This paper deals with the modelling of continuous bioreactors by neural networks. The detailed procedure of neural network modelling is given, along with comments on neural network topology, the training data set, and some key design parameters. Various simulations are carried out to study the feasibility of neural network modelling for this application. Simulation results obtained are satisfactory, concerning the modelling ability and noise rejection features of the neural network. It shows that the back-propagation neural network is a promising tool for bioreactor modelling.
Bastin, G., and Dochain, D.1985. 'Stable adaptive controllers for waste treatment by anaerobic digestion'. Env Techn Letters, 6, 584-593.
2.
Cybenko, G.1989. 'Approximation by superpositions of a sigmoid function' , Mathematics of Control, Signals and Systems, 2, 303-314.
3.
Dodd, N.1992. 'The importance of structure in neural networks'. In: Neural Networksfor Control and Systems, K. Warwick et al (Eds), Peter Peregrinus Ltd.
4.
Freeman, J.A., and Skapura, D.M.1991. Neural Networks - Algorithm, Applications, and Programming Techniques, Academic-Wesley Co.
5.
Girosi, F., and Poggio, T.1990. 'Networks and the best approximation property'. Biol Cybernetics, 63, 169-176.
6.
Glassey, J., Montague, G.A., Ward, A.C., and Kara, B.1992. 'Enhancing fermentation development procedure via neural networks'. Preprints of IFAC/IFIP/ IMACS int symp on Artificial Intelligence in Real Time Control, Delft , The Netherlands, 529-534.
7.
Hunt, K.J., and Sbarbaro, D.1991. 'Neural networks for nonlinear internal model control' . IEE Proc-D, 138(5), 431-438.
Hong, J.1986. 'Optimal substrate policy for a fed-batch fermentation with substrate and product inhibition kinetics'. Biotechnol Bioeng, 28, 1421-1431.
10.
Hornik, K., Stinchcombe, M., and White, H.1989. 'Multistage feedforward networks are universal approximators' . Neural Networks, 2, 359-366.
Isermann, R.R., Lachman, K.H., and Matko, D.1992. Adaptive Control Systems. Prentice Hall.
13.
Leonard, J.A., and Kramer, M.A.1990. 'Improvement of the back-propagation algorithm for training neural networks'. Computers and Chemical Engr, 14, 337-341.
14.
Mason, J.C., and Parks, P.C.1992. 'Selection of neural structures, some approximation theory guidelines'. In: Neural Networks for Control and Systems, K. Warwick et al (Eds), Peter Peregrinus Ltd, 151-179.
15.
Miller, W. T., Sutton, R. S., and Werbos, P. J. (Eds) 1990. Neural Networks for Control, The MIT Press.
16.
Montague, G.A., Morris, A.J., and Willis, M.J.1992. 'Artificial neural networks: Methodologies and applications in process control'. In: Neural Networks for Control and Systems , K. Warwick et al (Eds), Peter Peregrinus Ltd, 122-150.
17.
Ohno, H., Nakanishi, E., and Takamatsu, T.1976. 'Optimal control of sernibatch fermentation'. Biotechnol Bioeng, 18, 847-864.
18.
Ooyen, A.V., and Nienhuis, B.1992. 'Improving the convergence of back-propagation algorithm' . Neural Networks, 5, 465-471.
19.
Queinnec, I., Dahhou, B., and Msaad, M.1991. 'On adaptive control of fed-batch fermentation processes' . Europe Control Conf 9 1, Grenoble, France, 1634-1641.
Scragg, A. H (Ed) 1988. Biotechnology for Engineers, Ellis Horwood Ltd.
22.
Scragg, A. H. (Ed) 1991. Bioreactors in Biotechnology- A Practical Approach, Ellis Horwood Ltd.
23.
Sinclair, C.G., and Kristiansen, B.1987. Fermentation Kinetics and Modelling, Open University Press.
24.
Stephanopoulos, Ge, and Stephanopoulos, Gr. 1986. 'Artificial intelligence in the development and design of biochemical processes'. Trend in Biotechnol, 4(9), 241-249, Tibtech.
25.
Steyer, J.P., Pourciel, J.B., Simoes, D., and Uribelarrea, J.L.1991. Online biotechnological process control by means of real-time expert systems, Europe Control Conf 91, Grenoble, France, 1232-1235.
26.
Steyer, J.P., Queinnec, I., and Simoes, D.1992. 'Biotech: A real time application of artificial intelligence for fermentation processes'. Preprints of IFAC/ IFIP/IMACS int symp on Artificial Intelligence in Real Time Control, Delft, The Netherlands, 353-358.
27.
Thibault, J., and Breusegem, V.V.1991. 'Modelling, prediction and control of fermentation process via neural networks'. Europe Control Conf 91, Grenoble, France, 224--229.
28.
Warwick, K., Irwin, G. W. , and Hunt, K. J. (Eds) 1992. Neural Networks for Control and Systems, Peter Peregrinus Ltd.
