中华医学超声杂志

应用化学 ›› 1994, Vol. 0 ›› Issue (5): 54-59.

• 研究论文 • 上一篇    下一篇

人工神经网络方法预测气相色谱保留指数

张向东1, 赵立群2, 张国义2   

  1. 1. 辽宁大学化学系 沈阳 110036;
    2. 沈阳化工学院高分子系 沈阳
  • 收稿日期:1994-03-09 修回日期:1994-05-10 出版日期:1994-10-10 发布日期:1994-10-10

Ptediction of Gas Chromatographic Retention Index by Neural Network

Zhang Xiangdong1, Zhao Liqun2, Zhang Guoyi2   

  1. 1. Department of Chemistry, Liaoning University, Shenyang 110036;
    2. Department of Polymer Chemical Engineering, Shenyang Institute of Chemical Technology, Shenyang
  • Received:1994-03-09 Revised:1994-05-10 Published:1994-10-10 Online:1994-10-10

PDF

331

被引次数

5 | 2

摘要： 用误差反向传播(BP)的人工神经网络(ANN)模型及分子结构描述码作为输入特征参数,预测气相色谱保留指数。研究了链烷烃、环脂烃、烯烃及醇、酯、醚等300个化合物,预测结果平均相对误差不大于2.83%。

关键词: 气相色谱, 色谱保留指数, 人工神经网络, 分子描述码

Abstract: A back-propagation neural network model has been trained to predict the gas chromatographic retention indices.A group of molecular descriptors which are proposed to represent molecular branching,cyclization and unsaturation has been used as inputted structural parameters.In 300 acyclic and cyclic alkanes,alkenes,alcohols,esters,ketones and ethers studied,the mean relative error of the predicted results was less than 2.83%.

Key words: as chromatography, gas chromatographic retention index, artificial neutral net-work, molecular descriptor

网站版权 © 应用化学     本网站备案：吉ICP备12000082号