摘要
基于启发式方法(HM)和BP人工神经网络方法建立了5个参数的定量结构性质关系(QSPR)模型,用于预测80个芳香胺类化合物N—H键的键离解能(BDE).通过两种方法分别建立了线性和非线性的QSPR模型,相关系数R分别为0.823和0.976.通过对模型的稳定性和预测能力进行比较,发现BP人工神经网络方法能够更好地预测芳香胺类化合物N—H键的BDE值.
The bond dissociation energy (BDE) of 80 diverse arylamines was modeled using the five descriptors calculated from the molecular structure along with a quantitative structure-property relationship (QSPR) technique. The heuristic method (HM) and back-propagation neural network method were utilized to construct the linear and nonlinear prediction models, leading to the correlation coefficients R of 0.823 and 0.976. By comparison of the stability with prediction ability of the models, it was found that BP network was a good method for predicting the N—H BDE values of arylamines.
出处
《化学学报》
SCIE
CAS
CSCD
北大核心
2009年第10期1109-1115,共7页
Acta Chimica Sinica
基金
教育部"春晖计划"(No.Z2007-1-630010)
重庆市教委科学技术研究基金(No.KJ081102)
重庆三峡学院引进人才科研基金(No.2007-SXXYRC-008)资助项目
关键词
启发式方法
BP人工神经网络
定量结构性质关系
键裂解能
heuristic method
BP artificial neural network
quantitative structure-property relationship (QSPR)
bond dissociation energy (BDE)