Abstract: Most of the current intelligent algorithms are prone to local optimum when solving the parameter identification problem of proton exchange membrane fuel cells model,which results in low parameter identification accuracy and poor model generalization ability.To solve this problem,a parameter identification method of proton exchange membrane fuel cell based on improved chicken swarm optimization algorithm is proposed in this paper. Firstly,the Tent mapping strategy is introduced to initialize the population,as well as enhance the ergodicity and uniformity of the population. Secondly,the adaptive inertia weight based on individual feeding speed is designed to improve the optimization efficiency of individual hens,which tries to balance the exploitation and exploration ability of the algorithm. In addition,the long and short jump characteristics of Levy flight strategy is used to randomly update the position of chicken,so as to enhance the algorithm’s global search ability. Finally,the superiority of the algorithm is verified through the test functions of four groups,and the algorithm is applied to the parameter identification of H-12 stack. According to the results,it indicates that the algorithm has higher parameter identification accuracy and stronger generalization ability in contrast with whale optimization algorithm,flower pollination algorithm and so on.