期刊
COLLOID AND POLYMER SCIENCE
卷 287, 期 7, 页码 811-818出版社
SPRINGER
DOI: 10.1007/s00396-009-2035-y
关键词
Artificial neural network; Density function theory; Glass transition temperature; QSPR
资金
- Natural Science Foundation of China [20772028, 20772027]
In this article, the molecular average polarizability alpha, the energy of the highest occupied molecular orbital E (HOMO), the total thermal energy E (thermal), and the total entropy S were used to correlate with glass transition temperature T (g) for 113 polymers. The quantum chemical descriptors obtained directly from polymer monomers can represent the essential factors that are governing the nature of glass transition in polymers. Stepwise multiple linear regression (MLR) analysis and back-propagation artificial neural network (ANN) were used to generate the model. The final optimum neural network with 4-[4-2](2)-1 structure produced a training set root mean square error (RMSE) of 11 K (R = 0.973) and a prediction set RMSE of 17 K (R = 0.955). The results show that the ANN model obtained in this paper is accurate in the prediction of T (g) values for polymers.
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