Quantitative structure-activity relationship methods are used to study the quantitative structure tribo- ability relationship (QSTR), which refers to the tribology capability of a compound from the calculation of structure descriptors. Here, we used the Bayesian regularization neural network (BRNN) to establish a QSTR prediction model. Two-dimensional (2D) BRNN–QSTR models can flexibly and easily estimate lubricant-additive antiwear properties. Our results show that electron transfer and heteroatoms (such as S, P, O, and N) in a lubricant-additive molecule improve the antiwear ability. We also found that molecular connectivity indices are good descriptors of 2D BRNN–QSTR models.
Publications
- Article type
- Year
Article type
Year
Open Access
Research Article
Issue
Friction 2016, 4 (2): 105-115
Published: 28 March 2016
Downloads:22
total 1