses hidden risks, so we
needed new metrics in risk assessment,”
begins Carl Bristow, Director of Safety
& Manufacturing Excellence at Kemira
Oyj, a global chemical company.
Kemira operates over 60 production
facilities worldwide, but previously
lacked a comprehensive, real-time overview
of the true condition of its rotating
equipment, an essential requirement for
enabling a new, more sustainable maintenance
strategy. Traditional condition
monitoring practices focus mainly on
critical assets, leaving the overall picture
of asset health incomplete.
To improve data-driven management,
Kemira launched a collaboration
project with Asensiot Oy, a Finnish
Value-as-a-Service company, in 2021.
The goal was to create a new, scalable
operating model that would support
Kemira’s sustainable maintenance goals,
motivate field personnel, and allow for
easy and rapid implementation from
one plant to another. This approach
aimed to quickly identify concrete cases
to achieve Kemira’s strategic objectives.
Input/Metrics
New Metrics to Support Risk Assessment
Notifications to Non-Routine
Work Order Process
Reaction Time to Notification
Impactful Maintenance Action
Monthly Fault Progression Trend
Early-Stage Fault Condition Ratio
(Inadequate lubrication and bearing faults stages I-II)
Bad Actor Asset Scoring
New Metrics to Support Risk Assessment to Reduce Risk for Unplanned Repairs.
“Just as healthcare focuses on proactive
care for large populations, we decided to
bring the same large-scale preventive approach
to Kemira’s rotating assets. Yet, in
industry, the focus is often on scheduling
repairs, even though much of the risk of
unplanned failures can be minimized by
taking proactive actions to address fault
progression at an early stage,” says Aki
Karuveha, CEO of Asensiot Oy, a MyAsensiot
Condition Screening® company.
By partnering with Asensiot, Kemira
developed a new collaboration model
Integration Benefit
Timely updates on unscheduled
maintenance for stakeholders, reducing
operational surprises
Shorter reaction times reduces risk
exposures and potential negative impact
Only the positive maintenance impact
improves asset reliability and life
extension
Decreasing trend indicates lower risks
for the unplanned repairs
Decreasing level indicates lower risks
for the unplanned repairs
Identifies and prioritizes assets for
business impact ("bad actors") for
maintenance decision-making
with key metrics that provide proactive,
actionable information on rotating assets
in a structured format, integrated
directly into Kemira’s SAP/HANA
system. This enables early detection of
potential issues, supports optimized
maintenance planning, and reduces
the number of corrective interventions
required over the long term. It also
streamlines maintenance actions, ensuring
resources are focused on assets
that truly need attention-minimizing
unnecessary work and supporting the
36 maintworld 2/2025

INDUSTRY
Value Creation Process
POTENTIAL VALUE
REALIZED VALUE
CLIENT
Monthly
MEASUREMENT
ROUTINE
COMPLETED
maintenance
actions
Intensified or
monthly
MEASUREMENT
ROUTINE
Extended
Lifetime
Avoided
Unplanned
Shutdown
No impact
REVIEWS
ASENSIOT
1. DATA
NON-ROUTINE
maintenance
actions
notification
FEEDBACK
2. DATA
Verification of
the maintenance
action IMPACT
Value Creation Process from Monthly Measurement Routines to Value
company’s sustainability and operational
excellence goals.
From Vision to Reality:
A Scalable Solution
“At first, we wanted to understand
what kind of data we should collect and
how this could be done efficiently, using
available measurement technologies
and without requiring special skills at
our sites,” says Bristow.
At one of Kemira’s plants, a range
of measurement technology tests revealed
that wireless technology did not
provide a cost-effective solution for
achieving a comprehensive overview of
asset condition at scale. On the initiative
of Kemira’s field personnel, a pilot
was launched using an operating model
where relevant data is collected quickly
and easily with a route collector during
existing monthly inspection rounds.
RFID technology ensures that data is
always measured for the correct asset
and later enabled field observations
and asset-specific information to be accessed
via mobile devices.
“We want our field personnel at production
sites to be engaged in the process.
Regular route routines and field
observations support the development
of our safety culture. So monthly measurement
routine is much more than
only focusing on data,” adds Bristow.
The ability of in-house personnel to
conduct measurements provides exceptional
flexibility, especially for monitoring
batch processes, and enables
rapid response when a change in asset
performance is suspected. Additionally,
quickly verifying asset condition after
maintenance helps prevent failures that
could arise from potential installation or
assembly errors.
At Kemira’s production sites, comprehensive
measurements are routinely
performed once a month and more
frequently if needed with the collected
data uploaded to the supplier’s cloud
Value Delivery Process
POTENTIAL
DECISION
2. BAD ACTOR PRIORITY
1. EXTENSIVE COVERAGE
Value Delivery Process from the Potential to Realized Value
service. The volume of transferred data
is optimized, ensuring that only essential,
standardized raw signals are sent
for processing by artificial intelligence
algorithms to pinpoint focus areas.
“We need actionable information
integrated into our work order process,
not just alarms. It was clear to us that
technology alone would not support our
sustainable maintenance goals,” highlights
Carl Bristow.
Insights into Impact
In Kemira’s new condition screening
operating model, only essential action-
REALIZED VALUE
4. MAINTENANCE ACTION
3. MAINTENANCE PLANNING
5. MAINTENANCE
IMPACT
2/2025 maintworld 37

