Zastosowanie sieci neuronowych do wspomagania modelowania reaktorów chemicznych

Molga, E.

Artykuł - szczegóły

Tytuł artykułu

Zastosowanie sieci neuronowych do wspomagania modelowania reaktorów chemicznych

Autorzy

Molga E.

Identyfikatory

Warianty tytułu

Application of neural networks to support modelling of chemical reactors

Języki publikacji

Abstrakty

Przedmiotem pracy są badania nad zastosowaniem sztucznych sieci neuronowych S do wspomagania modelowania reaktorów chemicznych. Za najważniejszy element przeprowadzonych w ramach tej pracy studiów i badań należy uważać uzyskanie nowych metod rozwiązywania problemów neuronowego modelowania reaktorów przez konstruktywne rozwinięcie koncepcji modelu hybrydowego. Opracowano i przedstawiono kompleksową metodę tworzenia rodziny modeli neuronowych dla dowolnego typu reaktora oraz dla dowolnego układu reagującego. Zaproponowano i przeprowadzono systematyczną analizę procesu tworzenia modeli neuronowych, ze szczególnym uwzględnieniem zalet i wad proponowanego podejścia. Zasadniczy nacisk położono nie tylko na praktyczne znaczenie proponowanych metod postępowania, lecz przede wszystkim na określenie ilościowych, pojęciowych i poznawczych konsekwencji stosowania neuronowych modeli reaktorów. Proponowane metody modelowania oraz przeprowadzoną analizę porównawczą ilustrowano wynikami prac własnych, wykonanych dla złożonej, katalitycznej reakcji uwodorniania 2,4-dini-trotoluenu (DNT), prowadzonej w warunkach nieustalonych w wielofazowym reaktorze typu zbiornik z mieszadłem. Szeroko przedyskutowano podstawowe problemy praktycznego stosowania sieci neuronowych w inżynierii reaktorów chemicznych. Wskazano metody wyboru architektury sieci neuronowej (w tym bardzo istotnego wyboru zestawu danych wejście-wyjście), rozwiązywania problemów efektywności i dokładności uczenia sieci oraz wpływu jakości danych doświadczalnych j na dokładność i elastyczność uzyskiwanych rozwiązań. Zaproponowano robocze kryteria określające metody efektywnego postępowania w wymienionych wypadkach. Porównano modele neuronowe reaktora z modelowaniem klasycznym.

In this study an attempt has been made to systemize and develop achievements in the application of a neural network to support the modelling of chemical reactors. The most important part of the studies and investigations performed within the frame of this work is an elaboration of new methods to solve the problems of neural modelling of reactors by a creative development of the hybrid model. A new universal method to create a family of neural models for the reactor and reacting system of any type was elaborated and is presented. Based on this method a detailed analysis of the creation process of a neural model was performed. The influence of neural modelling of chemical reactors on the quality of the obtained predictions was considered as well as other aspects, such as the influence of the neural modelling on the development of classical models have also been taken into account in this analysis. The proposed methods of modelling as well as a comparative analysis are illustrated with the results of calculations carried out for a complex, catalytic hydrogenation of 2,4-dinitrotoluene (2,4-DNT) performed at non-steady state conditions in a multiphase stirred tank reactor. The methods of choosing the net input-output signals, the net architecture, the learning method and the number and quality of leaming data have been elaborated and their influence on the accuracy and elasticity of the obtained predictions have been widely discussed. A comparison of neural and classical modelling of reactors was performed.

Słowa kluczowe

sieci neuronowe reaktory chemiczne neuronowe modele reaktora

neural networks

Wydawca

Oficyna Wydawnicza Politechniki Warszawskiej

Czasopismo

Prace Wydziału Inżynierii Chemicznej i Procesowej Politechniki Warszawskiej

Rocznik

2001

Tom

Vol. 27, z. 1

Strony

5--146

Opis fizyczny

Bibliogr. 130 poz., rys., tab., wykr.

Twórcy

autor

Molga E.

