Design‐of‐Experiments Methods and their Application to Robust Multicriteria Optimization Problems

Abstract

AbstractDesign‐of‐experiments (DOE) methods are utilized to explore the design space and to build response surface models in order to facilitate the effective solution of multiobjective optimization problems. Response surface models provide an efficient means to rapidly model the trade‐off between conflicting goals. For robust design applications these approximation models are used efficiently and effectively to calculate variances due to noise factors using Taylor series expansions. This combined‐army approach is compared to Taguchi's original crossed‐array approach. The shape optimization of a flywheel with two conflicting design goals is used to illustrate the approach.