INDUSTRY
Example Cases
Impact of Fault Detection on Corrective Actions and Risk Mitigation. This figure illustrates how timely fault detection enables
effective corrective actions, such as the replacement of faulty components or the reduction of loading conditions. These interventions
significantly decrease the risk of catastrophic machine failure by addressing issues before escalation, thereby improving operational
reliability and extending equipment lifespan.
guiding, standardized non-routine notifications
are generated for SAP/HANA,
thanks to a scalable AI-algorithm-based
screening and expert validation process.
This allows Kemira to focus solely on
what matters, maintenance actions that
truly make an impact.
At the core of this new approach are
the people in the field and supporting
their daily work. User motivation
stems from information that makes
their work easier-most importantly, by
identifying concrete cases where users
can see the direct link between actionable
guidance and real impact. Without
impact, there is no value.
Following a successful pilot, the new
operating model was rolled out to 10
production sites in different countries
during 2023 (Wave 1). The deployment
of monthly monitoring was straightforward
and required no prior site-specific
information. For a two-person team,
the total fieldwork amounted to just
around 14 days. In 2024, Kemira implemented
the system at 16 additional
production sites (Wave 2).
38 maintworld 2/2025
“Sustainable reliability is not
just monitoring critical assets or
avoiding unplanned shutdowns by
scheduling repairs; its true impact at
scale lies in extending asset lifetime
and avoiding unnecessary maintenance
actions to reduce overall risk
of unplanned repairs,” explains Aki
Karuveha.
Kemira’s Wave 1 Statistics
• Wave 1: 10 Sites (Results from
November 2023 Onward)
• Deployment Time: 14 Days On-
Site / 2 Persons
• Measured: 779 Individual Assets
• Extended Asset Lifetime: 14
Realized Cases
• Avoided Unplanned Shutdowns:
45 Realized Cases
• Estimated Costs Avoided:
€2,264,000 (~7x ROI)
The Numbers Speak
“Kemira has achieved multiple benefits
by adopting a sustainable reliability
approach to rotating assets, including
increased equipment uptime, reduced
maintenance costs, decreased manpower
requirements, improved energy
efficiency, and a smaller ecological footprint,”
summarizes Carl Bristow.
Condition screening provides a
comprehensive monthly overview of
the health of rotating assets, delivering
an extensive situational picture that
seamlessly integrates with Kemira's
Asset Performance Management
(APM) in SAP/HANA. Without a realistic
picture of asset health, APM
becomes ineffective, leading to poor
decision-making, missed optimization
opportunities, increased risks, and
fragmented processes. Accurate asset
health data is essential for APM to
improve reliability, reduce costs, and
enhance efficiency.
Kemira is continuously improving
communication by linking SAP/HANA
with the supplier, enabling tracking of
maintenance actions and their impact
on resolving flagged issues, and supporting
efficient, active collaboration
between Kemira and Asensiot.

INDUSTRY
Importance of Early Detection of Excessive Bearing Friction for Proactive Maintenance. This figure demonstrates how early
identification of excessive friction within bearings enables proactive interventions, such as relubrication or adjustment. Detecting
abnormal friction is crucial for preventing fault progression that could otherwise result in severe and costly machine failures. Early
action not only safeguards equipment integrity but also minimizes risk for unplanned downtime and higher maintenance costs.
SUMMARY
Kemira’s proactive, data-driven
approach to rotating asset risk
assessment is delivering tangible
benefits across its global
operations. By focusing on early
detection, actionable insights,
and scalable processes, Kemira
is setting a new benchmark
for sustainable reliability and
maintenance excellence in the
process industry.
2/2025 maintworld 39

RAILWAY MAINTENANCE
The future of rail freight: the rise of the
Internet of Things and digitalisation
Rail freight transport is undergoing a major transformation, driven by significant
investments in the digitalisation of operations.
Text: VAULA AUNOLA Photos: SHUTTERSTOCK, HITACHI, RAIL VISION
ACCORDING to global technology research
firm ABI Research, IoT revenues
from freight rail will exceed $20 billion
by 2032.
– The global rail telematics market
is driven by the growing demand for efficient,
safe, and cost-effective transportation
systems. The expansion is driven
by the advancement of digitalization and
integration of IoT technologies with an
emphasis on real-time data analytics for
predictive maintenance, says Adhish
Luitel, Principal Analyst, ABI Research.
While Europe has made significant
progress in the deployment of IoT, North
America is still underdeveloped. According
to ABI Research the region has a Total
Addressable Market (TAM) of almost
2 million railcars, which offers significant
opportunities for IoT-based solutions.
TRILOGICAL TECHNOLOGIES: TELEMATICS
SOLUTIONS FOR LONG FREIGHT TRAINS
As freight demand increases, rail operators are moving to longer trains,
particularly in North America. Around half of freight trains are now over
1.65 km long, and this growth is continuing.
Trilogical Technologies presented its own technology at InnoTrans 2024.
The company has developed the Long-Train Intelligence System (LTIS® ) to
manage the complexity of longer trains by integrating real-time control
systems that improve safety and efficiency. Key features of the system
include:
Continuous Train Integrity: monitors wagon placement from start to
finish and ensures train integrity during transport.
Driver Advisory System: provides drivers with status updates and alerts
to prevent operational delays.
Condition monitoring: Uses sensors to detect anomalies and reacts
quickly to avoid disruptions.
Condition monitoring and predictive maintenance: Supports predictive
maintenance strategies that is estimated to reduce costs.
The role of IoT in railways
IoT technologies are transforming
freight rail operations by integrating
sensors, AI-based analytics, and cloud
computing into everyday logistics.
Smart train cars equipped with GPS, vibration
sensors and automated reporting
mechanisms can now send real-time
data to operational control centres.
This connection allows operators to
monitor location, freight condition and
potential maintenance problems, ensuring
maximum efficiency and safety
throughout the transport process.
Predictive maintenance
Predictive maintenance is one of the
most revolutionary aspects of IoT in
rail freight. By analysing data collected
in real-time from train wagons and infrastructure,
AI algorithms can predict
failures before they happen.
This reduces downtime, prevents
costly disruptions, and improves safety
by ensuring that potential mechanical
problems are resolved proactively.
40 maintworld 2/2025

