A New Approach to Ungrounded Fault Location in a Three-Phase Underground Distribution System using Combined Neural Networks & Wavelet Analysis

This paper presents the results of investigations into a new fault location technique based on a new modified cable model, in the EMTP software. The simulated data is then analysed using advanced signal processing technique based on wavelet analysis to extract useful information from signals and this is then applied to the artificial neural networks (ANNs) for locating ungrounded shunt faults in a practical underground distribution system. The paper concludes by comprehensively evaluation the performance of the technique developed in the case of ungrounded short circuit faults. The results indicate that the fault location technique has an acceptable accuracy under a whole variety of different systems and fault conditions.