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.
Zhang S, Lu X, Zhou Q, Li X, Zhang X, Li S, Ionic liquids, physicochemical properties, 1st Ed., 478 pages, Elsevier, Amsterdam, The Netherlands, 2009
Bose NK, Liang P, Neural networks fundamentals with graphs, algorithms, and applications, in electrical and computer engineering, McGraw-Hill Series, McGraw-Hill Companies, Inc., USA, 1996