Discrete wavelet transform and probabilistic neural network algorithm for fault location in underground cable

This paper proposes an algorithm based on a combination of discrete wavelet transform (DWT) and probabilistic neural network (PNN) for locating fault on underground cable. Simulations and the training process for the PNN are performed using ATP/EMTP and MATLAB. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from fault signals. The first peak time in first scale of each bus, that can detect fault, is used as input pattern for the training pattern. Various cases studies based on Thailand electricity distribution underground systems have been investigated so that the algorithm can be implemented. The results show that the proposed algorithm is capable of performing the fault location with satisfactory accuracy.