Improved Active Disturbance Rejection Control of Permanent-Magnet Synchronous Motor Based on BP neural network

In order to improve the anti-disturbance ability and tracking accuracy of the system, the active disturbance rejection control (ADRC) controller is applied to the speed regulating system of permanent magnet synchronous motor(PMSM), and the ADRC is combined with BP neural network. BP neural network realizes the optimization of extended state observer (ESO) parameters through continuous self-learning and adjusting weights, and improves the estimation accuracy of the summation disturbance of the extended state observer, which makes the control system have better dynamic performance and robustness. Finally, the simulation results prove the effectiveness of the method.