Prediction interval-based neural network modelling of polystyrene polymerization reactor – A new perspective of data-based modelling

Abstract In this paper, prediction interval (PI)-based modelling techniques are introduced and applied to capture the nonlinear dynamics of a polystyrene batch reactor system. Traditional NN models are developed using experimental datasets with and without disturbances. Simulation results indicate that traditional NNs cannot properly handle disturbances in reactor data and demonstrate a poor forecasting performance, with an average MAPE of 22% in the presence of disturbances. The lower upper bound estimation (LUBE) method is applied for the construction of PIs to quantify uncertainties associated with forecasts. The simulated annealing optimization technique is employed to adjust NN parameters for minimization of an innovative PI-based cost function. The simulation results reveal that the LUBE method generates quality PIs without requiring prohibitive computations. As both calibration and sharpness of PIs are practically and theoretically satisfactory, the constructed PIs can be used as part of the decision-making and control process of polymerization reactors.

[1]  Zainal Ahmad,et al.  Modelling and control of different types of polymerization processes using neural networks technique: A review , 2010 .

[2]  Saeid Nahavandi,et al.  A prediction interval-based approach to determine optimal structures of neural network metamodels , 2010, Expert Syst. Appl..

[3]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[4]  Amir F. Atiya,et al.  Comprehensive Review of Neural Network-Based Prediction Intervals and New Advances , 2011, IEEE Transactions on Neural Networks.

[5]  Amir F. Atiya,et al.  Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals , 2011, IEEE Transactions on Neural Networks.

[6]  H. Hapoglu,et al.  Application of experimental non-linear control based on generic algorithm to a polymerization reactor , 2009 .

[7]  Gülay Özkan,et al.  Non-linear generalised predictive control of a jacketed well mixed tank as applied to a batch process—A polymerisation reaction , 2006 .

[8]  Saeid Nahavandi,et al.  Construction of Optimal Prediction Intervals for Load Forecasting Problems , 2010, IEEE Transactions on Power Systems.

[9]  Jing Wang,et al.  Dynamic Modeling and Optimal Control of Batch Reactors, Based on Structure Approaching Hybrid Neural Networks , 2011 .

[10]  Saeid Nahavandi,et al.  A genetic algorithm-based method for improving quality of travel time prediction intervals , 2011 .

[11]  F. Mjalli,et al.  Hybrid modelling and kinetic estimation for polystyrene batch reactor using Artificial Neutral Network (ANN) approach , 2011 .

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

[13]  Saeid Nahavandi,et al.  Performance analysis of three advanced controllers for polymerization batch reactor: An experimental investigation , 2014 .

[14]  Saeid Nahavandi,et al.  Load Forecasting and Neural Networks: A Prediction Interval-Based Perspective , 2010 .

[15]  Iqbal M. Mujtaba,et al.  Neural network based modelling and control of batch reactor. , 2006 .

[16]  Keith Worden,et al.  Uncertainty analysis of a neural network used for fatigue lifetime prediction , 2008 .

[17]  Fabiano A.N. Fernandes,et al.  Neural network applications in polymerization processes , 2005 .

[18]  H. Hapoglu,et al.  APPLICATION OF FUZZY CONTROL METHOD WITH GENETIC ALGORITHM TO A POLYMERIZATION REACTOR AT CONSTANT SET POINT , 2006 .

[19]  Hale Hapoglu,et al.  Optimal temperature control in a batch polymerization reactor using fuzzy-relational models-dynamics matrix control , 2006, Comput. Chem. Eng..

[20]  Mohd Azlan Hussain,et al.  Control of polystyrene batch reactors using neural network based model predictive control (NNMPC): An experimental investigation , 2011 .

[21]  D. Srinivasan,et al.  Interval Type-2 Fuzzy Logic Systems for Load Forecasting: A Comparative Study , 2012, IEEE Transactions on Power Systems.

[22]  S. Nahavandi,et al.  Investigation of Process Dynamics and Control of Polystyrene Batch Reactor Using Hybrid Model , 2012, WCE 2012.

[23]  G. E. Eliçabe,et al.  Estimation and control in polymerization reactors. A review , 1988 .

[24]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[25]  M. Hussain,et al.  Optimization and control of polystyrene batch reactor using hybrid based model , 2012 .

[26]  Hale Hapoglu,et al.  Control of a polymerization reactor by fuzzy control method with genetic algorithm , 2003, Comput. Chem. Eng..

[27]  Robin A. Hutchinson,et al.  A comprehensive kinetic model for high‐temperature free radical production of styrene/methacrylate/acrylate resins , 2011 .

[28]  H. J. Van Zuylen,et al.  Bayesian committee of neural networks to predict travel times with confidence intervals , 2009 .

[29]  Tore Hägglund,et al.  Generalized feedforward tuning rules for non-realizable delay inversion , 2013 .

[30]  William Johns,et al.  Computer‐Aided Chemical Engineering , 2011 .

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

[32]  S. A. Sata,et al.  Temperature Control of a Bench‐Scale Batch Polymerization Reactor for Polystyrene Production , 2007 .

[33]  Marko Bacic,et al.  Model predictive control , 2003 .

[34]  Flávio Vasconcelos da Silva,et al.  Neural network model predictive control of a styrene polymerization plant: online testing using an electronic worksheet , 2012, Chemical Papers.

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

[36]  Iqbal M. Mujtaba,et al.  Neural-network approach to dynamic optimization of batch distillation: Application to a middle-vessel column , 2003 .

[37]  Shin'ichi Tamura,et al.  Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.

[38]  H. Troy Nagle,et al.  Performance of the Levenberg–Marquardt neural network training method in electronic nose applications , 2005 .

[39]  Hale Hapoglu,et al.  Self-tuning PID control of jacketed batch polystyrene reactor using genetic algorithm , 2008 .

[40]  Iqbal M. Mujtaba,et al.  Evaluation of neural networks-based controllers in batch polymerisation of methyl methacrylate , 2008, Neurocomputing.

[41]  Thong Ngee Goh,et al.  Neural network modeling with confidence bounds: a case study on the solder paste deposition process , 2001 .

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