Modeling of VLE and LLE Systems by using Thermodynamic model with ANFIS Structures and GMDH Type-Neural Network

Study of vapor - liquid and liquid – liquid Equilibrium plays an important role in the design, optimization and control of separation processes. In this research phase equilibrium of binary systems (1-propanol, water and 1-propanol, ethyl acetate) also ternary systems (water, ethylene glycol, 2-ethyl 1- hexanol and water, ethylene glycol, 1- heptanol) using thermodynamic models of NRTL and UNIQUAC were studied. Also Adaptive Nero-Fuzzy Inference System (ANFIS) and group method of Data handling (GMDH-type neural network) were used for modeling of systems. The VLE graphs (temperature based on mole fraction of vapor-liquid phases) for binary systems and LLE graphs for ternary systems at various temperatures by thermodynamics models were drawn. Accuracy of thermodynamic models, ANFIS model and GMDH type-Neural Network for the binary and ternary systems studied and compared with experimental data. Comparison of results shows that NRTL models have good fitness with the experimental data and the minimum error is related to the ANFIS Statistical model.