论文部分内容阅读
采用反向传播神经网络法(Back Propagation Neural Network,简称:BPNN)对31种含氮、硫的2-烷基黄原酸酯类润滑油添加剂的抗磨性能进行了摩擦学定量构效关系(Quantitative Structure Tribo-ability Relationship,简称:QSTR)的研究,得到了具有良好的稳定性和预测能力的BPNN-QSTR模型(R~2=0.998 4,R~2(LOO)=0.695 9,q~2=0.879 1).参考输入层的12种2D和3D结构描述符的敏感度,对影响抗磨性能的分子结构进行了相应的探讨.结果表明:分子中的N和S杂原子对其抗磨损性能有显著的影响;同时,分子长度、所含双键S原子和芳香环数量以及分子支化程度等都是影响抗磨性能的主要因素.
Abrasion resistance of 31 kinds of nitrogen and sulfur-containing 2-alkylxanthate lubricants was studied by tribological structure-activity relationship with Back Propagation Neural Network (BPNN) Quantitative Structure Tribo-ability Relationship (QSTR), BPNN-QSTR models with good stability and predictive ability were obtained (R ~ 2 = 0.998 4, R ~ 2 (LOO) = 0.695 9, q ~ 2 = 0.879 1). Referring to the sensitivity of 12 kinds of 2D and 3D structure descriptors in the input layer, the molecular structures influencing the anti-wear properties are discussed correspondingly. The results show that the N and S heteroatoms in the molecule are resistant to wear Performance at the same time, the molecular length, the number of double bonds containing S atoms and aromatic rings and the degree of molecular branching are the main factors that affect the anti-wear properties.