ANN Based Directional Fault Detector/Classifier for Protection of Transmission Lines

An accurate fault detection, classification and direction estimation of double end fed transmission lines based on application of artificial neural networks is presented in this paper. The proposed method uses the phase voltage and current available at only the local end of line. This method is adaptive to the variation of fault inception angle, fault location and high fault resistance. The algorithm detects the type of fault, identifies the faulted phase and the direction of fault whether it is forward or reverse fault. The Simulation results show that single phase-to-ground faults (both forward and reverse) can be correctly detected within one cycle time from the inception of fault. The proposed scheme allows the protection engineers to increase the reach setting upto 95% of the line length i.e. greater portion of line length can be protected as compared to earlier techniques in which the reach setting is 85% only. Large number of fault simulations using MATLAB® has proved the accuracy and effectiveness of the proposed algorithm. Keywords— Artificial Neural Network, Fault direction estimation and distance location.