Prediction of binodal curve of H2O/DMAc/PSf system by ANN method

Xue Zhong He; Xiang Ping Zhang; Jin Dun Liu; Suo Jiang Zhang

Prediction of binodal curve of H₂O/DMAc/PSf system by ANN method

Xue Zhong He, Xiang Ping Zhang, Jin Dun Liu, Suo Jiang Zhang^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Based on the literature data, a Back-Propagation (BP) network was designed for prediction of the liquid-liquid equilibrium properties of H₂O/DMAc (A'-A'-dimethylacetamide)/PSf (polysulfone) system in terms of the ANN (Artificial Neural Network) theory. Two input neurons (temperature and mass fraction of PSf) and two output neurons (mass fractions of water and DMAc) have been chosen as variables of the network. The results show that predicted ARD (average relative deviation) values of water and DMAc concentrations are 1.86% and 0.10%, respectively, therefore the proposed ANN method in this work could be used to predict the binodal curve of H₂O/DMAc/PSf system in the temperature range of 20-60°C. From this work, it can be concluded that the properly selected and trained network provides an effective method for prediction of the liquid-liquid equilibrium properties of H₂O/DMAc/PSf system, which could be used for guiding experimental researches in preparation of asymmetry polymer membrane.

Original language	English
Pages (from-to)	178-181
Number of pages	4
Journal	Guocheng Gongcheng Xuebao/The Chinese Journal of Process Engineering
Volume	4
Issue number	2
State	Published - Apr 2004
Externally published	Yes

Keywords

Binodal curve
Liquid-liquid equilibrium
Neural network
Polymer system
Prediction

Cite this

@article{eb63d381b26b4fd184f52363c67198aa,

title = "Prediction of binodal curve of H2O/DMAc/PSf system by ANN method",

abstract = "Based on the literature data, a Back-Propagation (BP) network was designed for prediction of the liquid-liquid equilibrium properties of H2O/DMAc (A'-A'-dimethylacetamide)/PSf (polysulfone) system in terms of the ANN (Artificial Neural Network) theory. Two input neurons (temperature and mass fraction of PSf) and two output neurons (mass fractions of water and DMAc) have been chosen as variables of the network. The results show that predicted ARD (average relative deviation) values of water and DMAc concentrations are 1.86% and 0.10%, respectively, therefore the proposed ANN method in this work could be used to predict the binodal curve of H2O/DMAc/PSf system in the temperature range of 20-60°C. From this work, it can be concluded that the properly selected and trained network provides an effective method for prediction of the liquid-liquid equilibrium properties of H2O/DMAc/PSf system, which could be used for guiding experimental researches in preparation of asymmetry polymer membrane.",

keywords = "Binodal curve, Liquid-liquid equilibrium, Neural network, Polymer system, Prediction",

author = "He, {Xue Zhong} and Zhang, {Xiang Ping} and Liu, {Jin Dun} and Zhang, {Suo Jiang}",

year = "2004",

month = apr,

language = "英语",

volume = "4",

pages = "178--181",

journal = "Guocheng Gongcheng Xuebao/The Chinese Journal of Process Engineering",

issn = "1009-606X",

publisher = "Science Press",

number = "2",

}

TY - JOUR

T1 - Prediction of binodal curve of H2O/DMAc/PSf system by ANN method

AU - He, Xue Zhong

AU - Zhang, Xiang Ping

AU - Liu, Jin Dun

AU - Zhang, Suo Jiang

PY - 2004/4

Y1 - 2004/4

N2 - Based on the literature data, a Back-Propagation (BP) network was designed for prediction of the liquid-liquid equilibrium properties of H2O/DMAc (A'-A'-dimethylacetamide)/PSf (polysulfone) system in terms of the ANN (Artificial Neural Network) theory. Two input neurons (temperature and mass fraction of PSf) and two output neurons (mass fractions of water and DMAc) have been chosen as variables of the network. The results show that predicted ARD (average relative deviation) values of water and DMAc concentrations are 1.86% and 0.10%, respectively, therefore the proposed ANN method in this work could be used to predict the binodal curve of H2O/DMAc/PSf system in the temperature range of 20-60°C. From this work, it can be concluded that the properly selected and trained network provides an effective method for prediction of the liquid-liquid equilibrium properties of H2O/DMAc/PSf system, which could be used for guiding experimental researches in preparation of asymmetry polymer membrane.

AB - Based on the literature data, a Back-Propagation (BP) network was designed for prediction of the liquid-liquid equilibrium properties of H2O/DMAc (A'-A'-dimethylacetamide)/PSf (polysulfone) system in terms of the ANN (Artificial Neural Network) theory. Two input neurons (temperature and mass fraction of PSf) and two output neurons (mass fractions of water and DMAc) have been chosen as variables of the network. The results show that predicted ARD (average relative deviation) values of water and DMAc concentrations are 1.86% and 0.10%, respectively, therefore the proposed ANN method in this work could be used to predict the binodal curve of H2O/DMAc/PSf system in the temperature range of 20-60°C. From this work, it can be concluded that the properly selected and trained network provides an effective method for prediction of the liquid-liquid equilibrium properties of H2O/DMAc/PSf system, which could be used for guiding experimental researches in preparation of asymmetry polymer membrane.

KW - Binodal curve

KW - Liquid-liquid equilibrium

KW - Neural network

KW - Polymer system

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=3142740950&partnerID=8YFLogxK

M3 - 文章

AN - SCOPUS:3142740950

SN - 1009-606X

VL - 4

SP - 178

EP - 181

JO - Guocheng Gongcheng Xuebao/The Chinese Journal of Process Engineering

JF - Guocheng Gongcheng Xuebao/The Chinese Journal of Process Engineering

IS - 2

ER -

Prediction of binodal curve of H₂O/DMAc/PSf system by ANN method

Abstract

Keywords

Other files and links

Fingerprint

Cite this