In order to reduce the high error rate and error rate of traditional methods， an intelligent fault location method of distribution network with distributed power supply based on improved particle swarm is proposed. The objective function considering node characteristics and topological changes is constructed， and the fitness function and improved switching strategy are combined to accurately model the fault location problem. At the same time， using the global awareness search strategy to improve the particle swarm optimization algorithm， through initialization， region division， particle iteration and accurate fault identification， it can effectively avoid premature convergence， and significantly improve the accuracy and efficiency of fault location. Experimental results show that both the error rate and the error rate of the proposed method are effectively controlled within 1%， which significantly improves the accuracy and reliability of fault location in distribution network with distributed power supply.