聚甲基丙烯酸酯类玻璃化温度的量子化学-神经网络方法研究  

QUANTUM CHEMISTRY-ANN METHODS STUDY ON GLASS TRANSITION TEMPERATURES OF POLYACRYLATES

作　　者：刘万强[1] 王学业[1] 李新芳 龙清平[1] 文小红[1] 李建军[2] 

机构地区：[1]湘潭大学化学学院,湖南湘潭411105 [2]江苏出入境检验检疫局,江苏南京210001

出　　处：《高分子材料科学与工程》2006年第1期170-173,共4页Polymer Materials Science & Engineering

基　　金：湖南省自然科学基金项目(02JJY2019);湖南省中青年科技基金项目(01JZY2099)

摘　　要：用密度泛函(DFT)方法在6-31G(d)基组优化了32种聚甲基丙烯酸酯类的结构单元,得到了其量子化学参数,用模式识别,逐步回归和人工神经网络方法探讨了这些参数与聚甲基丙烯酸酯类Tg的关系,模式识别两类Tg大小不同的聚合物基本分布在不同区域,用逐步回归和人工神经网络方法所建立的定量模型的计算值与实验值的相关系数分别为0.9760,0.9912,预报结果与实验值基本一致。The structural units of thirty-two polymethacrylates had been optimized and their quantum chemical descriptors had been obtained by DFT/6-31G（d） method. The calculated results indicate that thermal energy, length of side chain, total molecular energy, most negative net charge, net charge of C6, polarizability, are main factors affecting glass transition temperature （Tg）. The regularity of Tg for polymethacrylates was discussed by the pattern recognition method with quantum chemical descriptors as features, the two class polymers of different Tg distribute in different regions. Then quantitative relationship had been studied between these descriptors and Tg with stepwise regression and ANN methods. The related coefficients between the calculated results and experimental data of Tg for two methods are 0. 9760.and 0. 9912 respectively.

关 键 词：聚甲基丙烯酸酯 玻璃化温度 量子化学参数 模式识别 人工神经网络 

分 类 号：O631.22[理学—高分子化学]