Zakład Kinetyki i Termodynamiki Procesowej, Politechnika Warszawska

Bibliografia

1. P. Wassermann, Neural computing – theory and practice, van Nostrand Reinhold, New York 1989.
2. R. Hecht-Nielsen, Neurocomputing, Addison Wesley, Amsterdam 1991.
3. J. von Neumann, The computer and the brain, Yale Univ. Press, New Haven 1958.
4. J. Hertz, A. Krogh, R. Palmer, Wstęp do teorii obliczeń neuronowych. WNT, Warszawa1993.
5. R. Tadeusiewicz, Sieci neuronowe, Akademicka Oficyna Wydawnicza, Warszawa 1993.
6. R. Tadeusiewicz, Podstawy biocybernetyki, PWN, Warszawa 1991.
7. W.S. McCulloch,W.H. Pitts, A logical calculus of the ideas imminent in nervous activity, Bull. Math. Biophysics., 5, 115-133, 1943.
8. B. Widrow, Generalization and information storage in networks of Adaline neurons, M.C. Jovitz, G.T. Jacobi, G. Goldstein (ed.), Sefl-organizing systems, Spartan Books, 435-461, 1962.
9. G. Carpenter, S. Grossberg, Massively parallel architecture for a self organizing neural pattern recognition machine, Computer vision, Graphic and Image Processing, vol. 37, 54-115, 1983.
10. T. Kohonen, Self-organization and associative memory, Verlag, Berlin 1988.
11. D. Hebb, The Organization of behaviour, Wiley, New York 1949.
12. N.J. Nilsson, Maszyny uczące się, PWN, Warszawa 1968.
13. B. Widrow, M. Lehr, 30 years of adaptive neural networks, Proc. IEEE, 78, 1415-1441, 1990.
14. A.B. Bulsari, H. Saxen, System identification using the symmetric logarithmoid as an activation function in a feed-forward neural network, Neural network world, 1, 221-224, 1991.
15. A.N. Kolmogorow, On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition, Doklady Akademii Nauk SSR, 114, 953-956, 1957.
16. G. Cybenko, Approximation by superposition of a sigmoidal function, Mathematics of Control, Systems and Signals, 2(4), 303-314, 1989.
17. K. Funahasahi, On the approximate realization of continuous mapping by neural networks, Neural Networks, 2, 183-192, 1989.
18. K. Hornik, M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators, Neural Networks, 2, 359-366, 1989.
19. T. Pggio, F. Girosi, Networks for approximation and learning, Proceedings of the IEEE, 78, 1481-1497, 1990.
20. T.L. McClelland, D.E. Rumelhart and the PDP Research group, Parallel distributed processing, MIT Press, Cambridge, Mass., 1986.
21. W.S. Sarle, Neural network FAQ, ftp://ftp.sas.com/pub/neural/FAQ.html
22. S. Osowski, Sieci neuronowe w ujęciu algorytmicznym, WNT, Warszawa 1996.
23. W.H. Press, S.A. Teukolsky, W.T. Vetterling, B.P. Flannery, Numerical Recipes, University Press, Cambridge 1992.
24. W.K. Taylor, computers and the nervous system. Models and analogues in biology, Cambridge Univ. Press, Cambridge 1960.
25. M. Minsky, Neural nets and the brain, Ph.D. Princeton Univ. New York 1954.
26. F. Rosenblatt, The perceptron: A probabilistic model for information storage and organization in the brain, Psych. Rev., 65, 386-408, 1958.
27. B. Widrow, M.E. Hoff, Adaptive swiching circuits, 1960 Western Electric Show and convention record, 4, 96-104, 1960.
28. M. Minsky, S. Papert, Perceptrons, MIT Press, Cambridge, Mass. 1969.
29. F. Rosenblatt, Principles of neurodynamics, Spartan, New York 1962.
30. J.A. Anderson, E. Rosenfeld, Neurocomputing – Foundations of Research, MIT Press, Cambridge, Mass. 1988.
