New method based on neuro-fuzzy system and PSO algorithm for estimating phase equilibria properties

The subject of this work is to propose a new method based on the ANFIS system and PSO algorithm conceive model for estimating solubility solid drugs in supercritical CO2 (sc-CO2). high nonlinear process was modeled by neuro-fuzzy approach (NFS). used two purposes: replacing standard backpropagation training NFS optimizing process. validation strategy has been carried out using linear regression analysis predicted versus experimental outputs. compared ANN terms accuracy. Statistical predictability optimized trained with (ANFIS-PSO) shows better agreement reference data than method. Furthermore, comparison AARD deviation (%) between results, results density-based models, set equations state demonstrates that ANFIS-PSO correlates far scCO2. A control also developed first time field phase equilibrium inverse (ANFISi) estimate pure component properties from without passing through GCM methods.