• DocumentCode
    3532233
  • Title

    Notes on intelligence based model predictive control scheme: A case study

  • Author

    Mazinan, A.H. ; Kazemi, M.F.

  • Author_Institution
    Dept. of Electr. Eng., Islamic Azad Univ. (IAU), Tehran, Iran
  • fYear
    2010
  • fDate
    7-9 July 2010
  • Firstpage
    474
  • Lastpage
    478
  • Abstract
    This paper describes an intelligence based model predictive control scheme in dealing with a complicated system. In the control strategy proposed here, the system has to be first represented through a multi-Takagi-Sugeno-Kang (TSK) fuzzy-based model approach and subsequently a multi-generalized predictive control (GPC) scheme is realized in line with the investigated model outcomes, at a number of operating points of the system. In this control strategy, the proposed multi-GPC scheme is instantly updated to derive the system by activating the best control scheme through a new GPC identifier. To demonstrate the effectiveness of the proposed control scheme, the simulations are carried out and the results are compared with those obtained using the traditional GPC scheme. The results verify the validity of the proposed control scheme.
  • Keywords
    fuzzy control; intelligent control; large-scale systems; predictive control; GPC identifier; intelligence based model predictive control scheme; multi-generalized predictive control scheme; multiTakagi-Sugeno-Kang fuzzy-based model approach; Artificial neural networks; Control system synthesis; Control systems; Electronic mail; Linear approximation; Neural networks; Nonlinear control systems; Nonlinear systems; Predictive control; Predictive models; GPC identifier; Multi-TSK fuzzy-based model approach; generalized predictive control scheme; linear model approximation; multi-GPC scheme;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Systems (IS), 2010 5th IEEE International Conference
  • Conference_Location
    London
  • Print_ISBN
    978-1-4244-5163-0
  • Electronic_ISBN
    978-1-4244-5164-7
  • Type

    conf

  • DOI
    10.1109/IS.2010.5548324
  • Filename
    5548324