Artificial Neural Network Modeling of Solubilities of 21 Commonly Used Industrial Solid Compounds in Supercritical Carbon Dioxide

Farhad Gharagheizi (1) , Ali Eslamimanesh (2) , Amir H. Mohammadi (3) , Dominique Richon (3)

1 Department of Chemical Engineering
2 CEP - Centre Énergétique et Procédés
3 CEP/Fontainebleau

In this communication, a feed-forward artificial neural network algorithm has been applied to calculate/ predict the solubilities of 21 of the commonly used industrial solid compounds in supercritical carbon dioxide. An optimized three-layer feed-forward neural network using critical properties of solute and operating temperature and pressure is presented. Application of the model for 795 data points of 21 compounds gives a squared correlation coefficient of 0.9533 and an average absolute deviation of about 14% from the experimental values.

Domaines: Génie des procédés

Farhad Gharagheizi, Ali Eslamimanesh, Amir H. Mohammadi, Dominique Richon. Artificial Neural Network Modeling of Solubilities of 21 Commonly Used Industrial Solid Compounds in Supercritical Carbon Dioxide. Industrial and engineering chemistry research, 2011, 50, pp.221-226. ⟨10.1021/ie101545g⟩. ⟨hal-00573680⟩