Академический Документы
Профессиональный Документы
Культура Документы
TAGUCHI
METHOD
SECOND EDITION
Ranjit K. Roy
Copyright © 2010 Society of Manufacturing Engineers
987654321
ACKNOWLEDGMENTS
This book would not be in circulation today without the Society
of Manufacturing Engineers undertaking continued printing of the
first edition after the original publisher folded technical publish-
ing activities. For this second edition, I am indebted to Rosemary
Csizmadia of SME, who was relentless in her conviction of market
demand for the book even in difficult economic times. I would also
like to thank Ellen Kehoe of SME for her grasp of language and
insight into the technology in editing the manuscript.
I am grateful to my professional and business associates, Larry
Smith, Mike Comerford, Greg Adams, Larry Tracey, Dave White,
and Jay Chandra, for their trust in my ability to support their clients
seeking training and application of the Taguchi technique. I would
like to express my sincere thanks to Larry Smith, in particular, who
spent an extraordinary amount of time on a meticulous review, and
to Andrea Stamps, Kush Shah, Side Zhao, Fred Schenkelberg, and
Pradeep Kumar for their detailed and constructive suggestions.
Finally, I thank my wife, Krishna, who has put up with my
dedication to the life of an independent consultant, trainer, and
author for more than two decades.
Ranjit K. Roy
January 2010
Contents
Preface .......................................................................................................................... ix
Abbreviations and Symbols ........................................................................... xii
3 Measurement of Quality
THE QUALITY CHARACTERISTIC ........................................................................................ 25
VARIATION AS A QUALITY YARDSTICK .............................................................................. 26
COST OF VARIATION .......................................................................................................... 27
QUALITY AND VARIATION ................................................................................................. 27
THE QUALITY WE ARE AFTER ............................................................................................ 29
vi A Primer on the Taguchi Method
7 Loss Function
DERIVATION OF LOSS FUNCTION .................................................................................... 185
AVERAGE LOSS FUNCTION FOR PRODUCT POPULATION ............................................... 189
APPLICATION OF LOSS FUNCTION CONCEPTS ............................................................... 189
LOOKS OF PERFORMANCE IMPROVEMENT ..................................................................... 196
EXERCISES ................................................................................................................ . 202
BACKGROUND
Mankind has always had a fascination with quality. Today’s
technology is testimony to man’s incessant desire to provide a
higher level of quality in products and services to increase market
share and profits. Sometimes quality is essential. A pacemaker that
controls heart action must operate continuously and precisely. An
erratic pacemaker is valueless, useless, and dangerous.
Driven by the need to compete on price and performance and
to maintain profitability, quality-conscious manufacturers are
increasingly aware of the need to optimize products and processes.
Quality achieved by means of design optimization is found by many
manufacturers to be cost effective in gaining and maintaining a
competitive position in the world market.
Response
68
Similarly, the main effect for 64 Sugar level 65
chocolate chips is 22.5%. It 60
is important to note that, in 56 55
this example, only the main 52 S1
effects are analyzed; no at- 48
44 45
tempt is made to analyze the
40
interactions between the fac- C1 C2
EXERCISES
1-1. What are the three main disadvantages of the conventional
design of experiments approach as compared with Taguchi’s
method?
1-2. Which one of the two factor effect graphs in Figure 1-2 indi-
cates the existence of an interaction between the two factors
of an experiment?
1-3. A product involves three primary parameters at three differ-
ent levels of each. To optimize the product, a full factorial
design is planned for experimental evaluations. How many
possible design configurations need to be tested to achieve
the objective?
1-4. Draw a factor graph for the experiment shown in Table 1-3
and discuss the results.
Quality Through Product and Process Optimization 7
B2 B1
Response
Response
B1 B2
A1 A2 A1 A2
Factor A Factor A
B2 65 45 B2 =
Average A1 = A2 =
Response to A
(A2 – A1)
2 Taguchi Approach to
Quality and Cost
Improvement
BACKGROUND
After the Second World War, Allied forces found the quality of
the Japanese telephone system to be extremely poor and totally
unsuitable for long-term communication purposes. To improve
the system to a state-of-the-art level, the Allied command rec-
ommended that Japan establish research facilities similar to the
Bell Laboratories in the United States. The Japanese founded the
Electrical Communication Laboratories (ECL), with Dr. Genichi
Taguchi in charge of improving R&D productivity and enhancing
product quality. Taguchi observed that a great deal of time and
money was expended in engineering experimentation and testing,
with little emphasis on the process of creative brainstorming to
minimize the expenditure of resources.
Taguchi started to develop new methods to optimize the
process of engineering experimentation. He developed the
techniques that are now known as the Taguchi Methods. His
greatest contribution lies not in the mathematical formulation
of the design of experiments (DOE) but rather in the accompa-
nying philosophy. His approach is more than a method to lay
out experiments. It is a concept that has produced a unique
and powerful quality improvement discipline that differs from
traditional practices.
Two completely opposing points of view are commonly held
about Taguchi’s contribution to the statistical design of experi-
ments. One view holds that his contribution to the field of quality
control is one of the most significant developments of the last
few decades. The other view maintains that many of the ideas
10 A Primer on the Taguchi Method
TAGUCHI PHILOSOPHY
Taguchi espoused an excellent philosophy for quality control
in the manufacturing industries. Indeed, his doctrine is creating
an entirely different breed of engineers who think, breathe, and
live quality. He has, in fact, given birth to a new quality culture
in this country. Ford Motor Company, for example, decreed in the
early 1990s that all Ford Motor and suppliers’ engineers be trained
in the Taguchi methodology and that these principles be used
to resolve quality issues. Taguchi’s philosophy has far-reaching
consequences, yet it is founded on three very simple and funda-
mental concepts. The whole of the technology and techniques arise
entirely out of these three ideas. These concepts are:
1. Quality should be designed into the product and not
inspected into it.
2. Quality is best achieved by minimizing the deviation from a
target. The product should be so designed that it is immune
to uncontrollable environmental factors.
3. The cost of quality should be measured as a function of
deviation from the standard, and the losses should be
measured system-wide.
Taguchi built on W.E. Deming’s observation that 85% of poor
quality is attributable to the manufacturing process and only 15%
to the worker. Hence, Taguchi developed manufacturing systems
that were “robust” or insensitive to daily and seasonal variations
of environment, machine wear, and other external factors. The
three principles were his guides in developing these systems,
Taguchi Approach to Quality and Cost Improvement 11