Modelling and control of different types of polymerization processes using neural networks technique: A review

Polymerization process can be classified as a nonlinear type process since it exhibits a dynamic behaviour throughout the process. Therefore, it is highly complicated to obtain an accurate mechanistic model from the nonlinear process. This predicament always been a “wall” to researchers to be able to devise an optimal process model and control scheme for such a system. Neural networks have succeeded the other modelling and control methods especially in coping with nonlinear process due to their very conciliate characteristics. These characteristics are further explained in this work. The predicament that is encountered by researchers nowadays is lack of data which consequently lead to an imprecise mechanistic model that scarcely conforms to the desired process. The implementations of the neural network model not only restrict to polymerization reactor but to other difficult-to-measure parameters such as polymer quality, polymer melts index and mixture of initiators. This work is aimed to manifest ascendancy of neural networks in modelling and control of polymerization process. Le processus de polymerisation peut etre categorise comme un processus de type non lineaire, puisqu'il affiche un comportement dynamique tout au long du processus. Par consequent, il est tres complique d'obtenir un modele mecaniste precis du processus non lineaire. Cette situation fâcheuse a toujours represente un « mur » pour les chercheurs qui souhaitent concevoir un schema de controle et de modelisation du processus optimal pour un tel systeme. Les reseaux neutres ont succede aux autres methodes de modelisation et de controle, surtout pour s'occuper du processus non lineaire en raison de leurs caracteristiques tres conciliantes. Ces caracteristiques sont expliquees plus en detail dans ce travail. La situation fâcheuse rencontree par les chercheurs aujourd'hui est le manque de donnees, ce qui mene par consequent a un modele mecaniste imprecis qui est a peine conforme au processus souhaite. Les mises en œuvre du modele des reseaux neutres se limitent non seulement au reacteur de polymerisation, mais aux autres parametres difficiles a mesurer, comme la qualite du polymere, l'indice de fluidite du polymere et le melange des initiateurs. Ce travail cherche a manifester l'ascendance des reseaux neutres en modelisant et controlant le processus de polymerisation.

[1]  Jie Zhang,et al.  Inferential estimation of polymer quality using bootstrap aggregated neural networks , 1999, Neural Networks.

[2]  Michael I. Jordan,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[3]  Yuan Tian,et al.  Modeling and optimal control of a batch polymerization reactor using a hybrid stacked recurrent neural network model , 2001 .

[4]  Hong Yue,et al.  Steady-State Modeling and Control of Molecular Weight Distributions in a Styrene Polymerization Process Based on B-Spline Neural Networks , 2007, ISNN.

[5]  A. J. Morris,et al.  Estimation of impurity and fouling in batch polymerisation reactors through the application of neural networks , 1999 .

[6]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[7]  T. Sathish,et al.  Modelling and optimization of fermentation factors for enhancement of alkaline protease production by isolated Bacillus circulans using feed‐forward neural network and genetic algorithm , 2008, Journal of applied microbiology.

[8]  Amanda J. C. Sharkey,et al.  Treating Harmful Collinearity in Neural Network Ensembles , 1999 .

[9]  Luiz Augusto da Cruz Meleiro,et al.  ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process , 2009, Comput. Chem. Eng..

[10]  Mohd Azlan Hussain,et al.  Mathematical Model and Advanced Control for Gas-phase Olefin Polymerization in Fluidized-bed Catalytic Reactors , 2008 .

[11]  Fabiano A.N. Fernandes.  Selection of a mixture of initiators for batch polymerization using neural networks , 2005 .

[12]  S. Grossberg.  Neural Networks and Natural Intelligence , 1988 .

[13]  Yoshua Bengio,et al.  Boosting Neural Networks , 2000, Neural Computation.

[14]  Jinyoung Kim,et al.  Neural network modeling of temperature behavior in an exothermic polymerization process , 2002, Neurocomputing.

[15]  Pádraig Cunningham,et al.  Stability problems with artificial neural networks and the ensemble solution , 2000, Artif. Intell. Medicine.

[16]  Sherif Hashem,et al.  Optimal Linear Combinations of Neural Networks , 1997, Neural Networks.

[17]  Hooshang Jazayeri-Rad,et al.  The nonlinear model-predictive control of a chemical plant using multiple neural networks , 2004, Neural Computing & Applications.

[18]  Geoffrey E. Hinton,et al.  How neural networks learn from experience. , 1992, Scientific American.

[19]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[20]  Cláudio Augusto Oller do Nascimento,et al.  Use of neural networks for modeling of olefin polymerization in high pressure tubular reactors , 1994 .

[21]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[22]  Yu-Lun Chiu,et al.  Dynamic modeling of batch polymerization reactors via the hybrid neural-network rate-function approach , 2007 .

[23]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[24]  Amanda J. C. Sharkey,et al.  Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems , 1999 .

[25]  Eric B. Bartlett,et al.  Process modeling using stacked neural networks , 1996 .

[26]  Kumpati S. Narendra,et al.  Nonlinear adaptive control using neural networks and multiple models , 2001, Autom..

[27]  Robert Ebewele,et al.  Polymer Science and Technology , 2000 .

[28]  Silvia Curteanu,et al.  Neural network-based modeling for semi-batch and nonisothermal free radical polymerization , 2006 .

[29]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[30]  Jie Zhang.  Improved on-line process fault diagnosis through information fusion in multiple neural networks , 2006, Comput. Chem. Eng..

