醇类汽油定性定量分析通用模型的研究
|
摘要
为了建立醇类汽油定性定量分析判别的通用模型,采用WQF-510A傅里叶变换红外光谱仪与OPUS光谱采集软件获得甲醇汽油、乙醇汽油的中红外光谱。利用主成分(PC)分析和偏最小二乘(PLS)判别法对醇类汽油样品进行定性判别;通过无信息变量消除进行波段筛选,并基于无信息变量消除-偏最小二乘(UVE-PLS)和无信息变量消除-最小二乘支持向量机(UVE-LSSVM)两种方法分别建立醇类汽油的通用模型后用数据进行评价检验。结果表明,利用PC和DPLS对醇类汽油样品定性判别准确率达到100%;基于UVE-LSSVM方法建立的通用模型效果最好,决定系数和预测集均方根误差分别为0.945和2.187。该研究表明醇类汽油定性定量分析判别通用模型是可行的,该模型可以作为醇类汽油醇含量检测的技术参考和理论依据。
In order to establish a general model for qualitative and quantitative analysis of alcohol gasoline, mid-infrared spectra of methanol gasoline and ethanol gasoline were obtained by using WQF-510 A Fourier transform infrared spectrometer and OPUS spectral acquisition software. Principal component(PC) analysis and partial least square(PLS) discrimination were used to identify the alcohol gasoline samples. Band screening was conducted by uninformation variable elimination(UVE). The general model of alcohol gasoline was established based on UVE-PLS and UVE-LSSVM(least square support vector machine) and the data were evaluated. The results show that, the accuracy rate of qualitative discrimination of alcohol gasoline by PC analysis and PLS discrimination is 100%.The general model based on UVE-LSSVM method has the best effect, with root mean square error prediction of 2.187 and decision coefficient of 0.945 respectively. The general model is feasible to identify alcohol gasoline by qualitative and quantitative analysis, which can be used as technical reference and theoretical basis for alcohol gasoline alcohol content detection.
In order to establish a general model for qualitative and quantitative analysis of alcohol gasoline, mid-infrared spectra of methanol gasoline and ethanol gasoline were obtained by using WQF-510 A Fourier transform infrared spectrometer and OPUS spectral acquisition software. Principal component(PC) analysis and partial least square(PLS) discrimination were used to identify the alcohol gasoline samples. Band screening was conducted by uninformation variable elimination(UVE). The general model of alcohol gasoline was established based on UVE-PLS and UVE-LSSVM(least square support vector machine) and the data were evaluated. The results show that, the accuracy rate of qualitative discrimination of alcohol gasoline by PC analysis and PLS discrimination is 100%.The general model based on UVE-LSSVM method has the best effect, with root mean square error prediction of 2.187 and decision coefficient of 0.945 respectively. The general model is feasible to identify alcohol gasoline by qualitative and quantitative analysis, which can be used as technical reference and theoretical basis for alcohol gasoline alcohol content detection.
引文
[1] ZHU T,CH G Q,LIU Y,et al.Study on absorption spectrum and fluorescence spectrum of methanol solution[J].Laser Technology,2005,29(5):470-472 (in Chinese).
[2] LI Y R.Determination of methanol in by mid-infrared motor methanol gasoline spectroscope[J].Shanxi Chemical Industry,2014,34(4):38-39(in Chinese).
[3] JIN P P,ZHANG T,WANG M,et al.Application of mid-infrared spectroscope analysis of methanol gasoline[J].Energy and Energy Conservation,2012(5):3-7(in Chinese).
[4] OUYNAG A G,LIU J,WANG Y P,et al.Detection of ethanol content in ethanol gasoline by near infrared spectroscopy [J].Laser and Infrared,2012,42(8):901-904(in Chinese).
[5] HENSELER J,RINGLE C M,SINKOVICS R R.The use of partial least squares path modeling in international marketing[J].Advances in International Marketing,2009,20(1):277-319.
[6] LI Y R,SUN R P,WANG Y M,et al.Determination of methanol in methanol gasoline for motor vehicles by gas chromatography [J].Modern Chemical Industry,2013,33(2):113-115(in Chinese).
[7] DING H Y,HUANG R H,WANG Zh W,et al.Simulations and app-lications of bubble/dew curve for different ethanol-gasoline [J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2012,40(6):113-116(in Chinese).
[8] JIN P P,ZHANG T,WANG M,et al.Mid-infrared analyzers for the determination of methanol fuels[J].Automobile Science and Technology,2012(5):66-70(in Chinese).
[9] LIU Y D,WU M M,SUN X D.Simultaneous detection of surfacedeficiency and soluble solids content for yellow peach by online visible-near infrared [J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(6):289-295(in Chinese).
[10] DAN T N,DAI L K.The spectral band selection method based on PLS projection analysis[J].Spectroscopy and Spectral Analysis,2009,29(2):351-354(in Chinese).
[11] ZHU Z W,CHEN M X,ZHANG L,et al.Study on determination of each component in aromatics device by Raman spectrometer[J].Laser Technology,2014,38(6):839-844(in Chinese).
[12] ZU Q,ZHANG S F,CAO Y,et al.Research on identification of cabbages and weeds combining spectral imaging technology and SAM taxonomy [J].Spectroscopy and Spectral Analysis,2015,35(2):479-485(in Chinese).
