Abstract
Neural networks and nonlinear time series models provide two paradigms for developing input-output models for nonlinear systems. Methodology for developing neural networks with radial basis functions (RBF) and nonlinear auto-regressive (NAR) models are described. Dynamic input-output models for a MIMO chemical reactor system are developed by using standard back-propagation neural networks with sigmoid functions, neural networks with RBF and time series NAR models. The NAB. models are more parsimonious and more accurate in predictions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bhat, N. and T. J McAvoy (1990): Use of Neural Networks for Dynamic Modeling and Control of Chemical Process Systems, Computers Chem. Engng 14 (4/5) 573
Chen S., S. A. Billings and W. Lou (1989): Orthogonal least squares methods and its application to non-linear system identification, Int. J. Ctrl., 50 (5), 1873–1896
Cybenko, G. (1989): Approximations by Superpositions of a Sigmoidal Function, Math. Cont. Signal & Systems, 2 303–314
Haber R. and H. Unbehauen (1990): Structure Identification of Nonlinear Dynamic Systems - A survey on Input/Output Approaches, Automatica, 26, 651–677
Haesloop, D. and B. Holt (1990): A Neural Network Structure for System Identification, Proc. Amen. Cntrl Conf. 2460
Hernandez, E. and Y. Arkun (1990): Neural Network Modelling and an Extended DMC Algorithm to Control Nonlinear Systems, Proc. Amen. Cntrl Conf. 2454
Hinunelblau, D. M. (1972): Applied Nonlinear Programming, McGraw-Hill, New York
Holcomb, T. and M. Moran (1990): Analysis of Neural Controllers, AIChE Annual Meeting. Paper No. 16a.
Hoskins, J. C. and D. M Himmelblau (1988): Artificial Neural Network Models of Knowledge Representation in Chemical Engineering Comput. Chem. Engng 12, 881
Korenberg M. J. (1985): Orthogonal Identification of Nonlinear Difference Equation Models, Models, midwest Symp. on Circuits and Systems, Louisville, KY
Leonard, J. A and M. Kramer (1990): Classifying Process Behavior with Neural Networks: Strategies for Improved Training and Generalization, Proc. Amen. Cntrl Conf. 2478
Leontaritis I. J. and S. A. Billings (1985): Input-output parametric models for nonlinear systems, lot. J. Ctrl., 41, 303–344
Lin, Han-Fei (1992): Approximate Dynamic Models with Back-Propagation Neural Networks, Project Report, Illinois Institute of Technology
Moody and Darken (1988): learning with Localized Receptive Fields, Research Report YALEU/DCS/RR-649, Yale Computer Science Department, New Haven, Connecticut
Niranjan M. and F. Fallside (1988): Neural Networks and Radial Basis Functions in Classifying Static Speech Patterns, Report No. CUED/F-INFENG/TR 22, University Engineering Department, Cambridge, England
Ozgulsen F., R. A. Adomaitis and A. Cinar (1991): Chem. Eng. Sci., in press
Pollard, J. F., D. B. Garrison, M R Broussard and K Y. San (1990): Process Identification using Neural Networks, AIChE Annual Meeting. Paper No. 96a
Rigopoulos, K. (1990): Selectivity and Yield Improvement by Forced Periodic Oscillations: Ethylene Oxidation Reaction, Ph D. Thesis, Illinois Institute of Technology, Chicago,U
Roat, S. and C. F. Moore (1990): Application of Neural Networks and Statistical Process Control to Model Predictive Control Schemes for Chemical Process Industry, AIChE Annual Meeting. Paper No. 16b.
Saner and Slotine (1991): Gaussian Neural Networks for Direct Adaptive Control, Proc. Amer. Control Conf., 2153
Ungar, L. H., B. A Powell and S. N. Kamens (1990): Adaptive Networks for Fault Diagnosis and Process Control, Computers Chem. Engng 14 (4/5) 561
Venkatasubramanian, V., R Vaidyanathan and Y. Yamamato (1990): Process Fault Detection and Diagnosis Using Neural Networks: I. Steady State Processes, Comput. Chem. Engng 14, 699
Whiteley, J. R and J. F. Davis (1990): Backpropagation Neural Networks for Qualitative Interpretation of Process Data, AIChE Annual Meeting. Paper No. 96d
Willis, M. J., G. A. Montague, A. J. Morris, and M. T. Tham (1991): Artificial Neural Networks:- A Panacea to Modelling Problems?, Proc. Amen. Cntrl Conf. 2337
Yao, S. C. and E. Zafriou (1990): Control System Sensor Failu a Detection via Network of Local Receptive Fields, Proc. Amen. Cntrl Conf. 2472
Ydstie, B. E. (1990): Forecasting and Control Using Adaptive Connectionist Networks, Computers Chem. Engng 14 (4/5) 583
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Raich, A., Wu, X., Lin, HF., Cinar, A. (1996). A Comparative Study of Neural Networks and Nonlinear Time Series Techniques for Dynamic Modeling of Chemical Processes. In: Reklaitis, G.V., Sunol, A.K., Rippin, D.W.T., Hortaçsu, Ö. (eds) Batch Processing Systems Engineering. NATO ASI Series, vol 143. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60972-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-60972-5_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-64635-5
Online ISBN: 978-3-642-60972-5
eBook Packages: Springer Book Archive