RAILWAY MAINTENANCE
HITACHI RAIL, CONNECTED PLACES CATAPULT
ANNOUNCE AI RAIL MAINTENANCE TECH
In 2021, Connected Places Catapult (CPC) initiated a technical collaboration that
brought together Hitachi Rail, LNER, and Network Rail. The collaboration led to a successful
six-month trial on the East Coast Main Line, testing Hitachi’s technology.
The digital overhead line monitoring technology, which Hitachi unveiled at the
latest InnoTrans in Berlin, promises to boost punctuality for passengers and improve
safety for trackside engineers.
CPC played a pivotal role in supporting the partnership, focusing on understanding
user needs and fostering new collaborative working models, thus navigating the
challenging “valley of death” in technology innovation.
The project involved mounting cameras on trains to monitor overhead lines in
real-time, with machine learning algorithms identifying potential faults to inform
maintenance needs.
– The UK’s railway ecosystem has an important part to play in the development
of this technology, which is now available to infrastructure operators worldwide,
said Hitachi Rail IM and Digital Services Manager Ben Earle.
Following the trial, Hitachi Rail has refined the product, integrating it into its
HMAX digital asset monitoring platform.
HMAX, Hitachi Rail’s digital asset management suite, enhances the management of railways
by seamlessly integrating operational data from across railway assets and infrastructure
into a single platform, optimising the utilisation of railway systems and associated
resources. In addition to providing live time monitoring, the system enables the virtual simulation
of the physical environment, accelerating the evolution of railway systems.
RAIL VISION:
AI-POWERED OBJECT
DETECTION FOR RAIL
SAFETY
By integrating electro-optic sensors
and machine learning, Rail Vision
helps improve situational awareness,
reduce operational risks, and
optimize maintenance strategies.
The company's AI-powered
object detection system is designed
to help train drivers avoid accidents.
Its key features include:
Detection and classification of
objects (e.g. cars, animals and people)
up to a distance of 2 km.
Multi-form alerts (visual, audible
and colour) to ensure that drivers
react to dangerous situations.
Operation in poor visibility conditions,
particularly useful in marshalling
yards and at night.
CPC and Hitachi Rail have advanced their AI-powered rail maintenance
technology to the commercial stage.
AI-Powered object detection
Identifies hazards up to 2 km away.
Replacing many manual tasks
Traditionally, machine vision and
sensor-based inspection equipment,
often installed at railway crossings, has
been at the forefront of improving operational
visibility.
Rail brake inspections are also a
critical but time-consuming task.
These inspections ensure that the
air brake system is functioning correctly
throughout the train, which
can be more than a mile long. Manual
checks require extensive coordination
between train crews and control
centres, which can cause delays and
inefficiencies.
IoT technologies offer a solution by
providing real-time data and predictive
analytics, ultimately improving safety,
reducing downtime, and improving
compliance.
Challenges of integration
The deployment of IoT on freight railways
faces a number of challenges. In North
America, for example, the adoption of IoTbased
visibility solutions has been slow
compared to Europe, largely due to the
extensive infrastructure and the different
regulatory environments in different
states and countries. In addition, integrating
legacy rail systems into modern IoT
frameworks requires significant investments
in hardware, software, and training.
Security is another growing concern.
As more and more train cars are
connected, cybersecurity risks will
increase, making it important for operators
to put in place robust security
measures. Strong encryption, real-time
threat monitoring and compliance with
industry security standards are essential
for the successful digital transformation
of the industry.
"AI algorithms can predict failures
before they happen."
"The deployment of IoT on freight
railways faces a number of challenges."
2/2025 maintworld 41

