Application of Rbf Neural Network Improved by Pso Algorithm in Fault Diagnosis

The current fault diagnosis methods based on conventional BP neural network and RBF neural network exist long training time, slow convergence speed and low judgment accuracy rate and so on. In order to improve the ability of fault diagnosis, this paper puts forward a kind of fault diagnosis method based on RBF Neural Network improved by PSO algorithm. By using particle swarm algorithm’s heuristic global optimization ability, the connection weight values of RBF neural network are optimized. And then combined with RBF neural network’s nonlinear processing ability, transformer fault samples are trained and tested. The experimental results show that, compared with conventional fault diagnosis methods based on BP neural network and RBF neural network, the method based on RBF Neural Network improved by PSO algorithm can effectively avoid the problems of RBF neural network’s instability, RBF neural network easily falling into local minima and low correct diagnosis rate, which can effectively improve the convergence speed and the efficiency of fault diagnosis.