31. S. Grossberg, Some nonlinear networks capable of a learning a spatial pattern of arbitrary complexity, Proceedings of the Natinal Academy od Sciences, USA, 60, 758-765, 1968.
32. S. Grossberg, Embedding fields: A theory of learning with physiological implications, J. Mathm. Psychology, 6, 209-239, 1969.
33. S. Grossberg, Competitive learning: From interactive activation to adaptive resonance, Cognitive Science, 11, 23-63, 1987.
34. J.J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. Natl. Acad. Sci. U.S., 79, 2554-2558, 1982.
35. J.J. Hopfield, Neurons with graded have collective computational properties like those of two state neurons, Proc. Natl. Acad. Sci. U.S., 81, 3088-3092, 1984.
36. T. Kohonen, Associative memory: A system – theoretical approach, Springer-Verlag, Berlin 1977.
37. T. Kohonen, A simple paradigm for the self-organized formation of structured feature maps, w S. Amari, M. Arrib (red.) Competition and cooperation in neural nets, Verlag, Berlin 1982.
38. J.C. Hoskins, D.M. Himmelblau, Artificial neural network models of knowledge representation in chemical engineering, Comput. Chem. Engng., 12, 881-890, 1988.
39. A.B. Bulsari (ed.), Neural networks for chemical engineers, Computer-Aided Chemical Engineering, 6, Elsevier, Amsterdam 1995.
40. N. Bhat, T.J. McAvovy, Use of neural nets for dynamic modelling and control of chemical process systems, Comput. Chem. Engng., 14, 573-583, 1990.
41. B. Joseph, F.W. Hanratty, Predictive control of quality in a batch manufacturing process using artificial neural network models, Ind. Eng. Chem. Res., 32, 1951-1961, 1993.
42. A.J. Morris, G.A. Montague, M.J. Willis, Artificial neural networks: Studies in process modelling and control, Trans IchemE, 42, Part A, 3-19, 1994.
43. K.S. Nerendra, K. Parthasarathy, Identification and control of dynamical systems using neural networks, IEEE Trans. Neural Networks, 1, 4-27, 1990.
44. L.H. Ungar, B.A. Powell, S.N. Kamens, Adaptive networks for fault diagnosis and process control, Comput. Chem. Eng., 14, 561-572, 1990.
45. D.C. Psichogios, L.H. Ungar, Direct and indirect model based control using artificial neural networks, Ind. Eng. Chem. Res., 30, 2564-2573, 1991.
46. R.d. de Veaux, D.C. Psichogios, L.H. Ungar, a comparison of two nonparametric estimation schemes: MARS and neural networks, Comput. Chem. Eng., 17, 819-837, 1993.
47. R.E. de Veaux, R. Bain, L.H. Ungar, Hybrid neural network models for environmental process control, Environmetrics, 10, 225-236, 1999.
48. J.L. Dirion, B. Ettedui, M. Cabassud, M.V. Le Lann, G. Casamatta, Elaboration of a neural network system for semi-batch reactor temperature control: an experimental study, Chem. Eng. Proc., 35, 225-234, 1996.
49. J.L. Dirion, M. Cabassud, M.V. Le Lann, G. Casamatta, Development of adaptive neural -networks for flexible control of batch processes, Chem. Eng. J., 63, 65-77, 1996.
50. I.M. Galvan, J.M. Zaldivar, Application of recurrent neural networks in chemical batch reactors, Part I. NARMA modelling of the dynamic behaviour of the heat transfer fluid temperature, chem. Eng. Process., 36, 505-518, 1997.
51. H. Wang, Y. Oh, E.S. Yoon, Strategies for modelling and control of nonlinear chemical processes using neural networks, Comput. Chem. Eng., 22, S823-S826, 1998.
