期刊
FRICTION
卷 4, 期 2, 页码 105-115出版社
TSINGHUA UNIV PRESS
DOI: 10.1007/s40544-016-0104-z
关键词
quantitative structure tribo-ability relationship; Bayesian regularization neural network; lubricant additive; antiwear
资金
- National Basic Research (973) Program of China [2013CB632303]
- National Natural Science Foundation of China (NSFC) [51075309]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据