Abstract
This paper describes an experimental investigation concerning the use of neural networks to achieve the non-linear control of a continuous stirred tank fermenter. The influent dilution rate and the substrate concentration have been selected as control variables. The backpropagation learning algorithm has been used for both off-line and on-line identification of the inverse model which provides the control action. Experimental results show the performance and the implementation simplicity of this control approach.
Similar content being viewed by others
References
Bastin, G.; Dochain, D.: On-line estimation and control of bioreactors. Elsevier Sc. Pub. (1990)
Thibault J.; Grandjean, B. P. A.: Neural networks in process control — A survey. IFAC Symposium on Advanced Control of Chemical Processes, October, 14–16 (1991)
Saint-Donat, J.; Bhat, N.; McAvoy, T.: Neural net based predictive control. Int. J. Control 54 (1991) 1453–1468
Breusegem, V.; Thibault, J.; Chéruy, A.: Adaptive neural models for on-line prediction in fermentation. Canad. J. Chem. Eng. 69 (1991) 481–487
Thibault, J.; Breusegem, V.; Chéruy, A.: On-line prediction of fermentation variables using neural networks. Biotech. and Bioeng. 36 (1990) 1041–1048
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Cont. Sign. Syst. 2 (1989) 303–314
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chtourou, M., Najim, K., Roux, G. et al. Control of a bioreactor using a neural network. Bioprocess Engineering 8, 251–254 (1993). https://doi.org/10.1007/BF00369837
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00369837