Discrete wavelet transform and back-propagation neural networks algorithm for fault classification in underground cable

This paper proposes a new technique using discrete wavelet transform (DWT) and back-propagation neural network (BPNN) for fault classifications on underground cable. Simulations and the training process for the back-propagation neural network are performed using ATP/EMTP and MATLAB. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from these signals. Positive sequence current signals are used in fault detection decision algorithm. The variations of first scale high frequency component that detect fault are used as an input 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 are shown that an average accuracy values obtained from BPNN can indicate the fault classification with satisfactory accuracy, and will be very useful in the development of a power system protection scheme.