Using Multi-Population Intelligent Genetic Algorithm to Find the Optimal Parameters for a Nano-Particle Milling Process
Nano-particles have been successfully and widely applied in many applications. The wet-type mechanical milling process is a popular method used to produce nano-particles. Therefore, it is very important to improve the milling process capability and quality by setting the optimal milling parameters. In this study, an integrated method is proposed to find the optimal process parameters for the nano-particle milling process. First, the orthogonal array (OA) experiment is applied to obtain the analytic data of the milling process. Then the response surface method (RSM) is applied to modeling the nano-particle milling process and calculate the objective (fitness) value, and the generalized Pareto-based scale-independent fitness function (GPSIFF) is used to define the non-dominated solutions. Finally, the multi-population intelligent genetic algorithm (MPIGA) is proposed to find the Pareto-optimal solutions. The results show that the integrated MPIGA, RSM and GPSIFF approach can generate the Pareto-optimal solutions for the decision maker to set the optimal parameters in the nano-particle milling process.
Manufacturing Nano-particle Multi-objective genetic algorithm Pareto-optimal
Chi-Hung SU Tung-Hsu HOU
Department of Industrial Engineering and Management,National Yunlin University of Science and Technology,123 University Road,Section 3,Douliu,Yunlin 640,Taiwan,China
国际会议
北京
英文
2007-05-30（万方平台首次上网日期，不代表论文的发表时间）