Artificial neural network model for optimizing operation of a seawater reverse osmosis desalination plant

Young Geun Lee, Yun Seok Lee, Jong June Jeon, Sangho Lee, Dae Ryook Yang, In S. Kim, Joon Ha Kim

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

An artificial neural network (ANN) was developed to predict the performance of a seawater reverse osmosis (SWRO) desalination plant, and was then applied to the simulation of feed water temperature. The model consists of five input parameters (i.e., feed temperature, feed total dissolved solids (TDS), trans-membrane pressure (TMP), feed flow rate, and time) and two output parameters (i.e., permeate TDS and flow rate). Then, the one-year operation data (n = 200) from the Fujairah SWRO plant was divided into three data sets (i.e., training, validation, and test data set) to develop the ANN model. The trained ANN model was subsequently found to produce good agreement between the observed and simulated data (TDS: R2 = 0.96; flow rate: R2 = 0.75) in the test data set. The results of this study show that the variation of the feed water temperature and TMP was found to significantly affect both the permeate TDS and flow rate. From subsequent simulations with various temperature controls, it is further suggested that the permeate TDS can be reduced using a linear increase control (from 27.5 to 29.5°C) for the feed temperature in an SWRO hybrid system with multi-stage flash (MSF) distillation, such as the Fujairah plant.

Original languageEnglish
Pages (from-to)180-189
Number of pages10
JournalDesalination
Volume247
Issue number1-3
DOIs
Publication statusPublished - 2009 Oct 1

Fingerprint

Reverse osmosis
Desalination
Seawater
artificial neural network
seawater
Neural networks
Flow rate
water temperature
membrane
Membranes
Temperature
Water
temperature
Hybrid systems
distillation
Temperature control
Distillation
simulation
reverse osmosis
desalination plant

Keywords

  • Artificial neural network (ANN)
  • Hybrid system
  • Multi-stage flash (MSF)
  • Seawater reverse osmosis membrane (SWRO)
  • Temperature control

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Mechanical Engineering
  • Chemistry(all)
  • Materials Science(all)
  • Water Science and Technology

Cite this

Artificial neural network model for optimizing operation of a seawater reverse osmosis desalination plant. / Lee, Young Geun; Lee, Yun Seok; Jeon, Jong June; Lee, Sangho; Yang, Dae Ryook; Kim, In S.; Kim, Joon Ha.

In: Desalination, Vol. 247, No. 1-3, 01.10.2009, p. 180-189.

Research output: Contribution to journalArticle

Lee, Young Geun ; Lee, Yun Seok ; Jeon, Jong June ; Lee, Sangho ; Yang, Dae Ryook ; Kim, In S. ; Kim, Joon Ha. / Artificial neural network model for optimizing operation of a seawater reverse osmosis desalination plant. In: Desalination. 2009 ; Vol. 247, No. 1-3. pp. 180-189.
@article{cc9c50c42b354ce1bf0895269d6b79a2,
title = "Artificial neural network model for optimizing operation of a seawater reverse osmosis desalination plant",
abstract = "An artificial neural network (ANN) was developed to predict the performance of a seawater reverse osmosis (SWRO) desalination plant, and was then applied to the simulation of feed water temperature. The model consists of five input parameters (i.e., feed temperature, feed total dissolved solids (TDS), trans-membrane pressure (TMP), feed flow rate, and time) and two output parameters (i.e., permeate TDS and flow rate). Then, the one-year operation data (n = 200) from the Fujairah SWRO plant was divided into three data sets (i.e., training, validation, and test data set) to develop the ANN model. The trained ANN model was subsequently found to produce good agreement between the observed and simulated data (TDS: R2 = 0.96; flow rate: R2 = 0.75) in the test data set. The results of this study show that the variation of the feed water temperature and TMP was found to significantly affect both the permeate TDS and flow rate. From subsequent simulations with various temperature controls, it is further suggested that the permeate TDS can be reduced using a linear increase control (from 27.5 to 29.5°C) for the feed temperature in an SWRO hybrid system with multi-stage flash (MSF) distillation, such as the Fujairah plant.",
keywords = "Artificial neural network (ANN), Hybrid system, Multi-stage flash (MSF), Seawater reverse osmosis membrane (SWRO), Temperature control",
author = "Lee, {Young Geun} and Lee, {Yun Seok} and Jeon, {Jong June} and Sangho Lee and Yang, {Dae Ryook} and Kim, {In S.} and Kim, {Joon Ha}",
year = "2009",
month = "10",
day = "1",
doi = "10.1016/j.desal.2008.12.023",
language = "English",
volume = "247",
pages = "180--189",
journal = "Desalination",
issn = "0011-9164",
publisher = "Elsevier",
number = "1-3",

