Multi-response robust design based on improved desirability function

摘要: Robust design, which is an important technology of continuous quality improvement activity, has been widely applied to optimal design product or process. In this paper, a new approach integrating improved desirability function and dual response surface models proposed tackle the problem multi-response robust design. We build two functions for mean variance through combining models, respectively. Furthermore, we separately give objective weights by using entropy weight theory. Then, overall considering location effect dispersion optimized hybrid genetic algorithm obtain optimum parameter settings. An example illustrated verify effectiveness method. The results show that can achieve more feasible