Integration of the response surface methodology with the compromise decision support problem in developing a general robust design procedure

Wei Chen*, Kwok Leung Tsui, Janet K. Allen, Farrokh Mistree

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapter

32 Scopus citations

Abstract

In this paper we introduce a comprehensive and rigorous robust design procedure to overcome some limitations of the current approaches. A comprehensive approach is general enough to model the two major types of robust design applications, namely, robust design associated with the minimization of the deviation of performance caused by the deviation of noise factors (uncontrollable parameters), and robust design due to the minimization of the deviation of performance caused by the deviation of control factors (design variables). We achieve mathematical rigor by using, as a foundation, principles from the design of experiments and optimization. Specifically, we integrate the Response Surface Method (RSM) with the compromise Decision Support Problem (DSP). Our approach is especially useful for design problems where there are no closed-form solutions and system performance is computationally expensive to evaluate. The design of a solar powered irrigation system is used as an example. Our focus in this paper is on illustrating our approach rather than on the results per se.

Original languageEnglish (US)
Title of host publication21st Annual Design Automation Conference
Pages485-492
Number of pages8
Volume82
Edition1
StatePublished - Dec 1 1995
EventProceedings of the 1995 ASME Design Engineering Technical Conference - Boston, MA, USA
Duration: Sep 17 1995Sep 20 1995

Other

OtherProceedings of the 1995 ASME Design Engineering Technical Conference
CityBoston, MA, USA
Period9/17/959/20/95

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Integration of the response surface methodology with the compromise decision support problem in developing a general robust design procedure'. Together they form a unique fingerprint.

Cite this