Artificial neural approach for modeling the heat and mass transfer characteristics in three-phase fluidized beds

Farouq S. Mjalli, A. Al-Mfargi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The study of reactor design and modeling is conducted frequently both at the initial stage of equipment design as well as during further stages of equipment operation. Fluidized bed three-phase reactors have very complex behavior which relies to a high extent on the mass and heat transfer characteristics of the reaction constituents. Numerous previous experimental and theoretical based studies for modeling heat and mass transfer coefficients have the common shortcoming of low prediction efficiency compared to 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 newly developed heat and mass transfer coefficients models proved to be of high prediction quality compared to experimental data and previous correlations. The new correlations will be used in a further study for the hybrid steady state and dynamic modeling of fluidized bed catalytic reactors.

Original languageEnglish
Pages (from-to)4542-4552
Number of pages11
JournalIndustrial and Engineering Chemistry Research
Volume47
Issue number13
DOIs
Publication statusPublished - Jul 2 2008

Fingerprint

Fluidized beds
heat transfer
mass transfer
Mass transfer
Heat transfer
Heat transfer coefficients
modeling
prediction
artificial neural network
Neural networks
reactor

ASJC Scopus subject areas

  • Polymers and Plastics
  • Environmental Science(all)
  • Chemical Engineering (miscellaneous)

Cite this

Artificial neural approach for modeling the heat and mass transfer characteristics in three-phase fluidized beds. / Mjalli, Farouq S.; Al-Mfargi, A.

In: Industrial and Engineering Chemistry Research, Vol. 47, No. 13, 02.07.2008, p. 4542-4552.

Research output: Contribution to journalArticle

@article{0d5e22e7a5fe47c08f201fd3993c3ef9,
title = "Artificial neural approach for modeling the heat and mass transfer characteristics in three-phase fluidized beds",
abstract = "The study of reactor design and modeling is conducted frequently both at the initial stage of equipment design as well as during further stages of equipment operation. Fluidized bed three-phase reactors have very complex behavior which relies to a high extent on the mass and heat transfer characteristics of the reaction constituents. Numerous previous experimental and theoretical based studies for modeling heat and mass transfer coefficients have the common shortcoming of low prediction efficiency compared to 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 newly developed heat and mass transfer coefficients models proved to be of high prediction quality compared to experimental data and previous correlations. The new correlations will be used in a further study for the hybrid steady state and dynamic modeling of fluidized bed catalytic reactors.",
author = "Mjalli, {Farouq S.} and A. Al-Mfargi",
year = "2008",
month = "7",
day = "2",
doi = "10.1021/ie0715714",
language = "English",
volume = "47",
pages = "4542--4552",
journal = "Industrial & Engineering Chemistry Product Research and Development",
issn = "0888-5885",
publisher = "American Chemical Society",
number = "13",

}

TY - JOUR

T1 - Artificial neural approach for modeling the heat and mass transfer characteristics in three-phase fluidized beds

AU - Mjalli, Farouq S.

AU - Al-Mfargi, A.

PY - 2008/7/2

Y1 - 2008/7/2

N2 - The study of reactor design and modeling is conducted frequently both at the initial stage of equipment design as well as during further stages of equipment operation. Fluidized bed three-phase reactors have very complex behavior which relies to a high extent on the mass and heat transfer characteristics of the reaction constituents. Numerous previous experimental and theoretical based studies for modeling heat and mass transfer coefficients have the common shortcoming of low prediction efficiency compared to 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 newly developed heat and mass transfer coefficients models proved to be of high prediction quality compared to experimental data and previous correlations. The new correlations will be used in a further study for the hybrid steady state and dynamic modeling of fluidized bed catalytic reactors.

AB - The study of reactor design and modeling is conducted frequently both at the initial stage of equipment design as well as during further stages of equipment operation. Fluidized bed three-phase reactors have very complex behavior which relies to a high extent on the mass and heat transfer characteristics of the reaction constituents. Numerous previous experimental and theoretical based studies for modeling heat and mass transfer coefficients have the common shortcoming of low prediction efficiency compared to 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 newly developed heat and mass transfer coefficients models proved to be of high prediction quality compared to experimental data and previous correlations. The new correlations will be used in a further study for the hybrid steady state and dynamic modeling of fluidized bed catalytic reactors.

UR - http://www.scopus.com/inward/record.url?scp=47849092501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47849092501&partnerID=8YFLogxK

U2 - 10.1021/ie0715714

DO - 10.1021/ie0715714

M3 - Article

AN - SCOPUS:47849092501

VL - 47

SP - 4542

EP - 4552

JO - Industrial & Engineering Chemistry Product Research and Development

JF - Industrial & Engineering Chemistry Product Research and Development

SN - 0888-5885

IS - 13

ER -