eduzhai > Applied Sciences > Engineering >

Optimal Tracking Current Control of Switched Reluctance Motor Drives Using Reinforcement Q-learning Scheduling

  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: In this paper, a novel Q-learning scheduling method for the currentcontroller of switched reluctance motor (SRM) drive is investigated. Q-learningalgorithm is a class of reinforcement learning approaches that can find thebest forward-in-time solution of a linear control problem. This paper willintroduce a new scheduled-Q-learning algorithm that utilizes a table of Q-coresthat lies on the nonlinear surface of a SRM model without involving anyinformation about the model parameters to track the reference currenttrajectory by scheduling infinite horizon linear quadratic trackers (LQT)handled by Q-learning algorithms. Additionally, a linear interpolationalgorithm is proposed to guide the transition of the LQT between trainedQ-cores to ensure a smooth response as state variables evolve on the nonlinearsurface of the model. Lastly, simulation and experimental results are providedto validate the effectiveness of the proposed control scheme.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×