Get access

Neural network architecture for process control based on the RTRL algorithm

Authors

  • Tibor Chovan,

    1. Expert Systems Applications Development Group, Dept. of Chemical Engineering, Katholieke Universiteit Leuven, de Croylaan 46, B-3001 Heverlee, Belgium
    Current affiliation:
    1. Dept. of Chemical Engineering Cybernetics, University of Veszprem, Egyetem utca 10, P.O. Box 158, H-8201 Veszprem, Hungary
    Search for more papers by this author
  • Thierry Catfolis,

    Corresponding author
    1. Expert Systems Applications Development Group, Dept. of Chemical Engineering, Katholieke Universiteit Leuven, de Croylaan 46, B-3001 Heverlee, Belgium
    • Expert Systems Applications Development Group, Dept. of Chemical Engineering, Katholieke Universiteit Leuven, de Croylaan 46, B-3001 Heverlee, Belgium
    Search for more papers by this author
  • Kürt Meert

    1. Expert Systems Applications Development Group, Dept. of Chemical Engineering, Katholieke Universiteit Leuven, de Croylaan 46, B-3001 Heverlee, Belgium
    Search for more papers by this author

Abstract

Neural-network-based control schemes are generally designed by replacing standard elements of the classic control schemes by feedforward neural networks. The introduction of discrete time recurrent networks, which are inherently dynamic systems, into those schemes can simplify the design of neural controllers. The concept of applying recurrent networks in indirect adaptive control schemes is described. A combined network cluster consisting of the control network and the model network is constructed to allow the use of the real-time recurrent learning algorithm. To demonstrate the feasibility of the method two simulation examples are presented.

Get access to the full text of this article

Ancillary