On the Application of Artificial Neural Networks to Process Control

  • M. J. Willis
  • G. A. Montague
  • C. Peel


In this chapter, the suitability of the artificial neural network methodology for solving some process engineering problems is discussed. First the concepts involved in the formulation of artificial neural networks for the modelling of dynamic (time dependent) systems are presented. Next the suitability of the technique to provide estimates of difficult to measure quality variables is demonstrated by application to industrial data. Measurements from established instruments are used as secondary variables for estimation of the ‘primary’ quality variables. The advantage of using these estimates for feedback control is then demonstrated. The possibility of using neural network models directly within a model based control strategy is also considered, making use of an on-line optimisation routine to determine the ‘optimal’ settings for standard industrial controllers. Application of the control algorithm to a nonlinear distillation system is used to indicate the potential of the neural network based control philosophy.


Artificial Neural Network Hide Layer Neural Network Model Artificial Neural Network Model Distillation Column 
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. Bhat N. and McAvoy T.J. (1990). ‘Use of neural nets for dynamic modelling and control of chemical process systems’, Comput. Chem. Eng., pp 573-583Google Scholar
  2. Cybenko G. (1989). Approximation by Superpositions of a Sigmoidal Function. Mathematics of Control, Signals and Systems, 2, pp. 303-314.Google Scholar
  3. Di Massimo, C, Montague, G.A., Willis, M.J., Tham, M.T. and Morris, A.J. (1991). Towards Improved Penicillin Fermentation via Artificial Neural Netwroks’, Accepted for Publication in Comput. Chem. Eng.Google Scholar
  4. Eaton, J.W. and Rawlings, J.B. (1990) ‘Feedback Control of Chemical Processes using On-line Optimisation Techniques’, Comput Chem. Eng. 14, 4/5, pp 469-479.Google Scholar
  5. Economou, C.G. and M. Morari (1986). Internal model control 5: Extension to nonlinear systems. Ind. Eng. Chem. Process Des. Dev., 25, 403 411.Google Scholar
  6. Edelman J., Fewell A. and Solomons G.L. (1983). Myco-protein — a new food. Nutrition Abstracts and Reviews in Clinical Nutrition, Series A, Vol 53, 6, pp 471–480Google Scholar
  7. Fletcher, R. (1980). Practical methods of optimization, Volume 1. John Wiley.Google Scholar
  8. Guilandoust, M.T., Morris, A.J. and Tham, M.T. (1987). ‘Adaptive Inferential Control’. Proc.IEE, Vol 134, Pt.D.Google Scholar
  9. Hecht-Nielson R. (1991). ‘Neuro-computing’, Addison WesleyGoogle Scholar
  10. Holden, A.V. (1976). Models of the stochastic activity of neurones, Springer Verlag.Google Scholar
  11. Hornik K., Stinchcombe M., and White H. (1989). ‘Multilayer feedforward networks are universal approximators’, Neural Networks, Vol 2, pp 359-366Google Scholar
  12. Hunt K.J. and Sbarbaro D. (1992).’ studies in neural network based control’ in ‘Neural networks for control and systems’ Ed Warwick K., Irwin G.W. and Hunt K.J. pp 94-122Google Scholar
  13. Isermann R. (1981). ‘Digital control systems’, Springer Verlag.Google Scholar
  14. Lee, P.L. and G.R. Sullivan (1988). ‘Generic Model Control’, Comput. Chem. Eng., 12, 6, 573–580.CrossRefGoogle Scholar
  15. McCulloch W.S. and Pitts W. (1943). ‘A logical calculus of the ideas immanent in nervous activity’, Bulletin of Math.Bio, 5, 115–133.MathSciNetzbMATHCrossRefGoogle Scholar
  16. Powell M.J.D. (1964). ‘An efficient method for finding the minimum of a function of several variables without calculating derivatives’, Comput. J., 7, pp 155–162.MathSciNetzbMATHCrossRefGoogle Scholar
  17. Tham, M.T., Montague, G.A., Morris, A.J. and Lant, P.A. (1991). ‘Soft-sensors for process estimation and inferential control’, J.Proc.Cont., Vol 1, pp 3–14.CrossRefGoogle Scholar
  18. Tham, M.T., Morris, A.J. and Montague, G.A. (1989) ‘Soft sensing: A solution to the problem of measurement delays’, Chem. Eng. Res, and Des., 67, 6, 547–554.Google Scholar
  19. Wang Z., Tham M.T., Morris A.J., (1991). ‘Multilayer Feedforward Neural Networks: Approximated canonical decomposition of nonlinearity’. Accepted for publication Int. J. Cont.Google Scholar
  20. Willis, M.J., C. Di Massimo, G.A. Montague, M.T. Tham and A.J. Morris (1991). On neural networks in chemical process control, Proc IEE, PtD., 138, 3, 256–266.Google Scholar
  21. Willis, M.J., Montague, G.A., Morris, A.J. and Tham, M.T.(1991b) ‘Artificial neural networks — A panacea to modelling problems?’, Proc. American Control Conference, Boston.Google Scholar

Copyright information

© Springer Science+Business Media New York 1995

Authors and Affiliations

  • M. J. Willis
    • 1
  • G. A. Montague
    • 1
  • C. Peel
    • 1
  1. 1.Dept. of Chemical and Process EngineeringUniversity of Newcastle upon TyneNewcastle upon TyneUK

Personalised recommendations