Viscosity prediction of ternary mixtures containing ILs using multi-layer perceptron artificial neural network

Mostafa Lashkarblooki, Ali Zeinolabedini Hezave, Adel M. Al-Ajmi, Shahab Ayatollahi

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

Ionic liquids (ILs) have been considered as a good candidate to be replaced by the conventional solvent in recent years due to their potential consumptions and unique properties. In the present study, artificial neural network was used to predict the ternary viscosity of mixtures containing ILs. A collection of 729 experimental data points were gathered from the previously public shed literatures. Different topologies of a multilayer feed forward artificial neural network (MFFANN) were examined and optimum architecture was determined. Ternary viscosity data from the literature for 5 ILs with 547 data points have been used to train the network. In addition, to differentiate dissimilar substances, the molecular mass and boiling point temperature of the three components and two compositions of the non-ILs components were considered as input variables. It must be mentioned that due to the high boiling temperature of the ILs, most of them decomposes before achieving their boiling point. Therefore, Valderrama group contribution method was utilized to obtain the boiling points of the ionic liquids used for this study. Finally, the capability of the designed network was tested by predicting ternary viscosity of mixtures not considered during the training process of the network (182 ternary viscosity data points for 5 ILs). The results demonstrated that the proposed network was able to well predict the ternary viscosity data points even by using the predicted values of boiling temperatures of ionic liquids.

Original languageEnglish
Pages (from-to)15-20
Number of pages6
JournalFluid Phase Equilibria
Volume326
DOIs
Publication statusPublished - Jul 25 2012

Fingerprint

Ionic Liquids
self organizing systems
Multilayer neural networks
Ionic liquids
Viscosity
viscosity
Neural networks
boiling
liquids
predictions
Boiling point
Boiling liquids
sheds
Molecular mass
Temperature
Multilayers
temperature
Topology
education
topology

Keywords

  • ANN model
  • Ionic liquids ternary viscosity
  • Mass transfer
  • Numerical analysis
  • Optimization
  • Solutions

ASJC Scopus subject areas

  • Chemical Engineering(all)
  • Physical and Theoretical Chemistry
  • Physics and Astronomy(all)

Cite this

Viscosity prediction of ternary mixtures containing ILs using multi-layer perceptron artificial neural network. / Lashkarblooki, Mostafa; Hezave, Ali Zeinolabedini; Al-Ajmi, Adel M.; Ayatollahi, Shahab.

In: Fluid Phase Equilibria, Vol. 326, 25.07.2012, p. 15-20.

Research output: Contribution to journalArticle

Lashkarblooki, Mostafa ; Hezave, Ali Zeinolabedini ; Al-Ajmi, Adel M. ; Ayatollahi, Shahab. / Viscosity prediction of ternary mixtures containing ILs using multi-layer perceptron artificial neural network. In: Fluid Phase Equilibria. 2012 ; Vol. 326. pp. 15-20.
@article{31040dde91ac4c0792dbc0317464b985,
title = "Viscosity prediction of ternary mixtures containing ILs using multi-layer perceptron artificial neural network",
abstract = "Ionic liquids (ILs) have been considered as a good candidate to be replaced by the conventional solvent in recent years due to their potential consumptions and unique properties. In the present study, artificial neural network was used to predict the ternary viscosity of mixtures containing ILs. A collection of 729 experimental data points were gathered from the previously public shed literatures. Different topologies of a multilayer feed forward artificial neural network (MFFANN) were examined and optimum architecture was determined. Ternary viscosity data from the literature for 5 ILs with 547 data points have been used to train the network. In addition, to differentiate dissimilar substances, the molecular mass and boiling point temperature of the three components and two compositions of the non-ILs components were considered as input variables. It must be mentioned that due to the high boiling temperature of the ILs, most of them decomposes before achieving their boiling point. Therefore, Valderrama group contribution method was utilized to obtain the boiling points of the ionic liquids used for this study. Finally, the capability of the designed network was tested by predicting ternary viscosity of mixtures not considered during the training process of the network (182 ternary viscosity data points for 5 ILs). The results demonstrated that the proposed network was able to well predict the ternary viscosity data points even by using the predicted values of boiling temperatures of ionic liquids.",
keywords = "ANN model, Ionic liquids ternary viscosity, Mass transfer, Numerical analysis, Optimization, Solutions",
author = "Mostafa Lashkarblooki and Hezave, {Ali Zeinolabedini} and Al-Ajmi, {Adel M.} and Shahab Ayatollahi",
year = "2012",
month = "7",
day = "25",
doi = "10.1016/j.fluid.2012.04.017",
language = "English",
volume = "326",
pages = "15--20",
journal = "Fluid Phase Equilibria",
issn = "0378-3812",
publisher = "Elsevier",

