Preferences help
enabled [disable] Abstract
Number of results
2004 | 2 | 1 | 113-140
Article title

Direct and inverse neural network modeling in free radical polymerization

Title variants
Languages of publication
The first part of this paper reviews of the most important aspects regarding the use of neural networks in the polymerization reaction engineering. Then, direct and inverse neural network modeling of the batch, bulk free radical polymerization of methyl methacrylate is performed. To obtain monomer conversion, number and weight average molecular weights, and mass reaction viscosity, separate neural networks and, a network with multiple outputs were built (direct neural network modeling). The inverse neural network modeling gives the reaction conditions (temperature and initial initiator concentration) that assure certain values of conversion and polymerization degree at the end of the reaction. Each network is a multi-layer perceptron with one or two hidden layers and a different number of hidden neurons. The best topology correlates with the smallest error at the end of the training phase. The possibility of obtaining accurate results is demonstrated with a relatively simple architecture of the networks. Two types of neural network modeling, direct and inverse, represent possible alternatives to classical procedures of modeling and optimization, each producing accurate results and having simple methodologies.
Physical description
1 - 3 - 2004
1 - 3 - 2004
  • [1] Handbook of Neural Computation, IOP Publishing LTd. and Oxford University Press, 1997.
  • [2] R. Dhib and W. Hyson: “Neural Network Identification of Styrene Free Radical Polymerization”, Polym. Reaction Eng., Vol. 10, (2002), pp. 101–113.[Crossref]
  • [3] F.A.N. Fernandes and L.M.F. Lona: “Application of neural networks for the definition of the operating conditions of fluidized bed polymerization reactors”, Polym. Reaction Eng., Vol. 10, (2002), pp. 181–192.[Crossref]
  • [4] W.M. Chan and C.A.O. Nascimento: “Use of Neural Networks for Modeling of Olefin Polymerization in High Pressure Tubular Reactors”, J. Appl. Polym. Sci., Vol. 53, (1994), pp. 1277–1289.[Crossref]
  • [5] J. Zhang, A.J. Morris and E.B. Martin: “Long-term prediction models based on mixed order locally recurrent neural networks”, Comput. Chem. Eng., Vol. 22, (1998), pp. 1051–1063.[Crossref]
  • [6] Y. Tian, J. Zhang and J. Morris: “Modeling and Optimal Control of a Batch Polymerization Reactor Using a Hybrid Stacked Recurrent Neural Network Model”, Ind. Eng. Chem. Res., Vol. 40, (2001), pp. 4525–4535.[Crossref]
  • [7] C.A.O. Nascimento, R. Giudici and N. Scherbakoff: “Modeling of Industrial Nylon-6,6 Polymerization Process in a Twin-Screw Extruder Reactor. II. Neural Networks and Hybrid Models”, J. Appl. Polym. Sci., Vol. 72, (1999), pp. 905–912.<905::AID-APP6>3.0.CO;2-7
  • [8] P.H.H. Araújo, C. Sayer, J.C. de la Cal, J.M. Asua, E.L. Lima and J.C. Pinto: “Utilization of neural networks as soft sensors to monitor emulsion polymerization reactions (average particle diameter and conversion)”, II ENPROMER, Florianópolis (Brazil), 1999.
  • [9] J. Zhang: “Developing robust non-linear models through bootstrap aggregated neural networks”, Neurocomputing, Vol. 25, (1999), pp. 93–113.[Crossref]
  • [10] J. Zhang, E.B. Martin, A.J. Morris and C. Kiparissides: “Inferential Estimation of Polymer Quality Using Stacked Neural Networks”, Comput. Chem. Eng., Vol. 21, (1997), pp. s1025-s1030. [Crossref]
  • [11] R.G. Gosden, K. Sahakaro, A.F. Johnson, J. Chen, R.F. Li, X.Z. Wang and Z.G. Meszena: “Living Polymerization Reactors: Molecular Weight Distribution Control Using Inverse Neural Network Models”, Polym. Reaction Eng., Vol. 9, (2001), pp. 249–270.[Crossref]
  • [12] J. Zhang, A.J. Morris, E.B. Martin and C. Kiparissides: “Prediction of polymer quality in batch polymerization reactors using robust neural networks”, Chem. Eng. J., Vol. 69, (1998), pp. 135–143.[Crossref]
  • [13] Y. Tian, J. Zhang and J. Morris: “Optimal control of a batch emulsion copolymerization reactor based on recurrent neural network models”, Chem. Eng. Proc., Vol. 41, (2002), pp. 531–538.[Crossref]
  • [14] J. Wei, Y. Xu and J. Zhang: “Neural Networks Based Model Prdictive Control of an Industrial Polypropylene Process”, In: Proceedings of the 2002 IEEE International Conference on Control Applications, Glasgow, (Scotland, U.K.), 2002, pp. 397–402.
  • [15] V. Seth and S.K. Gupta: “Free Radical Polymerization Associated with the Trommsdorff Effect under Semibatch Reactor Conditions: An Improved Model”, J. Polym. Eng., Vol. 15, (1995/96), pp. 283–326.
  • [16] V. Dua, D.N. Saraf and S.K. Gupta: “Free-Radical Polymerization Associated with the Trommsdorff Effect Under Semibatch Reactor Conditions. III. Experimental Responses to Step Changes in Initiator Concentration”, J. Appl. Polym. Sci., Vol. 59, (1996), pp. 749–758.<749::AID-APP20>3.0.CO;2-J[Crossref]
  • [17] S. Curteanu and V. Bulacovschi: “Empirical models for viscosity variation in bulk free radical polymerization”, Hung. J. Ind. Chem., in press.
  • [18] S. Curteanu and V. Bulacovschi: “Modeling and Simulation of Free Radical Polymerization. I. Description of Gel and Glass Effects with Chiu’s Model”, Roum. Chem. Quart. Rev., Vol. 7, (1999), pp. 281–296.
  • [19] S. Curteanu, V. Bulacovschi and M. Constantinescu: “Free Radical Polymerization of Methyl Methacrylate. Modeling and Simulation at High Conversion”, Hung. J. Ind. Chem., Vol. 27, (1999), pp. 287–293.
  • [20] C. Petrila, S. Curteanu and S. Ungureanu: “Optimal Temperature Trajectory of Free Radical Polymerization of Methl Methacrylate”, Revista de Chimie, in press.
Document Type
Publication order reference
YADDA identifier
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.