Fault diagnosis method based on wavelet neural network for power system turbo-generator

An effective method for composite fault diagnosis based on integration of wavelet transform and neural networks is presented. The, fault diagnosis model of turbogenerator set is established and a new method of detecting fault symptom signal based on discrete binary wavelet transform is discussed. Wavelet transform is used to extract effect character vector which is sent to neural networks to complete pattern recognition. With sufficient samples training, the type of fault mode can be obtained when signal representing fault is inputted to the trained neural networks. The diagnosis result approves to be accurate and comprehensive. The method can be generalized to other devices' fault diagnosis.