计算机与应用化学
計算機與應用化學
계산궤여응용화학
COMPUTERS AND APPLIED CHEMISTRY
2009年
6期
723-728
,共6页
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
多元線性迴歸%多元非線性迴歸%人工神經網絡%烷基苯%沸點%摩爾體積
다원선성회귀%다원비선성회귀%인공신경망락%완기분%비점%마이체적
MLR (Multiple Linear Regression)%NLMR (Nonlinear Mnltivariable Regression)%ANN (artificial neural network)%alkylbenzenes%boiling point%molar volume
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个数字编码作为捕述符,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犁.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 cm3·mol-1.
本文中建立瞭幾箇定量的模型預測80箇烷基苯的沸點和79箇烷基苯的摩爾體積.每箇烷基苯的結構用其分子式得到的6箇數字編碼來描述.把這6箇數字編碼作為捕述符,運用多元線性迴歸,多元非線性迴歸和人工神經網絡地方法來分彆建立定量構效關繫模犛.模型具有很好的預測性.沸點的3箇預測模型,RMS偏差都小于9℃,摩爾體積的3箇預測模型的RMS偏差都小于6 cm3·mol-1.
본문중건립료궤개정량적모형예측80개완기분적비점화79개완기분적마이체적.매개완기분적결구용기분자식득도적6개수자편마래묘술.파저6개수자편마작위포술부,운용다원선성회귀,다원비선성회귀화인공신경망락지방법래분별건립정량구효관계모리.모형구유흔호적예측성.비점적3개예측모형,RMS편차도소우9℃,마이체적적3개예측모형적RMS편차도소우6 cm3·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 cm3.mol-1.