Densities of ammonium and phosphonium based deep eutectic solvents: Prediction using artificial intelligence and group contribution techniques

K. Shahbaz, S. Baroutian, F. S. Mjalli, M. A. Hashim, I. M. Alnashef

Research output: Contribution to journalArticle

107 Citations (Scopus)

Abstract

As applications of deep eutectic solvents are growing fast as green alternatives, prediction of physical properties data for such systems becomes a necessity for engineering application designs and new process developments. In this study, densities of three classes of deep eutectic solvents, based on a phosphonium and two ammonium salts, were measured. Two predictive models based on artificial intelligence and group contribution methods were proposed for accurate estimation and evaluation of deep eutectic solvent densities. A feed forward back propagation neural network with 9 hidden neurons was successfully developed and trained with the measured density data. The group contribution method applied the modified Lydersen-Joback-Reid, Lee-Kesler and the modified Rackett equations. The comparison of the predicted densities with those obtained by measurement confirmed the reliability of the neural network and the group contribution method with average absolute errors of 0.14 and 2.03%, respectively. Comparison of the model performances indicated a better predictability of the developed neural network over the group contribution method.

Original languageEnglish
Pages (from-to)59-66
Number of pages8
JournalThermochimica Acta
Volume527
DOIs
Publication statusPublished - Jan 10 2012

Fingerprint

artificial intelligence
Ammonium Compounds
eutectics
Eutectics
Artificial intelligence
Neural networks
predictions
Backpropagation
Neurons
Physical properties
Salts
neurons
physical properties
engineering
salts
evaluation

Keywords

  • Artificial neural network
  • Deep eutectic solvent
  • Density
  • Estimation

ASJC Scopus subject areas

  • Physical and Theoretical Chemistry
  • Condensed Matter Physics
  • Instrumentation

Cite this

Densities of ammonium and phosphonium based deep eutectic solvents : Prediction using artificial intelligence and group contribution techniques. / Shahbaz, K.; Baroutian, S.; Mjalli, F. S.; Hashim, M. A.; Alnashef, I. M.

In: Thermochimica Acta, Vol. 527, 10.01.2012, p. 59-66.

Research output: Contribution to journalArticle

@article{729b478d3a4e49ba813290e389dfb256,
title = "Densities of ammonium and phosphonium based deep eutectic solvents: Prediction using artificial intelligence and group contribution techniques",
abstract = "As applications of deep eutectic solvents are growing fast as green alternatives, prediction of physical properties data for such systems becomes a necessity for engineering application designs and new process developments. In this study, densities of three classes of deep eutectic solvents, based on a phosphonium and two ammonium salts, were measured. Two predictive models based on artificial intelligence and group contribution methods were proposed for accurate estimation and evaluation of deep eutectic solvent densities. A feed forward back propagation neural network with 9 hidden neurons was successfully developed and trained with the measured density data. The group contribution method applied the modified Lydersen-Joback-Reid, Lee-Kesler and the modified Rackett equations. The comparison of the predicted densities with those obtained by measurement confirmed the reliability of the neural network and the group contribution method with average absolute errors of 0.14 and 2.03{\%}, respectively. Comparison of the model performances indicated a better predictability of the developed neural network over the group contribution method.",
keywords = "Artificial neural network, Deep eutectic solvent, Density, Estimation",
author = "K. Shahbaz and S. Baroutian and Mjalli, {F. S.} and Hashim, {M. A.} and Alnashef, {I. M.}",
year = "2012",
month = "1",
day = "10",
doi = "10.1016/j.tca.2011.10.010",
language = "English",
volume = "527",
pages = "59--66",
journal = "Thermochimica Acta",
issn = "0040-6031",
publisher = "Elsevier",

}

TY - JOUR

T1 - Densities of ammonium and phosphonium based deep eutectic solvents

T2 - Prediction using artificial intelligence and group contribution techniques

AU - Shahbaz, K.

AU - Baroutian, S.

AU - Mjalli, F. S.

AU - Hashim, M. A.

AU - Alnashef, I. M.

PY - 2012/1/10

Y1 - 2012/1/10

N2 - As applications of deep eutectic solvents are growing fast as green alternatives, prediction of physical properties data for such systems becomes a necessity for engineering application designs and new process developments. In this study, densities of three classes of deep eutectic solvents, based on a phosphonium and two ammonium salts, were measured. Two predictive models based on artificial intelligence and group contribution methods were proposed for accurate estimation and evaluation of deep eutectic solvent densities. A feed forward back propagation neural network with 9 hidden neurons was successfully developed and trained with the measured density data. The group contribution method applied the modified Lydersen-Joback-Reid, Lee-Kesler and the modified Rackett equations. The comparison of the predicted densities with those obtained by measurement confirmed the reliability of the neural network and the group contribution method with average absolute errors of 0.14 and 2.03%, respectively. Comparison of the model performances indicated a better predictability of the developed neural network over the group contribution method.

AB - As applications of deep eutectic solvents are growing fast as green alternatives, prediction of physical properties data for such systems becomes a necessity for engineering application designs and new process developments. In this study, densities of three classes of deep eutectic solvents, based on a phosphonium and two ammonium salts, were measured. Two predictive models based on artificial intelligence and group contribution methods were proposed for accurate estimation and evaluation of deep eutectic solvent densities. A feed forward back propagation neural network with 9 hidden neurons was successfully developed and trained with the measured density data. The group contribution method applied the modified Lydersen-Joback-Reid, Lee-Kesler and the modified Rackett equations. The comparison of the predicted densities with those obtained by measurement confirmed the reliability of the neural network and the group contribution method with average absolute errors of 0.14 and 2.03%, respectively. Comparison of the model performances indicated a better predictability of the developed neural network over the group contribution method.

KW - Artificial neural network

KW - Deep eutectic solvent

KW - Density

KW - Estimation

UR - http://www.scopus.com/inward/record.url?scp=83555165025&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83555165025&partnerID=8YFLogxK

U2 - 10.1016/j.tca.2011.10.010

DO - 10.1016/j.tca.2011.10.010

M3 - Article

AN - SCOPUS:83555165025

VL - 527

SP - 59

EP - 66

JO - Thermochimica Acta

JF - Thermochimica Acta

SN - 0040-6031

ER -