Real-time IP controller based on neural network for permanent magnet synchronous motors

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 real-time IP position controller based on identified inertia is designed by neural network for permanent magnet synchronous motor (PMSM) servo system. The neural networks configuration is simple and reasonable, and the weight has definitely physical meaning. It has rapidly adjusting character to realize the real-time control. To demonstrate the advantages of the proposed real-time IP control scheme based on neural network, the simulation was executed in this research. The simulation results show that the proposed control scheme not only enhances the fast tracking performance, but also increases the robustness of the synchronous motor drive system.