论文部分内容阅读
以汽车内饰件中立柱上面板注塑成型为例,建立了模流CAE分析模型,运用Moldflow 2015软件对注塑成型工艺参数进行仿真,对注塑过程中的翘曲原因进行了分析;结合塑件的翘曲优化目标,提出了一种结合Tugachi正交试验法、BP神经网络、Matlab数值分析改善产品翘曲变形的注塑成型工艺参数寻优方法,基于此方法对注塑成型工艺参数进行了多次优化,并对优化结果进行了CAE模流分析验证。结果表明:神经网络预测结果与CAE模流分析结果相近,塑件最小翘曲量能降低至1.497 mm,对应的注塑成型工艺参数为:T_θ(205℃)、T_s(40℃)、P_I(60 MPa)、t_i(2.2 s)、P_(h1)(85 MPa)、t_(h1)(11.5 s)、P_(h2)(30 MPa)、t_(h2)(7 s)、t_c(20 s),将最终寻优所得参数输入注塑机,经试模验证后,产品注塑翘曲得到改善,与CAE分析预期值接近;提出的注塑参数优化设计方法能有效降低模具试模成本,缩短模具生产周期。
Taking the injection molding of the middle column of automobile interior trim as an example, a flow CAE analysis model was established, the injection molding process parameters were simulated by using Moldflow 2015 software, and the cause of warpage in the injection molding process was analyzed. Warping optimization goal, this paper proposed an optimization method of injection molding process parameters based on Tugachi orthogonal test method, BP neural network and Matlab numerical analysis to improve product warping deformation. Based on this method, the parameters of injection molding process were optimized several times , And the optimization results were verified by CAE mode flow analysis. The results show that the prediction results of neural network are similar to those of CAE mode flow analysis, the minimum warpage of plastic parts can be reduced to 1.497 mm, and the corresponding injection molding process parameters are: T_θ (205 ℃), T_s (40 ℃), P_I (20 s), t_i (2.2 s), P_ (h1) (85 MPa), t_ (h1) (11.5 s), P_ (h2) , The final optimization of the parameters obtained input injection molding machine, the test model validation, the product injection warpage improved, and CAE analysis of the expected value is close to; the proposed injection molding parameter optimization design method can effectively reduce the cost of die trial mold, shorten the mold production cycle .