Ali Valypoor Tayeby - Department of Chemical Engineering, Sistan and Baluchestan University, Zahedan, Iran
Taleb Zaree - Department of Chemical Engineering, Sistan and Baluchestan University, Zahedan, Iran
Javad Omidi - Department of Chemical Engineering, Sistan and Baluchestan University, Zahedan, Iran
Rahbar Rahimi - Department of Chemical Engineering, Sistan and Baluchestan University, Zahedan, Iran

Liquid liquid equilibrium (LLE) data are important for designing and modeling of process equipments. Since it is not always possible to carry out experiments at all possible temperatures, generally thermodynamic models based on equations of state are used for estimation of LLE. In this work, artificial neural networks(ANNs) were applied to predict and estimate liquid–liquid equilibrium data for ternary system, n- hexane, methanol and water. This ANNs model can predict the LLE data of this ternary system with a range of 278.15K to 328.15K at atmospheric pressure. The ANNs prediction has shown better agreement with experimental data than UNIQUAQ model prediction at higher temperature.

Artificial neural networks, liquid-liquid equilibria, UNIQUIC