In this research, the ability of multilayer perceptron neural networks to estimate vapour-liquid equilibrium data have been studied Four typical binary refrigerant systems containing R227ea have been investigated in a large range of temperatures and pressures The systems are categorised into four groups, based on their different deviations from the Raoult's law The networks with one hidden layer consisted of five neurons are developed as the optimal structure For these binary systems, uncertainties in the artificial neural networks (ANNs) estimations were not more than 1 03% In addition, the abilities of ANNs are shown by comparisons with Margules, van Laar, and some other correlations