Detection and Classification of Power System Faults using Discrete Wavelet Transform and Rule Based Decision Tree

This research work aims to present an approach supported by discrete wavelet transform and rule based decision tree for the detection and classification of different types of power system faults. Faults under investigation include, line to ground (LG) fault, line to line (LL) fault, double line fault with involvement of ground (LLG) and three phase fault with involvement of ground (LLLG). Current captured on a bus of the test system is used for the detection of the faults. The current signal is decomposed up to three levels of decomposition for detection of faults. A fault index using the sum absolute values of detail coefficients is proposed to detect different types of faults. Detailed simulation study is performed in MATLAB/Simulink environment using an IEEE-34 node test network. It is established that proposed method effectively detects and classify power system faults.