Sage Journals: Discover world-class research

Abstract

The success of model-based control of chemical processes is dependent on good process models. For processes that are poorly known, the generic modelling capability of neural networks offers an attractive alternative. However, for satisfactory performance, the conventional implementations of neural networks require large sets of offline data in addition to online measurement of key variables, such as concentrations. Meeting each of these requirements is often infeasible in chemical processes. By combining the structural information from a first-principles model and the virtual supervisor-artificial immune algorithm, a novel hybrid neural network, called a structure approaching hybrid neural networks (SAHNN), is proposed. The proposed approach solves the structural problem of neural models and requires a more manageable number of offline data and online key variables. The accurate prediction of online partially unmeasurable concentrations in a batch reactor demonstrated that SAHNN is a promising tool to model complicated batch processes and can be utilized as a vehicle for the control and optimization of other similar chemical reactors.

Keywords

structure approaching hybrid neural networks modelling batch reactor virtual supervisor artificial immune algorithm

Get full access to this article

View all access options for this article.

References

Tsoukas

Tirrell

Stephanopoulos

‘Multiobjective dynamic optimization of semibatch copolymerization reactors.’

Chem. Engng Sci. 37 (1982): 1785–1795

Dube

M. A.

Penlidis

Mutha

R. K.

Cluett

W. R.

‘Mathematical modeling of emulsion copolymerization of acrylonitrile/butadiene.’

Ind. Engng Chem. Res. 35 (1996): 4434–4448

Terwiesch

Argarwal

Rippin

D. W. T.

‘Batch unit optimization with imperfect modeling: A survey.’

J. Process Control 4 (1994): 238–258

Zhang

Morris

A. J.

Martin

E. B.

Kiparissides

‘Prediction of polymer quality in batch polymerization reactors using robust neural networks.’

Chem. Engng J. 69 (1998): 135–143

Cybenko

‘Approximation by super positions of a sigmoidal function.’

Math. Control Signals Systems 2 (1989): 303–314

Sjoberg

Zhang

Ljung

Benveniste

Delyon

Glorennec

Hjalmarsson

Juditsky

‘Nonlinear black-box modeling in system identification: A unified overview.’

Automatica 31 (1995): 1691–1724

Bhat

McAvoy

‘Use of neural nets for dynamic modeling and control of chemical process system.’

Computers Chem. Engng 14 (1990): 573–583

Hunt

K. J.

Sbarbaro

Zbikowski

Gawthrop

P. J.

‘Neural networks for control systems - a survey.’

Automatica 28 (1992): 1083–1112

H. T.

Bhat

Minderman

P. A.

McAvoy

T. J.

‘Integrating neural networks with first principles models for dynamic modeling.’

In Proceedings of the Third IFAC Symposium on The dynamics and control of chemical reactors, distillation columns and batch processes (DYCORD'92), College Park, Maryland, USA, April 1992, pp. 77–82.

10.

Thompson

M. L.

Kramer

M. A.

‘Modeling chemical processes using prior knowledge and neural networks.’

AIChE J. 40 (1994): 1328–1340

11.

Klimasauskas

C. C.

‘Hybrid modeling for robust nonlinear multivariable control.’

ISA Trans. 37 (1998): 291–297

12.

C. W.

Hussain

M. A.

‘Hybrid neural network - prior knowledge model in temperature control of a semi-batch polymerization process.’

Chem. Engng Processing 43 (2004): 559–570

13.

Xiong

Jutan

‘Grey box modeling and control of chemical processes.’

Chem. Engng Sci. 57 (2002): 1027–1039

14.

Crowley

T. J.

Choi

K. Y.

‘Online monitoring and control of a batch polymerization reactor.’

J. Process Control 6 (1996): 119–127

15.

Gamboa-Torres

A. E.

Flores-Tlacuahuac

‘Effect of process modeling on the nonlinear behaviour of a CSTR reaction.’

Chem. Engng J. 77 (2000): 153–164

16.

Tian

Zhang

Morris

‘Optimal control of a fed-batch bioreactor based on an augmented recurrent neural network model.’

Neurocomputing 48 (2000): 919–936

17.

Lightbody

O'Reilly

Irwin

G. W.

Kelly

McCormick

‘Neural modeling of chemical plant using MLP and B-spline networks.’

Control Engng Practice 5 (1997): 1501–1515

18.

Cao

L. L.

D. Z.

Zhang

C. Y.

H. Y.

‘Control and modeling of temperature distribution in a tubular polymerization process.’

Computers Chem. Engng 31 (2007): 1516–1524

19.

Kim

Y. H.

Lewis

F. L.

Abdallah

C. T.

‘A dynamic recurrent neural-network-based adaptive observer for a class of non-linear system.’

Automatica 33 (1997): 1539–1543

20.

Edgar

T. F.

Himmelblau

D. M.

Optimization of chemical processes, (McGraw-Hill, New York 1989)

21.

Schenker

Agarwal

‘Prediction of infrequently measurable quantities in poorly modeled processes.’

J. Process Control 5 (1995): 329–339

22.

Jiao

L. C.

Wang

‘A novel genetic algorithm based on immunity.’

IEEE Trans. System, Man, Cybernetics 30 (2000): 552–561

Intelligent modelling of a batch reactor with partially unmeasurable states based upon a structure approaching hybrid neural networks

Abstract

Abstract

Keywords

Get full access to this article

References