Abstract: In view of problem that fault line selection method for small current grounding system is difficult to be suitable for different grounding modes, the paper proposed a fault line selection method for small current grounding system based on RBF neural network optimized by particle swarm. The method uses particle swarm optimization algorithm to optimize RBF neural network, takes parameters confirmed by the RBF neural network as particles of the particle swarm optimization algorithm. The simulation result shows that the method has high convergence efficiency, small sum of square of error, high accuracy of line selection, high sensitivity and a certain feasibility.