Hybrid modeling of ethylene to ethylene oxide heterogeneous reactor

In this research a dynamic grey box model (GBM) of ethylene oxide (EO) fixed bed reactor has been presented. In the first step of the study, kinetic model of the existing reactions was obtained using artificial neural network (ANN) approach. In order to build the ANN model industrial data of a typical EO reactor were employed. Time, C2H4, C2H4O, CO2, H2O and O2 mole fractions were network inputs and the multiplication of reaction rate and catalyst deactivation (r * a)was ANN output. From 164 data, 109 data were employed to train ANN. After employing different training algorithms, it was found that, the radial basis function network (RBFN) training algorithm provides the best estimations of the data. This best obtained network was tested against fifty five unseen data. The network estimations were close to unseen data which confirmed generalization capability of the obtained network. In the next step of study, (r * a) was estimated with ANN and then the hybrid model of the reactor was solved. Simulation results were compared with EO mechanistic model and also with plant industrial data. It was found that GBM is 8.437 times more accurate than the mechanistic model. Research highlights ? ANN can model rate of ethylen epoxidation. ? Grey box model is more accurate than mechanistic model. ? Grey box model provides good extrapolation.

[1]  Sungwon Hwang,et al.  Heterogeneous catalytic reactor design with optimum temperature profile I: application of catalyst dilution and side-stream distribution , 2004 .

[2]  Tegoeh Tjahjowidodo,et al.  Identification of pre-sliding and sliding friction dynamics: Grey box and black-box models , 2007 .

[3]  C. H. Bartholomew.  Mechanisms of catalyst deactivation , 2001 .

[4]  Wei-Kang Yuan,et al.  Optimization of the fixed-bed reactor for ethylene epoxidation , 2005 .

[5]  Manuel R. Arahal,et al.  Serial grey-box model of a stratified thermal tank for hierarchical control of a solar plant , 2008 .

[6]  Mark A. Kramer,et al.  Modeling chemical processes using prior knowledge and neural networks , 1994 .

[7]  Ali Elkamel,et al.  Hybrid artificial neural network—First principle model formulation for the unsteady state simulation and analysis of a packed bed reactor for CO2 hydrogenation to methanol , 2005 .

[8]  K. R. Westerterp,et al.  An experimental study of the kinetics of the selectivity oxidation of ethene over a silver on a-alumina catalyst , 1995 .

[9]  Wolfgang Marquardt,et al.  A grey-box modeling approach for the reduction of nonlinear systems , 2008 .

[10]  Jose A. Romagnoli,et al.  Modelling and Optimisation of an Industrial Ethylene Oxide Reactor , 2009 .

[11]  Zhu Bingchen,et al.  Modelling catalytic reaction-absorption coupling process of ethylene oxide synthesis in slurry reactor , 1999 .

[12]  Catalytic incineration of ethylene oxide in the packed bed reactor , 2006 .

[13]  George M. Bollas,et al.  A Computer-Aided Tool for the Simulation and Optimization of the Combined HDS–FCC Processes , 2004 .

[14]  Chien-Cheng Lee,et al.  Noisy time series prediction using M-estimator based robust radial basis function neural networks with growing and pruning techniques , 2009, Expert Syst. Appl..

[15]  G. Hoflund,et al.  Study of Cs-promoted, α-alumina-supported silver, ethylene-epoxidation catalysts. II. Effects of aging , 1996 .

[16]  Chrysanthos E. Gounaris,et al.  Modelling of the performance of industrial HDS reactors using a hybrid neural network approach , 2005 .

[17]  Arvind Varma,et al.  Ethylene Epoxidation on Ag-Cs/α-Al2O3 Catalyst: Experimental Results and Strategy for Kinetic Parameter Determination , 2000 .

[18]  Jc Jaap Schouten,et al.  Transient Kinetic Modeling of the Ethylene and Carbon Monoxide Oxidation over a Commercial Automotive Exhaust Gas Catalyst , 2000 .

[19]  G. P. Rangaiah,et al.  First-Principles, Data-Based, and Hybrid Modeling and Optimization of an Industrial Hydrocracking Unit , 2006 .

[20]  Christian Inard,et al.  Grey-box identification of air-handling unit elements , 2007 .

[21]  George M. Bollas,et al.  Using hybrid neural networks in scaling up an FCC model from a pilot plant to an industrial unit , 2003 .

[22]  Kun Soo Chang,et al.  Hybrid neural network modeling of a full-scale industrial wastewater treatment process. , 2002, Biotechnology and bioengineering.

[23]  Farhad Faradji,et al.  Plausibility assessment of a 2-state self-paced mental task-based BCI using the no-control performance analysis , 2009, Journal of Neuroscience Methods.

[24]  Rubens Maciel Filho,et al.  Neural network and hybrid model: a discussion about different modeling techniques to predict pulping degree with industrial data , 2001 .

[25]  P. Linke,et al.  Heterogeneous catalytic reactor design with optimum temperature profile II: application of non-uniform catalyst , 2004 .

[26]  Leifur Þ. Leifsson,et al.  Grey-box modeling of an ocean vessel for operational optimization , 2008, Simul. Model. Pract. Theory.

[27]  Sanjeev S. Tambe,et al.  Reaction Modeling and Optimization Using Neural Networks and Genetic Algorithms: Case Study Involving TS-1-Catalyzed Hydroxylation of Benzene , 2002 .

[28]  M. Morbidelli,et al.  Optimization of a nonisothermal nonadiabatic fixed-bed reactor using dirac-type silver catalysts for ethylene epoxidation , 1994 .

[29]  Jyh-Shyong Chang,et al.  Optimization of Batch Polymerization Reactors Using Neural-Network Rate-Function Models , 2002 .

[30]  Jeroen Lammertyn,et al.  Development and validation of "grey-box" models for refrigeration applications: a review of key concepts , 2006 .

[31]  Bojan Stopar,et al.  GPS orbit approximation using radial basis function networks , 2009, Comput. Geosci..

[32]  G. L. Montrasi,et al.  Oxidation of ethylene to ethylene oxide: catalyst deactivation in an industrial run , 1983 .

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