Permanent magnet synchronous motor's sensorless vector control with artificial neural network observer

Abstract

In this paper, a new method for sensorless vector control of permanent magnet synchronous motor (PMSM) using artificial neural network (ANN) observer is developed. This method based on determination of rotor position and thereby speeds by ANN observers. The rotor position angle and rotating speed are estimated by evaluating the instantaneous values of stator voltages and currents. The proposed method was implemented in MATLAB/Simulink software package program. The obtained results are in acceptable error limits for a wide speed range.