[an error occurred while processing this directive]

高等学校化学研究 ›› 2001, Vol. 17 ›› Issue (1): 31-40.

• Articles • 上一篇    下一篇

Estimation and Prediction of Gas Chromatography Retention Indices of Hydrocarbons in Straight-run Gasoline by Using Artificial Neural Network and Structural Coding Method

YIN Chun-sheng, GUO Wei-min, LIU Wei, ZHAO Wei, PAN Zhong-xiao   

  1. Department of Applied Chemistry, University of Science and Technology of China, Hefei 230026, P. R. China
  • 收稿日期:1999-12-14 出版日期:2001-01-24 发布日期:2011-08-04
  • 基金资助:

    Supported by the National Natural Science Foundation of China(No.29775001).

Estimation and Prediction of Gas Chromatography Retention Indices of Hydrocarbons in Straight-run Gasoline by Using Artificial Neural Network and Structural Coding Method

YIN Chun-sheng, GUO Wei-min, LIU Wei, ZHAO Wei, PAN Zhong-xiao   

  1. Department of Applied Chemistry, University of Science and Technology of China, Hefei 230026, P. R. China
  • Received:1999-12-14 Online:2001-01-24 Published:2011-08-04
  • Supported by:

    Supported by the National Natural Science Foundation of China(No.29775001).

PDF (PC)

摘要： The molecular structures of hydrocarbons in straight-run gasoline were numerically coded. The nonlinear quantitative relationship(QSRR) between gas chromatography(GC) retention indices of the hydrocarbons and their molecular structures were established by using an error back-propagation(BP) algorithm. The GC retention indices of 150 hydrocarbons were then predicted by removing 15 compounds(as a test set) and using the 135 remained molecules as a calibration set. Through this procedure, all the compounds in the whole data set were then predicted in groups of 15 compounds. The results obtained by BP with the correlation coefficient and the standard deviation 0.993 4 and 16.54, are satisfied.

关键词: Structural encoding, GC retention index, Neural network, Error back-propagation(BP)

Abstract: The molecular structures of hydrocarbons in straight-run gasoline were numerically coded. The nonlinear quantitative relationship(QSRR) between gas chromatography(GC) retention indices of the hydrocarbons and their molecular structures were established by using an error back-propagation(BP) algorithm. The GC retention indices of 150 hydrocarbons were then predicted by removing 15 compounds(as a test set) and using the 135 remained molecules as a calibration set. Through this procedure, all the compounds in the whole data set were then predicted in groups of 15 compounds. The results obtained by BP with the correlation coefficient and the standard deviation 0.993 4 and 16.54, are satisfied.

Key words: Structural encoding, GC retention index, Neural network, Error back-propagation(BP)