Heat Capacity of Ionic Liquids Using Artificial Neural Networks and the Concept of Mass Connectivity

Abstract

Artificial neural networks and the concept of mass connectivity index are used to correlate and predict the heat capacity at constant pressure of ionic liquids (ILs). Different topologies of a multilayer feed-forward artificial neural network were studied, and the optimum architecture was determined. Heat-capacity data at several temperatures taken from the literature for 31 ILs with 477 data points were used for training the network. To discriminate among the different substances, the molecular mass of the anion and of the cation and the mass connectivity index were considered as the independent variables. The capabilities of the designed network were tested by predicting heat capacities for situations not considered during the training process (65 heat-capacity data for nine ILs). The results demonstrate that the chosen network and the variables considered allow estimating the heat capacity of ILs with acceptable accuracy for engineering calculations. The program codes and the necessary input files to calculate the mass connectivity index and the heat capacity for other ILs are provided.