J4

• 化学 • 上一篇    下一篇

人工神经网络-近红外光谱法非破坏监控蛇床子SFE-CO2萃取物的质量

郭 晔, 王 彬, 曲 楠, 赵羚志, 李文良, 弥 宏, 任玉林   

  1. 吉林大学 化学学院, 长春 130012
  • 收稿日期:2007-04-05 修回日期:1900-01-01 出版日期:2008-03-26 发布日期:2008-03-26
  • 通讯作者: 任玉林

Application of Artificial Neural Networknearinfrared Reflectance Spectroscopy in Controlling Extractant of Fructus Cnidii by SFE-CO2

GUO Ye, WANG Bin, QU Nan, ZHAO Lingzhi, LI Wenliang, MI Hong, REN Yulin   

  1. College of Chemistry, Jilin University, Changchun 130012, China
  • Received:2007-04-05 Revised:1900-01-01 Online:2008-03-26 Published:2008-03-26
  • Contact: REN Yulin

摘要: 将人工神经网络与近红外漫反射光谱相结合, 对蛇床子超临界CO2萃取物中的蛇床子素和欧前胡素同时进行快速、 非破坏的定量分析. 分别利用 萃取物的原始光谱和两种预处理光谱(一阶导数和标准归一化)建立了网络的数学校正模型, 并把所得结果进行了比较, 确定用一阶导数光谱所建立的模型为最佳网络模型.

关键词: 人工神经网络, 近红外漫反射光谱, 蛇床子, 超临界CO2萃取

Abstract: A rapid and nondestructive analytical method for simultaneous analysis of osthol and imperatorin in the extractant of Fructus Cnidii obtained by supercritical carbon dioxide fluid extraction (SFE-CO2) was developedby artificial neural network based on nearinfrared spectroscopy. The artificial neural network (ANN) models of original spectrum and two pretreated spectra (firstderivative and standard normal variate, respectively) of osthol and imperatorin were established. In the models the concentrations of osthol and imperatorin were determined simultaneouslyand compared. The best model of determining the concentrations of osthol and imperatorin was obtained via their firstderivative spectra.

Key words: artificial neural network, near infrared diffuse ref lectance spectrum, Fructus Cnidii, supercritical carbon dioxide extraction

中图分类号: 

  • O657.33