TECHNOLOGY
Industrial Robotics: Trends
Defining the Next Generation
Industrial robotics is experiencing a transformative shift, driven by rapid
advancements in artificial intelligence (AI), machine learning, and automation
technologies. No longer confined to repetitive assembly tasks, robots have
become central to the future of manufacturing, logistics, healthcare, and industrial
maintenance. As companies demand greater efficiency, precision, and adaptability,
robotics is evolving from a supportive tool to a strategic asset.
Text: NINA GARLO Photos: JUSMATICS OY, THE DANISH ACADEMIC SOCIETY OF ROBOTICS (DACASROB)
TO BETTER understand these
changes, Maintworld spoke with
Christian Schlette, Professor at the
Mærsk Mc-Kinney Møller Institute
(MMMI) Head of the University
of Southern Denmark’s Center for
Large Structure Production (LSP)
and co-founder of the Danish Academic
Society of Robotics (DACAS-
Rob). According to Schlette, a trend
in industrial robotics is the integration
of AI, which allows machines to
make autonomous decisions, learn
from their environments, and optimize
performance in real time.
“AI is increasingly enabling robots
to handle dynamic environments and
more complex tasks that go beyond
hard-coded programming,” Schlette
explains.
Among other innovations, collaborative
robots—or cobots—have gained
ground for their ability to safely operate
alongside human workers, enhancing
both productivity and workplace
safety. Autonomous mobile robots
(AMRs) are also reshaping logistics
and warehousing, while soft robotics
is opening doors to automation in
fields that require delicate, adaptive
handling—such as food processing and
healthcare.
Robotics in Industrial
Maintenance
In maintenance, robotics is ushering
in a new era of predictive diagnostics.
Robots equipped with sensors
Professor Christian Schlette is co-founder of the Danish Academic Society of Robotics
(DACASRob).
and powered by AI can now identify
and address problems before they
cause downtime. This shift from
reactive to proactive maintenance
reduces costs and improves operational
efficiency. Robots are also
being deployed in hazardous environments,
performing inspections or
repairs that would be dangerous for
human workers.
Leading Industries in Adoption
Industries such as automotive, electronics,
healthcare, and logistics are
leading the charge in adopting robotics.
In automotive manufacturing,
robots improve speed and precision on
the production line. Electronics companies
use robotics to handle microcomponents
with accuracy. In healthcare,
surgical robots and diagnostic
systems are transforming patient care.
Warehouses are relying on robots to
streamline everything from inventory
tracking to order fulfillment.
The Role of AI and
Machine Learning
AI and machine learning are at the
core of this robotics revolution. These
technologies enable predictive analytics
for maintenance, enhance visual
42 maintworld 2/2025

TECHNOLOGY
recognition systems for quality control,
and allow robots to make decisions on
the fly. This autonomy is making robots
smarter, more efficient, and more adaptable
to real-world challenges.
Cobots: Redefining Human-
Robot Collaboration
Cobots are changing how humans and
machines interact in the workplace.
They are designed to assist rather
than replace, taking over repetitive
or physically demanding tasks while
allowing human workers to focus on
more complex activities. Because cobots
are relatively affordable and easy
to implement, they are especially valuable
for small and medium-sized enterprises
(SMEs) looking to embrace
automation without major infrastructure
changes.
Addressing Labour Shortages
and Skills Gaps
The growing use of robotics is helping
industries deal with persistent labour
shortages. By automating routine
jobs, businesses can operate efficiently
with fewer workers. At the same
time, AI-powered training tools are
helping employees develop new skills
and transition into roles that support
or manage automated systems.
Challenges in Integration
Despite their promise, robotics
systems can be challenging to integrate
into existing operations. High
upfront costs, compatibility issues
with older equipment, and the need
for workforce reskilling are common
hurdles. However, many companies
are overcoming these obstacles
through strategic planning, modular
solutions, and service-based models
such as Robotics-as-a-Service (RaaS),
which reduces financial risk by converting
capital expenses into operational
ones.
Supporting Sustainability Goals
Robotics is also contributing to more
sustainable industrial practices. Intelligent
automation can optimize
energy use, reduce material waste,
and enhance recycling efficiency.
Robots can be programmed to perform
tasks with precision and consistency,
leading to fewer errors and
less scrap, especially in high-precision
industries.
The robotic system developed by Jusmatics Oy is tailored for machining metal components
used in heavy vehicle manufacturing. Its CAM system generates robot-executable toolpaths
directly, removing the need for separate robot programming. This streamlined process
improves consistency and strengthens the integration between design and production.
HOW DACAS-ROB IS SHAPING THE FUTURE OF
ROBOTICS IN DENMARK
At the forefront of robotics research and collaboration, the Danish Academic
Society of Robotics (DACAS-Rob) connects universities and industry to
drive innovation in robotics. Through joint research, educational initiatives,
and applied projects, DACAS-Rob supports Denmark’s position as a key
player in European robotics.
The society shares insights through webinars, video discussions, and
its official YouTube channel, which highlights the latest in Danish robotics
research and academic contributions. A dedicated webinar series also
showcases leading-edge developments from across the country.
https://dacas-rob.org/
2/2025 maintworld 43

