Solubility modeling of supercritical fluid extraction in a wide range compounds: comparison between fuzzy-genetic and new empirical models

In the current study, two methods based on a new empirical equation and fuzzy-genetic model are proposed to estimate solute solubility in supercritical fluid (SCF). New proposed models are trained with comprehensive dataset collected from literature with more than 3,260 experimental data at different temperature and pressure. In order to testify the accuracy, the proposed models are compared to other empirical equations. The amounts of average values of absolute relative deviation (AARD)were obtained 7.74% for fuzzy-genetic model and 9.27% for new proposed empirical model. The reasonable accuracy of developed models for estimating the solubility of solutes in SCF extraction process is represented. From literature solubility data, the authors obtained new estimation models for solute solubility in CO₂ supercritical which are in agreement with measured experimental values.