A recognition method of plate shape defect based on RBF-BP neural network optimized by genetic algorithm

Based on analysis of plate shape defect pattern in cold rolling, a defect recognition method using RBF-BP combinational neural network model optimized by genetic algorithm is proposed in this paper. The method makes use of genetic algorithm to optimize the weights and thresholds of the input layer, hidden layer and output layer in the RBF-BP network, and a GA-RBF-BP network model is formed. It can identify six membership degrees of common basic pattern of shape defect. The method better fuses the advantages of BP and RBF neural network by using genetic algorithm. Approaching speed of the network is faster and recognition accuracy is higher. In this paper, the proposed GA-RBF-BP model is simulated by MATLAB and compared with the simulation results of RBF-BP neural network. The results show that the GA-RBF-BP recognition method has a better effect than the RBF-BP network method. And it is also more suitable for real-time flatness control.