Fault classification technique for series compensated transmission line using support vector machine

Abstract

This paper presents a new fault classification technique using support vector machine (SVM) for a series compensated transmission line with a fixed series capacitor placed at the middle of the line. The proposed method uses the samples of one cycle duration of three line currents ( I R , I Y and I B ) and zero sequence current ( I 0) as features of SVM to accomplish the fault classification task. For each of these four currents ( I R , I Y , I B and I 0), one corresponding SVM has been used. The samples of individual line currents and zero sequence current are fed to individual SVMs which, in turn, identify the involvement of the corresponding phase or ground in the fault. The feasibility of the proposed algorithm has been tested on a 300 km, 400 kV series compensated transmission line through detailed digital simulation studies using PSCAD/EMTDC for a large data set of 25,200 test cases comprising of all the 10 types of faults with varying fault resistances, different fault inception angles, different fault positions (before and after series capacitor), pre-fault power transfer levels, percentage compensation levels and source impedance values. The results indicate that the proposed technique is fast, accurate and robust for a wide variation in system and fault conditions.