Application of NN as a scheme of off-line PD diagnosis method on traction motor stator coil

Insulation failure of traction motor stator coil depends on the continuous stress imposed on it and knowing the insulation condition is important for safe operation. In this paper, application of NN (neural network) as a scheme of off-line PD (partial discharge) diagnosis method, which occurs at the stator coil of traction motor, was studied. For PD data acquisition, three defective models are made; internal void discharge model, slot discharge model and surface discharge model. PD data for recognition were acquired from PD detector. Statistical distributions and parameters are calculated to distinguish between model discharge sources. Also these statistical distribution parameters are applied to classify PD sources by NN, with a good recognition rate on the discharge sources.