A Machine Learning and Wavelet-Based Fault Location Method for Hybrid Transmission Lines

Abstract

This paper presents a single-ended traveling wave-based fault location method for a hybrid transmission line: an overhead line combined with an underground cable. Discrete wavelet transformation (DWT) is used to extract transient information from the measured voltages. Support vector machine (SVM) classifiers are utilized to identify the faulty-section and faulty-half. Bewley diagrams are observed for the traveling wave patterns and the wavelet coefficients of the aerial mode voltage are used to locate the fault. The transient simulation for different fault types and locations are obtained by ATP using frequency-dependent line and cable models. MATLAB is used to process the simulated transients and apply the proposed method. The performance of the method is tested for different fault inception angles (FIA), different fault resistances, non-linear high impedance faults (NLHIF), and non-ideal faults with satisfactory results. The impact of cable aging on the proposed method accuracy is also investigated.