Motor fault diagnosis of RBF neural network based on immune genetic algorithm

RBF neural network is a single hidden layer of three-front network. Although approximation capacity, classification ability and learning speed of RBF neural network is superior to BP network, it is difficult to find the optimal value of the center point and width as well as the connection threshold, this article uses the immune genetic algorithm to optimize the three parameters of RBF neural network. First, determining the RBF neural network structure and hidden layer nodes; then using immune genetic algorithm to optimize these parameters; final, the optimized RBF neural network is used to predict motor failure. The experiments showed that the predict results of immune genetic optimized RBF neural network are significantly better than the direct result of RBF neural network both in the reproduction ability and in the generalization ability.