A single-phase ground fault location method based on transient resistance estimation

Abstract

In order to solve the problem of accurate single-phase ground fault location in distribution network, this paper proposes a single-phase ground fault location method based on transient resistance estimation and optimal search of fault location results. First, based on the fault characteristic data, the Extreme Learning Machine (ELM) transient resistance estimation model is trained to estimate the current fault transient resistance value. Then calculate the correlation between the current fault feature information and the segment fault feature information to determine the section where the current fault is located. Finally, an optimal search model of fault points based on the admittance matrix is established to realize the accurate location of single-phase ground fault within the segment. Simulation results show that the proposed method has accurate location results and strong anti-interference ability. Compared with the existing methods, it requires lower monitoring conditions and is more suitable for engineering practice.