Application of Radial Basis Neural Networks in Fault Diagnosis of Synchronous Generator

This paper presents the application of radial basis neural networks to the development of a novel method for the condition monitoring and fault diagnosis of synchronous generators. In the proposed scheme, flux linkage analysis is used to reach a decision. Probabilistic neural network (PNN) and discrete wavelet transform (DWT) are used in design of fault diagnosis system. PNN as main part of this fault diagnosis system and DWT are combined effectively to construct the classifier. The PNN is trained by features extracted from the magnetic flux linkage data through the discrete Meyer wavelet transform. Magnetic flux linkage data is provided by a FEM (Finite Element Method) simulation of a real synchronous generator and estimated by generalized regression neural network (GRNN). Then PNN is tested with experimental data, derived from a 4-pole, 380V, 1500 rpm, 50 Hz, 50 KVA, 3-phase salient-pole synchronous generator.