SME Logo
Chapter 4- Attractions and Benefits of the Taguchi Method (eChapter from A Primer on the Taguchi Method, 2nd Edition ) Image

Chapter 4- Attractions and Benefits of the Taguchi Method (eChapter from A Primer on the Taguchi Method, 2nd Edition )

Author(s)/Editor(s): Ranjit K Roy
Published By:

Published: 03/01/2010
Product ID:

Select Type:

SME Members: $ 8.00
Non members: $ 10.00


A Primer on the Taguchi Method, 2nd EditionThe Taguchi method offers two new powerful elements. First, the method is a disciplined way of developing a product or investigating complex problems. Second, it provides a means to cost-effectively investigate the available alternatives. Although Dr. Taguchi’s method was built on well-developed concepts of optimization through the design of experiments, his philosophy regarding the value of quality and the procedure for carrying out experiments were new. The power and popularity of the method lies in the discipline rather than the technique itself. The attractiveness and the resultant potential for cost savings will be reviewed in this chapter. The technique is applied in five steps, as follows: 1. Brainstorm the quality characteristics and design parameters important to the product/process under study, 2. Design the experiment and prescribe individual test recipes, 3. Conduct the experiments, 4. Analyze the results to determine the optimum conditions; 5. Run a confirmatory test(s) using the optimum conditions. Brainstorming is a necessary and important step in the application process. The nature and content of the brainstorming is dependent on the type of project under study. Taguchi recommends the participation of all relevant functional organizations, including marketing. Taguchi experiments are designed according to some strict rules. A set of orthogonal arrays (OAs) is used to design the experiments. A single OA may accommodate several experimental situations. Commonly used OAs are available for two-, three-, and four-level factors. Some standard arrays accommodate factors of mixed levels. In many situations, a standard OA is modified to suit a particular experiment that requires factors of mixed levels. The process of experiment design includes selecting the suitable OA, assigning the factors to the appropriate columns, and determining the conditions for the individual experiments. When noise factors are included in the experiment, the noise factor condition for each individual experiment is also determined. The signal-to-noise (S/N) ratio expresses the scatter around a target value. The larger the ratio, the smaller the scatter.