Predicting the superheat limit temperature of binary mixtures based on the quantitative structure property relationship

This study was devoted to develop the quantitative relationship model between the superheat limit temperature of binary mixtures and their molecular structures based on the quantitative structure-property relationship. The integral additive descriptors method was used to calculate the molecular descriptors of binary mixtures. The genetic algorithm combined with the multiple linear regression (GA-MLR) was used to select optimal subset of descriptors which had significant contribution to the superheat limit temperature. Three different external validations, which checked the stability and predictive capability of the obtained models, were employed to build the models. And the applicability domain for the models was also defined. The results showed the presented models were valid and predictive and there was strong linear relationship between the superheat limit temperature of binary mixtures and their molecular structures. This study can provide a new way to predict the superheat limit temperature of binary mixtures.