Viscosity of ionic liquids using the concept of mass connectivity and artificial neural networks

Artificial neural networks (ANN) and the concept of mass connectivity index are used to correlate and predict the viscosity of ionic liquids. Different topologies of a multilayer feed forward artificial neural network were studied and the optimum architecture was determined. Viscosity data at several temperatures taken from the literature for 58 ionic liquids with 327 data points were used for training the network. To discriminate among the different substances, the molecular mass of the anion and of the cation, the mass connectivity index and the density at 298 K were considered as the independent variables. The capabilities of the designed network were tested by predicting viscosities for situations not considered during the training process (31 viscosity data for 26 ionic liquids). The results demonstrate that the chosen network and the variables considered allow estimating the viscosity of ionic liquids with acceptable accuracy for engineering calculations. The program codes and the necessary input files to calculate the viscosity for other ionic liquids are provided.

[1]  Ralf-Uwe Ebert,et al.  Application of Neural Networks to Modeling and Estimating Temperature-Dependent Liquid Viscosity of Organic Compounds , 2001, J. Chem. Inf. Comput. Sci..

[2]  Elazer R. Edelman,et al.  Adv. Drug Delivery Rev. , 1997 .

[3]  G. Padmavathi,et al.  Neural modelling of Mooney viscosity of polybutadiene rubber , 2005, Comput. Chem. Eng..

[4]  J. Coutinho,et al.  A group contribution method for viscosity estimation of ionic liquids , 2008 .

[5]  K. Tochigi,et al.  Prediction of the Liquid Viscosities of Pure Components and Mixtures Using Neural Network and ASOG Group Contribution Methods , 2004 .

[6]  Jouko Yliruusi,et al.  Prediction of physicochemical properties based on neural network modelling. , 2003, Advanced drug delivery reviews.

[7]  A. Klamt,et al.  Room temperature ionic liquids as replacements for conventional solvents – A review , 2002 .

[8]  S. Bretsznajder.  Prediction of transport and other physical properties of fluids , 1971 .

[9]  J. Valderrama,et al.  Critical Properties, Normal Boiling Temperatures, and Acentric Factors of Fifty Ionic Liquids , 2007 .

[10]  Suojiang Zhang,et al.  Ionic Liquids: Physicochemical Properties , 2009 .

[11]  D. Rochefort.  Ionic Liquids in Chemical Analysis , 2009 .

[12]  João Aires-de-Sousa,et al.  Estimation of melting points of pyridinium bromide ionic liquids with decision trees and neural networks , 2005 .

[13]  José O. Valderrama,et al.  Mass connectivity index, a new molecular parameter for the estimation of ionic liquid properties , 2010 .

[14]  A. Ouadi,et al.  Task-specific ionic liquids bearing 2-hydroxybenzylamine units: synthesis and americium-extraction studies. , 2006, Chemistry.

[15]  J. Valderrama,et al.  Density of Ionic Liquids Using Group Contribution and Artificial Neural Networks , 2009 .

[16]  K. Kobe.  The properties of gases and liquids , 1959 .

[17]  R. Scopelliti,et al.  Synthesis and characterization of ionic liquids incorporating the nitrile functionality. , 2004, Inorganic chemistry.

[18]  J. Valderrama,et al.  Critical Properties of Ionic Liquids. Revisited , 2009 .

[19]  The development of computational chemistry approach to predict the viscosity of lubricants , 2003 .

[20]  D. Himmelblau.  Applications of artificial neural networks in chemical engineering , 2000 .