Constrained hybrid neural modelling of biotechnological processes

International Journal of Chemical Reactor Engineering

Volumn 8, Issue , 2010, Pages

  Karama, Asma ^a   Bernard, Olivier ^b   Gouzé, Jean Luc ^b  

^a CADI AYYAD UNIVERSITY   (Morocco)

^b INRIA   (France)

Author keywords

Biotechnological processes; Constraints; Hybrid modelling; Mass balance modelling; Neural networks

Indexed keywords

BIOTECHNOLOGY; WASTEWATER TREATMENT;

BIOTECHNOLOGICAL PROCESS; CONDITION; CONSTRAINT; GENERAL METHODOLOGIES; HYBRID MODEL; HYBRID NEURAL MODELING; MASS BALANCE; MASS-BALANCE MODELING; MODELING APPROACH; NEURAL-NETWORKS;

NETWORK ARCHITECTURE;

EID: 77249103255     PISSN: 21945748     EISSN: 15426580     Source Type: Journal    
DOI: 10.2202/1542-6580.2117     Document Type: Article

References (32)

1. Bajpai, R. K. and Reuss, M. (1980). A mechanistic model for penicillin pro- duction. J. Chem. Tech. Biotechnol., 30:332-344.
2. Bastin, G. and Dochain, D. (1990). On-line Estimation and Adaptive Control of Bioreactors. Elsevier.
3. Bernard, O. and Bastin, G. (1998). Structural identi cation of nonlinear math- ematical models for bioprocesses. In NOLCOS IFAC symposium, pages 448-453.
4. Bernard, O. and Bastin, G. (2005a). Identi cation of reaction schemes for bioprocesses: determination of an incompletely known yield matrix. Bio- process and Biosystem Engineering, 27:293-302.
5. Bernard, O. and Bastin, G. (2005b). On the estimation of the pseudo- stoichiometric matrix for macroscopic mass balance modeling of biotech- nological processes. Mathematical Biosciences, 193:51-77.
6. Bernard, O., Hadj-Sadok, Z., Dochain, D., Genovesi, A., and Steyer, J. P. (2001). Dynamical model development and parameter identi cation for an anaerobic wastewater treatment process. Biotech. Bioeng., 75:424-438.
7. Bernard, O. and Queinnec, I. (2006). Dynamic models of biochemical processes: properties of the models. In Dochain, D., editor, Automatic Control of bioprocesses, Paris. Hermes Science.
8. Chen, L., Bernard, O., Bastin, G., and Angelov, P. (2000). Hybrid modeling of biotechnological process using neural networks. Control Engineering Practice, 8:821.
9. Côte, M., Grandjean, B. P. A., Lessard, P., and Thibault, J. (1995). Dynamic modeling of the activated sludge process: improving prediction using neu- ral network. Water Research., 29:995.
10. Delbès, C., Moletta, R., and Godon, J. J. (2001). Bacterial and archaeal 16s rdna and 16s rrna dynamics during an acetate crisis in an anaerobic digestor ecosystem. FEMS Microbiology Ecology, 35:19-26.
11. Feyo de Azevedo, S., Dahm, B., and Oliviera, F. R. (1997). Hybrid Modelling of biochemical Processes: a comparison with the conventional approach. Computers & chemical Engineering, 21:S751-S756.
12. Gallinari, P. (1997). Heuristiques pour la généralisation, chapter 14. Statistique et méthodes neuronales. Dunod edition.
13. Graef, S. P. and Andrews, J. F. (1974). Mathematical modeling and control of anaerobic digestion. In CEP Symp. Ser., volume 70(136), pages 101-127.
14. Hertz, J., Krogh, A., and Palmer, R. (1991). Introduction to the Theory of Neural Computation. Addison-Wesley.
15. Hess, J. and Bernard, O. (2008). Design and study of a risk management crite- rion for an unstable anaerobic wastewater treatment process. J. Process. Contr., 18:71{79.
16. Hinchlie, M., Montague, G., and Willis, M. (2004). Hybrid approach to modeling an industrial polyethylene process. AIChE Journal, 49(12):3127 3137.
17. Karama, A., Bernard, O., Genovesi, A., Dochain, D., Benhammou, A., and Steyer, J. P. (2001a). Hybrid modelling of anaerobic wastewater treatment processes. Water Science and Technology Journal, 43(1):43-50.
18. Karama, A., Bernard, O., Gouze, J., Benhammou, A., and Dochain, D. (2001b). Hybrid neural modelling of an anaerobic digester with respect to biological constraints. Water Science & Technology Journal, 43(7):1-8.
19. Karim, M. N. and Rivera, S. L. (1992). Arti cial neural networks in bioprocess estimation. Biochemical Engineering biotechnology, 46:1-33.
20. Kay, H. and Ungar, R. (2004). Estimating monotonic functions and their bounds. AIChE Journal, 46(12):2426 2434.
21. Leonard, J. A. and Kramer, M. A. (1990). Improvements of the backprop- agation algorithm for training neural networks. Computers & Chemical Engineering, 16:819-835.
22. Maher, M., Dahhou, B., and Zeng, F. (1995). Experimental results in model reference; adaptive estimation and control of a fermentation process. Con- trol Eng. Practice, 3:313-320.
23. Montague and Morris (1994). Neural network contributions in biotechnology. Tibtech., 12:312-324.
24. Mosey, F. E. (1983). Mathematical modelling of the anaerobic digestion pro- cess: regulatory mechanisms for the formation of short-chain volatile acids from glucose. Water Science and Technology, 15:209-232.
25. Psichogios, D. C. and Ungar, L. H. (1992). A hybrid neural network- rst principles approach to process modelling. AIChe Journal, 10:1499-1511.
26. Rumelhart, D. . E. and McCelland, J. L. (1986). Learning Internal Representa- tions by Error Propagation. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge, MA.
27. Schubert, J., Simutis, R., Dors, M., Havlik, I., and Lubbert, A. (1994). Bio- process optimisation and control application of hybrid modelling. Journal of Biotechnology, 35:51-68.
28. Scott, G. M. and Ray, W. H. (1993). Creating e-cient non linear neural net- work process models that allow model interpretation. Journal of Process Control, 3:163-178.
29. Thibault, J., van Berugesen A., V., and Cheruy (1990). On-line prediction of fermentation variables using neural networks. Biotechnology And Bioengi- neering, 36(1041-1048).
30. Thompson, M. and Kramer, M. A. (1994). Modeling chemical processes using prior knowledge and neural networks. AIChE Journal, 40:1328-1340.
31. Van Can, H. J. L., Hellinga, C., Luyben, K. A. M., and Heijnen, J. J. (1996). Strategy for dynamic process modeling based on neural networks in macro- scopic balances. AIChE Journal, 42:3403-3418.
32. Werbos, P. (1990). Backpropagation through time: What it does and how to do it? Proc. IEEE Trans. Neural Networks, 3:95-100.