论文部分内容阅读
基于Moldflow模拟仿真的结果,结合GA算法优化BP网络的结构,建立了模具温度,熔体温度,保压压力,注射速度等工艺参数与塑件体积收缩率的BP网络模型.获得了最优的工艺参数组合,同时预测结果与实际结果吻合.通过神经网络算法(BP)预测注塑工艺参数对塑件质量的影响,可以有效降低其他建模方法的难度和工作量,方法可以推广到塑件其他质量预测过程中.
Based on the results of Moldflow simulations and the optimization of BP network structure with GA algorithm, a BP network model of process parameters such as mold temperature, melt temperature, packing pressure, injection speed and volume shrinkage of plastic parts was established. The optimal The results show that the predicted results are in good agreement with the actual results.The prediction of the influence of injection molding process parameters on the quality of plastic parts by the neural network algorithm can effectively reduce the difficulty and workload of other modeling methods and can be extended to plastic parts and other Quality prediction process.