基于代理模型和改进遗传算法的注塑翘曲优化

提出一种最小化制品翘曲的注塑工艺参数优化集成方法.以空调柜机顶盖注塑制品开发为例,该方法使用Moldflow软件分析制品的翘曲变形,运用田口方法确定与制品翘曲量密切相关的工艺因素,然后采用响应曲面法(RSM)和改进的精英保留自适应遗传算法(EAGA)相结合的方法,建立主要影响工艺参数与制品翘曲量之间的关系模型,通过对模型寻优以实现对制品翘曲的优化.该方法的适用性在制品的实际生产中得到了验证.

Surrogate model and improved genetic algorithm-based warpage optimization of injection molding

In this paper,an integrated optimization method was proposed to minimize warpage.An air-condition top cover was taken as an example in the research of warpage optimization of injection molding.Molflow software was used to analyze the warpage deformation of the injection-molded parts,and the significant process parameters influencing warpage were determined using FE analysis results based on Taguchi method.Then a predictive model for warpage index was created and the optimum process parameter values were solved by combining response surface methodology (RSM) and an effective genetic algorithm (GA) improved by using self-adaptive and elitism strategies.The actual production shows that the optimization method proposed is feasible and effective in processing plastic part.