MARKET RESEARCH
Text: NINA GARLO Photo: SHUTTERSTOCK
AI-Based Predictive
Maintenance Set to Hit
$1.69 Billion by 2030
Why cloud, edge, and smart data are
reshaping industrial upkeep—globally
Industrial maintenance has traditionally been reactive—fixing broken pumps,
stalled belts, or unplanned shutdowns. But that’s changing quickly. According to
the AI-Based Predictive Maintenance Market Report 2025–2030 by Research and
Markets, global spending on AI-powered maintenance tools is expected to grow
from USD 939.73 million in 2025 to USD 1.69 billion by 2030.
THE REPORT published in April highlights
the accelerated shift from
schedule-based to condition-based
maintenance, driven by advances in
AI and machine learning. AI systems
now flag early signs of issues, reducing
the need to wait for breakdowns.
Predictive maintenance offers a clear
return on investment by minimizing
downtime, reducing repair costs, and
extending asset life.
“This not only safeguards critical
assets but also ensures operational
continuity in high-stakes industries,”
the report states.
The Power Duo:
Cloud and Edge
Cloud-based and edge technologies
play a crucial role in this transformation,
according to the report. Edge
devices process real-time data onsite,
while the cloud handles broader
analytics across multiple sites, even
globally. This hybrid approach is vital
for industries in remote or bandwidthlimited
regions like mining, offshore
energy, and rail transport.
According to the report, the Americas
lead in AI adoption, driven by significant
investments in smart infrastructure and
digital transformation. Manufacturing
and logistics sectors in this region are
particularly advanced in integrating AI.
CYBERSECURITY SHOULD
BE A TOP PRIORITY, AS THE
CONVERGENCE OF IOT AND
AI TECHNOLOGIES CREATES
NEW VULNERABILITIES,
THE REPORT HIGHLIGHTS.
Europe, the Middle East, and Africa are
following closely, with stricter emissions
and safety regulations driving the
adoption of AI-powered maintenance.
“Environmental considerations are
pushing sustainable, efficiency-oriented
practices,” the report notes.
Asia-Pacific, particularly China,
India, and South Korea, is also experiencing
rapid growth due to industrialization
and strong government
support. High IoT adoption makes
the region ideal for implementing AIbased
solutions.
Startups Pushing Innovation
While tech giants like IBM, ABB, and
Siemens dominate in the industry,
startups are contributing to innovation.
“Agile companies are reshaping
the competitive landscape,” says
the report, citing firms like Clarifai,
Craftworks GmbH, and Nanoprecise.
Canadian startup Nanoprecise uses
44 maintworld 2/2025

MARKET RESEARCH
AI systems now flag early signs of issues, reducing the need to wait for breakdowns.
vibration sensors and AI to monitor
wear in machinery, making predictive
maintenance more accessible for
smaller manufacturers.
What’s Next?
Industry leaders must adopt a layered
strategy that combines technological
and operational initiatives, the report
suggests. First, investing in integrated
AI systems that aggregate and analyse
data from various sources is key.
Embracing cloud and edge AI will
improve predictive capabilities and
mitigate risks.
Cybersecurity should be a top
priority, as the convergence of IoT
and AI technologies creates new
vulnerabilities, the report continues.
Ensuring these systems are secure is
as critical as ensuring the accuracy
of predictive algorithms. Partnering
with technology providers that offer
comprehensive security solutions
will be essential.
Additionally, workforce training
and upskilling in AI and machine
learning will enable teams to stay agile
and adapt to technological changes.
Collaborations with tech vendors, academia,
and industry experts will keep
companies at the forefront of innovation.
Regular evaluations of predictive
maintenance systems will improve
maintenance outcomes and uncover
new business opportunities.
The key takeaway from the report?
The report makes it clear that predictive
maintenance is no longer optional.
It has become a strategic tool for performance,
resilience, and cost control.
Those who adopt it now—CIOs, plant
managers, and maintenance teams—will
not just save money; they will set new
standards for reliability in the age of AI.
Source: AI-Based Predictive Maintenance
Market Report 2025–2030:
A Projected US$1.69 Billion Landscape
– Businesses Must Invest in Cloud and
Edge Technologies for Future Success,
Research and Markets, April 2, 2025.
2/2025 maintworld 45

TECHNOLOGY
Text: DIEGO GALAR
Photos: ISTOCK, SHUTTERSTOCK Images: DIEGO GALAR
The Digital Twin Paradox:
Data Can Remember –
But Physics Knows
The concept of the digital twin has matured. What began as a passive mirror
of physical systems has evolved into a strategic, intelligent asset, capable of
sensemaking, foresight, and context-driven adaptation. This article explores how
digital twins have advanced through successive generations, why physics-based
modelling is now essential, and how hybrid approaches like Physics-Informed
Neural Networks offer the key to navigating unpredictable, high-risk scenarios—the
so-called Black Swan events.
46 maintworld 2/2025

