• DocumentCode
    2466316
  • Title

    A Research on Control Methods of Ball and Beam System Based on Adaptive Neural Network

  • Author

    Wei, Wei ; Xue, Peng

  • Author_Institution
    Coll. of Electr. & Electron. Eng., Changchun Univ. of Technol., Changchun, China
  • fYear
    2010
  • fDate
    17-19 Dec. 2010
  • Firstpage
    1072
  • Lastpage
    1075
  • Abstract
    The composition and control process of the ball and beam system are introduced in the paper, a mathematical model of ball and beam system based on Lagrange equations is set up with the application of the energy balance principle concerning dynamics, and on the base of analysis on such model, the design of a controller is worked out by utilizing the techniques of adaptive neural network. A reference model and the training algorithm equation having realized control on adaptive neural network have been deduced, and, in combination with the designed parameters of the ball and beam system, a simulation experiment concerning the system is carried out which as a result shows that, compared with the traditional neural control method, the new control method has advantages such as high convergence speed, low influence of initial weight, etc. and has better solved the design and control issues concerning multiple-parameter nonlinear system.
  • Keywords
    control system synthesis; model reference adaptive control systems; neurocontrollers; nonlinear systems; Lagrange equations; adaptive neural network control; ball and beam control system; controller design; energy balance principle; multiple-parameter nonlinear system; reference model; training algorithm equation; Adaptation model; Adaptive systems; Artificial neural networks; Control systems; Equations; Mathematical model; Training; ball and beam system; neural network; reference model; training algorithm;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational and Information Sciences (ICCIS), 2010 International Conference on
  • Conference_Location
    Chengdu
  • Print_ISBN
    978-1-4244-8814-8
  • Electronic_ISBN
    978-0-7695-4270-6
  • Type

    conf

  • DOI
    10.1109/ICCIS.2010.265
  • Filename
    5709446