Neural network modeling for separation of bentonite in tubular ceramic membranes

Nidal Hilal, Oluwaseun Ogunbiyi, Mohammed Al-Abri

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The neural network model is used for obtaining an estimation of permeate flux and rejection over the entire range of process variables. This approach has been extended in this study and applied to the prediction of flux sustainability and membrane efficiency of ceramic tubular membranes. Experimental results involving the use of turbulence promoters and the empty membrane filtration have been obtained and are directly compared to the predicted values from the black box model. Flux sustainability and membrane efficiency are dependent on feed temperature, system pressure, feed concentration and crossflow velocity. Neural networks also offer the added advantage of being quite straightforward in its application. The possibility of using BPNN (back-propagation network) to accurately predict variable effects on flux sustainability is included. Turbulence promoters were used experimentally to significantly enhance membrane efficiency and flux sustainability during microfiltration of dilute bentonite suspensions. Artificial neural networks can predict very accurately real system behaviour with relative errors reaching at most 5%. In order to obtain the data set necessary to train the different networks, three concentrations, three system pressures, three feed temperatures and one feed flowrate were tested in several operating conditions.

Original languageEnglish
Pages (from-to)175-182
Number of pages8
JournalDesalination
Volume228
Issue number1-3
DOIs
Publication statusPublished - 15 Aug 2008
Externally publishedYes

Fingerprint

Bentonite
Ceramic membranes
bentonite
ceramics
Sustainable development
Fluxes
membrane
Neural networks
Membranes
sustainability
modeling
Turbulence
turbulence
Microfiltration
back propagation
Backpropagation
artificial neural network
train
Suspensions
temperature

Keywords

  • Back-propagation
  • Bentonite
  • Crossflow microfiltration
  • Neural network
  • Turbulence promoters

ASJC Scopus subject areas

  • Filtration and Separation

Cite this

Neural network modeling for separation of bentonite in tubular ceramic membranes. / Hilal, Nidal; Ogunbiyi, Oluwaseun; Al-Abri, Mohammed.

In: Desalination, Vol. 228, No. 1-3, 15.08.2008, p. 175-182.

Research output: Contribution to journalArticle

Hilal, Nidal ; Ogunbiyi, Oluwaseun ; Al-Abri, Mohammed. / Neural network modeling for separation of bentonite in tubular ceramic membranes. In: Desalination. 2008 ; Vol. 228, No. 1-3. pp. 175-182.
@article{e0f517d998eb4551936a70a5f5ffe66f,
title = "Neural network modeling for separation of bentonite in tubular ceramic membranes",
abstract = "The neural network model is used for obtaining an estimation of permeate flux and rejection over the entire range of process variables. This approach has been extended in this study and applied to the prediction of flux sustainability and membrane efficiency of ceramic tubular membranes. Experimental results involving the use of turbulence promoters and the empty membrane filtration have been obtained and are directly compared to the predicted values from the black box model. Flux sustainability and membrane efficiency are dependent on feed temperature, system pressure, feed concentration and crossflow velocity. Neural networks also offer the added advantage of being quite straightforward in its application. The possibility of using BPNN (back-propagation network) to accurately predict variable effects on flux sustainability is included. Turbulence promoters were used experimentally to significantly enhance membrane efficiency and flux sustainability during microfiltration of dilute bentonite suspensions. Artificial neural networks can predict very accurately real system behaviour with relative errors reaching at most 5{\%}. In order to obtain the data set necessary to train the different networks, three concentrations, three system pressures, three feed temperatures and one feed flowrate were tested in several operating conditions.",
keywords = "Back-propagation, Bentonite, Crossflow microfiltration, Neural network, Turbulence promoters",
author = "Nidal Hilal and Oluwaseun Ogunbiyi and Mohammed Al-Abri",
year = "2008",
month = "8",
day = "15",
doi = "10.1016/j.desal.2007.10.006",
language = "English",
volume = "228",
pages = "175--182",
journal = "Desalination",
issn = "0011-9164",
publisher = "Elsevier",
number = "1-3",

}

TY - JOUR

T1 - Neural network modeling for separation of bentonite in tubular ceramic membranes

AU - Hilal, Nidal

AU - Ogunbiyi, Oluwaseun

AU - Al-Abri, Mohammed

PY - 2008/8/15

Y1 - 2008/8/15

N2 - The neural network model is used for obtaining an estimation of permeate flux and rejection over the entire range of process variables. This approach has been extended in this study and applied to the prediction of flux sustainability and membrane efficiency of ceramic tubular membranes. Experimental results involving the use of turbulence promoters and the empty membrane filtration have been obtained and are directly compared to the predicted values from the black box model. Flux sustainability and membrane efficiency are dependent on feed temperature, system pressure, feed concentration and crossflow velocity. Neural networks also offer the added advantage of being quite straightforward in its application. The possibility of using BPNN (back-propagation network) to accurately predict variable effects on flux sustainability is included. Turbulence promoters were used experimentally to significantly enhance membrane efficiency and flux sustainability during microfiltration of dilute bentonite suspensions. Artificial neural networks can predict very accurately real system behaviour with relative errors reaching at most 5%. In order to obtain the data set necessary to train the different networks, three concentrations, three system pressures, three feed temperatures and one feed flowrate were tested in several operating conditions.

AB - The neural network model is used for obtaining an estimation of permeate flux and rejection over the entire range of process variables. This approach has been extended in this study and applied to the prediction of flux sustainability and membrane efficiency of ceramic tubular membranes. Experimental results involving the use of turbulence promoters and the empty membrane filtration have been obtained and are directly compared to the predicted values from the black box model. Flux sustainability and membrane efficiency are dependent on feed temperature, system pressure, feed concentration and crossflow velocity. Neural networks also offer the added advantage of being quite straightforward in its application. The possibility of using BPNN (back-propagation network) to accurately predict variable effects on flux sustainability is included. Turbulence promoters were used experimentally to significantly enhance membrane efficiency and flux sustainability during microfiltration of dilute bentonite suspensions. Artificial neural networks can predict very accurately real system behaviour with relative errors reaching at most 5%. In order to obtain the data set necessary to train the different networks, three concentrations, three system pressures, three feed temperatures and one feed flowrate were tested in several operating conditions.

KW - Back-propagation

KW - Bentonite

KW - Crossflow microfiltration

KW - Neural network

KW - Turbulence promoters

UR - http://www.scopus.com/inward/record.url?scp=47049092954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47049092954&partnerID=8YFLogxK

U2 - 10.1016/j.desal.2007.10.006

DO - 10.1016/j.desal.2007.10.006

M3 - Article

VL - 228

SP - 175

EP - 182

JO - Desalination

JF - Desalination

SN - 0011-9164

IS - 1-3

ER -