TECHNOLOGY
Evolution of the Digital Twin: From Data to
Understanding
Digital Twin 1.0 emerged from the world of operational technology
(OT), characterized by real-time data acquisition
and system visualization. These early twins mirrored reality
without interpretation. They offered data, but not meaning;
measurements, but not insights. Their role was reactive, not
proactive. In a way, Digital Twin 1.0 was like a digital photograph—faithful,
detailed, and ultimately flat. There was no
depth, no sense of consequence, no capacity to engage with
time. The twin showed what was, but had nothing to say about
what could be.
Digital Twin 2.0 integrated IT and OT systems, expanding
the scope to include enterprise data, ontologies, and
structured coordination. It allowed visibility across operational
and managerial layers, allowing stakeholders
to ask, “What can I see and manage in my data?” While it
improved situational awareness, it still lacked the ability
to predict outcomes or guide actions. It was more like an
instrument panel than a mirror—a dashboard that contextualized
what had happened, but remained tethered to
retrospective logic.
Then came Digital Twin 3.0, and with it, a deeper awareness
of limitations. This phase highlighted a growing tension
between data science and the reality of industrial
systems when operations and maintenance professionals
encountered the limitations of purely statistical or blackbox
machine learning models. Algorithms might detect patterns,
but they could not explain them. A prediction without
understanding is like a prophecy—possibly correct, but fundamentally
unusable.
In this phase, digital twins began to resemble the portrait
of Dorian Gray: an image evolving in parallel with the physical
object, revealing degradation and change, but leaving us
uncertain as to what was driving the transformation. Beyond
reflection or replication, we needed reasoning. There was
a clear need for digital twins to become trustworthy decision
aids—not just dashboards or mirrors. That need laid the
groundwork for a new wave of hybrid approaches, in which
machine learning was enhanced with physics-based understanding.
This shift was not only technical, but also cultural:
engineers demanded interpretability, transparency, and
causal reasoning, arguing, "Without physics, we guess. With
physics, we project."
Data Aren’t Enough
The limitations of purely data-driven methods in industrial
contexts are well-documented. Traditional machine
learning often fails to generalize to unseen conditions or
rare events. It performs well when past patterns are stable,
frequent, and well-represented. But the real world rarely
behaves so cooperatively. In many cases, these models are
trained on narrow slices of history—bounded, biased, and
blind to what lies outside them.
When datasets are noisy, incomplete, or suffer from selection
bias, models become fragile. Perhaps most critically, they
produce results that are difficult for domain experts to interpret.
This lack of transparency isn’t merely inconvenient—it
can be dangerous. In safety-critical environments like energy,
transportation, or manufacturing, trust is not optional. If the
model can’t explain itself, engineers won’t act on it.
As systems grow more complex and interdependent,
organizations are confronted with a paradox: they have
more data than ever before, yet are increasingly unable to
convert those data into meaningful decisions. Retrospective
analytics focus on past correlations and cannot account for
emergent behaviours, cascading faults, or nonlinear dynamics.
They can tell us what happened, but not why—or what’s
about to happen next.
Even advanced deep learning architectures, powerful as
they may be, remain prisoners of their data. They extrapolate
patterns; they do not infer causality. They can classify failures
but rarely understand failure mechanisms. As a result, they
fall short in helping us manage uncertainty, assess risk, or
build resilient systems.
Without physics, data are directionless. They show movement
but not motive, change but not consequence. What
is needed is a new class of models—ones that can reason,
generalize, and anticipate. Only by embedding domain
knowledge, physical laws, and contextual understanding
into our models can we move from surface-level prediction
to strategic foresight.
2/2025 maintworld 47

TECHNOLOGY
Black Swan Events and Limits of Prediction
Black Swan events—rare, high-impact failures that escape
conventional forecasting—pose one of the greatest challenges
to modern predictive systems. These events may be triggered
by subtle system degradation, unexpected interactions
between components, or sudden environmental changes.
What makes them especially dangerous is their invisibility in
historical datasets: they lie outside the statistical envelope of
what has previously occurred.
The core issue is that traditional machine learning is retrospective.
It learns only from what it has seen. If a critical
failure mode has never been captured in data or has occurred
so infrequently that it leaves no meaningful statistical signature,
the system remains blind to it. This is the paradox of the
Black Swan: the more catastrophic the event, the less likely it
is to be represented in our records. Absence of data becomes a
dangerous illusion of safety.
In complex, tightly coupled industrial systems, this blind spot
is a systemic risk. These systems often operate across wide ranges
of physical conditions and are subject to wear, aging, and environmental
variation. Over time, they can drift into failure modes
that were never present in commissioning or early operation.
Machine learning, dependent on narrow training distributions,
cannot extrapolate meaningfully into these outlier states.
To address this, we must introduce the laws of physics as a
structural layer in our predictive architecture. Physics doesn’t
require observation to assert truth—it governs even in the
absence of data. By incorporating physical principles such as
conservation laws, thermodynamics, structural dynamics, or
fluid mechanics into our models, we can give them a broader
frame of reference. These principles can become a scaffolding
for uncertainty, constraining predictions to remain plausible
even when data are incomplete, noisy, or unprecedented.
The integration of physics is not just about increasing accuracy;
it is also about building resilience into the logic of prediction.
With physical knowledge embedded into them, systems
can run simulations of hypothetical conditions, stress-test
critical functions, and explore how anomalies might evolve—
long before those paths are evident in sensor data.
By moving beyond statistical mimicry and embedding an
understanding of how systems behave, we can start to detect
the early tremors of Black Swan events. Only then can predictive
systems evolve from pattern matchers into risk sentinels.
Articulating Physics through Synthetic
Data and Simulation
In the industrial world, the scarcity of failure data isn't just an
inconvenience—it’s a fundamental obstacle. Critical failures,
while rare and undesirable, are exactly the scenarios predictive
models need to understand. But when they do happen,
the conditions leading up to them are often chaotic, undocumented,
or too hazardous to safely replicate. This creates a
structural blind spot: the moments we most need to predict
are the ones we least understand.
To overcome this, industries are turning to virtual prototyping
and physics-based simulation as a new foundation
for intelligent modelling. Platforms like Modelica, finite element
modelling (FEM), and multi-body simulations allow engineers
to recreate both normal and failure-prone behaviours
of systems in controlled digital environments. These simulations
are not only safe—they are hyper-configurable, enabling
us to observe how a component responds under stress,
fatigue, corrosion, overload, or even misuse.
The result is a new class of training data: synthetic, scenario-rich,
and physically grounded. We can simulate how
a rolling bearing degrades under variable loads, how thermal
stresses propagate in a turbine, or how a gearbox responds to
lubrication loss. Every simulation becomes an experiment—
an opportunity to generate labelled datasets that fill the gaps
in historical operation.
Techniques such as fault injection, stress testing, and
parametric sweeping create data far beyond the reach
of real-world experimentation. Because these simulations
are based on first-principle physics, the resulting data both
reflect possible system behaviours and reinforce the laws
governing them.
Digital twins built on this foundation stop being passive reflectors
of yesterday’s data. Instead, they become experimental
testbeds, able to project future scenarios, evaluate resilience
strategies, and validate potential interventions without
touching the factory floor. In this way, synthetic data become
not a compromise, but a catalyst for more robust, resilient,
and explainable predictive models.
Physics-Informed Neural Networks:
From Data to Understanding
Synthetic data provide a plethora of rich behavioural patterns,
but it’s the learning method that determines how
much value we can extract from them. Traditional neural
networks, even when trained on large datasets, remain lim-
48 maintworld 2/2025

