Artificial neural network based fault locator for EHV transmission system

This paper describes the design and implementation of an accurate fault location technique using artificial neural networks (ANN) for the 400 kV Iranian transmission systems. The technique utilises voltage and current fault data at one line end only. These values are stored as waveform samples by a digital fault recorder (DFR) in the substations. The instantaneous three phase voltages and currents derived at the fault locator point on the line which contain fault information at different frequencies are used to train and test the artificial neural network (ANN). The paper presents the result of simulation studies to determine the performance and practical implementation of the technique.