Multiple Dynamic Quality Systems Using Hybrid Neuro-Ants Technique

Robust parameter design has been successfully applied to a variety of engineering problems for enhancing the robustness of the system; however, it cannot deal with multiple dynamic quality systems. Although several other approaches have been presented to resolve this problem, they are unable to efficiently treat the situations that the control factors have continuous values. This study incorporates desirability functions into a hybrid neuro-ants technique to optimize the parameter design of multiple dynamic quality systems with continuous parameters. The objective is to find the best parameter settings so as to maximize simultaneously the robustness of each response. The proposed approach is illustrated with a constructed example.