NEURAL NETWORK–BASED HEAT AND MASS TRANSFER COEFFICIENTS FOR THE HYBRID MODELING OF FLUIDIZED REACTORS

The complex flow patterns induced in fluidized bed catalytic reactors and the competing parameters affecting the mass and heat transfer characteristics make the design of such reactors a challenging task to accomplish. The models of such processes rely heavily on predictive empirical correlations for the mass and heat transfer coefficients. Unfortunately, published empirical-based correlations have the common shortcoming of low prediction efficiency compared with experimental data. In this work, an artificial neural network approach is used to capture the reactor characteristics in terms of heat and mass transfer based on published experimental data. The developed ANN-based heat and mass transfer coefficients relations were used in a conventional FCR model and simulated under industrial operating conditions. The hybrid model predictions of the melt-flow index and the emulsion temperature were compared to industrial measurements as well as published models. The predictive quality of the hybrid model was superior to other models. This modeling approach can be used as an alternative to conventional modeling methods.

[1]  Navid Mostoufi,et al.  Modeling of fluidized bed reactor of ethylene polymerization , 2004 .

[2]  Shik Namkoong,et al.  Mechanism of Heat Transfer to Fluidized Beds , 1965 .

[3]  Yong Kang,et al.  Heat and mass transfer in three-phase fluidized-bed reactors—an overview , 1997 .

[4]  Fluidized-bed reactor and physical-chemical properties modeling for polyethylene production , 1999 .

[5]  K. Kato,et al.  Bubble assemblage model for fluidized bed catalytic reactors , 1969 .

[6]  L. Reh,et al.  Wall-to-bed heat transfer in circulating fluidized beds , 1998 .

[7]  F. García-Ochoa,et al.  Estimation of oxygen mass transfer coefficient in stirred tank reactors using artificial neural networks. , 2001, Enzyme and microbial technology.

[8]  W. Ray,et al.  THE DYNAMIC BEHAVIOUR OF FLUIDIZED BED REACTORS FOR SOLID CATALYZED GAS PHASE OLEFIN POLYMERIZATION , 1985 .

[9]  David W. Bacon,et al.  Gas Phase Ethylene Polymerization: Production Processes, Polymer Properties, and Reactor Modeling , 1994 .

[10]  H. Mickley,et al.  Mechanism of heat transfer to fluidized beds , 1955 .

[11]  N. Mostoufi,et al.  TWO-PHASE MODELING OF A GAS PHASE POLYETHYLENE FLUIDIZED BED REACTOR , 2006 .

[12]  F. Mjalli,et al.  Representation of Adsorption Data for the Isopropanol‐Water System using Neural Network Techniques , 2005 .

[13]  P. E. Gishler,et al.  HEAT TRANSFER IN A FLUIDIZED SOLIDS BED , 1950 .

[14]  S. Sablani.  A neural network approach for non-iterative calculation of heat transfer coefficient in fluid–particle systems , 2001 .

[15]  Ronald W. Breault,et al.  A review of gas–solid dispersion and mass transfer coefficient correlations in circulating fluidized beds , 2006 .

[16]  Neural networks for predicting mass transfer parameters in supercritical extraction , 2000 .

[17]  Martin T. Hagan,et al.  Neural network design , 1995 .

[18]  C. A. Coulaloglou,et al.  Alpha-omega and beyond industrial view of gas/liquid/solid reactor development , 1992 .

[19]  Jamal Chaouki,et al.  Characterization of dynamic gas–solid distribution in fluidized beds , 2000 .

[20]  Bruce D. Baker,et al.  Exploratory Application of Systems Dynamics Modeling to School Finance Policy Analysis. , 2002 .

[21]  B. Reddy,et al.  Axial and radial heat transfer studies in a circulating fluidized bed , 1997 .

[22]  Arun S. Mujumdar,et al.  USE OF NEURAL NETWORK TO PREDICT INDUSTRIAL DRYER PERFORMANCE , 1993 .

[23]  V. Kvasnicka,et al.  Feedforward Neural Network Methodology , 2001, IEEE Trans. Neural Networks.

[24]  Thomas J. Harris,et al.  A comparison of two-phase and well-mixed models for fluidized-bed polyethylene reactors , 1994 .

[25]  M. Louge,et al.  Convective heat transfer scaling at the wall of circulating fluidized bed risers , 2000 .

[26]  J. A. Dente,et al.  Characteristic Functions and Process Identification by Neural Networks , 1997, Neural Networks.

[27]  F. Fernandes,et al.  Heterogeneous modeling for fluidized-bed polymerization reactor , 2001 .

[28]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[29]  N. Mostoufi,et al.  Evaluation of heat transfer coefficient in gas–solid fluidized beds using cluster-based approach , 2007 .

[30]  G Shahaf,et al.  Learning in Networks of Cortical Neurons , 2001, The Journal of Neuroscience.

[31]  J. Macgregor,et al.  A kinetic model for industrial gas-phase ethylene copolymerization , 1990 .

[32]  John R. Grace,et al.  Effect of bubble interaction on interphase mass transfer in gas fluidized beds , 1981 .

[33]  Jinguo Yang,et al.  Local instantaneous temperature and time‐averaged heat transfer coefficient in the bottom zone of a circulating fluidized bed , 2004 .

[34]  Y. Islamoglu,et al.  Heat transfer analysis using ANNs with experimental data for air flowing in corrugated channels , 2004 .

[35]  Andreas Hans Kemna,et al.  Identification of combined physical and empirical models using nonlinear A priori knowledge , 1994 .

[36]  Faïçal Larachi,et al.  Heat and Mass Transfer in Cocurrent Gas−Liquid Packed Beds. Analysis, Recommendations, and New Correlations , 2003 .

[37]  P. Nag,et al.  Bed-to-wall heat transfer behavior in a pressurized circulating fluidized bed , 2002 .

[38]  Navid Mostoufi,et al.  Modular simulation of fluidized bed reactors , 2004 .

[39]  Three-phase multi-compartment model for fluidized-bed catalytic reactors: autothermicity and multiplicity of steady states , 1992 .

[40]  M. Peters,et al.  Simulation of particulate removal in gas‐solid fluidized beds , 1982 .

[41]  Francis J. Doyle,et al.  A dynamic neural network approach to nonlinear process modeling , 1997 .

[42]  Murray Smith,et al.  Neural Networks for Statistical Modeling , 1993 .

[43]  S. D. Kim,et al.  MASS TRANSFER AND PHASE HOLDUP CHARACTERISTICS IN THREE-PHASE FLUIDIZED BEDS , 1993 .

[44]  A. Baskakov,et al.  Heat transfer to objects immersed in fluidized beds , 1973 .

[45]  S. Prasher,et al.  A NEURAL NETWORK APPROACH FOR EVALUATION of SURFACE HEAT TRANSFER COEFFICIENT , 1999 .

[46]  Alice E. Smith,et al.  Estimation of a mass transfer coefficient for nylon manufacture using multiple neural networks , 2001 .

[47]  C. Hsu,et al.  MgCI2-Supported Ziegler-Natta Catalysts for Olefin Polymerization: Basic Structure, Mechanism, and Kinetic Behavior , 1993 .

[48]  W. H. Ray,et al.  Polymerization of olefins through heterogeneous catalysis X: Modeling of particle growth and morphology , 1992 .