Abstract
Introduction: Nowadays, five-phase permanent magnet synchronous motors have been widely used in the industrial and transportation fields, and the existing sliding mode control methods for speed control systems can no longer meet the requirements such as fast response and good stability.Methods: In light of the aforementioned considerations, the study initially employs mathematical modeling to elucidate the five-phase permanent magnet synchronous motor. Secondly, on the basis of proportional-integral-derivative sliding mode control, radial basis function and Takagi-Sugeno-Kang fuzzy model are introduced for parameter identification and optimization and regulation. Finally, a new neural network regulation algorithm and speed control strategy are proposed.Results and Discussion: The experimental results demonstrated that the expected parameter optimization rate of the regulation algorithm can reach 90%, and the overshooting amount under small inertia working condition is only 3%, and the adjustment time is 0.02 s. The new control algorithm can be used to control the motor speed with the lowest speed fluctuation and the fastest recovery time. In addition, when affected by the load torque, the motor speed controlled by the new strategy fluctuated the least, with a speed drop of only 1% and the fastest recovery time of 0.02 s. It exhibited the lowest control error of 3.7% and the lowest overshooting amount of 5.9%.Conclusion: In summary, the suggested approach has the potential to significantly enhance the speed control system’s control performance while maintaining strong resilience and anti-interference capabilities. The method has certain guiding significance for the practical application of five-phase permanent magnet synchronous motor speed control system.