Fault classification and location of power transmission lines using artificial neural network

This paper describes the application of an artificial neural network (ANN) based algorithm with modular structure to the fault classification and location of a single-circuit high voltage transmission line. Different fault types containing single-phase to ground, two-phase, two-phase to ground and three-phase are considered. The variation of fault resistance is considered, too. The operation of proposed strategy is not dependent on fault inception angle (FIA). A new classification method is proposed for decreasing of training time and dimensions of ANN. Using the proposed method, high accuracy of fault classification is achieved. Fundamental component of pre-fault and post-fault positive sequence component of currents and voltages of three phases have been used as inputs to proposed ANN. The output of the ANN is the estimated fault location. A two machine power system model is simulated by PSCAD/EMTDC to obtain the mentioned voltages and currents values. The neural network toolbox of MATLAB is used for training and testing of ANN.