• DocumentCode
    3034253
  • Title

    Neural Network Control Techniques of Hybrid Active Power Filter

  • Author

    You-hua Jiang ; Yong-Wei Chen

  • Author_Institution
    Sch. of Comput. & Inf. Technol., Shanghai Univ. of Electr. Power, Shanghai, China
  • Volume
    4
  • fYear
    2009
  • fDate
    7-8 Nov. 2009
  • Firstpage
    26
  • Lastpage
    30
  • Abstract
    A multi-object optimization approach was developed for the design of hybrid active power filters (HAPF) to give better mitigation of the harmonics and better reactive power compensation. The neural network technique was used with optimization theory to improve the algorithm precision and stability. The optimization is more effective since the performance goals and optimization parameters were optimized together. Secondly, this paper presents the design of a hierarchical fuzzy current control scheme for a shunt active power filter compared with a single fuzzy controller scheme. It provides superior current tracking capability and switch frequency signal is limit in the permit range. Finally, many simulations and experimental result demonstrate the validity of the theory.
  • Keywords
    active filters; electric current control; fuzzy control; neurocontrollers; optimisation; power filters; reactive power control; hierarchical fuzzy current control scheme; hybrid active power filter; multi-object optimization; neural network control; reactive power compensation; shunt active power filter; Active filters; Current control; Design optimization; Fuzzy control; Neural networks; Power harmonic filters; Power system harmonics; Reactive power; Stability; Switches; hierarchical fuzzy current control; hybrid active power filters; multi-object optimization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-3835-8
  • Electronic_ISBN
    978-0-7695-3816-7
  • Type

    conf

  • DOI
    10.1109/AICI.2009.296
  • Filename
    5376898