Fault Detection and Classification in Transmission Lines Using ANFIS

Abstract

This paper presents an application of ANFIS approach for automated fault disturbance detection and classification in transmission lines using measured data from one terminal of the transmission line. The ANFIS design and implementation are aimed at high-speed processing which can provide selection real-time detection and classification of faults. The ANFIS has been proposed not only to detect all shunt faults but also to identify the type of faults for digital distance protection system. The proposed technique is able to accurately identify the phase(s) involved in all ten types of shunt faults that may occur in a transmission line. The ANFIS's were trained and tested using various sets of field data. The field data are obtained from the simulation of faults at various points of a transmission line using a computer program based on Matlab. Various fault scenarios (fault types, fault locations and fault impedance) are considered in this paper. The inputs to ANFIS's are phase current and voltage measurement available at the relay location based on Root-Mean-Square values. The outputs of ANFIS's are 1 or 0 for detection of faults and type of fault. Through simulated process, the results indicate that the speed and selectivity of the approach are quite robust and provides adequate performance for a transmission and distribution monitoring, control and protection applications.