Metal stress state coefficient model based on RBF neural network

Stress state influence coefficient;  RBF neural networks;  Model

Based on the measured data of 4 steel plates rolled by 200 71 mm rolling mill, the RBF neural network prediction model of stress state coefficient in the rolling deformation zone was established by using the Matlab artificial neural network toolbox. By analyzing the influencing factors of the stress state coefficient and combining with the traditional mathematical model, the input layer parameters of the network are established, and the experimental adjustment of the width coefficient spread in the function newrb() determines the optimal network structure form, which improves the prediction accuracy of the model and the generalization ability of the network. The test results show that the RBF network model has good generalization ability. Compared with the traditional BP neural network model, the results show that the RBF network has higher accuracy and better generalization ability.