Zastosowanie sieci neuronowych w inżynierii reaktorów chemicznych

• Autorzy: Molga E.

Warianty tytułu

EN

Application of neural networks in chemical reactor engineering

• Języki publikacji: PL

Abstrakty

PL

Przedstawiono możliwości zastosowania sieci neuronowych do wspomagania modelowania reaktorów chemicznych. Zaproponowano uniwersalną metodę tworzenia .rodziny. modeli neuronowych. Scharakteryzowano podstawowe problemy oraz ograniczenia stosowalności modelowania neuronowego, opracowano kryteria zastosowań sieci neuronowych do modelowania.

EN

Application of artificial neural networks (ANN) In modelling of chemical reactors has been discussed. An universal method of creating a family of neural models for different reactors has been proposed. A detailed analysis of basic problems and limitations of neural modeling has also been characterized. The general conclusions and useful criteria of application have been formulated.

Słowa kluczowe

PL

model neuronowy; reaktor; reaktor chemiczny; sieć neuronowa

• Wydawca: Komitet Inżynierii Chemicznej i Procesowej Polskiej Akademii Nauk
• Czasopismo: Inżynieria Chemiczna i Procesowa
• Rocznik: 2004
• Tom: T. 25, z. 3/4
• Strony: 1981--1990
• Opis fizyczny: BIbliogr. 35 poz., rys., tab.

Twórcy

autor

Molga E.

