Using DEA's multi-choice method to reach multi-response optimization in Taguchi's problem

Abstract

Taguchi method is a traditional approach for robust experimental design that seeks to obtain a best combination set of factors/levels with lowest societal cost solution to achieve customers' requirements. So far, the Taguchi method can only be used for a single response problem; it cannot be used to optimize a multi-response problem. In this paper, an optimal procedure based on data envelopment analysis (DEA) for multi-response robust design is proposed. With the proposed procedure, a set of multiple responses for each combination of factors/levels (CFL) (the each CFL is named decision-making unit (DMU)) is firstly transformed into a relative efficiency value by DEA technique to obtain its relative performance. Then according to the relative performance, the multi-choice from the relative efficiency value 100% can assist engineers' favorite choice, which is also the best, and then the optimal factor/level combination will be determined. Two case studies in Su [1] are resolved by the proposed optimal procedure. Compared with Taguchi method and Su's method, the result deriving from the proposed optimal procedure indicates it offers a superior solution to the multi-response problems.