Support vector machine based fault section identification and fault classification scheme in six phase transmission line

Abstract

<p><span lang="EN-US">The higher complexity of a six phase transmission system (SPTS) construction and the large number of possible faults makes the protection task challenging. Moreover, the reverse &amp; forward path faults in SPTS cannot be detected by traditional relay as it becomes under-reach. In this paper, a support vector machine (SVM) method including Haar wavelets for SPTS fault section identification and fault classification is focused. The positive-sequence component phase angle and currents at middle two buses are used to formulate a suggested method. Feasibility of suggested SVM is tested with a 138 kV, 300 km, 60 Hz, SPTS in MATLAB based Simulink platform. Several major parameters including far end and near end location <span>conditions are taken to investigate the reach setting and accuracy of proposed SVM. This relaying method can detect the existence of fault in reverse &amp; forward</span> path in 1 ms time.</span></p>