Hydroelectric generating unit vibration fault diagnosis via BP neural network based on particle swarm optimization

In order to improve the correct rate, this paper puts forward a method of the vibration fault diagnosis of hydroelectric generating unit by neural network based on particle swarm optimization (PSO). Some fault characteristics through the feature extraction are selected as the inputs of neural network for training, then the fault diagnosis is accomplished via the trained and optimized neural network. The experimental result shows that this method gains good classification result, and it has a more rapid convergence speed and higher diagnosis precision than BP neural network model, which provides a new way in the field of fault diagnosis of hydroelectric generating unit.