}

TY - JOUR

T1 - Artificial neural network model for optimizing operation of a seawater reverse osmosis desalination plant

AU - Lee, Young Geun

AU - Lee, Yun Seok

AU - Jeon, Jong June

AU - Lee, Sangho

AU - Yang, Dae Ryook

AU - Kim, In S.

AU - Kim, Joon Ha

PY - 2009/10/1

Y1 - 2009/10/1

N2 - An artificial neural network (ANN) was developed to predict the performance of a seawater reverse osmosis (SWRO) desalination plant, and was then applied to the simulation of feed water temperature. The model consists of five input parameters (i.e., feed temperature, feed total dissolved solids (TDS), trans-membrane pressure (TMP), feed flow rate, and time) and two output parameters (i.e., permeate TDS and flow rate). Then, the one-year operation data (n = 200) from the Fujairah SWRO plant was divided into three data sets (i.e., training, validation, and test data set) to develop the ANN model. The trained ANN model was subsequently found to produce good agreement between the observed and simulated data (TDS: R2 = 0.96; flow rate: R2 = 0.75) in the test data set. The results of this study show that the variation of the feed water temperature and TMP was found to significantly affect both the permeate TDS and flow rate. From subsequent simulations with various temperature controls, it is further suggested that the permeate TDS can be reduced using a linear increase control (from 27.5 to 29.5°C) for the feed temperature in an SWRO hybrid system with multi-stage flash (MSF) distillation, such as the Fujairah plant.

AB - An artificial neural network (ANN) was developed to predict the performance of a seawater reverse osmosis (SWRO) desalination plant, and was then applied to the simulation of feed water temperature. The model consists of five input parameters (i.e., feed temperature, feed total dissolved solids (TDS), trans-membrane pressure (TMP), feed flow rate, and time) and two output parameters (i.e., permeate TDS and flow rate). Then, the one-year operation data (n = 200) from the Fujairah SWRO plant was divided into three data sets (i.e., training, validation, and test data set) to develop the ANN model. The trained ANN model was subsequently found to produce good agreement between the observed and simulated data (TDS: R2 = 0.96; flow rate: R2 = 0.75) in the test data set. The results of this study show that the variation of the feed water temperature and TMP was found to significantly affect both the permeate TDS and flow rate. From subsequent simulations with various temperature controls, it is further suggested that the permeate TDS can be reduced using a linear increase control (from 27.5 to 29.5°C) for the feed temperature in an SWRO hybrid system with multi-stage flash (MSF) distillation, such as the Fujairah plant.

KW - Artificial neural network (ANN)

KW - Hybrid system

KW - Multi-stage flash (MSF)

KW - Seawater reverse osmosis membrane (SWRO)

KW - Temperature control

UR - http://www.scopus.com/inward/record.url?scp=69349086550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69349086550&partnerID=8YFLogxK

U2 - 10.1016/j.desal.2008.12.023

DO - 10.1016/j.desal.2008.12.023

M3 - Article

VL - 247

SP - 180

EP - 189

JO - Desalination

JF - Desalination

SN - 0011-9164

IS - 1-3

ER -