Artificial neural networks modeling of ozone bubble columns: Mass transfer coefficient, gas hold-up, and bubble size

Mahad S. Baawain, Mohamed Gamal El-Din, Daniel W. Smith

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

This study aims at applying artificial neural network (ANN) modeling approach in designing ozone bubble columns. Three multi-layer perceptron (MLP) ANN models were developed to predict the overall mass transfer coefficient (kLa, s-1), the gas hold-up (εG, dimensionless), and the Sauter mean bubble diameter (dS, m) in different ozone bubble columns using simple inputs such as bubble column's geometry and operating conditions. The obtained results showed excellent prediction of kLa, εG, and dS values as the coefficient of multiple determination (R2) values for all ANN models exceeded 0.98. The ANN models were then used to determine the local mass transfer coefficient (kL, m.s-1). A very good agreement between the modeled and the measured kL values was observed (R2 = 0.85).

Original languageEnglish
Pages (from-to)343-352
Number of pages10
JournalOzone: Science and Engineering
Volume29
Issue number5
DOIs
Publication statusPublished - Sep 2007

Fingerprint

Bubble columns
Ozone
artificial neural network
bubble
mass transfer
Mass transfer
Gases
ozone
Neural networks
gas
modeling
Multilayer neural networks
Bubbles (in fluids)
geometry
Geometry
prediction

Keywords

  • Artificial Neural Networks
  • Bubble Columns
  • Bubble Size
  • Gas Hold-up
  • Local Mass Transfer Coefficient
  • Modeling
  • Overall Mass Transfer Coefficient
  • Ozone
  • Sauter Mean Bubble Diameter

ASJC Scopus subject areas

  • Environmental Science(all)
  • Environmental Chemistry

Cite this

Artificial neural networks modeling of ozone bubble columns : Mass transfer coefficient, gas hold-up, and bubble size. / Baawain, Mahad S.; El-Din, Mohamed Gamal; Smith, Daniel W.

In: Ozone: Science and Engineering, Vol. 29, No. 5, 09.2007, p. 343-352.

Research output: Contribution to journalArticle

@article{325d251aa03f42dfade03abc25ec30dc,
title = "Artificial neural networks modeling of ozone bubble columns: Mass transfer coefficient, gas hold-up, and bubble size",
abstract = "This study aims at applying artificial neural network (ANN) modeling approach in designing ozone bubble columns. Three multi-layer perceptron (MLP) ANN models were developed to predict the overall mass transfer coefficient (kLa, s-1), the gas hold-up (εG, dimensionless), and the Sauter mean bubble diameter (dS, m) in different ozone bubble columns using simple inputs such as bubble column's geometry and operating conditions. The obtained results showed excellent prediction of kLa, εG, and dS values as the coefficient of multiple determination (R2) values for all ANN models exceeded 0.98. The ANN models were then used to determine the local mass transfer coefficient (kL, m.s-1). A very good agreement between the modeled and the measured kL values was observed (R2 = 0.85).",
keywords = "Artificial Neural Networks, Bubble Columns, Bubble Size, Gas Hold-up, Local Mass Transfer Coefficient, Modeling, Overall Mass Transfer Coefficient, Ozone, Sauter Mean Bubble Diameter",
author = "Baawain, {Mahad S.} and El-Din, {Mohamed Gamal} and Smith, {Daniel W.}",
year = "2007",
month = "9",
doi = "10.1080/01919510701549236",
language = "English",
volume = "29",
pages = "343--352",
journal = "Ozone: Science and Engineering",
issn = "0191-9512",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

TY - JOUR

T1 - Artificial neural networks modeling of ozone bubble columns

T2 - Mass transfer coefficient, gas hold-up, and bubble size

AU - Baawain, Mahad S.

AU - El-Din, Mohamed Gamal

AU - Smith, Daniel W.

PY - 2007/9

Y1 - 2007/9

N2 - This study aims at applying artificial neural network (ANN) modeling approach in designing ozone bubble columns. Three multi-layer perceptron (MLP) ANN models were developed to predict the overall mass transfer coefficient (kLa, s-1), the gas hold-up (εG, dimensionless), and the Sauter mean bubble diameter (dS, m) in different ozone bubble columns using simple inputs such as bubble column's geometry and operating conditions. The obtained results showed excellent prediction of kLa, εG, and dS values as the coefficient of multiple determination (R2) values for all ANN models exceeded 0.98. The ANN models were then used to determine the local mass transfer coefficient (kL, m.s-1). A very good agreement between the modeled and the measured kL values was observed (R2 = 0.85).

AB - This study aims at applying artificial neural network (ANN) modeling approach in designing ozone bubble columns. Three multi-layer perceptron (MLP) ANN models were developed to predict the overall mass transfer coefficient (kLa, s-1), the gas hold-up (εG, dimensionless), and the Sauter mean bubble diameter (dS, m) in different ozone bubble columns using simple inputs such as bubble column's geometry and operating conditions. The obtained results showed excellent prediction of kLa, εG, and dS values as the coefficient of multiple determination (R2) values for all ANN models exceeded 0.98. The ANN models were then used to determine the local mass transfer coefficient (kL, m.s-1). A very good agreement between the modeled and the measured kL values was observed (R2 = 0.85).

KW - Artificial Neural Networks

KW - Bubble Columns

KW - Bubble Size

KW - Gas Hold-up

KW - Local Mass Transfer Coefficient

KW - Modeling

KW - Overall Mass Transfer Coefficient

KW - Ozone

KW - Sauter Mean Bubble Diameter

UR - http://www.scopus.com/inward/record.url?scp=35648974837&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35648974837&partnerID=8YFLogxK

U2 - 10.1080/01919510701549236

DO - 10.1080/01919510701549236

M3 - Article

AN - SCOPUS:35648974837

VL - 29

SP - 343

EP - 352

JO - Ozone: Science and Engineering

JF - Ozone: Science and Engineering

SN - 0191-9512

IS - 5

ER -