| 饱和醇结构-保留定量相关的人工神经网络模型 |
| |
| 引用本文： | 周莲,吴启勋.饱和醇结构-保留定量相关的人工神经网络模型[J].西南民族学院学报(自然科学版),2007,33(6):1369-1372. |
| |
| 作者姓名： | 周莲 吴启勋 |
| |
| 作者单位： | 青海大学化工学院 青海西宁810016(周莲)，青海民族学院化学系 青海西宁810017(吴启勋) |
| |
| 摘 要： | 以拓扑指数为结构描述符,用基于Levenberg-Marquardt优化的BP神经网络建立了醇类化合物的结构与色谱保留值的相关性模型,用于未知醇类化合物在SE-30和OV-3两根色谱柱上保留指数的同时预测,其学习速率优于文献中普通BP神经网络法,预测准确度与普通BP神经网络法接近,但优于多元线性回归法,因而是一种较好的预测有机化合物气相色谱保留指数的方法.
|
| 关 键 词： | 结构-保留相关 饱和醇 人工神经网络 拓扑指数 |
| 文章编号： | 1003-2843（2007）06-1369-04 |
| 收稿时间： | 2007-09-29 |
| 修稿时间： | 2007年9月29日 |
Model of artificial neural network for quantitative structure -retention relations of saturated alcohols |
| |
| ZHOU Lian,WU Qi-xun.Model of artificial neural network for quantitative structure -retention relations of saturated alcohols[J].Journal of Southwest Nationalities College(Natural Science Edition),2007,33(6):1369-1372. |
| |
| Authors: | ZHOU Lian WU Qi-xun |
| |
| Abstract: | A model of back-propagation artificial neural network based on Levenberg-Marquardt algorithm for determining the relations between the structure of alcohols and their chromatographic retention indices has been set by means of topological indices. The model is used for the simultaneous prediction of retention indices of alcohols on SE-30 and OV-3 columns. The results show that the method has higher training rate and equal accuracy in comparison with common BP artificial neural network ,and better accuracy than that of multiple linear regression. Therefore,the model is a more satisfactory method for prediction of chromatographic retention indices of organic compounds. |
| |
| Keywords: | structure -retention relation saturated alcohol artificial neural network topological indice |
| 本文献已被 CNKI 维普 等数据库收录！ |
