• DocumentCode
    3306208
  • Title

    Training neuroemulators using Multicriteria Extended Kalman Filter and pseudoregularization for Model Reference Adaptive Neurocontrol

  • Author

    Chernodub, A.N.

  • Author_Institution
    Neurotechnologies Dept., Inst. of Math. Machines & Syst. Problems NASU, Kiev, Ukraine
  • fYear
    2012
  • fDate
    3-5 Oct. 2012
  • Firstpage
    391
  • Lastpage
    396
  • Abstract
    Problems of identification and control of nonlinear dynamic plants using Model Reference Adaptive Neurocontrol are considered. Pseudoregularization problem for effective training of neuroemulators is stated, Multicriteria Extended Kalman Filter method for solving this problem is proposed. Results of numerical experiments of training neuroemulators and neurocontrollers are presented.
  • Keywords
    Kalman filters; model reference adaptive control systems; neurocontrollers; nonlinear dynamical systems; model reference adaptive neurocontrol; multicriteria extended Kalman filter; neuroemulator training; nonlinear dynamic plants; pseudoregularization problem; Atmospheric modeling; Jacobian matrices; Model Reference Adaptive Neurocontrol; Multicriteria Extended Kalman Filter; adaptive control; neural networks; neurocontrol;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 2012 4th International Congress on
  • Conference_Location
    St. Petersburg
  • ISSN
    2157-0221
  • Print_ISBN
    978-1-4673-2016-0
  • Type

    conf

  • DOI
    10.1109/ICUMT.2012.6459698
  • Filename
    6459698