Neural network-based sensorless direct power control of permanent magnet synchronous motor

In this paper, a sensorless permanent magnet synchronous motor (PMSM) drive was presented based on direct power control (DPC) technique. To estimate the rotor’s position and speed of PMSM, a drastic sensorless strategy was developed according to artificial neural network (ANN) to reduce the cost of the drive and enhance the reliability. The proposed sensorless scheme was an innovative model reference adaptive system (MRAS) speed observer for DPC control PMSM drives. The suggested MRAS speed observer employed the current model as an adaptive model. The ANN was then designed and trained online by employing a back propagation network (BPN) algorithm. Performance of the proposed strategy was adopted using simulation analysis. The results showed the fast dynamic response, low ripples in motor’s currents, power, and electromagnetic torque, as well as good performance in tracking speed and power references.