Phase equilibrium modeling in ethanol + congener mixtures using an artificial neural network

Artificial neural networks have been applied for the correlation and prediction of vapor–liquid equilibrium in binary ethanol mixtures found in alcoholic beverage production. The main interest of the study is the acceptable modeling of the bubble pressure and concentration of congeners (substances different from ethanol) in the vapor phase, considered to be an important enological parameter in the alcoholic industry. Nine binary ethanol + congener mixtures have been considered for analysis. Vapor–liquid equilibrium data of these systems were taken from the literature. Predictions using artificial neural networks were compared with available literature data and with results obtained using equations of state. The study shows that the neural network model is a good alternative method for the estimation of phase equilibrium properties.