Abstract
A combination of multiple neural networks (NNs) is selected and used to model nonlinear multi-input multi-output (MIMO) processes with time delays. An optimisation procedure for a nonlinear model-predictive control (MPC) algorithm based on this model is then developed. The proposed scheme has been applied and evaluated for two example problems, including the MPC of a multi-component distillation column.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb1.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb2.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb3.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb4.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb5.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb6.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb7.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb8.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb9.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb10.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb11.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs00521-004-0399-y/MediaObjects/s00521-004-0399-yflb12.gif)
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Garcia CE, Morari M (1982) Internal model control. 1. A unifying review and some new results. Ind Eng Chem Proc Des Dev 21:308–323
Garcia CE, Morshedi AM (1986) Quadratic programming solution of dynamic matrix control (QDMC). Chem Eng Comm 46:073–087
Henson MA (1998) Nonlinear model predictive control: current status and future directions. Comp Chem Eng 23(2):187–202
Billings SA, Fakhouri SY (1982) Identification of systems containing linear dynamic and static nonlinear elements. Automatica 18:15–26
Leontardis IJ, Billings SA (1985) Input-output parametric model for nonlinear systems, part 1 and 2. Int J Contr 41:303–344
Narendra KS, Parthasarathy K (1990) Identification and control of dynamic systems using neural networks. IEEE Trans Neur Netw 1(1):4–27
Bhat N, McAvoy TJ (1990) Use of neural nets for dynamic modeling and control of chemical process systems. Comp Chem Eng 14(4/5):573–583
Benne M, Grondin-Perez B, Chabriat P, Herve P (2000) Artificial neural networks for modeling and predictive control of an industrial evaporation process. J Food Eng 46(4):227–234
Martin G, McGarel S (2001) Nonlinear mil control. ISA Trans 40(4):369–379
Lennox B, Montague GA, Frith AM, Gent C, Beuan V (2001) Industrial application of neural networks—an investigation. J Proc Contr 11(5):497–507
Duarte M, Suarez A, Bassi D (2001) Control of grinding plants using predictive multivariable neural control. Powd Technol 115(2):193–206
Franks RGE (1972) Modeling and simulation in chemical engineering. Wiley, New York
Ishida M, Zhan J (1995) Neural model-predictive control of distributed parameter crystal growth process. AICHE J 41(10):2333–2336
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jazayeri-Rad, H. The nonlinear model-predictive control of a chemical plant using multiple neural networks. Neural Comput & Applic 13, 2–15 (2004). https://doi.org/10.1007/s00521-004-0399-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-004-0399-y