An Artificial Neural Network for the surface tension of alcohols

• Published in: Fluid phase equilibria Vol. 449; pp. 28 - 40
• Main Authors: Mulero, Ángel, Pierantozzi, M., Cachadiña, Isidro, Di Nicola, G.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.10.2017
• Subjects: Alcohols; Artificial neural network; Fluid properties; Surface tension; Surface tension; Artificial neural network; Alcohols; Fluid properties
• ISSN: 0378-3812; 1879-0224
• DOI: 10.1016/j.fluid.2017.06.003

An Artificial Neural Network model is proposed for the calculation and prediction of the surface tension of alcohols. A total amount of 4316 data for 147 alcohols was used for training, validating and testing the network model. After considering different architectures, the one giving better results includes an input layer that uses four independent variables (temperature, critical point temperature, critical density, and radius of gyration), two hidden layers with 21 neurons each one, and one neuron in the output layer was found to give the best results. Overall mean absolute percentage deviation of 1.04% was found, whereas models based on corresponding-states principle give mean deviations higher than 11.3%. •An Artificial Neural Network is developed for the calculation of surface tension of alcohols.•4316 surface tension data for 147 alcohols were used.•Overall mean absolute percentage deviation of 1.04% was found.•Detailed analysis of results for several alcohols is made.