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 fo...

Full description

Bibliographic Details
Main Authors: Mjalli, Farouq Sabri, Al-Mfargi, A.
Format: Article
Published: Taylor & Francis 2010
Subjects:
_version_ 1825720670266327040
author Mjalli, Farouq Sabri
Al-Mfargi, A.
author_facet Mjalli, Farouq Sabri
Al-Mfargi, A.
author_sort Mjalli, Farouq Sabri
collection UM
description 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.
first_indexed 2024-03-06T05:38:39Z
format Article
id um.eprints-15355
institution Universiti Malaya
last_indexed 2024-03-06T05:38:39Z
publishDate 2010
publisher Taylor & Francis
record_format dspace
spelling um.eprints-153552019-05-09T04:44:29Z http://eprints.um.edu.my/15355/ Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors Mjalli, Farouq Sabri Al-Mfargi, A. Q Science (General) 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. Taylor & Francis 2010 Article PeerReviewed Mjalli, Farouq Sabri and Al-Mfargi, A. (2010) Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors. Chemical Engineering Communications, 197 (3). pp. 318-342. ISSN 0098-6445, DOI https://doi.org/10.1080/00986440903088819 <https://doi.org/10.1080/00986440903088819>. https://doi.org/10.1080/00986440903088819 doi:10.1080/00986440903088819
spellingShingle Q Science (General)
Mjalli, Farouq Sabri
Al-Mfargi, A.
Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
title Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
title_full Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
title_fullStr Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
title_full_unstemmed Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
title_short Neural network-based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
title_sort neural network based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors
topic Q Science (General)
work_keys_str_mv AT mjallifarouqsabri neuralnetworkbasedheatandmasstransfercoefficientsforthehybridmodelingoffluidizedreactors
AT almfargia neuralnetworkbasedheatandmasstransfercoefficientsforthehybridmodelingoffluidizedreactors