PMSM Sensorless Control based on Adaptive Luenberger Observer

In this paper, a luenberger observer is designed to estimate the rotor position and speed of a sensorless permanent magnet synchronous motor. A neural network (NN) is used to improve the adaptability of the permanent magnet synchronous motor. Firstly, based on the mathematical model of permanent magnet synchronous motor in two-phase stationary reference frame, the general luenberger observer for vector control is constructed. A phase-locked loop is used to improve the estimated accuracy of the luenberger observer. To deal with the disturbance problem of load changes and model plant mismatches, neural networks are used to adjust control parameters in real time according to the running state of the motor. Simulation results validate the effectiveness of the presented control scheme.