Study of gearbox fault diagnosis based on a modified PSO algorithm

Particle swarm optimization algorithm with adaptive velocity (VPSO) has been proposed, based on the moving maximum limited velocity set in original particle swarm optimization (PSO) algorithm, in this paper. The testing results by neural network show that this algorithm is better than original PSO in convergent speed and accuracy, and its parameters selection is flexible and is easily realized. The modified algorithm has been applied to fault diagnosis system of neural network for an experimental gearbox, and compared to the PSO and back propagation neural network (BP) algorithm. The conclusion is that VPSO applying to fault diagnosis system not only has higher discrimination for gearbox faults, but also greatly improves the accuracy and efficiency of fault diagnosis.