To solve the shortcomings of the permanent magnet synchronous motor (PMSM) control strategy, which is highly dependent on the motor parameters, an improved deadbeat predictive current control (DPCC) model Super Twisting Algorithm (STA) control is proposed. Firstly, the robust current control model is used to improve the stability of deadbeat predictive current control against inductance mismatch. Then, a disturbance observer based on the Super Twisting Algorithm is introduced, the estimated current of the observer is used as the sampling current, and the estimated observation error is fed back to the deadbeat predictive current control to improve the stability of the system and eliminate the system delay. The Super Twisting Algorithm effectively eliminates the problem of “chatter” in the sliding mode control system. Simulation experiments show that the proposed control strategy can effectively reduce system error and improve the robustness of the system when the motor parameters are mismatched.