基于近红外光谱的食用植物油中反式脂肪酸含量快速定量检测及模型优化研究

利用近红外光谱技术对食用植物油中反式脂肪酸（Trans fatty acids,TFA）含量进行快速定量检测,并通过波段选择、预处理方法、变量筛选及建模方法对TFA含量预测模型进行优化。采用AntarisⅡ傅里叶变换近红外光谱仪在4000~10000 cm$1光谱范围采集98个食用植物油样本的近红外透射光谱,然后采用气相色谱法测定TFA的真实含量。首先,对样本原始光谱进行波段、预处理方法优选;在此基础上,采用竞争自适应重加权法（Competitive adaptive reweighted sampling,CARS）筛选TFA相关的重要变量,最后应用主成分回归、偏最小二乘和最小二乘支持向量机...

Full description

Saved in:
Bibliographic Details
Published in分析化学 Vol. 45; no. 11; pp. 1694 - 1702
Main Author 莫欣欣 孙通 刘木华 叶振南
Format Journal Article
LanguageChinese
Published 江西农业大学工学院,江西省高校生物光电技术及应用重点实验室, 南昌 330045%江西出入境检验检疫局,综合技术中心, 南昌 330038 2017
Subjects
定量检测
模型优化
竞争自适应重加权法变量筛选
近红外光谱
食用植物油
Near infrared spectroscopy
食用植物油
Competitive adaptive reweighted sampling variable selection
定量检测
竞争自适应重加权法变量筛选
Edible vegetable oils
近红外光谱
模型优化
Model optimization
Quantitative detection
Online AccessGet full text
ISSN0253-3820
DOI10.11895/j.issn.0253-3820.170329

Cover

More Information
Summary:利用近红外光谱技术对食用植物油中反式脂肪酸（Trans fatty acids,TFA）含量进行快速定量检测,并通过波段选择、预处理方法、变量筛选及建模方法对TFA含量预测模型进行优化。采用AntarisⅡ傅里叶变换近红外光谱仪在4000~10000 cm$1光谱范围采集98个食用植物油样本的近红外透射光谱,然后采用气相色谱法测定TFA的真实含量。首先,对样本原始光谱进行波段、预处理方法优选;在此基础上,采用竞争自适应重加权法（Competitive adaptive reweighted sampling,CARS）筛选TFA相关的重要变量,最后应用主成分回归、偏最小二乘和最小二乘支持向量机方法分别建立食用植物油中TFA含量的预测模型。研究结果表明,近红外光谱技术检测食用植物油中的TFA含量是可行的,优化后的最佳预测模型的校正集和预测集R2分别为0.992和0.989,RMSEC和RMSEP分别为0.071%和0.075%。最佳预测模型所用的变量仅26个,占全波段变量的0.854%。此外,与全波段偏最小二乘预测模型相比,其预测集R2由0.904上升为0.989,RMSEP由0.230%下降为0.075%。由此表明,模型优化非常必要,CARS能有效筛选TFA相关的重要变量,极大减少建模变量数,从而简化预测模型,并较大提高预测模型的精度和稳定性。
Bibliography:MO Xin-Xin1, SUN Tong＊1, LIU Mu-Hua1, YE Zhen-Nan21（Key Laboratory of Jiangxi University for Optics-Electronics Application of Biomaterials,College of engineering, Jiangxi Agricultural University, Nanchang 330045, China）2（Comprehensive Technology Center, Jiangxi Entry-Exit Inspection and Quarantine Bureau, Nanchang 330038, China）
22-1125/O6
Edible vegetable oils; Near infrared spectroscopy; Model optimization; Competitive adaptivereweighted sampling variable selection; Quantitative detection
Near infrared spectroscopy（ NIR） was used to detect trans fatty acids（ TFA） in edible vegetable oils quantitatively. And prediction model of TFA was optimized through band selection,pretreatment method,variable selection and modeling method. NIR spectra of 98 edible vegetable oil samples were collected in spectral range of 4000-10000 cm$1 using an Antaris II Fourier transform near infrared spectrometer,and the true content of TFA was measured by gas chromatography. First,optimization of waveband and pretreatment method was c
ISSN:0253-3820
DOI:10.11895/j.issn.0253-3820.170329