In this paper, a modified particle swarm optimization algorithm (MPSO) is proposed and implemented for identification of the generalized Prandtl–Ishlinskii model for piezoelectric actuators. To prevent the particles from converging to the local optimum, an effective informed strategy is proposed to improve the quality of the equilibrium point and balance the exploration and exploitation of the algorithm. Also, a random mutation operator is introduced to produce potential good particles and help the swarm jump out from the local optimum. The algorithmic parameters of the proposed MPSO are optimized via simulation. Experiments are carried out to verify the effectiveness of the proposed approach on a piezoelectric actuated platform. The MPSO is compared with the other methods in terms of accuracy and efficiency. The results demonstrate that the MPSO is superior to its competitors for identification of the generalized Prandtl–Ishlinskii model.