|
|
|
|
|
|
Research on Selection Method of LIBS Feature Variables Based on CART Regression Tree |
YOU Wen1, XIA Yang-peng1, HUANG Yu-tao1, LIN Jing-jun2*, LIN Xiao-mei3* |
1. Department of Electronics and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
2. Department of Mechanical and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
3. Jilin University of Architecture and Technology,Changchun 130012, China |
|
|
Abstract When laser induced breakdown spectroscopy (LIBS) is used for detection, due to the many and complex spectral lines, there are much redundant information, which will affect the quantitative analysis. Therefore, extracting effective feature variables is of great significance in the quantitative analysis of LIBS. In this paper, the method of selecting the spectral characteristics of the Ca element in the CaCl2 solution was analyzed, and the accuracy and stability of the univariate model, partial least square regression and CART regression tree calibration model were compared. In view of the large volatility of the surface of the water body, the poor spectral stability, and the fact that the spectrum is affected by the matrix effect and the self-absorption effect, the fitting coefficient (R2) obtained by the univariate model is only 0.933 2, and the training root mean square error (RMSEC), prediction root mean square error (RMSEP) and average relative error (ARE) are 0.019 2 Wt%, 0.017 7 Wt% and 11.604% respectively. After partial least squares regression optimization, the model R2 is increased to 0.975 3, and RMSEC, RMSEP and ARE are reduced to 0.010 8 Wt%, 0.013 Wt% and 7.49%, respectively. Although the model’s accuracy has been improved, it is still difficult to meet the analysis requirements. In order to further improve the accuracy of quantitative analysis, a CART regression tree calibration model was established. When constructing the tree model, this method uses the square error minimization criterion to select the optimal combination of characteristic variables from the complex spectral information to make classification decisions, thereby establishing the calibration curve of the Ca element. Through the variable selection of the CART regression tree, the number of characteristic variables is reduced from 100 to 6, and the compression rate of variables reaches 94%, which significantly reduces the interference of irrelevant spectral lines. The correlation coefficients of the regression tree model are R2, RMSEC, RMSEP and ARE is 0.997 5, 0.003 5 Wt%, 0.006 1 Wt% and 2.500%, respectively. Compared with the traditional univariate and partial least square regression, the CART regression tree model has higher accuracy and lower error. Through effective screening of characteristic variables, this paper eliminates the interference of irrelevant signals, significantly reduces the influence of matrix effect and self-absorption effect on LIBS quantitative analysis, and improves the accuracy and stability of quantitative analysis.
|
Received: 2020-10-10
Accepted: 2021-02-04
|
|
Corresponding Authors:
LIN Jing-jun, LIN Xiao-mei
E-mail: 1124270941@qq.com;187049860@qq.com
|
|
[1] Guo L B, Zhu Z H, Li J M, et al. Optics Express, 2018, 26(3): 2634.
[2] YANG Ming-qing, WANG Chao, YAN Zhi-quan(杨明清, 王 超, 阎治全). China Petroleum Exploration(中国石油勘探), 2018, 23(1): 117.
[3] GUO Jin-jia, LU Yuan, et al(郭金家, 卢 渊, 等). Journal of Atmospheric and Environmental Optics(大气与环境光学学报), 2020, 15(1): 13.
[4] Shin Sungho, Moon Youngmin, Lee Jaepil. Plasma Science and Technology, 2019, 21(3): 34011.
[5] YANG You-sheng, ZHANG Yan, et al(杨友盛, 张 岩, 等). Laser & Optoelectronics Progress(激光与光电子学进展), 2015, 52(5): 053001.
[6] ZHANG Lei, WANG Zhe, DING Hong-bin, et al(张 磊, 王 哲, 丁洪斌,等). Journal of Atmospheric and Environmental Optics(大气与环境光学学报), 2016, 11(5): 338.
[7] XIN Yong, LI Yang, CAI Zhen-rong, et al(辛 勇, 李 洋, 蔡振荣, 等). Metallurgical Analysis(冶金分析), 2019, 39(1): 15.
[8] Bilge G, Sezer B, Boyaci I H, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2018, 145: 115.
[9] Jun H M, Kim J H, Lee S H, et al. Energy, 2018, 160: 225.
[10] ZHANG Le-hao, ZHANG Li, WU Zhong-chen, et al(张乐豪, 张 立, 武中臣, 等). Acta Photonica Sinica(光子学报), 2020,(6): 0630002.
[11] WU Yi-qing, SUN Tong, LIU Jin, et al(吴宜青, 孙 通, 刘 津, 等). Laser & Optoelectronics Progress(激光与光电子学进展), 2018, 55(1): 013005.
[12] HU Li, ZHAO Nan-jing, et al(胡 丽, 赵南京, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(8): 2585.
[13] GUO Kai-chen, WU Zhong-chen, ZHU Xiang-ping, et al(郭恺琛, 武中臣, 朱香平, 等). Acta Photonica Sinica(光子学报), 2019, 48(10): 1030002.
[14] Sun Chen, Tian Ye, Gao Liang, et al. Scientific Reports, 2019, 9(1): 11363.
