ρ–T–P prediction for ionic liquids using neural networks

Abstract Densities of ionic liquids have been estimated using a combined method that includes an artificial neural network and a simple group contribution method. A total of 2410 data points of density at several temperatures and pressures (ρ–T–P), corresponding to 250 ionic liquids, have been used to train this network, developed using Matlab. To discriminate between the different substances, the molecular mass and the structure of the molecule, were given as input variables. Then, the ρ–T–P values of 72 other ionic liquids (773 data points) were predicted and results compared to experimental data from the literature. The study shows that the chosen artificial neural network and the group contribution method represent an excellent alternative for the estimation of densities of ionic liquids with acceptable accuracy.