To overcome the inherent deficiencies in the particle swarm optimization(PSO)algorithm, such as premature convergence, and to take into account the effects of inertia weight on the identification accuracy, an improved PSO algorithm, which combines the adaptive inertia weight PSO algorithm with the global optimum location mutation PSO algorithm, is proposed in this paper, in order to identify the double-fed induction generator(DFIG)parameters. First, the identifiability of the DFIG parameters and the difficulties in identification are analyzed. Then, the identification steps based on this improved PSO algorithm are illustrated. Compared with the basic PSO algorithm, the adaptive inertia weight PSO algorithm, and the global optimum location mutation PSO algorithm, the proposed algorithm has faster convergence, smaller errors, and higher identification accuracy, even at a wide search range.