Machinery Update July / August 2020

52 MACHINERY UPDATE JULY/AUGUST 2020 www.machineryupdate.co.uk
Feature: Automation, robotics & vision systems
Inspection is a very challenging stage in pharmaceutical manufacturing, so a ‘one size fits all’ approach will not work with Deep Learning
Whether in
automated
driving,
computer
games
or face recognition –
Artificial Intelligence (AI) is
transforming our everyday
lives and so why not also
apply them to pharmaceutical
inspection? “One of the
main challenges consists in
transferring these applications
to complex pharmaceutical
processes and developing
suitable implementation and
validation concepts for this
strictly regulated industry,”
says Andreas Gross, global
product manager inspection
technology at Syntegon
Technology. And here,
he explains the thinking
behind Syntegon’s latest
developments in this area.
Inspection is a very
challenging stage in the
pharmaceutical manufacturing
process. This is especially
true for products with difficult
characteristics, such as highly
viscous parenteral solutions
where air bubbles cannot be
completely eliminated and
their differentiation from
particles is problematic.
Those cases usually require
long development and
optimisation times for vision
algorithms before achieving
a balanced operational level
of detection and false reject
rates. AI has the potential of
shortening this development
period and optimising the
desired results more quickly.
Agglomerations or other
AI benefits
inspections
Syntegon is working to bring the benefits of AI and
Deep Learning to deliver life-changing pharma gain
types of inherent morphological
features that are similar to
particles, as well as bubbles
resembling glass particles,
can cause false rejection of
good containers with current
vision technology. Especially
for high-cost products, every
single false reject is one too
many. AI applications have the
potential of further increasing
detection rates and decreasing
the number of false rejects in
difficult products like bubbly
and dense solutions.
While many pharmaceutical
producers and machine
manufacturers are considering
the use of AI, and some
have already issued first
studies, reservations
about implementation and
validation are keeping most
companies from using these
applications in real production
environments. In parallel,
machine vision software
companies are already offering
Deep Learning vision tools as
part of their portfolios.
Hence, it is not necessary for
manufacturers of automated
vision inspection machines
to develop their own Deep
Reservations about validation
are keeping some companies from
using AI in pharma manufacturing
Learning algorithms or neural
networks. In fact, the existing
solutions only require moderate
software modifications.
Additionally, an upgrade of
the vision computers with
higher processing power
can be realised with Graphic
Processing Units (GPUs),
which are widely available in
the gaming industry.
Inspection technology
experts can easily perform
the required upgrades for
visual inspection usage, as
was discussed at the 2019 PDA
Visual Inspection Forum in
Washington DC. However,
there is one crucial point
that must be considered to
enable validation: in contrast
to many other industries,
the Deep Learning model for
pharmaceutical use must be
‘frozen’ once the development
▸