Abstract:By means of artificial neural network(ANN),a quantitative structureproperty relationship (QSPR) model was constructed to predict the antiwear properties measured with wear volumes of 36 lubricating additives under three loads,196,294 and 392 N.The load factor of measurement and three molecular descriptors (including the number of phosphorous atoms in lubricating additives,a twodimension autocorrelation descriptor reflecting molecular size and symmetry,and a threedimension descriptor denoting molecular polarity and reactivity) were used as input vectors to develop the model.The typical backpropagation (BP) neural network was employed to fit the relationships between the four descriptors and wear volumes.The results show that the model in this paper possesses statistical significance and is more accurate compared with the models reported in the literature.There are nonlinear relationships between the wear volumes and the three molecular descriptors,which suggests the molecular descriptors can reflect the important structure factors affecting antiwear properties of lubricant additives.