• Wydział Inżynierii Chemicznej i Procesowej Politechniki Warszawskiej

Bibliografia

• [1] HOSK1NS J.C., Himmelblau D.M., Artificial neural network models of knowledge representation in chemical engineering, Comput. Chem. Engng., 1988, 12, 881-890.
• [2] PSICHOGLOS D.C., ungar L.H., Direct and indirect model based control using artificial neural networks, Ind. Eng. Chem. Res., 1991, 30, 2564-2573.
• [3] Wang H., Oh Y., YOON E.S., Strategies for modeling and control of nonlinear chemical processes using neural networks, Comput. Chem. Eng., 1998, 22, S823-S826.
• [4] Palancar M.C., Aragon J.M., Torrecilla J.S., pH-Control system based on artificial neural networks, Ind. Eng. Chem. Res., 1998, 37, 2729-2740.
• [5] HUSSAIN M.A., Review of the applications of neural networks in chemical process control - simulation and online implementation. Art. Int. Eng., 1999, 13, 55-68.
• [6] Castro J.J!, Doyle F.J., Plantwide control of the fiber line in a pulp mill, Ind. Eng. Chem. Res.,2002,41, 1310-1320.
• [7] MEERT K., RJJCKAERT M., Intelligent modelling in the chemical process industry with neural networks: case study, Comput. Chem. Eng., 1998, 22, S587-S593.
• [8] Chouai A., Cabassud M., Le Laan M.V., Courdon C, Casamatta G., Use of neural networks for liquid-liquid extraction column modelling: an experimental study, Chem. Eng. Process., 2000, 39, 171-180.
• [9] Michalopoulos J., Papadokonstadakis S:, Arampatzis G, Lygeros A., Modelling of an industrial fluid catalytic cracking unit using neural networks, Chem. Eng. Res. Des., 2001, 79(A2), 137-142.
• [10] MOLGA E., Neural network approach to support modelling of chemical reactors: problems, resolutions, criteria of application, Chem. Eng. Process., 2003, 42, 675-695.
• [11] Galvan I.M., isasi P., zaldivar J.M., PNNARMA model: an alternative to phenomenological models in chemical reactors, Eng. App. Artif. Intel., 2001, 14, 139-154.
• [12] PSICHOGIOS D.C., Ungar L.H., A hybrid neural network-first principles approach to process modelling, AIChE J., 1992, 38, 1499-1511.
• [13] Saxen B., Saxen H., A neural-network based model of bioreaction kinetics, Can. J. Chem. Eng., 1996,74, 124-131.
• [14] Chen V.C.P., rollins D.k., Issues regarding artificial neural network modelling for reactors and fermenters, Bioproc.Eng., 2000, 22, 85-93.
• [15] Patnaik P.R., Hybrid neural simulation of a fed-batch bioreactor for a non-ideal recombinant fermentation, Bioproc. Biosys. Eng., 2001, 24, 151-161.
• [16] Karjala T.W., HLMMELBLAU D.M., Dynamic rectification of data via recurrent neural nets and the extended Kalman filter, AIChE J., 1996, 42, 2225-2239.
• [17] Iliuta I., larachi F., Grandjean B., Pressure drop and liquid holdup in trickle flow reactors: improved Ergun constants and slip correlations for the slit model, Ind. Eng. Chem. Res., 1998, 37, 4542-4550.
• [18] Sharma R., Singhal D., Ghosh R., Dwivedi A., Potential applications of artificial neural networks to thermodynamics: vapour-liquid equilibrium predictions, Comput.Chem.Eng., 1998, 22, 1907-1911.
• [19] Iliuta M.C., Iliuta I., Larachi F., Vapour-liquid equilibrium data analysis for mixed solvent-electrolyte systems using neural network models, Chem. Eng.Sci., 2000, 55,2813-2825.
• [20] Neagu D., Palade V., A neuro-fuzzy approach for functional genomics data interpretation and analysis, Neural Comput. Appl., 2003,12, 153-159.
• [21] Galvan I.M., Zaldivar J.M., Hernandez H., Molga E., The use of neural networks for fitting complex kinetic data, Comp. Chem. Engng., 1996, 20, 1451-1465.
• [22] Molga E. and Westerterp k.R., Neural network based model of the kinetics of catalytic hydrogenation reactions, 1997, Studies in Surface Science and catalysis, G.F. Froment and k.C. Waugh (ed.), Proceedings International Symposium on Dynamics of Surfaces and Reaction Kinetics in Heterogeneous Catalysis, Antwerpen , Belgium, September 15-17, pp. 379-388.
• [23] molga E., Cherbanski R., Hybrid first principle - neural network approach to modelling of the liquid-liquid reacting system, Chem. Eng. Sci., 1999, 54, 2467-2473.
• [24] molga E.J., van WOEZLK B.A.A. AND westerterp K.R., Neural networks for modelling of chemical reaction systems with complex kinetics: oxidation of 2-octanol with nitric acid, Chem. Eng. Proa, 2000, 39, 323-334.
• [25] MOLGA E., Zastosowanie sieci neuronowych do wspomagania modelowania reaktorow chemicznych, Prace Wydz. Inz. Chem. i Proc. PW, 2001, XXVII, 1-148.
• [26] baldyga J., molga E., Application of neural networks to model bioreactors with mixed microbial populations, ISCRE 17, Hong Kong, China, August 25-28, 2002, Proceedings, http://www.ust.hk/iscrel7/ - Full papers, paper No. 0692.
• [27] Molga E., Cherbanski R., Catalytic reaction performed in the liquid-liquid system: comparison of conventional and neural networks modelling methods, Catal. Today, 2003, 79-80, 241-247.
• [28] Molga E., westerterp K.R., Kinetics of hydrogenation of 2,4-dinitrotoluene over a palladium on alumnina catalyst, Chem. Eng. Sci., 1992, 47, 1733-1749.
• [29] leontaritis I.J., billings S.A., Input-output parametric models for non-linear system: I. deterministic non-linear systems: 2. Stochastic non-linear systems, Int. J. Control, 1985,41, 303-344.
• [30] Levin A.U., Nerendra K.S., identification using feedforward networks, Neural Comput., 1995, 7, 349-357.
• [31] Osowski S., Sieci neuronowe w uje^ciu algorytmicznym, 1996, WNT, Warszawa.
• [32] Henrique H.H., Lima E. L., Seborg D.E., Model structure determination in neural network models, Chem. Eng. Sci., 2000, 55, 5457-5469.
• [33] kolmogorow A.N., On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition, Dokl. Akad. Nauk SSR, 1957, 114,953-956.
• [34] DEMUTH H., BEALE M., Neural Network Toolbox for use with Mathlab, 1992, The Math-Works, Inc., Natick.
• [35] HENRIQUE H.H., LIMA E. L., SEBORG D.E., Model structure determination in neural network models, Chem. Eng. Sci., 2000, 55, 5457-5469. 4