[15] Ma F, et al. Journal of Analytical Atomic Spectrometry, 2020, 35: 478. |
[1] |
LIU Jia1, 2, GUO Fei-fei2, YU Lei2, CUI Fei-peng2, ZHAO Ying2, HAN Bing2, SHEN Xue-jing1, 2, WANG Hai-zhou1, 2*. Quantitative Characterization of Components in Neodymium Iron Boron Permanent Magnets by Laser Induced Breakdown Spectroscopy (LIBS)[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 141-147. |
[2] |
LIU Hao-dong1, 2, JIANG Xi-quan1, 2, NIU Hao1, 2, LIU Yu-bo1, LI Hui2, LIU Yuan2, Wei Zhang2, LI Lu-yan1, CHEN Ting1,ZHAO Yan-jie1*,NI Jia-sheng2*. Quantitative Analysis of Ethanol Based on Laser Raman Spectroscopy Normalization Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3820-3825. |
[3] |
YANG Wen-feng1, LIN De-hui1, CAO Yu2, QIAN Zi-ran1, LI Shao-long1, ZHU De-hua2, LI Guo1, ZHANG Sai1. Study on LIBS Online Monitoring of Aircraft Skin Laser Layered Paint Removal Based on PCA-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3891-3898. |
[4] |
LIN Hong-jian1, ZHAI Juan1*, LAI Wan-chang1, ZENG Chen-hao1, 2, ZHAO Zi-qi1, SHI Jie1, ZHOU Jin-ge1. Determination of Mn, Co, Ni in Ternary Cathode Materials With
Homologous Correction EDXRF Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3436-3444. |
[5] |
HUANG Li, MA Rui-jun*, CHEN Yu*, CAI Xiang, YAN Zhen-feng, TANG Hao, LI Yan-fen. Experimental Study on Rapid Detection of Various Organophosphorus Pesticides in Water by UV-Vis Spectroscopy and Parallel Factor Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3452-3460. |
[6] |
LI Zhong-bing1, 2, JIANG Chuan-dong2, LIANG Hai-bo3, DUAN Hong-ming2, PANG Wei2. Rough and Fine Selection Strategy Binary Gray Wolf Optimization
Algorithm for Infrared Spectral Feature Selection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3067-3074. |
[7] |
SUN Cheng-yu1, JIAO Long1*, YAN Na-ying1, YAN Chun-hua1, QU Le2, ZHANG Sheng-rui3, MA Ling1. Identification of Salvia Miltiorrhiza From Different Origins by Laser
Induced Breakdown Spectroscopy Combined with Artificial Neural
Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3098-3104. |
[8] |
LIU Shu1, JIN Yue1, 2, SU Piao1, 2, MIN Hong1, AN Ya-rui2, WU Xiao-hong1*. Determination of Calcium, Magnesium, Aluminium and Silicon Content in Iron Ore Using Laser-Induced Breakdown Spectroscopy Assisted by Variable Importance-Back Propagation Artificial Neural Networks[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3132-3142. |
[9] |
KONG De-ming1, LIU Ya-ru1, DU Ya-xin2, CUI Yao-yao2. Oil Film Thickness Detection Based on IRF-IVSO Wavelength Optimization Combined With LIF Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2811-2817. |
[10] |
ZHAO Yu-wen1, ZHANG Ze-shuai1, ZHU Xiao-ying1, WANG Hai-xia1, 2*, LI Zheng1, 2, LU Hong-wei3, XI Meng3. Application Strategies of Surface-Enhanced Raman Spectroscopy in Simultaneous Detection of Multiple Pathogens[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2012-2018. |
[11] |
LI Chang-ming1, CHEN An-min2*, GAO Xun3*, JIN Ming-xing2. Spatially Resolved Laser-Induced Plasma Spectroscopy Under Different Sample Temperatures[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2032-2036. |
[12] |
ZHAO Yang1, ZHANG Lei2, 3*, CHENG Nian-kai4, YIN Wang-bao2, 3*, HOU Jia-jia5, BAI Cheng-hua1. Research on Space-Time Evolutionary Mechanisms of Species Distribution in Laser Induced Binary Plasma[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2067-2073. |
[13] |
WANG Bin1, 2, ZHENG Shao-feng2, GAN Jiu-lin1, LIU Shu3, LI Wei-cai2, YANG Zhong-min1, SONG Wu-yuan4*. Plastic Reference Material (PRM) Combined With Partial Least Square (PLS) in Laser-Induced Breakdown Spectroscopy (LIBS) in the Field of Quantitative Elemental Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2124-2131. |
[14] |
CHENG Xiao-xiang1, WU Na2, LIU Wei2*, WANG Ke-qing2, LI Chen-yuan1, CHEN Kun-long1, LI Yan-xiang1*. Research on Quantitative Model of Corrosion Products of Iron Artefacts Based on Raman Spectroscopic Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2166-2173. |
[15] |
HU Meng-ying1, 2, ZHANG Peng-peng1, 2, LIU Bin1, 2, DU Xue-miao1, 2, ZHANG Ling-huo1, 2, XU Jin-li1, 2*, BAI Jin-feng1, 2. Determination of Si, Al, Fe, K in Soil by High Pressure Pelletised Sample and Laser-Induced Breakdown Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2174-2180. |
|
|
|
|