Sensorless speed control of permanent magnet synchronous motor based on RBF neural network

Rotor position and speed signals are needed for the precise control of permanent magnet synchronous motor (PMSM). Thus in the sensorless PMSM control system, it is particularly important to estimate the rotor position and speed accurately. In this paper, a neural network observer based sensorless speed control strategy is proposed for PMSM. The inputs of each neural network observer are the estimated currents and the current estimation errors corresponding, while the output of each neural network observer is the back electromotive force (EMF). So the estimations of the back EMF are obtained from neural network observer, from which the estimations of the rotor position and speed are calculated, respectively. The Lyapunov theory is applied to prove the stability of the proposed neural network observer. The effectiveness and feasibility of the proposed method is indicated by the simulation results.