Surface tension of alcohols: A scaled equation and an artificial neural network

This work presents a new formula to calculate the surface tension of alcohols. As a first step, an analysis of the data available on the surface tension of alcohols was made. A total of 2121 data were collected for n-alcohols, aromatic alcohols, cycloaliphatic alcohols, 2-alkanols and methyl alkanols. The data were then regressed with the most reliable semi-empirical correlation methods in the literature based on the corresponding states theory. The scaled equation proposed is very simple and gives noticeable improvement with respect to existing equations. The same physical parameters considered in the scaled equation were also adopted as input parameters in a multi-layer perceptron neural network, to predict the surface tension of alcohols. The multilayer perceptron proposed has one hidden layer with 29 neurons, determined according to the constructive approach. The model developed was trained, validated and tested for the set of data collected, showing that the accuracy of the neural network model is very good. (C) 2015 Elsevier B.V. All rights reserved.