Suboptimal Nonlinear Predictive Control with MIMO Neural Hammerstein Models

  • Maciej Ławryńczuk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5027)


This paper describes a computationally efficient (suboptimal) nonlinear Model Predictive Control (MPC) algorithm with neural Hammerstein models. The Multi-Input Multi-Output (MIMO) dynamic model contains a steady-state nonlinear part realised by a set of neural networks in series with a linear dynamic part. The model is linearised on-line, as a result the MPC algorithm solves a quadratic programming problem. The algorithm gives control performance similar to that obtained in nonlinear MPC, which hinges on non-convex optimisation.


Model Predictive Control Distillation Column Quadratic Programming Problem Sampling Instant Manipulate Variable 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aoubi, M.: Comparison between the dynamic multi-layered perceptron and generalised Hammerstein model for experimental identification of the loading process in diesel engines. Control Engineering Practice 6, 271–279 (1998)CrossRefGoogle Scholar
  2. 2.
    Al-Duwaish, H., Karim, M.N., Chandrasekar, V.: Hammerstein model identification by multilayer feedforward neural networks. International Journal of Systems Science 28, 49–54 (1997)zbMATHCrossRefGoogle Scholar
  3. 3.
    Billings, S.A., Fakhouri, S.Y.: Identification of systems containing linear dynamic and static nonlinear elements. Automatica 18, 15–26 (1982)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Eskinat, E., Johnson, S., Luyben, W.L.: Use of Hammerstein models in identification of nonlinear systems. AIChE Journal 37, 255–268 (1991)CrossRefGoogle Scholar
  5. 5.
    Greblicki, W.: Non-parametric orthogonal series identification Hammerstein systems. International Journal of Systems Science 20, 2355–2367 (1989)zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Haykin, S.: Neural networks – a comprehensive foundation. Prentice-Hall, Englewood Cliffs (1999)zbMATHGoogle Scholar
  7. 7.
    Henson, M.A.: Nonlinear model predictive control: current status and future directions. Computers and Chemical Engineering 23, 187–202 (1998)CrossRefGoogle Scholar
  8. 8.
    Janczak, A.: Neural network approach for identification of Hammerstein systems. International Journal of Control 76, 1749–1766 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Ling, W.M., Rivera, D.: Nonlinear black-box identification of distillation column models – design variable selection for model performance enhancement. International Journal of Applied Mathematics and Computer Science 8, 793–813 (1998)zbMATHGoogle Scholar
  10. 10.
    Ławryńczuk, M.: A family of model predictive control algorithms with artificial neural networks. International Journal of Applied Mathematics and Computer Science 17, 217–232 (2007)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Maciejowski, J.M.: Predictive control with constraints. Prentice-Hall, Englewood Cliffs (2002)Google Scholar
  12. 12.
    Morari, M., Lee, J.H.: Model predictive control: past, present and future. Computers and Chemical Engineering 23, 667–682 (1999)CrossRefGoogle Scholar
  13. 13.
    Nešić, D., Mareels, I.M.Y.: Dead-beat control of a simple Hammerstein models. IEEE Transactions on Automatic Control 43, 1184–1188 (1998)CrossRefGoogle Scholar
  14. 14.
    Patwardhan, R.S., Lakshminarayanan, S., Shah, S.L.: Constrained nonlinear MPC usnig Hammerstein and Wiener models. AIChE Journal 44, 1611–1622 (1998)CrossRefGoogle Scholar
  15. 15.
    Qin, S.J., Badgwell, T.A.: A survey of industrial model predictive control technology. Control Engineering Practice 11, 733–764 (2003)CrossRefGoogle Scholar
  16. 16.
    Tatjewski, P.: Advanced control of industrial processes, Structures and algorithms. Springer, London (2007)zbMATHGoogle Scholar
  17. 17.
    Tatjewski, P., Ławryńczuk, M.: Soft computing in model-based predictive control. Int. Journal of Applied Mathematics and Computer Science. 16, 101–120 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Maciej Ławryńczuk
    • 1
  1. 1.Institute of Control and Computation EngineeringWarsaw University of TechnologyWarsawPoland

Personalised recommendations