sTRIVE final.pdf

levels and values for all identified
controllable and noise factors.
6 Developing Design for
Experimentation with the help of
Minitab Software.
The Taguchi’s method of statistical design
of experiments is done by using Orthogonal
Arrays. The choice of Orthogonal Array will
depend on the number of factors suggested
in step 5. Common arrays include an L8,
which looks at seven factors at two levels or
an L16, which looks at 15 factors at two
levels. An L8 or L16 array is ideal for initial
screening experiments.
7 Conducting the experiments as
per Designs and posting the
values in Minitab worksheet as
needed.
8 Analysis of data for selected
Quality Characteristics and
Interpretation of Analyses and
selection of the optimum levels
of the significant factors.
After collecting the data relating to
performance, against each of the critical
quality characteristics, it must be analyzed
to ascertain the precision and accuracy
achieved. This involves determining the
cause and effect relationship that exists
between the settings for each of the factors
and resulting performance on each measured
quality characteristic. Often this requires
several iterations of previous steps to arrive
at a full understanding of these relationships.
9 Prediction of the expected
results for optimal setting with
the help of Minitab.
10 Validation of optimal setting by a
confirmation Trails.
To verify that the relationships have been
correctly identified, the optimum settings for
the various factors are determined, and a
confirmation run carried out. This is
intended to ensure that the output is as
expected in terms of performance against
each quality characteristic and once
validated, these settings can then be
implemented as the new standard for each
factor.
Taguchi methods systematically reveal the
complex cause-effect relationships between
design parameters and performance. These
in turn lead to building quality performance
into processes and products before actual
production begins.
References
[1]. Montgomery, Douglas C., ‘Design and
Analysis of Experiments’, 5 th edition,
Wiley edition, 2006,
[2]. Bagchi, Tapan P., ‘Taguchi methods
explained – Practical steps to Robust
design’, Eastern Economy edition,
1993.
[3]. Christine Simms, John S. Garvin,
(2002),""It's a black art": "design of
experiments" switches on the light",
Managerial Auditing Journal, Vol. 17
Iss: 1 pp. 65 - 71
[4]. http://cms3.minitab.co.kr/board/minitab
_data/7.%20DesignofExperimentsAllT
opics.pdf
4
NOVEMBER 2012