When the Jiles-Atherton (J-A) hysteresis model is applied to analyze the hysteresis loop of current transformer, it is necessary to accurately identify the five key parameters in the J-A hysteresis model. Since the existing identification methods have the problems of long calculation time and poor optimization ability, an improved particle swarm optimization algorithm is proposed to identify the key parameters of J-A hysteresis model. With the genetic selection strategy is introduced into the particle swarm optimization (PSO) algorithm, the global search ability of the algorithm is improved by increasing the diversity of the particle swarm optimization, so as to improve the accuracy of the identification of the key parameters of J-A hysteresis model. In this paper, the calculation speed and accuracy of the proposed improved algorithm (gss-pso) are compared with other intelligent algorithms in identifying the key parameters of J-A hysteresis model. The results show that the error of the hysteresis loop calculated by the improved algorithm is the least, and the identification efficiency is higher, which proves the accuracy and effectiveness of the algorithm in parameter identification of J-A hysteresis model.