• DocumentCode
    2656022
  • Title

    A kind of modelling scheme based on ANN’s inverse model and EFRA(Exponential Forgetting and Resetting Algorithm) simulation for nonlinear system

  • Author

    Dongcai, Qu ; Qingjiu, Xu

  • Author_Institution
    Dept. of Control Eng., Naval Aeronaut. & Astronaut. Univ., Yantai
  • fYear
    2008
  • fDate
    16-18 July 2008
  • Firstpage
    176
  • Lastpage
    179
  • Abstract
    It was an important method to identify and model for nonlinear system based on the system´s inverse model recently years. In order to model to complex, unknown and the indefinite nonlinear object, besides the nonlinear object was reversible, but also need reasonable modelling structure scheme and inverse model with good performance. Based on ANN´s (artificial neural network) nonlinear mapping performance, the modelling scheme based on ANN´s inverse model had been designed in the article. Used EFRA (exponential forgetting and resetting algorithm), the ANN´s inverse model had been trained on-line, and the ANN´s inverse model with satisfied identification request had been gotten. After massive simulation researches have been done, it is proved the modelling structure scheme is reasonable, the EFRA is effective to raise effect of identification and modelling and control performance.
  • Keywords
    inverse problems; neural nets; nonlinear systems; ANN inverse model; EFRA simulation; artificial neural network; exponential forgetting-and-resetting algorithm; nonlinear system; Artificial neural networks; Control engineering; Electronic mail; Inverse problems; Neural networks; Nonlinear control systems; Nonlinear systems; Artificial neural network (ANN); EFRA(Exponential Forgetting and Resetting Algorithm); Inverse model; Modelling; Simulation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control Conference, 2008. CCC 2008. 27th Chinese
  • Conference_Location
    Kunming
  • Print_ISBN
    978-7-900719-70-6
  • Electronic_ISBN
    978-7-900719-70-6
  • Type

    conf

  • DOI
    10.1109/CHICC.2008.4604929
  • Filename
    4604929