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
SN - 0040-6031
VL - 527
SP - 59
EP - 66
JO - Thermochimica Acta
JF - Thermochimica Acta
ER -