Detection of diesel quality parameters by near infrared spectroscopy with sparse component analysis

ZHOU Yang; DAI Shu-guang; GE Ding-fei

doi:10.3788/OPE.20142202.0296

您当前的位置：

首页 >

文章列表页 >

Detection of diesel quality parameters by near infrared spectroscopy with sparse component analysis

Modern Applied Optics | 更新时间：2020-08-13

- Detection of diesel quality parameters by near infrared spectroscopy with sparse component analysis
- Optics and Precision Engineering Vol. 22, Issue 2, Pages: 296-303(2014)
- 作者机构：
  
  1. 浙江科技学院信息与电子工程学院,浙江杭州,310023
  2. 上海理工大学光电信息与计算机工程学院上海,200093
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20142202.0296
  CLC： O657.33;U473.1+2
- Received：06 May 2013，
  
  Published：20 February 2014
- 稿件说明：
移动端阅览
周扬,戴曙光,葛丁飞. 近红外光谱稀疏分量分析检测柴油品质参数[J]. 光学精密工程, 2014,22(2): 296-303

ZHOU Yang, DAI Shu-guang, GE Ding-fei. Detection of diesel quality parameters by near infrared spectroscopy with sparse component analysis[J]. Editorial Office of Optics and Precision Engineering, 2014,22(2): 296-303
周扬,戴曙光,葛丁飞. 近红外光谱稀疏分量分析检测柴油品质参数[J]. 光学精密工程, 2014,22(2): 296-303 DOI： 10.3788/OPE.20142202.0296.

ZHOU Yang, DAI Shu-guang, GE Ding-fei. Detection of diesel quality parameters by near infrared spectroscopy with sparse component analysis[J]. Editorial Office of Optics and Precision Engineering, 2014,22(2): 296-303 DOI： 10.3788/OPE.20142202.0296.

摘要

由于光谱盲源分离中的独立分量分析方法(ICA)在柴油品控参数近红外光谱定量分析时预测效果不理想

稳定性不高

本文提出了一种在稀疏特性下的盲源分离近红外光谱分析思路——近红外光谱稀疏分量分析法

并用该方法预测了柴油沸点、密度、芳烃总量等品控参数。首先利用柴油校正集光谱样本训练冗余字典并完成光谱在该字典下的稀疏变换

接着完成混合矩阵估计

最后用混合矩阵与柴油品控参数建立回归预测模型。针对混合矩阵估计中光谱稀疏度不为一时聚状特征模糊导致无法确定聚类数的问题

提出将AP聚类算法应用于聚类过程。实验表明

近红外光谱稀疏分量分析法对柴油沸点、密度、芳烃总量预测的相关系数(

)、预测均方根误差(RMSEP)分别达到了98.91%

99.68%

99.43%和2.84

0.88×10

-3

0.59

性能优于ICA及全谱偏最小二乘(PLS)等传统方法。该方法可作为一种柴油品控参数检测的有效盲源分离定量分析方法

并可推广于其它光谱检测领域。

Abstract

Independent Component Analysis(ICA) in a blind source separation method can not obtain ideal prediction results and excellent measuring stability in detecting diesel quality parameters by near-infrared spectroscopy. Therefore

a blind source separation method based on sparse characteristics of near-infrared spectroscopy is proposed. The method is named Near Infrared Spectroscopy with Sparse Component Analysis(NIFS SCA) and is used for the prediction of boiling points

density and total aromatics for the diesel. This method firstly trains the redundant dictionary by spectral samples and finishes the sparse transformation for the calibration sample. Then

it estimates the mixing matrix

and establishes the regression model between mixing matrix and diesel quality parameters. As the clustering progress is hard to determine the number of clusters when the sparsity of spectral is not equal to one and the clustering feature is fuzzy

the AP clustering algorithm is applied to the clustering process. The experiments show that the Relative coefficient(

) and the Root Mean Square Error of Prediction (RMSEP) of the NIFS SCA for diesel boiling point

density

total aromatic prediction respectively are 98.91%

99.68%

99.43% and 2.84

0.88×10

-3

0.59

which is better than those of ICA and the full spectrum PLS methods. The proposed method can be an effective blind source separation quantitative analysis method for detecting diesel quality parameters and also can be promoted to other spectral detection applications.

关键词

Keywords

references

JULIO C L A, CLAUDETE B H, RONEI J P. Determination of diesel quality parameters using support vector regression and near infrared spectroscopy for an in-line blending optimizer system[J]. Fuel, 2012,97:710-717.

WANG S J, WU D, LIU K S. Semi-supervised machine learning algorithm in near infrared spectral calibration: a case study on diesel fuels[J]. Advanced Science Letters, 2012,11(1):416-419.

ZHANG W B, YUAN W Q, ZHANG X M, et al.. Predicting the dynamic and kinematic viscosities of biodiesel-diesel blends using mid- and near- infrared spectroscopy[J]. Applied Energy, 2012,98: 122-127.

LI H D, LIANG Y Z, LONG X X, et al.. The contimuity of sample complexity and its relationship to multivariate calibration: a general perspective on first-order calibration of spectral data in analytical chemistry [J]. Chemometrics and Intelligent Laboratory System, 2013,122(3): 23-30.

de CARVALHO ROCNA W F,NOGUEIRA R,VAZ B G. Validation of model of multivariate calibration:an application to the determination of biodiesel blend levels in diesel by near-infared spectroscopy[J]. Journal of Chemometrics, 2012, 26(8-9):456-461.

SCHOLZ M, GAATZEK S, STERLINGA, et al.. Metabolite fingerprinting: detecting biological features by independent component analysis[J]. Bioinformatics, 2004, 20(15): 2447-2454.

SHAO X G, WANG W, HOU Z Y, et al.. A new regression method based on independent component analysis[J]. Talanta, 2006, 69: 676-680.

