Abstract
In this paper, an adaptive PI controller based on deep Q network (DQN) is proposed, which improves the speed control performance of the permanent magnet synchronous motor (PMSM) drive system and solves the contradiction between the rapidity and overshoot of the traditional PI controller. The mathematical model of PMSM vector control system with series PI controller is established, and the parameters of PI controller are calculated by pole assignment method. The damping factor of the speed loop series PI controller is taken as the variable coefficient of the adaptive PI controller and adjusted dynamically. The effectiveness of the proposed method is verified by simulation.KeywordsAdaptive PI controllerDeep Q networkPermanent magnet synchronous motor
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
