Adaptive Position Control of Permanent Magnet Synchronous Motor Drivesusing Neural Networks

A method is presented for position control of a permanent magnet synchronous motor (PMSM). First a linear descretized state-space model of a PMSM with unknown parameters is identified; the identified model is then controlled using state feedback with integrator techniques. The simulation results of a typical motor are obtained and the influence of pole placement, noise and load variations is studied. Finally, simulation results are confirmed with experimental results.