Rejection and modelling of sulphate and potassium salts by nanofiltration membranes

neural network and Spiegler-Kedem model

H. Al-Zoubi, N. Hilal, N. A. Darwish, A. W. Mohammad

Research output: Contribution to journalArticle

85 Citations (Scopus)

Abstract

This paper presents experimental data and modelling for three commercial nanofiltration membranes (NF90, NF270, N30F) used to treat highly concentrated different salts solutions (KCl, Na2SO4, and MgSO4) in a crossflow filtration set-up at a salinity level similar to that of seawater. The main parameters that have been studied in this work are feed pressure and salt concentration. The experimental data were correlated and analysed using artificial neural network (ANN) and Spiegler-Kedem model. Through the latter model, the reflection coefficient of all studied membranes and the solute permeability have been determined for all membranes at different salinity levels. The ANN's prediction of rejection vs. pressure and rejection vs. permeate flux for all investigated salt solutions is discussed. The results showed that both NF90 and NF270 produced a high rejection in the range of 95-99% at a pressure greater than 5 bar for Na2SO4, and MgSO4 salts, while for KCl the rejection was in the range of 30-89%. N30F gave relatively medium rejection and flux for Na2SO4 and MgSO4 salts and very low rejection and flux for KCl. A good agreement has been obtained using the ANN predictions and the experimental data with a deviation not more than 5% for most of the cases considered. The ANN interpolative performance for the medium concentration levels (which were not represented in the training phase) is shown to be of lesser quality. A comparison between ANN model and Spiegler-Kedem model is also discussed.

Original languageEnglish
Pages (from-to)42-60
Number of pages19
JournalDesalination
Volume206
Issue number1-3
DOIs
Publication statusPublished - 5 Feb 2007
Externally publishedYes

Fingerprint

Nanofiltration membranes
Potassium
potassium
Salts
artificial neural network
sulfate
membrane
salt
Neural networks
modeling
Fluxes
Membranes
salinity
Network performance
prediction
Seawater
solute
Sulfates
potassium sulfate
permeability

Keywords

  • Artificial neuron networks
  • Membrane
  • Nanofiltration
  • Permeate flux
  • Pre-treatment
  • Salt rejections
  • Seawater
  • Spiegler-Kedem model

ASJC Scopus subject areas

  • Filtration and Separation

Cite this

Rejection and modelling of sulphate and potassium salts by nanofiltration membranes : neural network and Spiegler-Kedem model. / Al-Zoubi, H.; Hilal, N.; Darwish, N. A.; Mohammad, A. W.

In: Desalination, Vol. 206, No. 1-3, 05.02.2007, p. 42-60.

Research output: Contribution to journalArticle

Al-Zoubi, H. ; Hilal, N. ; Darwish, N. A. ; Mohammad, A. W. / Rejection and modelling of sulphate and potassium salts by nanofiltration membranes : neural network and Spiegler-Kedem model. In: Desalination. 2007 ; Vol. 206, No. 1-3. pp. 42-60.
@article{5d3d32cfae734c2fa6f684d83975e9c4,
title = "Rejection and modelling of sulphate and potassium salts by nanofiltration membranes: neural network and Spiegler-Kedem model",
abstract = "This paper presents experimental data and modelling for three commercial nanofiltration membranes (NF90, NF270, N30F) used to treat highly concentrated different salts solutions (KCl, Na2SO4, and MgSO4) in a crossflow filtration set-up at a salinity level similar to that of seawater. The main parameters that have been studied in this work are feed pressure and salt concentration. The experimental data were correlated and analysed using artificial neural network (ANN) and Spiegler-Kedem model. Through the latter model, the reflection coefficient of all studied membranes and the solute permeability have been determined for all membranes at different salinity levels. The ANN's prediction of rejection vs. pressure and rejection vs. permeate flux for all investigated salt solutions is discussed. The results showed that both NF90 and NF270 produced a high rejection in the range of 95-99{\%} at a pressure greater than 5 bar for Na2SO4, and MgSO4 salts, while for KCl the rejection was in the range of 30-89{\%}. N30F gave relatively medium rejection and flux for Na2SO4 and MgSO4 salts and very low rejection and flux for KCl. A good agreement has been obtained using the ANN predictions and the experimental data with a deviation not more than 5{\%} for most of the cases considered. The ANN interpolative performance for the medium concentration levels (which were not represented in the training phase) is shown to be of lesser quality. A comparison between ANN model and Spiegler-Kedem model is also discussed.",
keywords = "Artificial neuron networks, Membrane, Nanofiltration, Permeate flux, Pre-treatment, Salt rejections, Seawater, Spiegler-Kedem model",
author = "H. Al-Zoubi and N. Hilal and Darwish, {N. A.} and Mohammad, {A. W.}",
year = "2007",
month = "2",
day = "5",
doi = "10.1016/j.desal.2006.02.060",
language = "English",
volume = "206",
pages = "42--60",
journal = "Desalination",
issn = "0011-9164",
publisher = "Elsevier",
number = "1-3",

