In order to obtain accurate parameters for a drive-train model, a method for parameter identification of a three-mass drive-train system with gusty wind excitation is proposed. According to the decoupling of the mechanical dynamics and electrical dynamics of fixed-speed wind turbine generators, the electrical dynamics can be neglected when identifying parameters of a drive-train model. Based on this, a simplified model for fixed-speed wind turbine generators was obtained. The identifiability of the parameters of the drive-train system and the difficulties in parameter identification were analyzed with the trajectory sensitivity analysis method. Finally, the parameters of the drive-train model were identified based on the particle swarm optimization(PSO)algorithm. The identified results are consistent with the trajectory sensitivity analysis results, verifying the feasibility of the proposed parameter identification method.