Comparison of recognition rates between BP and ANFIS with FCM clustering method on off-line PD diagnosis of defect models of traction motor stator coil

In this paper, we compared recognition rates between NN (neural networks) and clustering methods as a scheme of off-line PD (partial discharge) diagnosis which occurs at the stator coil of traction motor. To acquire PD data, three defective models are made. PD data for recognition were acquired from PD detector. And then statistical distributions were calculated to classify model discharge sources. These statistical distributions were applied as input data of two classification tools, BP (back propagation algorithm) of NN and ANFIS (adaptive network based fuzzy inference system) using FCM (fuzzy clustering means) methods. So, classification rates of BP were somewhat higher than ANFIS performed preprocessing clustering method. But other items of ANFIS were better than BP; learning time, parameter number, capability on field, simplicity of algorithm.