• DocumentCode
    489877
  • Title

    A Hopfield-Based Neuro-Diagnostic System

  • Author

    Chu, S.R. ; Shoureshi, Rahmat ; Healey, A.J.

  • Author_Institution
    School of Mechanical Engineering, Purdue University, W. Lafayette, IN 47907
  • fYear
    1992
  • fDate
    24-26 June 1992
  • Firstpage
    2629
  • Lastpage
    2633
  • Abstract
    A high potential application area for neural networks in the dynamic systems is the area of failure detection and identification. An innovation based failure diagnostic is considered in this paper. This scheme requires a fast on-line system identification technique. Formulation and development of a recurrent Hopfield network for system identification is presented. The general case of a combined parameter idenfification and state observation is considered.
  • Keywords
    Circuits; Equations; Intelligent networks; Mechanical engineering; Neural networks; Neurons; Real time systems; Recurrent neural networks; System identification; Technological innovation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    American Control Conference, 1992
  • Conference_Location
    Chicago, IL, USA
  • Print_ISBN
    0-7803-0210-9
  • Type

    conf

  • Filename
    4792616