TECHNOLOGY
ited by their lack of interpretability and adherence to physical
constraints.
Physics-Informed Neural Networks (PINNs) revolutionize
how machine learning models interact with knowledge.
Unlike standard networks that learn correlations from data
alone, PINNs encode known physical laws, such as partial
differential equations, conservation of mass and energy, or
thermodynamic boundaries, into the model’s structure. These
equations shape the loss functions, enforce behavioural constraints,
and inject meaning into every parameter.
questions, simulate failure paths, and anticipate how systems
might evolve, not only statistically, but also structurally. For
instance, a PINN model trained on turbine dynamics can predict
the onset of blade fatigue long before vibration sensors
detect anomalies.
Ultimately, PINNs elevate digital twins from descriptive
to prescriptive intelligence. They do not just signal change—
they explain it. They do not just see risk—they understand it.
And in doing so, they lay the groundwork for a new generation
of industrial decision-making, one that fuses data science with
engineering judgment in practical and profound ways.
Conclusion: From Echoes to Insight
The evolution of digital twins is not just technological—it is
conceptual. Instead of acting as mirrors of the physical world,
twins are becoming intelligent agents that combine data,
physics, and simulation into decision-ready insight.
Hybrid approaches, especially those using PINNs, represent
the frontier of this transformation. They allow us to
embed knowledge into our machines, not just feed them
numbers. They empower us to detect the swan song of an asset
before silence falls.
Most importantly, they offer a path to true contextual intelligence,
turning overwhelming complexity into meaningful,
actionable understanding. As Europe pushes for digital sovereignty
and resilient infrastructure, the time to embed explainable,
physics-informed intelligence into our systems is now.
This fusion creates models that are not only data-aware
but also physics-consistent. PINNs can infer system behaviour
in unmeasured conditions, extrapolate to unseen
scenarios, and remain faithful to the physical truths engineers
depend on. This makes them particularly valuable in
data-scarce domains, where historical measurements are
insufficient or unreliable.
In the context of digital twins, PINNs act as intelligent
intermediaries between simulation and reality.
They use synthetic data not just to train, but also
to refine and validate system models in real time. Their
predictions come with physical justifications, enabling
engineers to see the twin not as a black box, but as a
knowledgeable collaborator.
PINNs enable faster simulations, more accurate anomaly
detection, and predictive capabilities that are both interpretable
and grounded. They allow us to pose “what-if”
2/2025 maintworld 49

