Comparison of supervised machine learning techniques for PD classification in generator insulation

Abstract

Partial Discharge (PD) pattern analysis is widely used for condition assessment of generator stator winding insulation. The common PD sources of generator stator winding are slot discharge, end winding surface discharge, discharge at void in bulk insulation and discharge due to delamination on conductor surface and machine learning techniques are commonly used to discriminate them. This paper presents a comparison of different machine learning techniques to classify 352 Phase Resolved PD (PRPD) patterns obtained from a 37.5 MW, 12.5 kV generator. Ninety-six features representing each PRPD pattern were considered in this analysis. Based on the analysis, PRPD patterns were classified into different types of internal discharges. Nine different supervised machine learning algorithms under four different techniques i.e. functional based techniques, probabilistic techniques, decision tree models and nearest neighbor search were used. For the training process 70% of PRPD patterns were used whereas the remaining samples were used for the testing of the trained models. It was found that the accuracy is above 95% for most of the tested algorithms. It can be concluded that PDs in generator stator insulation can effectively be assessed by PD pattern classification through supervised machine learning techniques.