Correlation of Vapor-Liquid Equilibria for Commonly Used Binary Systems in Supercritical Fluid Extraction Processes

Abstract

In this paper, a comprehensive mathematical model is developed based on the Feed-ForwardBack Propagation Artificial Neural Network (FFBP-ANN). The model is employed for thecalculation of Vapor Liquid Equilibria (VLE) of four CO2-containing binary mixtures. Themixtures include CO2 - Tertpentanol was investigated at the temperature range from 313.14 to343.15 K. The following mixtures including CO2 - Isobutanol at 313.2 to 353.2 K, CO2 - methylacetate at 308.15 to 328.15 K and CO2 - diisopropyl ether at 265.15 to 333.15 K wereinvestigated as well. The related experimental data of open literature have been used to constructthe model. The results confirm that there is a reasonable conformity between the predicted valuesand the experimental data. Additionally, the ability of the ANN model is examined by comparison with the conventional thermodynamic models and ANN model predicted VLE datawith more accuracy.