52. M.C. Palancar, J.M. Aragon, J.S. Torrecilla, pH-Control system based on artificial neural networks, Ind. Eng. Chem. Res., 37, 2723-2740, 1998.
53. K. Meert, M. Rijckaert, Intelligent modelling in the chemical process industry with neural networks: case study, Comput. Chem. Eng., 22, S587-593, 1998.
54. C.A.O. Nascimento, R. Guidici, Neural network based approach for optimisation applied to an industrial nylon-6,6 polimerisation process, Comput. Chem. Eng., 22., S959-S600, 1998.
55. J. Zhang, A.J. Morris, E.B. Martin, C. Kiparissides, Estimation of impurity and fouling in batch polymerisation reactors through the application of neural networks, Computers Chem. Eng., 23, 301-314, 1999.
56. I.M. Galvan, J.M. Zaldivar, H. Hernandez, E. Molga, The use of neural networks for fitting complex kinetic data, Comput. Chem. Engng., 20, 1451-1465, 1996.
57. E. Molga and K.R. Westerterp, Neural network based model of the kinetics of catalytic hydrogenation reactions, 1997 Studies in Surface Science and catalysis, Ed.: G.F. Froment and K.C. Waugh, Proceedings International Symposium on Dynamics of Surfaces and Reaction Kinetics in Heterogeneous Catalysis, Antwerpen, Belgium, September 15-17, 379-388, 1997.
58. E. Molga, R. Cherbański, Hybrid first principle – neural network approach to modelling of the liquid-liquid reacting system, Chem. Eng. Sci., 54, 2467-2473, 1999.
59. E.J. Molga, B.A.A. van Woezik and K.R. Westerterp, Neural networks for modelling of chemical reaction systems with complex kinetics: oxidation of 2-octanol with nitric acid, Chem. Eng. Proc., 39, 323-334, 2000.
60. E.M. Assaf, R.C. Giorfano, C.A.O. Nascimento, Thermal runaway of ethylene oxidation reactors: prevision through neuronal networks, chem. Eng. Sci., 51, 3107-3112, 1996.
61. J.A. Blasco, N. Fueyo, J.C. Larroya, C. Dopazo, Y.J. Chen, A single-step time-integrator of a methane-air chemical system using artificial neural networks, Comput. Chem., Eng., 23, 1127-1133, 1999.
62. J.K. Bandyopadhyay, S. Annamalai, K.L. Gauri, application of artificial neural networks in modelling limestone-SO2 reaction, AIchE J., 42, 2295-2302, 1996.
63. A. Chouai, M. Cabassud, M.V. Le Laan, C. courdon, G. Casamatta, Use of neural networks for liquid-liquid extraction column modelling: an experimental study Chem. Eng. Process., 39,171-180, 2000.
64. I. Zbiciński, K. Ciesielski, Wpływ zakłóceń danych treningowych na symulację procesu suszenia za pomocą klasycznych i hybrydowych modeli neuronowych, Inż. Chem. Proc., 18, 469-486, 1997.
65. E. Piron, E. Latrille, F. Rene, Application of artificial neural networks for crossflow microfiltration modelling, Comput. Chem. Eng., 21, 1021-1030, 1997.
66. W.R. Bowen, M.G. Jones, H.N.S. Yousef, prediction od the rate of crossflow membrane ultrafiltration of colloids: a neural network approach, chem. Eng. Sci., 53, 3793-3802, 1998.
67. D.Dong, T.J. McAvoy, E. Zafiriou, Batch-to-batch optimization using neural network models, Ind. Eng. Chem. Res., 35, 2269-2276, 1996.
68. R. Altissimi, A. Brambilla, A. Deida, D. Semino, Optimal operation of a separation plant using artificial neural networks, Comput. Chem. Eng., 22, S939-S942, 1998.
69. C.A.O. Nascimento, R. Guardani, Neural network based approach for optimization of industrial chemical processes, Comput. Chem. Eng., 24, 2303-2314, 2000.
