With the development of permanent magnet synchronous motor (PMSM) in the field of rail transit, when the traditional linear or nonlinear regulator is used to design the speed loop, the system performance is restricted by the accuracy of the controlled object model and the adaptability of the regulator on complex working conditions. In this paper, a speed loop regulator is developed based on Action Dependent Heuristic Dynamic Programming (ADHDP) algorithm. The method doesn’t rely on a precise mathematical model of the controlled object, and aims to minimize the performance function Q. By training the evaluation network and execution network of ADHDP speed regulator with data, the motor control strategy is improved and the speed tracking effect is optimized. The results are verified by building a vector control simulation model of three-phase PMSM. After training, the ADHDP speed regulator has a strong self-learning ability, which can improve the control strategy in the regulator, improve the dynamic response characteristics and anti-disturbance ability of the motor speed tracking, and the speed tracking optimization is realized.
Optimization of Self-Learning Speed-Tracking Control for Permanent Magnet Synchronous Motor
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Kapitel : 28 ; 232-240
2022-02-22
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Optimization of Self-Learning Speed-Tracking Control for Permanent Magnet Synchronous Motor
British Library Conference Proceedings | 2022
|Europäisches Patentamt | 2023
|