Application of BP Neural Network in Prediction of Cu-Pb Composite Plates Properties

The artificial neural networks( ANN),which have broad application,are proposed to develop Cu-Pb composite plates materials. Based on the back propagation( BP) algorithm of the forward multilayer perceptron, the model to predict the shear stress under different ingredient of the third element and the hot dipping temperature for Cu-Pb composite plates are established. Then the relational model among the third element,hot dipping temperature and shear stress by using the limited data are studied,and the forecast average error is 4%. This model can satisfy the requirements of the precision of forecast in the project experiment process. The results show that the corresponding shear stress is greater when the third element in the element contains more Sn; the most appropriate temperature of hot-dip plating about is 340 ℃,after predicted with lead / the third element / the best performance of copper composite material element of the third group is the one-element Sn,hot dip plating temperature is 335 ℃; two-element is 90% Sn 10% Bi,and hot dip plating temperature is 345 ℃. The prediction results can be used for a reference in instructing the further experimental design.