70. D.C. Psichogios, L.H. Ungar, A hybrid neural network-first principles approach to process modelling, AIChE J., 38, 1499-1511, 1992.
71. B. Saxen, H. Sacrn, A neural-network based model of bioreaction kinetics, Can. J. Chem. Eng., 74, 124-131, 1996.
72. D. Sarkar, J.N. Modak, Adaptive optimization of continuous bioreactor using neural network model, chem. Eng. Comm., 143, 99-116, 1996.
73. V.C.P. Chen, D.K. Rollins, Issues regarding artificial neural network modelling for reactors and fermenters, Bioproc. Eng., 22, 85-93, 2000.
74. L.F.M. Zorzetto, R.M. Filho, M.R. Wolf-Maciel, Process modelling development through artificial neural networks and hybrid models, Comput. Chem. Eng., 24, 1355-1360, 2000.
75. Q. Zhang, S.J. Stanley, Real-time water treatment process control with artificial neural networks, J. Environ. Eng., Feb., 153-160, 1999.
76. C.A. Gntarski, P.R. Rodrigues, M. Mori, L.f. Prenem, Simulation of an industrial waste-water treatment plant using artificial neural networks, Comput. Chem. Eng., 24, 1719-1723, 2000.
77. T. W. Karjala, D.M. Himmelblau, Dynamic rectification of data via recurrent neural nets and the extended Kalman filter, AIChe J., 42, 2225-2239, 1996.
78. J. Chen, D.S.H. Wong, S.S. Jang, Product and process development using artificial neural-network model and information analysis, AIChE J, 44, 876-887, 1998.
79. K.F. McBrayer et al., The application of nonlinear dynamic data reconciliation to plant data, Comput. Chem. Eng., 22, 1907-1911, 1998.
80. A.P,. Bunz, B. Braun, R. Janowsky, Applicvation of quantitative structure-performance relationship and neural network models for the prediction of physical properties from molecular structure, Ind. Eng. Chem. Res., 37, 3043-3051, 1998.
81. I. Iliuta, F. Larachi, B. Grandjean, Pressure drop and liquid holdup in trickle flow reactors: improved ergun constants and slip correlations for the slit model, Ind. Eng. Chem. Res., 37, 4542-4550, 1998.
82. Z. Bensetiti, I. Iliuta, F. Larachi, B.P.A. Grandjean, Solubility of nitrous oxide in amine solutions, Ind. Eng. Res., 38, 328-332, 1999.
83. R. Sharma, D. Singhal, R. Ghosh, A. Dwivedii, Potential applications of artificial neural networks to thermodynamics: vapour-liquid equilibrium predictions, Comput. Chem. Eng., 22, 1907-1911, 1988.
84. M.C. Iliuta, I. Iliuta, F. Larachi, Vapour-liquid equilibrium data analysis for mixed solvent-electrolyte systems using neural network models, chem. Eng. Sci., 55, 2813-2825, 2000.
85. M.L. Mavrovouniotis, S. chang, Hierarchical neural networks for process modelling, Comp. Chem. Eng., 16, 347-369, 1992.
86. D.V. Sridhar, R.C. Seagrave, E.B. Bartlett, Process modelling using stacked neural networks, AIChE J., 42, 2529-2539, 1996.
87. M.L. Thompson, M.A. Kramer, Modelling chemical process using prior knowledge and neural networks, AIChE J., 40, 1328-1340, 1994.
88. A. Gurumoorthy, K.A. Kosanovich, Improving the prediction capability of radial basis function networks, Ind. Eng. Chem. Res., 37, 3956-3970, 1998.
89. R. Lanouette, J. Thibault, J.L. Valade, Process modelling with neural networks using small experimental dadasets, Computers Chem. Eng., 23, 1176-1176, 1999.
90. A. Tholudur, W.F. Ramirez, J.D. McMillan, Interpolated parameter functions for neural network models, Computers Chem. Eng., 24, 2545-2553, 2000.
91. H.M. Henrique, E.L. Lima, D.E. Seborg, Model structure determination in neural network models, Chem. Eng. Sci., 55, 5457-5469, 2000.
