Please wait a minute...
浙江大学学报(工学版)
J4  2012, Vol. 46 Issue (5): 824-829    DOI: 10.3785/j.issn.1008-973X.2012.05.008
    
Near-infrared spectroscopy soft-sensing method by combining
partial least squares discriminant analysis and support vector machine
DONG Xue-feng,DAI Lian-kui,HUANG Cheng-wei
State Key Lab oratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

To improve the performance of near-infrared spectral analysis, this paper proposes a soft-sensing method (PLS-DA-SVM) which combines partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM). Based on training samples with several classes, firstly, a binary tree built by PLSDA is introduced for multiple classification; secondly, sub-models for quantitative analy are constructed by partial least squares support vector machine (PLS-SVM). For a test sample, PLS-DA classification tree serves to determine its class, and the corresponding PLS-SVM sub-model is selected for quantitative analysis. A PLS-DA-SVM model with near-infrared spectroscopy data was established to determine the research octane number of gasoline samples. Monte Carlo cross validation was preformed with 57 product gasoline samples from 2 oil refineries. Results show that mean classification error rate for the recognition of gasoline brands is 0.07%, which is lower than other pattern recognition methods. Root mean square error of prediction (RMSEP) is reduced to 0.243 and correlation coefficient (R2) is up to 0.991, which show great improvement upon PLS, LS-SVM and other modeling methods．

Published: 01 May 2012
CLC:  0 657.3  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

DONG Xue-feng,DAI Lian-kui,HUANG Cheng-wei. Near-infrared spectroscopy soft-sensing method by combining
partial least squares discriminant analysis and support vector machine. J4, 2012, 46(5): 824-829.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2012.05.008     OR     http://www.zjujournals.com/eng/Y2012/V46/I5/824


结合PLS-DA与SVM的近红外光谱软测量方法

为了提高近红外光谱分析精度,提出结合偏最小二乘判别分析（PLS-DA）与支持向量机（SVM）的软测量方法（PLS-DA-SVM）.该方法利用一组由不同类别组成的训练样本,引入二叉树进行多重分类,节点分类器由PLS-DA方法建立；利用偏最小二乘支持向量机（PLS-SVM）建立每类样本的定量模型.预测时,用PLS-DA分类树对待测样本进行分类,选择相应的PLS-SVM模型进行定量分析.实验利用PLS-DA-SVM方法和近红外光谱数据建立汽油的研究法辛烷值软测量模型,针对2个批次共计57个成品汽油样本进行蒙特卡洛交叉检验.结果表明,对汽油牌号进行识别,平均分类错误率为0.07%,低于其他常用分类方法；对研究法辛烷值进行预测,均方误差达到0.243,复相关系数达到0.991,较PLS、LS-SVM等方法有显著提高.

［1］ WORKMAN J, WEYWR L. Practical guide to interpretive nearinfrared spectroscopy ［M］. Boca Raton: CRC Press, 2008: 94-96．
［2］ 陆婉珍主编. 现代近红外光谱分析技术［M］. 2版. 北京：中国石化出版社,2006: 59-86．
［3］ JAIN A K, DUIN R P W, MAO J C. Statistical pattern recognition: A review ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(1): 4-37．
［4］ BALABIN R M, SAFIEVA R Z, LOMAKINA E I. Gasoline classification using near infrared (NIR) spectroscopy data: Comparison of multivariate techniques ［J］. Analytica Chimica Acta, 2010, 671(1/2): 27-35．
［5］ GALTIER O, ABBAS O, LE DREAU Y. Comparison of PLS1DA, PLS2DA and SIMCA for classification by origin of crude petroleum oils by MIR and virgin olive oils by NIR for different spectral regions ［J］. Vibrational Spectroscopy, 2011, 55(1): 132140．
［6］ SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers ［J］. Neural Processing Letters, 1999, 9(3): 293-300．
［7］ BARKER M, RAYENS W. Partial least squares for discrimination ［J］. Journal of Chemometrics, 2003(3), 17: 166-173．
［8］ SYLVIE C, DOMINIQUE B, ACHIM K, et al. Application of PLSDA in multivariate image analysis ［J］. Journal of Chemometrics, 2006, 20(5): 221-229．
［9］ DE PEINDERA P, VREDENBREGTB M J, VISSERC T, et al. Detection of lipitor counterfeits: A comparison of NIR and raman spectroscopy in combination with chemometrics ［J］. Journal of Pharmaceutical and Biomedical Analysis, 2008, 47(4/5): 688-694．
［10］ 杨忠, 任海青, 江泽慧. PLSDA法判别分析木材生物腐朽的研究［J］. 光谱学与光谱分析, 2008, 28(4): 793-796．
YANG Zhong, REN Haiqing, JIANG Zehui. Discrimination of wood biological decay by NIR and partial least squares discriminant analysis (PLSDA) ［J］. Spectroscopy and Spectral Analysis, 2008, 28(4): 793-796．
［11］ KUANG J C, LUO X, WANG Z, et al. A PLSSVM model for reservoir identification in natural gas exploration ［C］∥ Proceedings of the 6th International Conference on Partial Least Squares and Related Methods. Beijing: Publishing House Electronics Industry, 2009: 84-92．
［12］ 吕建峰, 戴连奎. 偏最小二乘支持向量机（PLSSVM）在光谱定量分析中的应用［C］∥ 第六届全球智能控制与自动化大会. 大连: IEEE, 2006: 5228-5232．
LV Jianfeng, DAI Liankui. Application of partial least squares support vector machines (PLSSVM) in spectroscopy quantitative analysis ［C］∥ Proceedings of the 6th World Congress on Intelligent Control and Automation. Dalian: IEEE, 2006: 5228-5232．
［13］ 朱远平, 戴汝为. 基于SVM决策树的文本分类器［M］. 模式识别与人工智能, 2005, 18(4): 412-416．
ZHU Yuanping, DAI Ruwei. Text classifier based on SVM decision tree ［J］. Pattern Recognition and Artificial Intelligence, 2005, 18(4): 412-416．
［14］ SUYKENS J A K, VANDEWALLE J, DE MOOR B. Optimal control by least squares support vector machines ［J］. Neural Networks, 2001, 14(1): 23-35．
［15］ 许禄, 邵学广. 化学计量学方法［M］. 北京: 科学出版社, 2004: 90-92．
［16］ XU Q S, LIANG Y Z. Monte Carlo cross validation ［J］. Chemometrics and Intelligent Laboratory Systems, 2001, 56(1): 1-11．
No related articles found!