Transient actions analysis of power transformers based on S-transform and hidden Markov model

In this paper, the most important problem in the transformer relaying which is based on differential protection has been taken into consideration, and an effective solution has been proposed. When an internal fault occurs, as the differential current increases, relays should trip, but in the case of magnetizing inrush current which has almost the same amplitude as internal fault, it should stop wrong action. Hence, a method which can discriminate magnetizing inrush current from internal fault is required. Sometimes, when an external fault occurs, the magnitude of differential current can increase and leads to incorrect performance of differential relays. Therefore in the proposed method, discrimination of external fault from two former signal types is considered as well. The method proposed is based on the combination of S-transform and hidden Markov model (HMM). S-transform is used to extract some useful time-frequency information of the input signal, and then HMM is applied to classify signals by means of features extracted using S-transform. Classification process is performed in two different and independent routes (MAC and SDC routes). In the overall classification, results of both previous routes are considered to ensure this classification is very much reliable in different testing situations. Simulation process is performed by means of the combination of PSCAD/EMTDC and MATLAB software, and the effectiveness of the proposed technique has been verified with test cases. Copyright (C) 2013 John Wiley & Sons, Ltd.