High performance controller for interior permanent magnet synchronous motor drive using artificial intelligence method

This paper develops a high performance PI based controller for an Interior Permanent Magnet Synchronous Motor (IPMSM) drive. An artificial neural network is used for on-line tuning of the PI controller. The Genetic Algorithm (GA) has been used in this work in order to obtain the optimized values of the controller parameters for precise speed control for different operating conditions over a wide speed range. In this paper, an integral Anti-Windup (AW) strategy for the PI speed controller is also utilized to suppress the undesired side effect known as integrator windup when large set-point changes are made. The optimal behavior of the drive can be achieved by considering two control strategies: Maximum Torque Per Ampere (MTPA) and Flux-Weakening (FW). In developing the proposed controller, the PI controller parameters and, also, the anti-windup strategy are optimized by GA for some operating conditions, in a closed loop vector control scheme. By obtaining the parameters at a number of points in the possible operating region, a look-up table approach has been completed. Then, an ANN is trained by this look-up table. Ultimately, the well-trained ANN is utilized for on-line tuning of the controller parameters to ensure optimum drive performance under different disturbances and operating conditions.