Comparing Multi‐response Design Methods with Mixed Responses
- 27 July 2004
- journal article
- research article
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 20 (5) , 527-539
Abstract
The multi‐response optimization process is commonly applied to engineering design problems involving more than one quality characteristic of interest. Define quality characteristics as output responses that fall into three general categories: larger‐the‐better (LTB), smaller‐the‐better (STB), and nominal‐the‐best (NTB). In the multi‐response optimization process, the objective is to define a set of input factors that, when combined, provide the optimal overall response. This paper investigates the relationship between response types when they are mixed (i.e. LTB, and/or STB, and/or NTB) and the choice of approach. The paper demonstrates that the mix of response types impacts the choice of final input parameters and response levels. In addition, the choice of an additive versus a multiplicative approach may adversely impact the response relationship. That is, it may produce two optimal combinations of factor settings or drive responses away from their target values and toward their extreme values. Copyright © 2004 John Wiley & Sons, Ltd.Keywords
This publication has 12 references indexed in Scilit:
- A Unified Approach for Dual Response Surface OptimizationJournal of Quality Technology, 2002
- Comparing methods for the multi‐response design problemQuality and Reliability Engineering International, 2001
- A COMPARISON OF MULTIRESPONSE OPTIMIZATION SENSITIVITY TO PARAMETER SELECTIONQuality Engineering, 1999
- A Compromise Approach to Multiresponse OptimizationJournal of Quality Technology, 1998
- Modified Desirability Functions for Multiple Response OptimizationJournal of Quality Technology, 1996
- The Exact Relation of Taguchi's Signal-to-Noise Ratio to His Quality Loss FunctionJournal of Quality Technology, 1990
- DiscussionJournal of Quality Technology, 1985
- Simultaneous Optimization of Multiple Responses Represented by Polynomial Regression FunctionsTechnometrics, 1981
- Response Surface Techniques for Dual Response SystemsTechnometrics, 1973
- `` Direct Search'' Solution of Numerical and Statistical ProblemsJournal of the ACM, 1961