Classification of Automobile Lubricant by Near-Infrared Spectroscopy Combined with Machine Classification

Abstract:

The main objective of this paper is to classify four kinds of automobile lubricant by near-infrared (NIR) spectral technology and to observe whether NIR spectroscopy could be used for predicting water content. Principle component analysis (PCA) was applied to reduce the information from the spectral data and first two PCs were used to cluster the samples. Partial least square (PLS), least square support vector machine (LS-SVM), and Gaussian processes classification (GPC) were employed to develop prediction models. There were 120 samples for training set and test set. Two LS-SVM models with first five PCs and first six PCs were built, respectively, and accuracy of the model with five PCs is adequate with less calculation. The results from the experiment indicate that the LS-SVM model outperforms the PLS model and GPC model outperforms the LS-SVM model.

• Periodical: Key Engineering Materials (Volumes 460-461)
• Pages: 667-672
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.460-461.667
• Online since: January 2011
• Authors: Yun Zhao, Xing Xu, Yong He
• Keywords: Automobile Lubricant, Gaussian Processes Classification, Least Squares Support Vector Machines (Ls-SVM), Near Infrared Spectroscopy (NIRS), Partial Least Square (PLS)

References

[1] Givens D I, Deboever J L, Deaville E R: Thermogravimetric evaluation of perennial ryegrass (Lolium perenne) for the prediction of in vitro dry matter digestibility, Nutrition research reviews, Vol. 10 (1997) pp.83-114.

DOI: 10.1111/j.1744-7348.2008.00218.x

[2] Paradkar M M, Sivakesava S, Irudayaraj J: Rapid Determination of Swiss Cheese Composition by Fourier Transform Infrared/Attenuated Total Reflectance Spectroscopy, Journal of the science of food and agriculture, Vol. 82 (2002) pp.497-504.

DOI: 10.3168/jds.s0022-0302(06)72209-3

[3] Barton I I, Franklin E: Treating Peanut Hulls to Improve Digestibility for Ruminants, Spectroscopy Europe, Vol. 12 (2002) p.12.

[4] Liu Xian, Han Lu-Jia, Yang Zeng-Ling, Li Qiong-Fei: NIRS Method for Determination of Meat and Bone Meal Content in Ruminant Concentrates, Chinese Journal of Analytical Chemistry, Vol. 35 (2007) pp.1285-1289.

[5] Yan Yan-Lu, Zhao Long-Lian, Han Dong-Hai, Yang Shu-Ming: The Foundation and Application of Near Infrared Spectroscopy Analysis. Beijing: China Light Indus-try Press, (2005).

[6] Xu Guang-tong, Yuan Hong-fu: Development of modern near infrared spectroscopic techniques and its applications, Acta Petrolei Sinica, Vol. 15 (1999) pp.63-68.

[7] A. G. Mignani, L. Ciaccheri, N. Díaz-Herrera, A. A. Mencaglia, H. Ottevaere, H. Thienpont: Optical fiber spectroscopy for measuring quality indicators of lubricant oils, Meas. Sci. Technol., Vol. 20, pp.1-7, (2009).

DOI: 10.1088/0957-0233/20/3/034011

[8] A. R. Caneca, M. F. Pimentel, R. K. H. Galvao, C. E. da Matta; F. R. de Carvalho; I. M. Raimundo, Assessment of infrared spectroscopy and multivariate techniques for monitoring the service condition of diesel-engine lubricating oils, Talanta, Vol. 70 (2006).

DOI: 10.1016/j.talanta.2006.02.054

[9] J. Sjoblom, N. Aske, I. H. Auflem, Ø. Brandal, T. E. Havre, Ø. Sæther, Our current understanding of water-in-crude oil emulsions.: Recent characterization techniques and high pressure performance, Adv. Colloid Interface Sci., pp.100-102, pp.399-473, (2003).

DOI: 10.1016/s0001-8686(02)00066-0

[10] V., Kecman, Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models, MIT Press, MA: Cambridge, (2001).

DOI: 10.1016/s0925-2312(01)00685-3

[11] S. Kumar. Neural networks, Authorized ed., McGraw-Hill Education (Asia) Co. and Tsinghua University Press, 2006, pp.273-303.

[12] G. Taylor, R. Parr: Kernelized Value Function Approximation for Reinforcement Learning, unpublished.

[13] S. Kumar. Neural networks, Authorized ed., McGraw-Hill Education (Asia) Co. and Tsinghua University Press. 2006, pp.167-176.

[14] W. J. Wang, Z. B. Xu, W. Z. Lu, X. Y. Zhang: Determination of the spread parameter in the Gaussian kernel for classification and regression, Neurocomputing, Vol. 55 (2003), pp.643-663.

DOI: 10.1016/s0925-2312(02)00632-x

[15] C. E. Rasmussen, C. K. I. Williams, Gaussian Processes for Machine Learning, 1st ed., Cambridge: MIT Press, 2006, p.13.

[16] X. L. Li, Y. He, C. Q. Wu: Least square support vector machine analysis for the classification of paddy seeds by harvest year, Trans. Am. Soc. Agric. Biol. Eng., Vol. 51 (2008), pp.1793-1799.

DOI: 10.13031/2013.25294

[17] F. Javier Acevedo, Javier Jimea Nez, Saturnino Maldonado, Elena Domnguez, Araa Ntzazu Narvaa EZ: Classification of Wines Produced in Specific Regions by UV-Visible Spectroscopy Combined with Support Vector Machines, Journal of agricultural and food chemistry. Vol. 55 (2007).

DOI: 10.1021/jf070634q

[18] D. Wu, L. Feng, C. Zhang, Y. He: Early Detection of Botrytis Cinerea on Eggplant Leaves Based on Visible and Near-Infrared Spectroscopy, Transactions of the ASABE, Vol. 51 (2008), pp.1133-1139.

DOI: 10.13031/2013.24504

[19] Alessandra Borin, Marco Flores Ferrao, Cesar Mello, Danilo Althmann Maretto, Ronei Jesus Poppi: Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk, Analytica Chimica Acta, Vol. 579 (2006).

DOI: 10.1016/j.aca.2006.07.008

[20] F. Chauchard, R. Cogdill, S. Roussel, J.M. Roger, V. Bellon-Maurel: Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robust and portable sensor for acidity prediction in grapes, Chemom. Intell. Lab. Syst., Vol. 71 (2004).

DOI: 10.1016/j.chemolab.2004.01.003