Improving Robust Design with Preference Aggregation Methods

Robust design is a methodology for improving the quality of a product or process by minimizing the effect of variations in the inputs without eliminating the causes of those variations. In robust design, the putative best design is obtained by solving a multi-criteria optimization problem, trading off the nominal performance against the minimization of the variation of the performance measure. Because some existing methods combine the two criteria with a weighted sum or another fixed aggregation strategy, which are known to miss Pareto points, they may fail to obtain a desired design. To overcome this inadequacy, a more comprehensive preference aggregation method is implemented here into robust design. Three examples - one simple mathematical example, one multi-criteria structure design example, and one automotive example -- are presented to illustrate the effectiveness of the proposed method.

[1]  Carl D. Sorensen,et al.  A general approach for robust optimal design , 1993 .

[2]  Farrokh Mistree,et al.  A procedure for robust design: Minimizing variations caused by noise factors and control factors , 1996 .

[3]  S. Brown,et al.  Approximation of system reliability using a shooting Monte Carlo approach , 1994 .

[4]  George E. P. Box,et al.  Empirical Model‐Building and Response Surfaces , 1988 .

[5]  Kemper Lewis,et al.  Robust Design Through the Use of a Hybrid Genetic Algorithm , 2002, DAC 2002.

[6]  Wei Chen,et al.  Quality utility : a Compromise Programming approach to robust design , 1999 .

[7]  Xiaoping Du,et al.  A MOST PROBABLE POINT BASED METHOD FOR UNCERTAINTY ANALYSIS , 2000 .

[8]  A. E. Sepulveda,et al.  Approximation of System Reliabilities Using a Shooting Monte Carlo Approach , 1997 .

[9]  E. Antonsson,et al.  USING INDIFFERENCE POINTS IN ENGINEERING DECISIONS , 2000 .

[10]  Erik K. Antonsson,et al.  Aggregation functions for engineering design trade-offs , 1995, Fuzzy Sets Syst..

[11]  Achille Messac,et al.  Physical programming - Effective optimization for computational design , 1996 .

[12]  Kristin L. Wood,et al.  Computations with Imprecise Parameters in Engineering Design: Background and Theory , 1989 .

[13]  Wei Chen,et al.  Local approximation of the efficient frontier in robust design , 2000 .

[14]  Michael Joseph Scott,et al.  Formalizing Negotiation in Engineering Design , 1999 .

[15]  J. Dennis,et al.  A closer look at drawbacks of minimizing weighted sums of objectives for Pareto set generation in multicriteria optimization problems , 1997 .