[13] HAN Zh Zh,WAN J H,LIU K W,et al.Model optimization in prediction of gas octane value by NIR[J].Chinese Journal of Analysis Laboratory,2015,34(11):1268-1271(in Chinese).
[14] OUYANG A G,LIU J.Quantitative analysis of methanol gasoline based on near infrared and Raman spectroscopy [J].Journal of Southwest Normal University (Natural Science Edition),2012,37(9):98-101(in Chinese).
[15] YAO J,DAI L K,LIN Y L,et al.Determination of methanol ratio in methanol gasoline based on Raman characteristic peaks [J].Ch-inese Journal of Light Scattering,2013,25(1):59-65(in Chinese).
[16] OUYANG A G,TANG T Y,ZHOU X,et al.Methanol content determination in methanol gasoline with mid infrared spectroscopy ana-lysis using least square support vector machine[J].Chinese Journal of Luminescence,2016,37(10):1253-1258(in Chinese).
[17] WANG T,DAI L K,MA W W.Raman spectroscopy combined with backward interval partial east squares method for quantitative analysis of gasoline octane number[J].Analytical Chemistry,2018,46(4):623-629(in Chinese).
[18] CAI W,LI Y,SHAO X.A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra[J].Chemometrics and Intelligent Laboratory Systems,2008,90(2):188-194.
[19] HENSELER J,RINGLE C M,SINKOVICS R R.The use of partial least squares path modeling in international marketing [J].Advances in International Marketing,2009,20(1):277-319.
[20] MITRA V,WANG C J,BANERJEE S.Text classification:A least square support vector machine approach[J].Applied Soft Computing,2007,7(3):908-914.
[2] LI Y R.Determination of methanol in by mid-infrared motor methanol gasoline spectroscope[J].Shanxi Chemical Industry,2014,34(4):38-39(in Chinese).
[3] JIN P P,ZHANG T,WANG M,et al.Application of mid-infrared spectroscope analysis of methanol gasoline[J].Energy and Energy Conservation,2012(5):3-7(in Chinese).
[4] OUYNAG A G,LIU J,WANG Y P,et al.Detection of ethanol content in ethanol gasoline by near infrared spectroscopy [J].Laser and Infrared,2012,42(8):901-904(in Chinese).
[5] HENSELER J,RINGLE C M,SINKOVICS R R.The use of partial least squares path modeling in international marketing[J].Advances in International Marketing,2009,20(1):277-319.
[6] LI Y R,SUN R P,WANG Y M,et al.Determination of methanol in methanol gasoline for motor vehicles by gas chromatography [J].Modern Chemical Industry,2013,33(2):113-115(in Chinese).
[7] DING H Y,HUANG R H,WANG Zh W,et al.Simulations and app-lications of bubble/dew curve for different ethanol-gasoline [J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2012,40(6):113-116(in Chinese).
[8] JIN P P,ZHANG T,WANG M,et al.Mid-infrared analyzers for the determination of methanol fuels[J].Automobile Science and Technology,2012(5):66-70(in Chinese).
[9] LIU Y D,WU M M,SUN X D.Simultaneous detection of surfacedeficiency and soluble solids content for yellow peach by online visible-near infrared [J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(6):289-295(in Chinese).
[10] DAN T N,DAI L K.The spectral band selection method based on PLS projection analysis[J].Spectroscopy and Spectral Analysis,2009,29(2):351-354(in Chinese).
[11] ZHU Z W,CHEN M X,ZHANG L,et al.Study on determination of each component in aromatics device by Raman spectrometer[J].Laser Technology,2014,38(6):839-844(in Chinese).
[12] ZU Q,ZHANG S F,CAO Y,et al.Research on identification of cabbages and weeds combining spectral imaging technology and SAM taxonomy [J].Spectroscopy and Spectral Analysis,2015,35(2):479-485(in Chinese).
[13] HAN Zh Zh,WAN J H,LIU K W,et al.Model optimization in prediction of gas octane value by NIR[J].Chinese Journal of Analysis Laboratory,2015,34(11):1268-1271(in Chinese).
[14] OUYANG A G,LIU J.Quantitative analysis of methanol gasoline based on near infrared and Raman spectroscopy [J].Journal of Southwest Normal University (Natural Science Edition),2012,37(9):98-101(in Chinese).
[15] YAO J,DAI L K,LIN Y L,et al.Determination of methanol ratio in methanol gasoline based on Raman characteristic peaks [J].Ch-inese Journal of Light Scattering,2013,25(1):59-65(in Chinese).
[16] OUYANG A G,TANG T Y,ZHOU X,et al.Methanol content determination in methanol gasoline with mid infrared spectroscopy ana-lysis using least square support vector machine[J].Chinese Journal of Luminescence,2016,37(10):1253-1258(in Chinese).
[17] WANG T,DAI L K,MA W W.Raman spectroscopy combined with backward interval partial east squares method for quantitative analysis of gasoline octane number[J].Analytical Chemistry,2018,46(4):623-629(in Chinese).
[18] CAI W,LI Y,SHAO X.A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra[J].Chemometrics and Intelligent Laboratory Systems,2008,90(2):188-194.
[19] HENSELER J,RINGLE C M,SINKOVICS R R.The use of partial least squares path modeling in international marketing [J].Advances in International Marketing,2009,20(1):277-319.
[20] MITRA V,WANG C J,BANERJEE S.Text classification:A least square support vector machine approach[J].Applied Soft Computing,2007,7(3):908-914.