有机发光材料玻璃化转变温度与结构定量关系研究  

Study on Quantitative Relationship Between Glass Transition Temperatures and Structure of Organic Luminescent Materials

作　　者：禹新良[1] 李明旺 吴旨进 谢健 黄小可 黄赛金[1] YU Xiniang;LI Mingwang;WU Zhijin;XIE Jian;HUANG Xiaoke;HUANG Saijin(College of Materials and Chemical Engineering,Hunan Institute of Engineering,Xiangtan 411104,China)

机构地区：[1]湖南工程学院材料与化工学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2023年第4期54-58,共5页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湘潭市科技创新重点团队项目(ZY-CXTD20221004).

摘　　要：有机发光二极管(OLED)材料具有巨大的应用潜力,其有机发光材料玻璃化转变温度(Tg)是影响热稳定性的重要因素之一.本文将1944种用于OLED的有机发光材料分成训练集(1556种)和测试集(388种);将4885个Dragon参数缩减成472个后,基于线性回归得到含7个参数的子集,用于有机发光材料Tg/MW结构-性能定量关系(QSPR)建模.最佳随机森林回归模型(nodesize=5、ntree=200、mtry=2)产生的训练集决定系数R^(2)=0.979,测试集R^(2)=0.893,精度高于文献报道值.The potential applications of organic light-emitting diode(OLED)materials are enormous.The glass transition temperature(Tg)of the organic light-emitting materials is one of the most important factors affecting thermal stability.In this paper,1944 organic luminescent materials used in OLED are divided into a training set(1556 compounds)and a testing set(388 compounds).After reducing the number of descriptors calculated from 4885 to 472,a subset including seven descriptors is obtained to develop quantitative structure-property relationship(QSPR)models for Tg/MW,by using linear regression analysis.The best QSPR model based on random forest regression(nodesize=5,ntree=200,mtry=2)produces coefficients of determination R^(2)=0.979 for the training set,and R^(2)=0.893 for the test set,which is more accurate than that reported in the literature.

关 键 词：有机发光材料 玻璃化转变温度 结构-性能定量关系 随机森林回归 

分 类 号：O644.1[理学—物理化学] TQ012[理学—化学]