Premium
Comparing Multi‐response Design Methods with Mixed Responses
Author(s) -
Kros John F.,
Mastrangelo Christina M.
Publication year - 2004
Publication title -
quality and reliability engineering international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.913
H-Index - 62
eISSN - 1099-1638
pISSN - 0748-8017
DOI - 10.1002/qre.664
Subject(s) - multiplicative function , quality (philosophy) , response factor , set (abstract data type) , response surface methodology , process (computing) , design of experiments , mathematical optimization , response time , computer science , econometrics , response analysis , mathematics , statistics , engineering , chemistry , mathematical analysis , philosophy , computer graphics (images) , structural engineering , epistemology , chromatography , programming language , operating system
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.