TOIVIAINEN M, CORONA F, PAASO J, et al.. Blind source separation in diffuse reflectance NIR spectroscopy using independent component analysis[J]. Journal of Chemometrics, 2010, 24(10):514-522.

方利明, 林敏. 柴油近红外光谱的独立分量分析方法[J]. 石油学报(石油加工), 2008, 24(6): 726-732.

FANG L M, LIN M. Near infrared spectra analysis of diesel fuel by indenpendent component analysis[J]. Acta Petrolei Sinica(Petroleum Processing Section), 2008, 24(6): 726-732. (in Chinese)

HYVRINEN A. Independent component analysis: recent advances[J]. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2013, 371:1-20.

WALDMANN I P, TINETTI G, DEROO P, et al.. Blind extraction of an exoplanetary spectrum through independent component analysis[J]. The Astrophysical Journal, 2013, 766(1): 7-15.

ASAEI A, DAVIES M E, BOURLARD H, et al.. Computational methods for structured sparse component analysis of convolutive speech mixtures[C].Acoustics, Speech and Signal Processing (ICASSP),IEEE International Conference on IEEE, 2012:2425-2428.

周扬, 戴曙光, 吕进, 等. 训练字典及其稀疏表示在近红外光谱法检测柴油中的应用[J]. 化学学报, 2012, 70(18): 1969-1973.

ZHOU Y, DAI SH G, L J, et al.. Application of train dictionary and sparse representation in diesel property detection using near-infrared spectroscopy[J]. Acta Chimica Sinica, 2012, 70(18): 1969-1973. (in Chinese)

董天宝, 杨景曙. 稳健的欠定混合矩阵盲辨识[J]. 宇航学报, 2013, 34(3): 426-433.

DONG T B, YANG J SH. A robust underdetermined mixing matrix estimation algorithm[J]. Journal of Astronautics, 2013, 34(3): 426-433. (in Chinese)

杨合龙, 祝磊, 韩斌, 等. 运用近邻传播聚类分析进行SELDI-TOF蛋白质谱特征选择[J]. 中国生物医学工程学报, 2013, 32 (1):14-20.

YANG H L, ZHU L, HAN B, et al.. Feature selection and sample classification for SELDI-TOF mass spectrometry data based on affinity propagation clustering[J]. Chinese Journal of Biomedical Engineering, 2013, 32 (1): 14-20. (in Chinese)

SMITH L N,OLSON C C,JUDDK P, et al.. Denoising infrared maritime imagery using tailored dictionaries via modified K-SVD algorithm[J]. Applied Optics, 2012, 51(17): 3941-3949.

焦李成, 杨淑媛, 刘芳, 等. 压缩感知回顾与展望[J]. 电子学报, 2011, 39(7): 1651-1662.

JIAO L CH, YANG SH Y, LIU F, et al.. Development and prospect of compressive sensing[J]. Acta Electronica Sinica, 2011, 39(7): 1651-1662. (in Chinese)

王勇, 王雪, 孙欣尧. 基于稀疏信号重构的无线传感网络目标定位[J]. 仪器仪表学报, 2012, 33(2): 362-368.

WANG Y, WANG X, SUN X Y. Target location in wireless sensor networks using spares signal reconstruction[J]. Chinese Journal of Scientific Instrument, 2012, 33(2): 362-368. (in Chinese)

FREY B J, DUECK D. Clustering by passing messages between data points[J]. Science, 2007, 972(315): 972-976.

MAHMOUDI M, SAPIRO G. Sparse representations for range data restoration[J]. IEEE Transactions on Image Processing, 2012, 21(5): 2909-2915.

刘燕德, 周延睿, 彭彦颖. 基于近红外漫反射光谱检测鸡蛋品质[J]. 光学精密工程, 2013, 21(1): 40-45.

LIU Y D, ZHOU Y R, PENG Y Y. Detection of egg quality by near infrared diffuse reflectance spectroscopy[J]. Opt. Precision Eng., 2013, 21(1): 40-45. (in Chinese)

曹璞, 潘涛, 陈星旦. 小型近红外玉米蛋白质成分分析仪器设计的波段选择[J]. 光学精密工程, 2007,15(12): 1951-1958.

CAO P, PAN T, CHEN X D. Choice of wave band in design of minitype near-infrared corn protein content analyzer[J]. Opt. Precision Eng., 2007,15(12): 1951-1958. (in Chinese)

黄富荣, 潘涛, 张甘霖, 等. 应用近红外漫反射光谱快速测定土壤锌含量[J]. 光学精密工程, 2010, 18(3): 586-592.

HUANG F R, PAN T, ZHANG G L, et al.. Rapid measurement of zinc contents in soils by near-infrared diffuse reflectance spectroscopy[J]. Opt. Precision Eng., 2010, 18(3): 586-592. (in Chinese)

VAN L D, WU D Y, CHEN C S. Energy-efficient fast ICA implementation for biomedical signal separation[J]. IEEE Transactions on Networks, 2011, 22(11): 1809-1822.

Views

335

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Qualitative analysis of KCl composition for skin secretion based on near infrared spectroscopy

Rapid detection of oil yield of oil shale by combination of wavelengths in near infrared spectroscopy

Detection limit of glucose concentration in noninvasive measurement of glucose with near-infrared spectroscopy

Related Author

WANG Meng-jun

DONG Li-zhu

LIU Jian-fei

LI Gang

WANG Zhi-hong

ZHANG Fu-dong

TENG Fei

WANG Bing-jian

Related Institution

School of Information Engineering, Hebei University of Technology

College of Precision Instrument and Optic-electronics Engineering, Tianjing University

吉林大学仪器科学与电气工程学院

暨南大学理工学院光电工程系

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