基于NSGA-Ⅱ和熵权TOPSIS法的注塑工艺参数多目标优化

Multi-objective Optimization of Injection Molding Process Parameters Based on NSGA-ⅡAlgorithm and Entropy Weight TOPSIS Method

以某汽车保险盒盖板为研究对象,针对体积收缩和表面缩痕较大问题,以塑件顶出时的体积收缩率和缩痕指数作为优化目标,选取保压压力、保压时间、熔体温度、模具温度等工艺参数为试验因素,采用最优拉丁超立方试验设计结合模流分析建立分析样本,构建试验因素与优化目标之间的Kriging代理模型,应用带精英策略的非支配排序遗传算法(NSGA-Ⅱ)在代理模型内进行全局寻优,得到多目标优化的Pareto解集,基于熵权逼近理想解排序法(TOPSIS),从Pareto解集中决策出一组最优工艺参数组合并进行模拟验证。结果表明,Kriging代理模型预测结果能较好地与试验结果吻合,优化后顶出时体积收缩率降低了26.26%、缩痕指数降低了79.66%,优化结果显著,为实际生产过程提供了有益参考。

An automotive cover plate was used as research object.In order to solve the problem of lagre volume shrinkage and surface sink marks,taking the volume shrinkage and sink index of the plastic part as the optimization targets,and the injection molding process parameters,such as,holding pressure,holding time,melt temperature and mold temperature as the experiment factors,the optimal Latin hypercube experimental design combined with mold flow analysis was used to establish the analysis samples.Then the Kriging agent models between each influencing experiment factors and the optimization objectives were constructed.Applying the non-dominated sorting genetic algorithm with elite strategy(NSGA-Ⅱ)to obtain the Pareto optimal solution sets of multi-objective optimization in Kriging agent models,based on entropy weight technique for order preference by similarity to ideal solution(TOPSIS),a set of optimal process parameter combinations was determined from the Pareto optimal solution sets,and the accuracy of the optimization method was verified by mold flow analysis.The results show that the prediction results of the Kriging agent model are in good agreement with the simulation test results.The amount of volume shrinkage during ejection after optimization reduces 26.26%,and the sink index reduces 79.66%.The optimization results of the article are significant,and provide a useful reference for the actual production process.