基于代理模型和遗传算法的顺序注塑成型工艺优化

Optimization of Process Parameters in Sequential Injecting Molding Using Surrogate Model and Genetic Algorithm

提出了一种综合考虑常规注塑工艺参数与时序阀浇口参数,并集成响应面代理模型和遗传算法的优化策略,对顺序注塑成型工艺参数优化进行了研究。该策略以改善SIM制品综合品质为目标,基于中心复合试验和数值模拟结果,利用响应面代理模型构建SIM制品综合品质指标与工艺变量间的关系模型;采用遗传算法对模型进行优化以获取最优解。结果表明:基于时序阀控制的顺序注塑成型技术能有效地消除成形零件的熔接痕缺陷,构建的响应面代理模型能有效地描述SIM工艺变量对品质的影响关系。最后,对遗传算法得出的最优解进行模模拟分析验证,验证所提出优化策略的有效性。

A strategy which contains traditional injecting process parameters and valve gate settings was put forward. By integrating response surface surrogate model and genetic algorithm, the process parameters of sequential injection molding were studied. The strategy aimed to improve the SIM products＇ comprehensive qualities based on central composite experiment and numerical simulation results. The relation model of SIM products＇ comprehensive qualities between the process variables was built by using the response surface surrogate model. And then, the optimal solution was optimized by using the genetic algorithm. The results showed that sequential injection molding technology could effectively eliminate the welding defects of forming part. And the proposed response surface surrogate model could effectively describe the relationship of the SIM process variables impact on the quality. Finally, the optimal solution which calculated by the genetic algorithm was valid in the numerical simulation, and the result demonstrated the effectiveness of the proposed optimization strategy.