ANFIS Based DC Offset Removal Technique for Numerical Distance Relaying

Abstract

In this paper, an adaptive neuro-fuzzy inference system (ANFIS) is proposed to extract the fundamental component of the fault current utilizing the advantages of fuzzy logic and neural networks. The grey wolf optimizer algorithm (GWO) is utilized to estimate the fault current parameters. The proposed model is tested using both synthesized and simulated signals using Matlab software. The simulation is performed for different operating conditions by altering DC decaying current, time constant, harmonics, fault locations, fault resistance, and inception angels. The performance of the proposed technique is compared with that of the half cycle discrete Fourier transform (HCDFT) in the presence of the DC decaying current. The simulation results show that the ANFIS based technique accurately estimates the DC decaying current and extracts the fundamental component from the fault current within half a cycle following fault inception.