Abstract: To address the issues of low accuracy and long computation time in parameter identification of surface-mounted permanent magnet synchronous motors (PMSM), an improved coati optimization algorithm (ICOA) is proposed. The improved algorithm integrates a piecewise linear chaotic map (PWLCM) to enhance the randomness and diversity of the initial raccoon population, employs an orthogonal-Lévy global explorer to enrich search trajectories and improve global exploration ability, and introduces an adaptive normal cloud model with population diversity indicators and iteration progress factors to overcome premature convergence. A mathematical model of the surface-mounted PMSM is established, and the ICOA is applied to identify the permanent magnet flux linkage, d-q axis inductances, and stator resistance. The simulation results indicate that compared to the traditional COA algorithm, the identification accuracy of the four parameters improved by 12.33%, 2.75%, 1.13%, and 0.75%, all within 1.7%.