92. R. Rico-Martinez, R.A. Adomaitis, I.G. Kevrekidis, Nonivertibility in neural networks, Comput. Chem. Eng., 24, 2417-2433, 2000.
93. J. Graczyk, E. Iller, Matematyczne modele przepływu płynów w izotopowych badaniach reaktorów chemicznych, Postępy Techniki Jądrowej, 2, (568), 1974.
94. O. Levenspiel, Chemical Recation Engineering, J. Wiley, New York 1964.
95. K.R. Westerterp, W.P.M. van Swaaij, A.A.C.M. Beenackers, Chemical Reactor Design and Operation, J. Wiley, Chichester 1987.
96. L. Lapidus, N.R. Amundson, Chemical Reactor Theory, Eds., Prentice-Hall, Inc., Engel-wood Cliffs, New York 1977.
97. J. Szarawara, J. Skrzypek, A. Gawdzik, Podstawy inżynierii reaktorów chemicznych, WNT, Warszawa 1991.
98. A. Burghardt, Podstawy inżynierii reaktorów chemicznych, Wydawnictwa Uczelniane Politechniki Śląskiej, Gliwice 1977.
99. B. Tabiś, Zasady inżynierii reaktorów chemicznych, WNT, Warszawa, 2000.
100. J. Ingham, I.J. Dunn, E. Heinzle, J.E. Prenosil, Chemical Engineering Dynamics, VCH, Weinheim, 1994.
101. S. Osowski, Sieci neuronowe do przetwarzania informacji, Oficyna Wydawnicza Politechniki Warszawskiej, Warszawa, 2000.
102. E. Molga, K.R. Westerterp, Kinetics of hydrogenation of 2,4-dinitrotoluene over a palladium on alumina catalyst, Chem. Eng. Sci., 47, 1733-1749, 1992.
103. K.R. Westerterp, E.J. Molga, K.B. van Gelder, Catalytic hydrogenation reactors for the fine chemical industries. Their design and operation., Chem. Eng. Process., 36, 17-27, 1997.
104. E. Molga, S. Wroński, Modelowanie reaktorów w celu zapobiegania utracie kontroli (thermal runaway). Zastosowanie modeli tendencyjnych i sieci neuronowych. Konferencja Naukowa nt. „Inżynieria Chemiczna – współczesne kierunki badawcze w aspektach praktycznych”, Kraków, 9-10 czerwca, 1994, Mat. Konf., tom I, s. 69-76.
105. E. Molga, S. Wroński, Modelowanie reaktorów chemicznych z zastosowaniem sieci neuronowych – aspekty bezpieczeństwa, XV Ogólnopolska Konferencja Naukowa Inżynierii Chemicznej i Procesowej PAN, Gdańsk-Sobieszewo, 12-15 września, 1995, Mat. Konf., tom III, s. 167-172.
106. E. Molga, Zastosowanie sieci neuronowych do modelowania, rozpoznawania i oceny stanów instalacji technicznej w przemyśle chemicznym, VI Sympozjum Bezpieczeństwa Systemów, Zespół Bezpieczeństwa KBM PAN, Kiekrz k. Poznania, 10-13 czerwca 1996, Mat. Konf. Informator Wojsk Technicznych, s. 134-139.
107. E. Mogla, S. Wroński, Neural networks in runaway prevention – kinetic identification, reactor modelling and scale-up effects, 12th International Congress of Chemical and Process Engineering CHISA’96, 25-30 August 1996, Praha, Czech Republic. Mat. Konf. P. 5. 112, summaries 2 (Reaction Engineering), p. 70.
108. E. Molga, Zastosowanie sieci neuronowych do identyfikacji i modelowania procesów ze złożonymi reakcjami chemicznymi, VII Sympozjum Naukowo-Techniczne nt. „Inżynieria Reaktorów Chemicznych” Instytut Inżynierii Chemicznej PAN, Ustroń, 24-25 października, 1996, Mat. Konf. s. 77-82.
109. E. Molga, Neural networks for modelling of the reaction kinetics in homogeneous liquid catalytic system, The First European Congress on chemical Engineering, Florence, Italy, May 4-7, 1997, Proceedings, vol. 4, 2975-2978.