}

TY - JOUR

T1 - Rejection and modelling of sulphate and potassium salts by nanofiltration membranes

T2 - neural network and Spiegler-Kedem model

AU - Al-Zoubi, H.

AU - Hilal, N.

AU - Darwish, N. A.

AU - Mohammad, A. W.

PY - 2007/2/5

Y1 - 2007/2/5

N2 - This paper presents experimental data and modelling for three commercial nanofiltration membranes (NF90, NF270, N30F) used to treat highly concentrated different salts solutions (KCl, Na2SO4, and MgSO4) in a crossflow filtration set-up at a salinity level similar to that of seawater. The main parameters that have been studied in this work are feed pressure and salt concentration. The experimental data were correlated and analysed using artificial neural network (ANN) and Spiegler-Kedem model. Through the latter model, the reflection coefficient of all studied membranes and the solute permeability have been determined for all membranes at different salinity levels. The ANN's prediction of rejection vs. pressure and rejection vs. permeate flux for all investigated salt solutions is discussed. The results showed that both NF90 and NF270 produced a high rejection in the range of 95-99% at a pressure greater than 5 bar for Na2SO4, and MgSO4 salts, while for KCl the rejection was in the range of 30-89%. N30F gave relatively medium rejection and flux for Na2SO4 and MgSO4 salts and very low rejection and flux for KCl. A good agreement has been obtained using the ANN predictions and the experimental data with a deviation not more than 5% for most of the cases considered. The ANN interpolative performance for the medium concentration levels (which were not represented in the training phase) is shown to be of lesser quality. A comparison between ANN model and Spiegler-Kedem model is also discussed.

AB - This paper presents experimental data and modelling for three commercial nanofiltration membranes (NF90, NF270, N30F) used to treat highly concentrated different salts solutions (KCl, Na2SO4, and MgSO4) in a crossflow filtration set-up at a salinity level similar to that of seawater. The main parameters that have been studied in this work are feed pressure and salt concentration. The experimental data were correlated and analysed using artificial neural network (ANN) and Spiegler-Kedem model. Through the latter model, the reflection coefficient of all studied membranes and the solute permeability have been determined for all membranes at different salinity levels. The ANN's prediction of rejection vs. pressure and rejection vs. permeate flux for all investigated salt solutions is discussed. The results showed that both NF90 and NF270 produced a high rejection in the range of 95-99% at a pressure greater than 5 bar for Na2SO4, and MgSO4 salts, while for KCl the rejection was in the range of 30-89%. N30F gave relatively medium rejection and flux for Na2SO4 and MgSO4 salts and very low rejection and flux for KCl. A good agreement has been obtained using the ANN predictions and the experimental data with a deviation not more than 5% for most of the cases considered. The ANN interpolative performance for the medium concentration levels (which were not represented in the training phase) is shown to be of lesser quality. A comparison between ANN model and Spiegler-Kedem model is also discussed.

KW - Artificial neuron networks

KW - Membrane

KW - Nanofiltration

KW - Permeate flux

KW - Pre-treatment

KW - Salt rejections

KW - Seawater

KW - Spiegler-Kedem model

UR - http://www.scopus.com/inward/record.url?scp=33846786458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846786458&partnerID=8YFLogxK

U2 - 10.1016/j.desal.2006.02.060

DO - 10.1016/j.desal.2006.02.060

M3 - Article

VL - 206

SP - 42

EP - 60

JO - Desalination

JF - Desalination

SN - 0011-9164

IS - 1-3

ER -