HVDC transmission line fault localization base on RBF neural network with wavelet packet decomposition

High voltage direct current (HVDC) transmission lines fault location is extremely important in repairing the fault line timely and reducing outage losses, so as to guarantee the reliability of power supply and to improve the stability of power system. Traveling wave, which is a kind of non-stationary signal with mutation, spreads along the line when HVDC transmission line fault happens. The feature of the traveling wave with mutation contains the fault time, fault location. By analyzing the traveling wave, accurate fault location can be derived. In this paper, an HVDC transmission line fault localization algorithm based on radial basis function (RBF) neural network with wavelet packet decomposition (WPD) is proposed. For the sake of simplicity, the proposed algorithm is shorted for WPD-RBF in the rest of this paper. By using WPD algorithm, the feature of the traveling wave can be extracted from the voltage and current signals. These features are then used as the training input sample of RBF neural network to mapping to the line fault location. Simulation result indicates that, line fault position can be accurately localized by the proposed algorithm.