• DocumentCode
    488516
  • Title

    Optimizing Neural Net based Predictive Control

  • Author

    Donat, Jean Saint ; Bhat, Naveen ; McAvoy, Thomas J.

  • Author_Institution
    Department of Chemical Engineering, University of Maryland, College Park, MD 20742
  • fYear
    1990
  • fDate
    23-25 May 1990
  • Firstpage
    2466
  • Lastpage
    2472
  • Abstract
    Neural networks hold great promise for application in the general area of process control. This paper focuses on using a backpropagation network in an optimization based model predictive control scheme. Since analytical expressions for the gradient and Hessian of the neural net model can be derived and these expressions can be calculated in paralle, extremely fast computation times are possible. The control approach is illustrated on a pH CSTR example.
  • Keywords
    Algorithm design and analysis; Backpropagation algorithms; Biological neural networks; Chemicals; Computer architecture; Continuous-stirred tank reactor; Neural networks; Neurons; Predictive control; Speech analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    American Control Conference, 1990
  • Conference_Location
    San Diego, CA, USA
  • Type

    conf

  • Filename
    4791171