English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62379/95055 (66%)
Visitors : 2295924      Online Users : 17
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/120902


    Title: Q-Learning Fuzzy PID Controller Design for Motor Control
    Authors: Wong, Ching-Chang;Yeh, I-Shen;Chien, Shao-Yu
    Keywords: Fuzzy Control;Sliding Mode;PID Controller;Motor Control;Q-learning
    Date: 2021-02-03
    Issue Date: 2021-08-03 12:11:19 (UTC+8)
    Abstract: In this paper, a fuzzy PID control method based on Q-learning is proposed to control the motor so that it can adapt to different environments and meet the expectations of the request. There are two main parts: (1) a fuzzy control method is proposed to adjust the parameters KP, KI, and KD of the PID controller and (2) a Q-learning algorithm is proposed to learn the fuzzy rule base and the membership functions of the fuzzy variable. The fuzzy method is proposed to modify the parameters KP, KI, and KD of the PID controller, where the KP, KI, and KD of the PID controller will be automatically adjusted according to environmental changes or external disturbance. The Q-learning algorithm is proposed to learn the fuzzy rule base and the membership functions of the fuzzy variables. The Q-learning algorithm lets the fuzzy rule base and the membership functions of the fuzzy variable that originally relied on the expert rule can be obtained through repeated learning. A sliding mode is added in the Q-learning algorithm and fuzzy control to reduce the number of system parameters required in the learning process to improve the learning efficiency. The learning process is to learn membership functions of the fuzzy variables with the initial fuzzy rule base and the initial membership functions of the fuzzy variable, and then learn a new fuzzy rule base with the initial fuzzy rule base and the new membership functions of the fuzzy variable. Some experimental results of the voice coil motor, brushed DC motor, and Brushless DC motor are presented to illustrate that the proposed method can indeed effectively control these three motors.
    Relation: iRobotics 3(4), pp.1-7
    Appears in Collections:[電機工程學系暨研究所] 期刊論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML47View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback