HOME JOURNALS CONTACT

Information Technology Journal

Year: 2002 | Volume: 1 | Issue: 2 | Page No.: 173-179
DOI: 10.3923/itj.2002.173.179
Artificial Neural Network Based Nonlinear Model Predictive Control Strategy
Ebrahim Abdulla Al-Gallaf

Abstract: This paper presents the application of neural-network based Model Predictive Control (MPC) scheme to control a non-linear liquid-level system with interaction. We have employed a feed forward neural network as the model in MPC-algorithm and compared it with a model obtained by the conventional statistical identification method (Least Square Method which identifies the linearized model). A model predictive controller synthesis using a neural network based model were found to have better performance in terms of convergence of the system to the desired settling set points than using the statistical model.

Fulltext PDF

How to cite this article
Ebrahim Abdulla Al-Gallaf , 2002. Artificial Neural Network Based Nonlinear Model Predictive Control Strategy. Information Technology Journal, 1: 173-179.

Keywords: model predictive control, artificial neural networks and modeling

REFERENCES
  • Draeger, A., S. Engell and H. Ranke, 1995. Model predictive control using neural networks. IEEE Control Syst. Mag., 15: 61-66.
    CrossRef    Direct Link    

  • Fukuda, T. and T. Shibata, 1992. Theory and applications of neural networks for industrial control systems. IEEE Trans. Ind. Elect., 39: 472-489.
    CrossRef    Direct Link    

  • Garcia, C.E. and M. Morari, 1982. Internal model control: A unifying review and some new results. Ind. Eng. Chem. Process Des. Dev., 21: 308-323.
    CrossRef    Direct Link    

  • Garcia, C.E. and A.M. Morshedi, 1986. Quadratic programming solution of dynamic matrix control (QDMC). Chem. Eng. Commun., 46: 73-87.
    CrossRef    Direct Link    

  • Hunt, K.J., D. Sbarbaro, R. Zbikowski and P.J. Gawthrop, 1992. Neural networks for control systems: A survey. Automatica, 28: 1083-1099.
    Direct Link    

  • Karla, V.R. and H.H.C. Bakker, 1995. Neural-network-based model predictive control: A case study. Proceedings of the 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems, Nov. 20-23, Washington, DC., USA., pp: 355-355.

  • Lundstrom, P., J.H. Lee, M. Morari and S. Skogestad, 1995. Limitations of dynamic matrix control. Comput. Chem. Eng., 19: 409-421.
    CrossRef    Direct Link    

  • Narendra, K.S., 1996. Neural networks for control theory and practice. Proc. IEEE, 84: 1385-1406.

  • Warwick, K., 1996. An Introduction to Control Systems. 2nd Edn., World Scientific Publishing Co., USA
    Direct Link    

  • Ogata, K., 2001. Modern Control Engineering. 4th Edn., Prentice Hall, USA., ISBN-10: 0130609072, pp: 970
    Direct Link    

  • Wu, Z.Q. and C.J. Harris, 1995. Modelling and adaptive filtering of nonlinear systems using neural network. Technical Report, University of Southampton.

  • Zhan, J. and M. Ishida, 1997. The multi-step predictive control of nonlinear SISO processes with a neural MPC. Comput. Chem. Eng., 21: 201-210.

  • Montague, G.A., A.J. Morris and M.J. Willis, 1992. Neural network: Methodologies for process modeling and control. IFAC Artificial Intelligence in Real-Time Control.

  • Cutler, C.R. and B.L. Ramaker, 1980. Dynamic matrix control: A computer control algorithm. Proceedings of Joint Automatic Control Conference, San Francisco, CA.

    • © Science Alert. All Rights Reserved