采用组合算法的注塑制品翘曲变形预测

Warpage Deformation Prediction of Injection Products with Combinatorial Algorithm

为提高对注塑制品翘曲变形的预测能力,以笔记本电脑电池盖为例,提出采用组合算法对注塑制品翘曲变形进行预测。首先,利用注塑成型模拟软件对电池盖进行9次模拟实验,获得其在工程推荐工艺参数下的翘曲变形量。以此为样本数据,通过最优权值系数将BP神经网络、灰色理论和遗传算法进行有效组合,建立3种组合预测模型,与3种单一预测模型共同对电池盖的翘曲变形量进行预测。其次,根据平方和误差、平均绝对误差和平均相对误差3种预测误差评价指标,对6种预测模型的预测结果进行对比分析。最后,通过电池盖的实际制造验证组合预测方法的准确性。研究结果表明:组合预测模型的准确性优于单一预测模型,其中组合算术平均模型的预测结果与实际测量值最为接近,最大误差不超过5%,能够实现对塑件翘曲变形的准确预测。该预测方法可为注塑制品翘曲变形的预测提供新思路。

To improve the predictive ability of warpage deformation of injection products,a new combination algorithm was proposed taking a notebook battery cover as the example.Simulation experiments were performed nine times on the battery cover using injection molding simulation software to obtain the warpage amount under the recommended engineering process parameters.The sample data,BP neural network,grey theory and genetic algorithm were effectively combined by the optimal weight coefficient to construct three combined forecasting models,together with three single prediction models to predict the warpage amount of the battery cover.Then based on the three kinds of prediction error evaluation indexes,the prediction results of six models were compared and analyzed according to the square sum error,average absolute error and average relative error.Finally,the accuracy of the combinatorial algorithm was verified by the battery cover manufacturing.The results show that the accuracy of the combined prediction model is better than that of single prediction model.The prediction result of the combined arithmetic average model gets the closest to the actual measuring value,and the maximum error is not more than 5%.The proposed combination prediction method can accurately predict the warpage amount of plastic parts.