Neural network–based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors

Farouk Mjalli, A. Al-Mfargi

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)318-342
Number of pages25
JournalChemical Engineering Communications
Volume197
Issue number3
DOIs
Publication statusPublished - Jan 1 2010

Fingerprint

Heat transfer coefficients
Mass transfer
Heat transfer
Emulsions
Flow patterns
Fluidized beds
Neural networks

Keywords

  • Catalytic reactor
  • Fluidized bed reactor
  • Heat transfer
  • Mass transfer
  • Neural networks
  • Three phase

ASJC Scopus subject areas

  • Chemistry(all)
  • Chemical Engineering(all)

Cite this

Neural network–based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors. / Mjalli, Farouk; Al-Mfargi, A.

In: Chemical Engineering Communications, Vol. 197, No. 3, 01.01.2010, p. 318-342.

Research output: Contribution to journalArticle

@article{504870c005c6433fa8d031ab2d336955,
title = "Neural network–based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors",
abstract = "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.",
keywords = "Catalytic reactor, Fluidized bed reactor, Heat transfer, Mass transfer, Neural networks, Three phase",
author = "Farouk Mjalli and A. Al-Mfargi",
year = "2010",
month = "1",
day = "1",
doi = "10.1080/00986440903088819",
language = "English",
volume = "197",
pages = "318--342",
journal = "Chemical Engineering Communications",
issn = "0098-6445",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Neural network–based heat and mass transfer coefficients for the hybrid modeling of fluidized reactors

AU - Mjalli, Farouk

AU - Al-Mfargi, A.

PY - 2010/1/1

Y1 - 2010/1/1

N2 - 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.

AB - 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.

KW - Catalytic reactor

KW - Fluidized bed reactor

KW - Heat transfer

KW - Mass transfer

KW - Neural networks

KW - Three phase

UR - http://www.scopus.com/inward/record.url?scp=83555171772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83555171772&partnerID=8YFLogxK

U2 - 10.1080/00986440903088819

DO - 10.1080/00986440903088819

M3 - Article

VL - 197

SP - 318

EP - 342

JO - Chemical Engineering Communications

JF - Chemical Engineering Communications

SN - 0098-6445

IS - 3

ER -