Efficient optimization of the multi-response problem in the taguchi method through advanced data envelopment analysis formulations integration

Abstract

This study introduces an innovative strategy to address the multi-response challenge inherent in the Taguchi Method, frequently encountered in the enhancement of production processes and productivity indices. By integrating the Taguchi Method with Data Envelopment Analysis (DEA), experimental trials are transformed into Decision Making Units (DMUs), with response variables categorized as inputs and outputs. Advanced DEA models, including simultaneous DEA and super-efficiency models, are employed to determine the DMUs’ relative and cross efficiencies, thus retaining the advantages of the Taguchi Design of Experiments (DoE) while offering an optimal solution for enhancing multiple quality responses. The superiority of this approach is validated by the Addictive Model for Factor Effects, demonstrating enhanced outcomes and reduced computational effort compared to existing empirical and scholarly solutions. These findings have significant implications for advancing manufacturing practices that require multi-response optimization, marking a notable contribution to the field.