Find in Library

High voltage transmission lines are utilized to transmit electrical energy from the source to the substations. If any fault and disturbance are generated in the transmission lines and not detected, located and eliminated quickly, it may cause instability in the system. This paper presents fault location recognition in Kurdistan Regional power transmission system using artificial neural network (ANN). Load flow and short circuit calculations were performed with Power World Simulator (PWS) software. All Kurdistan region power system has been divided into 40 buses. The calculated results of the currents and the voltages at both line ends were used to train the ANN in Matlab to obtain correct fault location. The training testing and evaluation of the intelligent locator is done based on a multilayer perceptron feed forward artificial neural network with back propagation algorithm. The ANN used to locate the fault have been trained with different available sets of data from the selected power system model. Several algorithms have been carried out in order to train the network such that it locates the fault based on the input data provided. Proposed algorithm was developed by injecting the data randomly and massively to in rich the trained network. None-trained data has been used to validate the network and the network was able to locate the faults exactly.