On the application of artificial neural network for modeling liquid-liquid equilibrium

Abstract

Application of polarity scales and artificial neural network for direct modeling of liquid-liquid separation process was investigated. A simple add-in, named FeedGen, was developed for reproducing the feed data and expanding the liquid-liquid equilibrium pattern. It was concluded that solvatochromic polarity scales method cannot be used as a wide-range approach for direct modeling liquid-liquid equilibrium systems and is only applicable for limited set of data. In comparison, artificial neural networks reproduce features of these systems, satisfactorily well. Multilayered back propagation and GMDH type neural networks were compared in modeling the liquid-liquid ternary systems. It was shown that well-trained networks even could reproduce the outlier data, at different compositions and/or temperatures, acceptably.