Fault location using a new composite control technique, multiple classifier, and artificial neural network

Abstract

The aim of this project is to locate fault in the high voltage transmission line (TL) by adopting an accurate fault localization algorithm. First, the fault location was conducted using the conventional method of Ohm's law. Second, the algorithm was implemented by combining a multiple classifier along with Artificial Neural Network (ANN). Finally, the location of the fault was carried out by using Digital Signal Processing (DSP) based on the windowing technique and ANN. Source of input data is from the metering devices sampled using DSP technique. The collected data is then used to train the ANN, to locate the fault in order to reduce outage time, and minimize the cost of fixing the problem. Furthermore, all possible types of faults and locations were considered and tested to verify the proposed algorithm. Validation of these methods were done by using different types of real data networks that were saved in the MATLAB/SIMULINK.