论文部分内容阅读
电刷镀制备Al2O3-13%TiO2(AT13)复合陶瓷涂层是1个多参数耦合的非线性过程。在分析工艺参数对涂层厚度影响的基础上,通过实验采集样本,建立预测涂层厚度的误差反向传播(back propagation,BP)人工神经网络模型。为验证人工神经网络预测模型的准确性,将该模型的预测结果与多元线性回归模型(multiple linear regression model,MLR)的预测结果进行对比。结果表明:与传统多元线性回归模型相比,人工神经网络模型能捕捉工艺参数的非线性规律,能更好地预测涂层厚度,拟合优度R2达到0.86,模型具有较强的泛化能力和自适应能力,为实现电刷镀制作过程中涂层厚度的实时预测与控制提供参考。
Brush plating preparation of Al2O3-13% TiO2 (AT13) composite ceramic coating is a nonlinear multi-parameter coupling process. Based on the analysis of the influence of process parameters on the thickness of the coating, samples were collected through experiments to establish a back propagation (BP) artificial neural network model that predicts the thickness of the coating. To verify the accuracy of the ANN prediction model, the prediction results of this model are compared with those of the multiple linear regression model (MLR). The results show that compared with the traditional multiple linear regression model, the artificial neural network model can capture the non-linearity of the process parameters and predict the thickness of the coating better. The goodness-of-fit R2 reaches 0.86 and the model has strong generalization ability And self-adaptive ability to provide reference for real-time prediction and control of coating thickness in the process of brush plating.