Sensorless Control of PMSM using FOC Strategy Based on Multiple ANN and Load Torque Observer

This article presents the sensorless control system of a Permanent Magnet Synchronous Motor (PMSM), where the speed controller consists of a Multiple - Artificial Neural Networks (M-ANN) and the rotor speed is provided by a Sliding Mode Observer (SMO). The performance of the proposed control system is presented in comparison with the classic Field Oriented Control (FOC) system. The implementation of a load torque observer allows the selection of a specially trained corresponding ANN to obtain optimum performance over the load torque variation ranges. The PMSM equations, the speed and load torque observers equations, the main blocks and control structures, their parameterizations and the results of the numerical simulations obtained are presented. The good results obtained as a result of the numerical simulations involving the use of the usual Simulink and Stateflow blocks, which can be implemented in embedded systems recommend the real-time implementation of the proposed PMSM control system.