运用线性和非线性的方法预测烷基苯的沸点和摩尔体积(英文)  

Prediction of boiling point and molar volume of alkylbenzenes by linear and nonlinear methods

作　　者：阎爱侠[1] 王芸[1] 李嘉轩[1] 

机构地区：[1]北京化工大学化工资源有效利用国家重点实验室,生命科学与技术学院,北京100029

出　　处：《计算机与应用化学》2009年第6期723-728,共6页Computers and Applied Chemistry

基　　金：supported by the National Natural Science Foundationof China(20605003);National High Tech Project(2006AA02Z337);SRF for ROCS,and the“Special Funding for the Talent Enrollment”of Beijing University of Chemical Technology~~

摘　　要：本文中建立了几个定量的模型预测80个烷基苯的沸点和79个烷基苯的摩尔体积。每个烷基苯的结构用其分子式得到的6个数字编码来描述。把这6个数字编码作为描述符,运用多元线性回归,多元非线性回归和人工神经网络地方法来分别建立定量构效关系模型。模型具有很好的预测性。沸点的3个预测模型,RMS偏差都小于9℃,摩尔体积的3个预测模型的RMS偏差都小于6 cm^3·mol^(-1)。Several quantitative models for the prediction of boiling point （BP） of 80 alkylbenzenes and the molar volume （MV） of 69 alkylbenzenes were developed in this study. Each alkylbenzene was described by a simple set of six numeric codes derived from its molecular formula. With these six numeric codes as input descriptors, multiple linear regression （MLR）, nonlinear multivariable regression （NLMR） and artificial neural network （ANN） were applied to build the quantitative structure-property relationship （QSPR） models, respectively. The models show good prediction ability. For the three BP models, the root-mean-square （RMS） errors are less than 9℃; and for the three MV models, the RMS errors are less than 6 cm^3·mol^-1.

关 键 词：多元线性回归 多元非线性回归 人工神经网络 烷基苯 沸点 摩尔体积 

分 类 号：O6-39[理学—化学] O69