Advanced Fault Section Estimation System for Power Networks Based on Hybrid Fuzzy System and Radial Basis Function Neural Network

Abstract

Abstract Although the radial basis function neural network (RBF NN) offers a potential solution for fault section estimation (FSE) in power networks, it has to be totally retrained for the case of power network topology change or power network expansion and cannot provide any explanations for its diagnosis results due to the blackbox nature of the neural network. In this paper, the functional equivalence between RBF NN and fuzzy system (FS) is built up for FSE problem throughout the neural network training process. Furthermore, based on this point, a novel retraining strategy is presented for RBF NN, which can extract the unchanged knowledge from the original RBF NN and then insert the knowledge back to the new RBF NN about the changing part of the power network in the case of network topology change or expansion. The retraining strategy has been implemented and tested in a 4-bus power system. The simulation results show that the advanced FSE system with hybrid FS and RBF NN works successfully and efficiently in power networks.