[31]  Jie Zhang,et al.  Developing robust non-linear models through bootstrap aggregated neural networks , 1999, Neurocomputing.

[32]  Hein Putter,et al.  The bootstrap: a tutorial , 2000 .

[33]  Noel E. Sharkey,et al.  A Multi-Net System for the Fault Diagnosis of a Diesel Engine , 2000, Neural Computing & Applications.

[34]  Ke Chen,et al.  Improved learning algorithms for mixture of experts in multiclass classification , 1999, Neural Networks.

[35]  Seong-Whan Lee.  Off-Line Recognition of Totally Unconstrained Handwritten Numerals Using Multilayer Cluster Neural Network , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Michel Crucianu,et al.  Bayesian learning for recurrent neural networks , 2001, Neurocomputing.

[37]  K. Lagemann,et al.  NeNEB-an application adjustable single chip neural network processor for mobile real time image processing , 1996, Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing.

[38]  Mohd Azlan Hussain,et al.  Hybrid neural network—prior knowledge model in temperature control of a semi-batch polymerization process , 2004 .

[39]  Hervé Bourlard,et al.  Generalization and Parameter Estimation in Feedforward Netws: Some Experiments , 1989, NIPS.

[40]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[41]  C. Kiparissides,et al.  Inferential Estimation of Polymer Quality Using Stacked Neural Networks , 1997 .

[42]  Kotaro Hirasawa,et al.  Robust control for nonlinear systems by universal learning network considering fuzzy criterion and second order derivatives , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[43]  Christine W. Chan,et al.  Multiple neural networks for a long term time series forecast , 2004, Neural Computing & Applications.

[44]  Abdul Rauf Baig,et al.  A spatio-temporal neural network applied to visual speech recognition , 1999 .

[45]  Joachim Horn,et al.  Trajectory tracking of a batch polymerization reactor based on input–output-linearization of a neural process model , 2001 .

[46]  Cesare Furlanello,et al.  Model selection of combined neural nets for speech recognition , 1999 .

[47]  Cláudio Augusto Oller do Nascimento,et al.  Modeling of industrial nylon‐6,6 polymerization process in a twin‐screw extruder reactor. II. Neural networks and hybrid models , 1999 .

[48]  Jie Zhang,et al.  Batch-to-batch optimal control of a batch polymerisation process based on stacked neural network models , 2008 .

[49]  Silvia Curteanu,et al.  Hybrid Neural Network Models Applied to a Free Radical Polymerization Process , 2006 .

[50]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[51]  Bernhard Eikens,et al.  Process identification with multiple neural network models , 1999 .

[52]  Silvia Curteanu,et al.  Optimization Strategy Based on Genetic Algorithms and Neural Networks Applied to a Polymerization Process , 2007 .

[53]  Jie Zhang,et al.  Long-term prediction models based on mixed order locally recurrent neural networks , 1998 .

[54]  M. Rijckaert,et al.  Intelligent modelling in the chemical process industry with neural networks : A case study , 1998 .

[55]  Jie Zhang,et al.  Prediction of polymer quality in batch polymerisation reactors using robust neural networks , 1998 .

[56]  Paul D. Gader,et al.  Improved dynamic-programming-based handwritten word recognition using optimal order statistics , 1997, Optics & Photonics.

[57]  Jie Zhang,et al.  Inferential Estimation of Polymer Melt Index Using Sequentially Trained Bootstrap Aggregated Neural Networks , 2006 .

[58]  Vijay S. Desai,et al.  The Efficacy of Neural Networks in Predicting Returns on Stock and Bond Indices , 1998 .

[59]  Mansur R. Kabuka,et al.  Design of Supervised Classifiers Using Boolean Neural Networks , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[60]  Jie Zhang,et al.  Bayesian selective combination of multiple neural networks for improving long-range predictions in nonlinear process modelling , 2004, Neural Computing & Applications.

[61]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[62]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[63]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[64]  Desmond Fletcher,et al.  Forecasting with neural networks: An application using bankruptcy data , 1993, Inf. Manag..

[65]  T. M. English,et al.  Stacked generalization and simulated evolution. , 1996, Bio Systems.

[66]  Eric B. Bartlett,et al.  An information theoretic approach for combining neural network process models , 1999, Neural Networks.

[67]  V. Chitanov,et al.  Neural-fuzzy modelling of polymer quality in batch polymerization reactors , 2004, 2004 2nd International IEEE Conference on 'Intelligent Systems'. Proceedings (IEEE Cat. No.04EX791).

[68]  Ricardo A. F. Machado,et al.  Continuous polymerization in tubular reactors with prepolymerization: Analysis using two-dimensional phenomenological model and hybrid model with neural networks , 2004 .

[69]  George W. Irwin,et al.  Improving neural network training solutions using regularisation , 2001, Neurocomputing.

[70]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[71]  Rich Caruana,et al.  Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping , 2000, NIPS.

[72]  Georges Dupret,et al.  Bootstrap re-sampling for unbalanced data in supervised learning , 2001, Eur. J. Oper. Res..

[73]  Yuan Tian,et al.  Dynamic On‐Line Reoptimization Control of a Batch MMA Polymerization Reactor Using Hybrid Neural Network Models , 2004 .

[74]  D. M. Himmelblau,et al.  Online prediction of polymer product quality in an industrial reactor using recurrent neural networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).