}

TY - JOUR

T1 - Viscosity prediction of ternary mixtures containing ILs using multi-layer perceptron artificial neural network

AU - Lashkarblooki, Mostafa

AU - Hezave, Ali Zeinolabedini

AU - Al-Ajmi, Adel M.

AU - Ayatollahi, Shahab

PY - 2012/7/25

Y1 - 2012/7/25

N2 - Ionic liquids (ILs) have been considered as a good candidate to be replaced by the conventional solvent in recent years due to their potential consumptions and unique properties. In the present study, artificial neural network was used to predict the ternary viscosity of mixtures containing ILs. A collection of 729 experimental data points were gathered from the previously public shed literatures. Different topologies of a multilayer feed forward artificial neural network (MFFANN) were examined and optimum architecture was determined. Ternary viscosity data from the literature for 5 ILs with 547 data points have been used to train the network. In addition, to differentiate dissimilar substances, the molecular mass and boiling point temperature of the three components and two compositions of the non-ILs components were considered as input variables. It must be mentioned that due to the high boiling temperature of the ILs, most of them decomposes before achieving their boiling point. Therefore, Valderrama group contribution method was utilized to obtain the boiling points of the ionic liquids used for this study. Finally, the capability of the designed network was tested by predicting ternary viscosity of mixtures not considered during the training process of the network (182 ternary viscosity data points for 5 ILs). The results demonstrated that the proposed network was able to well predict the ternary viscosity data points even by using the predicted values of boiling temperatures of ionic liquids.

AB - Ionic liquids (ILs) have been considered as a good candidate to be replaced by the conventional solvent in recent years due to their potential consumptions and unique properties. In the present study, artificial neural network was used to predict the ternary viscosity of mixtures containing ILs. A collection of 729 experimental data points were gathered from the previously public shed literatures. Different topologies of a multilayer feed forward artificial neural network (MFFANN) were examined and optimum architecture was determined. Ternary viscosity data from the literature for 5 ILs with 547 data points have been used to train the network. In addition, to differentiate dissimilar substances, the molecular mass and boiling point temperature of the three components and two compositions of the non-ILs components were considered as input variables. It must be mentioned that due to the high boiling temperature of the ILs, most of them decomposes before achieving their boiling point. Therefore, Valderrama group contribution method was utilized to obtain the boiling points of the ionic liquids used for this study. Finally, the capability of the designed network was tested by predicting ternary viscosity of mixtures not considered during the training process of the network (182 ternary viscosity data points for 5 ILs). The results demonstrated that the proposed network was able to well predict the ternary viscosity data points even by using the predicted values of boiling temperatures of ionic liquids.

KW - ANN model

KW - Ionic liquids ternary viscosity

KW - Mass transfer

KW - Numerical analysis

KW - Optimization

KW - Solutions

UR - http://www.scopus.com/inward/record.url?scp=84861180898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861180898&partnerID=8YFLogxK

U2 - 10.1016/j.fluid.2012.04.017

DO - 10.1016/j.fluid.2012.04.017

M3 - Article

AN - SCOPUS:84861180898

VL - 326

SP - 15

EP - 20

JO - Fluid Phase Equilibria

JF - Fluid Phase Equilibria

SN - 0378-3812

ER -