110. E. Mogla, R. Cherbański, Modelling of liquid-liquid catalysed reaction systems with use of neural networks, 13th International Congress of Chemical and Process Engineering CHISA’98, 23-28 August 1998, Praha, Czech Republic. Mat. Konf.: CD-R?O?M.
111. E. Mogla, R. Cherbański, Zastosowanie sieci neuronowych do modelowania reagujących układów ciecz-ciecz, XVI Ogólnopolska Konferencja Inżynierii Chemicznej i procesowej, Kraków-Muszyna, 22-25 września, 1998, Mat. Konf., tom I, 303-308.
112. E. Mogla, Preventing thermal runaway in complex reacting systems: Application of reaction calorimeter supported with neural networks, Polish-German Workshop on Process Safety, May 14, 1998, Proceedings, pp. 25-30.
113. E. Mogla, R. Cherbański, L. Szpyrkowicz, Zastosowanie sieci neuronowych do modelowania oczyszczalni ścieków, IV Ogólnopolska Konferencja Naukowa „Inżynieria Procesowa w Ochronie Środowiska”, Jachranka, 21-22 września 2000, Mat. Konf., 83-92.
114. E.J. Molga, Neural network approach to support modelling of chemical reactors: problems, resolutions, criteria, Ind. Eng. Chem. Res., 2001, w przygotowaniu.
115. E.J. Molga, J. Bałdyga, Zastosowanie sieci neuronowych do modelowania bioreaktorów, praca niepublikowana.
116. I.J. Leontraritis, S.A. Billings, Imput-output parametric models for non-linear system: 1. Deterministic non-linear systems: 2. Stochastic non-linear systems., Int. J. Control, 41, 303-344, 1985.
117. A. U. Levin, K.S. Nerendra, Identification using feedforward networks, Neural Comput., 7, 349-357, 1995.
118. A. C. Costa, T.L.m. Alves, A.W.S. Henriques, R. Maciel Fiho, E.L. Lima, An adaptive optimal control scheme based on hybrid neural modelling, Comput. Chem. Eng., 22, S859-S862, 1998.
119. S. Gupta, P.H. Liu, S.A. Svoronos, R. Sharma, N.A. Abdel-Khalek, Y. Cheng, H. El-Shall, Hybrid forst-principles/neural networks model for column flotation, AIChE, 45, 557-566, 1999.
120. S. Haykin, Neural networks, a comprehensive foundation, Macmillan college, Publishing Company, New York 1994.
121. H.H. Henrique, E.L. Lima, D.E. Seborg, Model structure determination in neural network models, Chem. Eng. Sci., 55, 5457-5469, 2000.
122. H. Demuth, M. Beale, Neural Network Toolbox for use with Matlab, The Math-Works, Inc., Natick 1992.
123. B. Saxrn, H. Saxen, NNDT – A Neural Network Development Tool, Department of Chemical Engineering, Abo Akademi University, Abo 1995.
124. J. Denker, J. Schwartz, B. Wittner, S. Solla, R. Howard, L. Jackel and J. Hopfield, Large automatic learning, rule extraction and Generalization, Complex Systems, 1, 877-922, 1987.
125. S. Osowski, Sieci neuronowe, Oficyna Wydawnicza Politechniki Warszawskiej, Warszawa 1994.
126. V.N. Vapnik, A. Cherovonenkis, On the uniform convergence of relative frequencies of events to their probabilities, Theory of Probability and its Applications, vol. 16, 1971.
127. V.N. Vapnik, The Nature of statistical Learning Theory, springer, New York 1995.
128. D. Hush, B. Horne, Progress in supervised neural networks, IEEE Singnal Processing Magazine, January, 8-39, 1993.
129. K. Mehrotra, C. Mohan, S. Ranka, Bounds on the number of samples needed for neural learning, IEEE Trans. Neural Networks, 2, 548-558, 1991.
130. P. McCullagh, J.A. Nelder, Generalized Linear Models, 2nd ed., Chapman & Hall, London 1989.

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-article-PWA1-0033-0001