Abstract
A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic algorithm based feature selection designed to select informative variables from the set of available measurements. By only using informative inputs, the model's generalization ability can be enhanced. The approach proposed is applied to modeling of the liquid–phase methanol synthesis. It is shown that a hybrid modeling approach exploiting available a priori knowledge and experimental data can considerably outperform a purely analytical approach.
Similar content being viewed by others
References
Agarwal, M.: Combining neural and conventional paradigms for modelling, prediction and control, Int. J. Sys. Sci. 28(1), (1997) 65–81.
Baughman, R. and Liu, Y. A.: Neural Networks in Bioprocessing and Chemical Engineering, Academic Press, San Diego, 1995.
Bussche, K. M. V. and Froment, G. F.: A steady-state kinetic model for methanol synthesis and the water gas shift reaction on a commercial Cu/ZnO/Al2O3 catalyst, Chem. Engin. Sci. 161 (1996), 1–10.
Graaf, G. H., Sijtsema, P. J. J. M., Stanhius, E. J. and Joosten, G. E. H.: Chemical equilibria in methanol synthesis, Chem. Engin. Sci. 41(11) (1986), 2883–2890.
Graaf, G. H., Winkelman, J. G. M., Stanhius, E. J. and Beenackeers, A. A. C. M.: Kinetics of the three phase methanol synthesis, Chem. Engin. Sci. 43 (1988), 2161–2168.
Grabec, I. and Sachse, W.: Synergetics of Measurements, Prediction and Control, Series in Synergetics, Springer Verlag, Heidelberg, Germany, 1997.
Ledakowicz, S., Stelmachowski, M. and Chauk, A.: Methanol synthesis in bubble column slurry reactors, Chem. Engin. Process. 31 (1992), 213–219.
Lee, S., Berty, J. B., Green, H. L., Desirazu, S., Ko, M., Parmareswaran, V. and Sawant, A.: Thermodynamics, kinetics, and thermal stability of liquid phase methanol synthesis, In:Ninth Annual EPRI Contractor's Conference on Coal Liquefaction, Palo Alto, CA, pp. 15-28, 1985.
Moody, J. and Darken, C. J.: Fast learning in networks of locally-tuned processing units, Neural Computation 1 (1989), 281–294.
Poto?nik, P. and Grabec, I.: Neural-genetic system for modeling of antibiotic fermentation process. In: Proceedings of the International ICSC Symposium on Engineering of Intelligent Systems EIS'98, Tenerife, Spain, pp. 307-313, 1998.
Šetinc, M. and Levec, J.: On the kinetics of liquid-phase methanol synthesis over commercial Cu/ZnO/Al2O3 catalyst, Chem. Engin. Sci., in press, 1999.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Potočnik, P., Grabec, I., Šetinc, M. et al. Neural Net Based Hybrid Modeling of the Methanol Synthesis Process. Neural Processing Letters 11, 219–228 (2000). https://doi.org/10.1023/A:1009615710515
Issue Date:
DOI: https://doi.org/10.1023/A:1009615710515