Support Vector Machine Based Fault Classification and Faulty Section identification Scheme in Thyristor Controlled Series Compensated Transmission Lines

This paper presents a fault classification and faulty section identification scheme in Thyristor Controlled Series Compensator (TCSC) based transmission lines. The features derived from instantaneous current signals have been given to Support Vector Machine (SVM) classifiers for classifying faults and identifying faulty section. To validate the proposed method, a power system model with 400 kV, 300 km long, TCSC transmission line connected to sources at both the ends has been modelled using PSCAD/EMTDC. The SVM classifiers have been trained with 3,840 fault cases. Upon testing 14,400 fault cases with diversified fault and system scenario, the overall accuracy achieved for fault classification and faulty section identification with the proposed method is 99.83%.