Study on the Gasoline Classification Methods Based on near Infrared Spectroscopy
Study on the Gasoline Classification Methods Based on near Infrared Spectroscopy
复制标题
DOI：
10.1109/sopo.2010.5504441
复制
发表时间：
2010-06
期刊：
影响因子：
--
通讯作者：
J. Zhang;Li Jiang;Qian Yu;Zhe Chen
中科院分区：
文献类型：
--
作者：
J. Zhang;Li Jiang;Qian Yu;Zhe Chen
采用主成分分析和自组织竞争神经网络相结合的方法对93号和97号汽油进行分类，建立了近红外透射谱和反射光谱在1100-1700 nm波段的定性识别模型。在建模前用主成分分析方法对光谱数据进行压缩，选择三个累积可信度达到97%的主成分。基于主成分分析方法，建立了三层自组织竞争神经网络模型。将32个波长的吸光度作为自组织竞争神经网络的输入。学习参数设为0.01，训练迭代取为500。结果表明，采用主成分分析和自组织竞争神经网络相结合的方法，将近红外透射光谱和反射光谱定性识别模型应用于汽油产品的鉴别是可行的。
The purpose of this paper is to classify 93# and 97# gasoline by using principal component analysis (PCA) with self-organizing competitive neural network method and to establish near infrared transmission spectroscopy and reflectance spectroscopy qualitative identification model in 1100-1700nm spectral region. The spectral data is condensed by PCA method before modeling, and three principal components are chosen because their cumulative credibility has reached 97%. A three-layer self-organizing competitive neural network model is established based on the PCA method. Thirty-two wavelengths' absorbance is served as inputs of the self-organizing competitive neural network. The learning parameter is set as 0.01 and the training iteration is taken as 500. The conclusion is that it is feasible to apply near infrared transmission spectroscopy and reflectance spectroscopy qualitative identification model to discriminate the gasoline products as the PCA and self-organizing competitive neural networks method is used.