Non-Invasive Measurement of Water Content in Engine Lubricant Using Visible and Near Infrared Spectroscopy
ZHANG Yu1, 2, JIANG Lu-lu2, WU Di1, TAN Li-hong2, HE Yong1*
1. College of Biosystems Engineering & Food Science, Zhejiang University, Hangzhou 310029, China 2. Zhejiang Technology Institute of Economy, Hangzhou 310018, China
Abstract：Visible and near-infrared reflectance spectroscopy (Vis-NIRS) was applied to non-invasively measurement of water content in engine lubricant. Based on measured spectra, several spectral calibration algorithms were adopted to improve accuracy and simply calculation. Principal component analysis (PCA) and successive projections algorithm (SPA) were separately used to reduce variables of spectral model. Nine effective variables, 476, 483, 544, 925, 933, 938, 952, 970 and 974 nm, were selected by SPA, and were inputted into partial least square regression (PLSR) and multivariable linear regression (MLR) models. Both the two models obtained better results than full-spectra-PLSR model and PCA-PLSR model. It shows that SPA does not select uninformative but effective variables from full-spectrum. Least-square support vector machine (LS-SVM) was operated to improve Vis-NIRS’s ability based on full-spectrum and SPA, separately. High coefficients of determination for prediction set (R2p) up to 0.9 were obtained by both full-spectrum-LS-SVM and SPA-LS-SVM models. SPA-LS-SVM is better than full-spectrum-LS-SVM. The value of R2p of SPA-LS-SVM is 0.983 and residual predictive deviation (RPD) is 6.963. It is concluded that Vis-NIRS can be used in the non-invasive measurement of water content in engine lubricant, and SPA is a feasible and efficient algorithm for the spectral variable selection.
Key words：Visible and near infrared spectroscopy;Lubricant;Water content;Partial least square regression;Least-square support vector machine;Successive projections algorithm
张 瑜1,2，蒋璐璐2, 吴 迪1，谈黎虹2，何 勇1*. 基于可见-近红外光谱技术的润滑油含水量无损检测方法研究[J]. 光谱学与光谱分析, 2010, 30(08): 2111-2114.
ZHANG Yu1, 2, JIANG Lu-lu2, WU Di1, TAN Li-hong2, HE Yong1*. Non-Invasive Measurement of Water Content in Engine Lubricant Using Visible and Near Infrared Spectroscopy . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(08): 2111-2114.
[1] ZHOU Xin(周 鑫). Automobile Technology & Material(汽车工艺与材料)，2005, (7)：39. [2] He Y, Li X L, Shao Y N. International Journal of Food Properties, 2007, 10(1): 9. [3] Wu D, He Y, Nie P C, et al. Analytica Chimica Acta, 2009, 659(1-2): 229. [4] HE Zhi-hui, LIAN Wen-liu, CHEN Ya, et al(何智慧，练文柳, 陈 亚, 等). Chinese Journal of Analysis Laboratory(分析试验室), 2005, 24(6): 24. [5] Shao Y, He Y, Hu X. Applied Optics, 2007, 46(34): 8379. [6] YAN Yan-lu, ZHAO Long-lian, HAN Dong-hai, et al(严衍禄，赵龙莲，韩东海, 等). Infrared Spectroscopy Analysis Fundamentals and Applications(近红外光谱分析基础与应用). Beijing: China Light Industry Press(北京: 中国轻工业出版社), 2005. [7] Cen H Y, He Y. Trends in Food Science & Technology, 2007, 18(2): 72. [8] Galvao R K H, Araújo M C U, Fragoso W D, et al. Chemometrics and Intelligent Laboratory Systems, 2008, 92: 83. [9] Wu D, Yang H Q, Chen X J, et al. Journal of Food Engineering, 2008, 88(4): 474.
