Self-Tuning PI Controller Based on Neural Network for Permanent Magnet Synchronous Motor

In servo motor drive applications, the variation of load inertia will degrade drive performance severely. Good dynamic and static performance of servo system requires controlling inertia robustly. In order to get the moment of rotational inertia, online identification methods based on model reference adaptive identification (MRAI) were developed in this paper. Then a well-trained neural network supplies the PI controller with suitable gain according to each operating condition pair (inertia, angular velocity error, and angular velocity) detected. To demonstrate the advantages of the proposed self-tuning PI control technique based on neural network, the simulation was executed in this research. The simulation results show that the method not only enhances the fast tracking performance, but also increases the robustness of the synchronous motor drive.