New Approaches to the Identification of Semi-mechanistic Process Models
Keywords:
Hybrid models, Artificial Neural Networks, Baker’s yeast fermentationAbstract
In process engineering, first-principles models derived from dynamic mass, energy and momentum balances are mostly used. When the process is not perfectly known, the unknown parts of the first principles model should be represented by black-box models, e.g. by neural networks. This paper is devoted to the identification and application of such hybrid models. For the identification of the neural network elements of a hybrid model two methods are investigated in this article: back-propagation algorithm and direct optimization. We study three optimization algorithms: Sequential Quadratic Programming, Evolutionary Strategy and Particle Swarm Optimization. The different algorithms are compared in a case study, the baker’s yeast production process.
References
Abonyi, J., Babuska, R., Verbruggen, H. B., Szeifert, F. (1999). Constraint parameter Estimation in fuzzy modeling. FUZZ-IEEE'99 Conference, Seoul, Korea, 951–956. https://doi.org/10.1109/FUZZY.1999.793080
Can, H. van, Braake, H. te, Hellinga, C., Luyben, K., Heijnen, J. (1996). Strategy for dynamic process modeling based on neural networks and macroscopic balances. AIChE Journal, 42(12), 3403–3418. https://doi.org/10.1002/aic.690421211
Eberhart, R. C., Shi, Y. (1998). Comparison between genetic algorithms and particle swarm optimization., Proceedings of 7th annual conference on evolutionary computation, 611–616. https://doi.org/10.1007/BFb0040812
Hangos, K. M., Cameron, I. T. (2001). Process Modeling and Model Analysis. Academic Press.
Johansen, T. (1994). Operating regime based process modeling and identification. Ph.D thesis, Department of Engineering Cybernetics, Norwegian Institute of Technology, University of Trondheim, Norway.
Kennedy, J., Eberhart, R. C. (1995). Particle swarm optimization. Proceedings of IEEE International Conference on neural networks, Perth, Australia, 1942–1948. https://doi.org/10.1109/ICNN.1995.488968
Oliveria, R. (2004). Combining first principle modelling and artificial neural networks: a general framework., Comp. and Chem. Eng., 28(5), 755–766. https://doi.org/10.1016/j.compchemeng.2004.02.014
Psichogios, D. C., Ungar, L. H. (1992). A hybrid neural network - first principles approach to process modeling. AIChE Journal, 38(10), 1499–1511. https://doi.org/10.1002/aic.690381003
Rechenberg, I. (1973). Evolutionsstrategie: Optimierung technischer systeme nach prinzipien der biologischen evolution. Stuttgart: Frommann-Holzboog.
Schwefel, H.P, (1995). Numerical Optimization of Computer Models. publisher: Wiley, Chichester.
Simutis, R., Lubbert, A. (1997) Exploratory analysis of bioprocesses using artificial neural network-based methods. Biotechnology Progress, 13(4), 479–487. https://doi.org/10.1021/bp9700364
Sjöberg, J., Zhang, Q., Ljung, L., Benveniste, A., Delyon, B., Glorennec, P. Y., Hjalmarsson, H., Juditsky, A. (1995) Nonlinear black-box modeling in system identification: an unified overview. Automatica, 31(12), 1691–1724. https://doi.org/10.1016/0005-1098(95)00120-8
Spears, W. M., De Jong, K. A., Back, T., Fogel, D. B., Garis, H. (1993) An Overview of Evolutionary Computation. European Conference on Machine Learning. https://doi.org/10.1007/3-540-56602-3_163
Thompson, M. L., Kramer, M. A. (1994). Modeling chemical processes using prior knowledge and neural networks. AIChE Journal, 40(8), 1328–1340. https://doi.org/10.1002/aic.690400806
Tulleken, H. J. A. F. (1993). Gray-box modelling and identification using physical knowledge and {bayesian} techniques. Automatica, 29(2), 285–308. https://doi.org/10.1016/0005-1098(93)90124-C
Downloads
Published
Issue
Section
License
Copyright (c) 2004 Madár János, Abonyi János, Szeifert Ferenc
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
