Research of motor fault diagnosis based on PSO algorithm

Aiming at improving the convergence performance of conventional BP neural network, this paper presents a PSO algorithm instead of gradient descent method to optimize the weights and thresholds of BP network. The way of the algorithm is that in each iteration loop, on every dimension d of particle swarm containing n particles, choose the particle whose velocity is smallest to mutate its velocity according to some probability. The method could avoid the particle sticking to the local minimum effectively, also the new method could improve the convergence ability of BP network. Simulation results show that the new algorithm is very effective. It is successful to apply the algorithm to motor rotor broken fault diagnosis.