Establishing quantitative structure tribo-ability relationship model using Bayesian regularization neural network

详细信息    查看全文

• 作者：Xinlei Gao ; Kang Dai ; Zhan Wang ; Tingting Wang ; Junbo He
• 刊名：Friction
• 出版年：2016
• 出版时间：June 2016
• 年：2016
• 卷：4
• 期：2
• 页码：105-115
• 全文大小：1,417 KB
• 刊物主题：Mechanical Engineering; Nanotechnology; Tribology, Corrosion and Coatings; Physical Chemistry; Surfaces and Interfaces, Thin Films;
• 出版者：Springer Berlin Heidelberg
• ISSN：2223-7704
• 卷排序：4

文摘

Quantitative structure-activity relationship methods are used to study the quantitative structure triboability 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.Keywordsquantitative structure tribo-ability relationshipBayesian regularization neural networklubricant additiveantiwear