• DocumentCode
    3481958
  • Title

    Design of BPNN speed PI controller based on GA

  • Author

    Hu, Yinquan ; Liu, Heping ; Yi, Wencui

  • Author_Institution
    State Key Lab. of Power Transm. Equip. & Syst. Security & New Technol., Chongqing Univ., Chongqing, China
  • fYear
    2009
  • fDate
    5-7 Aug. 2009
  • Firstpage
    1474
  • Lastpage
    1478
  • Abstract
    Following the performance and disturbance rejection performance of motor is directly related to the application of DC speed control system in DC motor control. DC speed control system uses regular speed, current double closed-loop speed control, the inner ring and the outer ring generally use PI regulator. However, the rotational speed will produce inevitably overshoot and disturbance rejection performance is not good in double-loop speed control system. This paper describes design method of a BP neural network speed PI controller based on genetic algorithm, which eliminate the DC speed control system rotational speed of the overshoot, and improve the system dynamic performance, and use Matlab simulation software to verify its advantages.
  • Keywords
    DC motors; PI control; angular velocity control; backpropagation; closed loop systems; control system synthesis; machine vector control; neurocontrollers; BP neural network PI controller; DC motor control; DC speed control system; Matlab simulation software; closed-loop speed control; double-loop speed control system; genetic algorithm; Algorithm design and analysis; Control systems; DC motors; Genetic algorithms; Neural networks; Regulators; Robust control; Shape control; Three-term control; Velocity control; BPNN; DC Motor; Genetic Algorithm (GA); PI Controller;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automation and Logistics, 2009. ICAL '09. IEEE International Conference on
  • Conference_Location
    Shenyang
  • Print_ISBN
    978-1-4244-4794-7
  • Electronic_ISBN
    978-1-4244-4795-4
  • Type

    conf

  • DOI
    10.1109/ICAL.2009.5262731
  • Filename
    5262731