COLUMN
How Industry 4.0 Revolutionized
Manufacturing and Maintenance
The term "Industry 4.0" often emerges in conversations about the future of manufacturing. Industry
4.0 is not merely a technological upgrade; it's a fundamental transformation in how factories operate.
THIS ongoing evolution promises not just
improved productivity but also enhanced
efficiency, reduced downtime and a greater
ability to meet customer demands.
What Is Industry 4.0?
Industry 4.0, often known as the fourth industrial
revolution, is a transformative shift
in the manufacturing sector resulting from
the adoption of cutting-edge technologies.
The major goal of Industry 4.0 is to build
smart factories and highly automated environments
in which machines, systems and
people all connect seamlessly.
Industry 4.0 refers to more than just
automation. It also involves intelligent automation,
in which systems may self-monitor,
self-diagnose and make data-driven decisions.
Deploying Industry 4.0 technology
can result in efficiency gains of up to 20% in
industrial operations.
Examples of Industry 4.0 in Action
Several industries lead the way in leveraging
the capabilities of Industry 4.0, such as:
CONSUMER GOODS
In the consumer goods market, manufacturers
use AI and IoT to monitor and
optimize production processes, minimize
waste and improve product quality. Smart
factories, for example, may alter the output
in real time in response to demand. This
ensures that items reach customers as
promptly as possible.
AUTOMOTIVE MANUFACTURING
In the automotive industry, IoT sensors
monitor manufacturing lines, AI predicts
goals for maintenance departments and
robots assemble parts precisely. This integration
results in enhanced productivity and
reduced downtime.
CORE TECHNOLOGIES THAT ENABLE
"MAINTENANCE 4.0"
Let's look at how Industry 4.0 technologies
are affecting maintenance methods in the
manufacturing sector.
50 maintworld 2/2025
LINDSEY
WALKER
is the marketing
manager for
NEXGEN Asset
Management. She
excels at business
development,
project management
and asset management. Her passion
for writing allows her to share her
knowledge on asset management, geographic
information systems (GIS), software
implementation, training curriculum
development and similar topics.
Saving Time and Money With Artificial
Intelligence
AI is a game changer in maintenance. It
provides predictive analytics, allowing you to
anticipate equipment issues before they occur.
AI can offer appropriate industrial maintenance
management goals based on historical
data, saving you both time and money.
Predictive Maintenance Via Industrial
Internet of Things (IIoT)
IIoT combines machines, sensors and devices
to establish a network that continuously
collects data. This connectivity provides realtime
monitoring and predictive maintenance,
allowing you to deal with issues proactively
rather than reactively.
MAINTENANCE RECORD ANALYSIS
THROUGH BIG DATA
Imagine having access to a wealth of information
that can help you predict equipment
failures before they happen. With big data
analytics, you can analyze patterns from past
maintenance records, usage statistics and
even environmental conditions. This allows
you to implement a strong maintenance plan.
Advantages of Implementing
Maintenance 4.0
As businesses shift to Industry 4.0, the significance
of implementing Maintenance 4.0
practices becomes clear. Here are some of
the advantages:
IMPROVED ASSET MANAGEMENT
WITH REAL-TIME INFORMATION
Real-time information enables producers
to monitor asset performance continuously.
This allows timely decision-making based
on reliable data, resulting in better resource
allocation and less waste. Companies using
real-time monitoring often claim an increase
in asset utilization.
REDUCED MAINTENANCE COSTS WITH
SMART INVENTORY MANAGEMENT
Intelligent inventory management solutions
assist firms in maintaining ideal inventory
levels, eliminating extra costs and guaranteeing
that vital items are always available.
PREDICTIVE MAINTENANCE HELPS
TO REDUCE DOWNTIME
Predictive maintenance uses data analysis
techniques to predict probable issues before
they occur, hence reducing unnecessary
downtime. Companies can save greatly by
decreasing equipment failures and increasing
asset life by setting correct maintenance goals.
To Summarize
Industry 4.0 brought tremendous change
to production environments. It has helped
define new maintenance management goals
through the integration of sophisticated
technologies that promote automation, connection
and efficiency.
Industry 4.0's components — IoT, AI, big
data analytics, cloud computing and cyberphysical
systems — are altering not only factory
maintenance processes but the entire
manufacturing ecosystem.
As you investigate the potential of these
technologies, think about how they may be
integrated into your operations to increase
efficiency, save costs, achieve maintenance
goals and improve product quality. Embracing
these developments is more than just
keeping up with the competition; it is about
long-term survival.
Remember there is always more to learn.
It's an important part of preparing yourself
to succeed in the new manufacturing era.

VA3 PRO EX
INTRINSICALLY SAFE
3-CHANNEL ANALYZER, DATA COLLECTOR,
BALANCER, AND MUCH MORE ...
MASTER THE LANGUAGE OF YOUR MACHINERY

INSTRUMENTS
INSTRUMENTS
Leak Detection
Leak
Leak
Detection
Detection
Bearing Condition Monitoring
Bearing
Bearing
Condition
Condition
Monitoring
Monitoring
Bearing Lubrication
Bearing
Bearing
Lubrication
Lubrication
Steam Traps & Valves
Steam
Steam
Traps
Traps &
Valves
Valves
Electrical Inspection
Electrical
Electrical
Inspection
Inspection
TRAINING
TRAINING
CAT & CAT II Ultrasound Training
CAT
CAT &
CAT
CAT
II
II
Ultrasound
Ultrasound Training
Onsite Implementation Training
Onsite
Onsite
Implementation
Implementation
Training
Training
Application Specific Training
Application
Application
Specific
Specific
Training
Training
YOUR
PARTNER IN
CONTINUOUS SUPPORT
CONTINUOUS SUPPORT
Free support & license-free software
Free
Free
support
support &
license-free
license-free
software
software
Online Courses
Online
Online
Courses
Courses
Free access to our Learning Center
Free
Free
access
access
to
to
our
our
Learning
Learning
Center
Center
(webinars, articles, tutorials)
(webinars,
(webinars,
articles,
articles,
tutorials)
tutorials)
ULTRASOUND
CONTACT
CONTACT US
US
FOR
FOR AN
AN ONSITE
ONSITE
DEMONSTRATION
DEMONSTRATION
UE
UE SYSTEMS
SYSTEMS
+31-546 725 125
+31-546
+31-546
725
725
125
125
www.uesystems.eu
www.uesystems.eu
www.uesystems.eu
info@uesystems.eu
info@uesystems.eu
info@uesystems.eu