Power transformer protection based on decision tree approach

Abstract

This study introduces the concept of decision tree (DT) classification, a new approach to power transformer differential protection. The proposed technique is based on processing the differential current. The suggested method detects winding insulation failures and distinguishes them from magnetising inrush and sympathetic inrush conditions with classification accuracies of 100% for simulations and 95% for real-time studies. The internal faults can be accurately recognised from inrush current conditions in a few sampling cycle after the occurrence of a disturbance. Another advantage of the proposed method is that the fault detection algorithm does not depend on the selection of thresholds. Performance analysis of the DT is achieved by the simulation of different faults and switching conditions on a power transformer in power system computer aided design/electromagnetic transients including DC (PSCAD/EMTDC). Furthermore, the proposed method is also tested in laboratory environment. The accuracy of DT is also compared with support vector machine. Both experimental and simulation results are presented and discussed.