A Neural Network Based Control of a Simulated Biochemical Process

  • Abhay B. Bulsari
  • Henrik Saxén
Conference paper


This paper describes an application of feedforward neural networks for inverse plant control of a process with highly non-linear characteristics. A biochemical process was considered where the microorganism, Saccharomyces cerevisiae, a yeast, grows in a chemostat on a glucose substrate and produces ethanol as a product of primary energy metabolism. In this process, which is of immense interest to industries worldwide, three state variables were considered: microbial, substrate and product concentrations. The last one is the controlled variable, and the dilution rate is the manipulated variable. In the study, the quality of the control is analyzed for the case where all states are assumed to be measurable and the case where only the product concentration is available.


Neural Network Dilution Rate Feedforward Neural Network Product Concentration Continuous Stir Tank Reactor 
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]
    Bavarian, B., “Introduction to Neural Network for Intelligent Control”, IEEE Control Systems Magazine, April 1988.Google Scholar
  2. [2]
    Ydstie, B. E., “Forecasting and control using adaptive connectionist networks”, Comput. chem. Engng. 14 (1990) p. 583–599.CrossRefGoogle Scholar
  3. [3]
    Bhat N. and McAvoy, T. J., “Use of neural nets for dynamic modeling and control of chemical process systems” Comput. chem. Engng. 14 (1990) p. 573–582.CrossRefGoogle Scholar
  4. [4]
    Antsaklis, P. J., “Neural networks in control systems”, IEEE Control Systems Magazine (April 1990) p. 3-5.Google Scholar
  5. [5]
    Ungar, L.H., B.A. Powell and S.N. Kamens, “Adaptive networks for fault diagnosis and process control”, Comput. chem. Engng. 14 (1990) p. 561–572.CrossRefGoogle Scholar
  6. [6]
    Miller, W.T., R.S. Sutton and P.J. Werbos, “Neural networks for control”, MIT Press, Cambridge, USA, 1990.Google Scholar
  7. [7]
    Bulsari, A.B. and H. Saxén, “System identification of a biochemical process using feed-forward neural networks”, Neurocomputing 3 (1991) p. 125-133.MATHCrossRefGoogle Scholar
  8. [8]
    Elmqvist, H. et al., “Simnon user’s guide for MS-DOS computers, Version 3”, SSPA Systems, Göteborg, Sweden, 1990.Google Scholar
  9. [9]
    Bulsari, A.B. and H. Saxén, “Application of neural networks for filtering”, to be presented at International Conference on Neural Networks and Genetic Algorithms (ANNGA’ 93), Innsbruck, Austria, April 1993.Google Scholar
  10. [10]
    Bulsari, A.B. and H. Saxén, “System identification using the symmetric logarithmoid as an activation function in a feed-forward neural network”, Neural network world 1 (1991) p. 221–224.Google Scholar
  11. [11]
    Marquardt, D. W., “An algorithm for leastsquares estimation of nonlinear parameters”, J. SIAM 11 (1963) p. 431–441.MathSciNetMATHGoogle Scholar
  12. [12]
    A. Bulsari, B. Saxén and H. Saxén, “Programs for feedforward neural networks using the Levenberg-Marquardt method: Documentation and user’s manual” Report 90–2, Heat Eng. Lab, Åbo Akademi, Finland, October 1990.Google Scholar
  13. [13]
    Bulsari, A. and H. Saxén, “Estimation of a disturbance variable using feed-forward neural networks”. Proceedings of the 11th IASTED International Conference on Modelling, Identification and Control (MIC’92), Innsbruck, Austria, February 1992, p. 248–250.Google Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • Abhay B. Bulsari
    • 1
  • Henrik Saxén
    • 1
  1. 1.Heat Engineering Laboratory Department of Chemical EngineeringÅbo AkademiÅboFinland

Personalised recommendations