Fuzzy cellular fault diagnosis of power grids based on radial basis function neural network

Abstract

A fuzzy cellular fault diagnosis method of power grids based on the radial basis function neural network is proposed for solving the transportability problem of adapting to the network topology changes when applying neural networks to fault diagnosis of power grids. This method takes single line, bus and transformer as a cellular object, and takes all the associated protective relays (PRs) and circuit breakers (CBs) used to protect the cellule as inputs to develop a generalized cellular neural network diagnostic model. Moreover, a method for automatic generation of the diagnostic model during fault diagnosis is presented. In addition, taking into account the fault information's characteristic of incompleteness and uncertainty, a fuzzy sagittal diagram for each cellular type is adopted to describe the logic reasoning relationships between the components, PRs, and CBs. From the diagram, multiple fuzzy reasoning rules containing uncertainties can be extracted to train the generalized cellular neural network. The simulation results show that the proposed method is simple, efficient, and can solve different complex faults. Moreover, it can effectively adapt to network topology changes and has good fault tolerance and transportability. © 2014 State Grid Electric Power Research Institute Press.