Long-Term Predictions of Chemical Processes Using Recurrent Neural Networks: A Parallel Training Approach

Industrial and Engineering Chemistry Research

Volumn 31, Issue 5, 1992, Pages 1338-1352

  Su, Hong Te ^a   McAvoy, Thomas J ^a   Werbos, Paul ^b  

^a UNIVERSITY OF MARYLAND   (United States)

^b NATIONAL SCIENCE FOUNDATION   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMIC BEHAVIOUR; MODELLING-COMPUTER; NETWORK MODELS; NEURAL NETWORKS; PROCESS OPTIMIZATION;

BIOLOGICAL WATER TREATMENT; CATALYTIC CRACKING; NEURAL NETWORKS; REFINING; WASTEWATER TREATMENT;

CHEMICAL PROCESSES; LONG-TERM PREDICTIONS; PARALLEL TRAINING APPROACH; RECURRENT NEURAL NETWORKS;

CHEMICAL PLANTS;

EID: 0026868901     PISSN: 08885885     EISSN: 15205045     Source Type: Journal    
DOI: 10.1021/ie00005a014     Document Type: Article

References (33)

1. Baba, N. A new approach for finding the global minimum of error function of neural networks. Neural Networks 1989, 2 (5), 367-373.
2. Bhat, N.; McAvoy, T. J. Use of neural nets for dynamic modeling and control of chemical process systems. Comput. Chem. Eng. 1990, 14 (5), 573-583.
3. Chen, S.; Billings, S. A.; Grant, P. M. Non-linear system identification using neural networks. Int. J. Control 1990, 51 (6), 1191-1214.
4. Cybenko, G. Approximation by superpositions of sigmoidal function. Math. Controls, Signals Syst. 1988, 2, 303-314.
5. Gary, J. H.; Handwerk, G. E. Catalytic reforming and isomerization. Petroleum Refining: Technology and Economics-, Marcel Dekker: New York, 1975; Chapter 6.
6. Hopfield, J. J.; Tank, W. Computing with Neural Circuits: A Model. Science 1986, 233, 625-633.
7. Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators. Neural Networks 1989, 2, 359-366.
8. Leonard, L.; Kramer, M. A. Improvement of the backpropagation algorithm for training neural networks. Comput. Chem. Eng. 1990, 14 (3), 337-341.
9. Leontaritis, I. J.; Billings, S. A. Input-output parametric models for nonlinear systems. Int. J. Control 1985, 41, 303-344.
10. Ljung, L. System Identification: Theory for the User; Prentice-Hall: Englewood Cliffs, NJ, 1987.
11. McAvoy, T. J.; Su, H. T.; Wang, N. S.; Ming, H.; Horvath, J.; Sem-erjian, H. A comparison of neural networks and partial least squares for deconvoluting fluorescence spectra. Biotechnol. Bioeng. 1991, in press.
12. Mosteller, C. F.; Rourke, R. E. Sturdy Statistics: Nonparametric and Order Statistics; Addison-Wesley: Reading, MA, 1973.
13. Narendra, K. S.; Parthasarathy, K. Identification and control of dynamic system using neural networks. IEEE Trans. Neural Networks 1990, 1 (1), 4-27.
14. Narendra, K. S.; Gallman, P. G. An iterative method for the identification of nonlinear systems using a Hammerstein model IEEE Trans. Autom. Control 1966, AC-U (6), 546-550.
15. Pearlmutter, B. A. “Dynamic recurrent neural networks.”; Technical Report CMU-CS-90-196, Carnegie Mellon University: Pittsburgh, PA, 1990.
16. Pedersen, K. M.; Kummel, M.; Soeberg, H. Monitoring and control of biological removal of phosphorus and nitrogen by flow injection analyzers in a municipal pilot scale waste water treatment plant. Submitted for publication in Anal. Chim. Acta 1990.
17. Pineda, F. J. Recurrent backpropagation and the dynamical approach to adaptive neural computation. Neural Comput. 1989, 1, 167-172.
18. Qin, S. Z.; Su, H. T.; McAvoy, T. J. Comparison of four neural net learning methods for dynamic system identification. IEEE Trans. Neural Networks 1992, 3 (1), 122-130.
19. Rumelhart, D.; Hinton, G.; Williams, R. Parallel Distributed Processing; MIT Press: Cambridge, MA, 1986.
20. Saint-Donat, J.; Bhat, N.; McAvoy, T. J. Neural net based model predictive control. Int. J. Control 1991, 54 (6), 1453-1468.
21. Solis, F. J.; Wets, J. B. Minimization by random search techniques. Math. Oper. Res. 1981, 6, 19-30.
22. Wahlberg, B.; Ljung, L. Design variables for bias distribution in transfer function estimation. IEEE Trans. Autom. Control 1986, AC-31 (2), 134-144.
23. Wan, E. A. Temporal backpropagation for FIR neural networks. Int. Jt. Conf. Neural Networks 1990, 1, 575-580.
24. Werbos, P. J. Beyond regression: New tools for prediction and analysis in the behavioral sciences. Ph. D. Thesis, Harvard University, 1974.
25. Werbos, P. J. Advanced forecasting methods for global crisis warning and models of intelligence. Gen. Syst. 1977, 22, 25-38.
26. Werbos, P. J. Generalization of back-propagation with application to a recurrent gas market model. Neural Networks 1988, 1, 339-356.
27. Werbos, P. J. Maximizing long-term gas industry profits in two minutes in Lotus using neural network methods. IEEE Trans. Syst., Man, Cybernetics 1989, 19 (2), 315-333.
28. Werbos, P. J. Neurocontrol and Related Techniques; Maren, A. J., Ed.; Academic Press: New York, 1990.
29. Widrow, B.; Hoff, M. E. Adaptive switching circuits. WESCON Convention Record; IRE: 1960; Vol. 4, pp 96-104.
30. Williams, R. J.; Zipser, D. A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1989, 1, 270-280.
31. Williams, R. J.; Peng, J. An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Comput. 1990, 2 (4), 490-501.
32. Wismer, D. A.; Chattergy, R. Introduction to Nonlinear Optimization: A Problem Solving Approach; North-Holland: Amsterdam, 1978.
33. Young, P. Parameter estimation for continuous-time models: A survey. Automatica 1981, 17 (1), 23-39.