Study of Variable Selection Method Based on PLS for Quantitatively Measuring Heavy Metal in Water with LIBS
HU Li1, ZHAO Nan-jing2*, LI Da-chuang1，TANG Lei1, FANG Li2
1. School of Electronic and Information Engineering, Hefei Normal University, Hefei 230061, China
2. Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China
Abstract：The spectral characteristics of multiple variables were regularly extracted for concentration inversion in the quantitative analysis of heavy metal with LIBS. However, overlapped spectral information might be contained among variables and the complexity of the regression model also would be increased. To extract effective feature variables, the variable selection method based on PLS was studied. PLS model established with the concentration of the element under test used as the dependent variable and multiple LIBS spectrum characteristic variables used as independent variables. The optimal variable subset was extracted on the basis of the original variable importance projection index for variable selection. The results showed that the optimal variable subset for Pb was composed of the Pb Ⅰ 405.78 nm peak, the spectral values before Pb Ⅰ 405.78 nm peak, the intensity corrected by the internal standard element and the signal to background in lake water, and the correlation coefficient square of the training set was 0.912. The optimal variable subset was used for PLS regression analysis, and RSD and RE of the test set were 10.2% and 7.9%, respectively, significantly better than the predictive results of the internal standard. It also showed that variable screening results for different elements and different water samples was applicative to some extent, but the internal standard element failed in correction for different water samples. The results provided high quality characteristic data for the LIBS quantitative analysis, and the methods also provided a reference for other quantitative analysis involving variable selection.
Key words：Spectroscopy；Laser induced breakdown spectroscopy；Variable screening；PLS model
胡 丽，赵南京，李大创，唐 磊，方 丽. 基于PLS的水体重金属LIBS特征变量筛选方法研究[J]. 光谱学与光谱分析, 2017, 37(08): 2585-2589.
HU Li, ZHAO Nan-jing, LI Da-chuang，TANG Lei, FANG Li. Study of Variable Selection Method Based on PLS for Quantitatively Measuring Heavy Metal in Water with LIBS. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(08): 2585-2589.
[1] Brech F，Cross L. Appl. Spectrosc., 1962, 16(3): 59.
[2] Sadegh Cheri M，Tavassoli S H. Applied Optics, 2011, 50(9): 1227.
[3] XU Yuan, YAO Ming-yin, LIU Mu-hua，et al(徐 媛, 姚明印, 刘木华，等). Acta Optica Sinica(光学学报), 2011, 31(12): 290.
[4] LI Wen-hong，WU Zhi-xiang，WANG Rui-wen，et al(李文宏, 武志翔, 王芮雯，等). Chinese J. Lasers(中国激光), 2014, 41(6): 282.
[5] CHEN Xing-long, DONG Feng-zhong, TAO Guo-qiang，et al(陈兴龙, 董凤忠, 陶国强，等). Chinese J. Lasers(中国激光), 2013, 40(12): 243.
[6] WANG Chun-long, LIU Jian-guo, ZHAO Nan-jing，et al(王春龙, 刘建国, 赵南京，等). Acta Optica Sinica(光学学报), 2013, 33(3): 314.
[7] WANG Chun-long, LIU Jian-guo, ZHAO Nan-jing，et al(王春龙, 刘建国, 赵南京，等). Acta Phys. Sin.(物理学报), 2013, 62(12): 125201.
[8] WANG Hui-wen(王惠文) . Partial Least Squares Regression Method and Its Application(偏最小二乘回归方法及其应用). Beijing: National Defence Industry Press(北京： 国防工业出版社), 1999. 14.
[9] David A C，RadziemskiLeon J. Handbook of Laser-Induced Breakdown Spectroscopy. Cambridge University Press, 2006. 24.
[10] Zhang Y H, Xia Z N, Qin L T, et al. Mol. Graph. Model., 2010, 29: 214.
[11] ZHANG Heng-xi, GUO Ji-lian(张恒喜, 郭基联). Multivariate Date Analysis and Application of Small Sample(小样本多元数据分析及应用). Xi’an: Northwestern Polytechnical University Press(西安： 西北工业大学出版社), 2002. 99.
[12] Environmental Monitoring Analysis Method Standard System Revision Techical Quidance(环境监测分析方法标准制修订技术导则). Ministry of Environmental Protection(环境保护部)，2010.
