Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Yihan LYU; Weiran SONG; Zongyu HOU; Zhe WANG

doi:10.1088/2058-6272/ad370c

Plasma Science and Technology > 2024 > 26(7): 075509. > DOI: 10.1088/2058-6272/ad370c

Yihan LYU, Weiran SONG, Zongyu HOU, Zhe WANG. Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy[J]. Plasma Science and Technology, 2024, 26(7): 075509. DOI: 10.1088/2058-6272/ad370c

Citation:

PDF (1376 KB)

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

1.
State Key Laboratory of Power System Operation and Control, International Joint Laboratory on Low Carbon Clean Energy Innovation, Department of Energy and Power Engineering, Tsinghua University, Beijing 100084, People’s Republic of China
2.
Tsinghua University, Shanxi Research Institute Clean Energy, Taiyuan 030032, People’s Republic of China
3.
School of Energy and Electrical Engineering, Qinghai University, Xining 810016, People’s Republic of China

More Information

Author Bio:
Zhe WANG: zhewang@tsinghua.edu.cn
Corresponding author:
Zhe WANG, zhewang@tsinghua.edu.cn
Received Date: December 28, 2023
Revised Date: March 20, 2024
Accepted Date: March 21, 2024
Available Online: March 22, 2024
Published Date: June 26, 2024

Graphical Abstract

Abstract

Abstract

Laser-induced breakdown spectroscopy (LIBS) has become a widely used atomic spectroscopic technique for rapid coal analysis. However, the vast amount of spectral information in LIBS contains signal uncertainty, which can affect its quantification performance. In this work, we propose a hybrid variable selection method to improve the performance of LIBS quantification. Important variables are first identified using Pearson’s correlation coefficient, mutual information, least absolute shrinkage and selection operator (LASSO) and random forest, and then filtered and combined with empirical variables related to fingerprint elements of coal ash content. Subsequently, these variables are fed into a partial least squares regression (PLSR). Additionally, in some models, certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance. The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method. It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method. The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction (RMSEP) values of 1.605, 3.478 and 1.647, respectively, which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables, which are 1.959, 3.718 and 2.181, respectively. The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection, with RMSEP values dropping from 1.635, 3.962 and 1.647 to 1.483, 3.086 and 1.567, respectively. Such results demonstrate that using empirical knowledge as a support for data-driven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

FullText(HTML)

Acknowledgments

The authors are grateful for financial supports from National Natural Science Foundation of China (No. 62205172), Huaneng Group Science and Technology Research Project (No. HNKJ22-H105), Tsinghua University Initiative Scientific Research Program and the International Joint Mission on Climate Change and Carbon Neutrality.

References (32)

References

[1]	Sheta S et al 2019 J. Anal. At. Spectrom. 34 1047 doi: 10.1039/C9JA00016J
[2]	Winefordner J D et al 2004 J. Anal. At. Spectrom. 19 1061 doi: 10.1039/b400355c
[3]	Hu Z L et al 2022 Trends Analyt. Chem. 152 116618 doi: 10.1016/j.trac.2022.116618
[4]	Wang Z et al 2021 Trends Analyt. Chem. 143 116385 doi: 10.1016/j.trac.2021.116385
[5]	Li X L et al 2023 J. Hazard. Mater. 448 130885 doi: 10.1016/j.jhazmat.2023.130885
[6]	Hou Z Y et al 2016 J. Anal. At. Spectrom. 31 722 doi: 10.1039/C5JA00475F
[7]	Gu W L et al 2022 Anal. Chim. Acta 1205 339752 doi: 10.1016/j.aca.2022.339752
[8]	Song W R et al 2021 J. Anal. At. Spectrom. 36 111 doi: 10.1039/D0JA00386G
[9]	Cui X T et al 2021 Plasma Sci. Technol. 23 055505 doi: 10.1088/2058-6272/abf1ac
[10]	Dong M R et al 2019 J. Anal. At. Spectrom. 34 480 doi: 10.1039/C8JA00414E
[11]	Xing P J et al 2021 Anal. Chim. Acta 1178 338799 doi: 10.1016/j.aca.2021.338799
[12]	Guezenoc J et al 2017 Spectrochim. Acta Part B: At. Spectrosc. 134 6 doi: 10.1016/j.sab.2017.05.009
[13]	Bachler M O et al 2016 Spectrochim. Acta Part B: At. Spectrosc. 123 163 doi: 10.1016/j.sab.2016.08.010
[14]	Yang N F et al 2010 Soil Sci. 175 447 doi: 10.1097/SS.0b013e3181f516ea
[15]	Yao S C et al 2020 Spectrochim. Acta Part A: Mol. Biomol. Spectrosc. 239 118492 doi: 10.1016/j.saa.2020.118492
[16]	Legnaioli S et al 2019 Spectrochim. Acta Part B: At. Spectrosc. 155 123 doi: 10.1016/j.sab.2019.03.012
[17]	Zhang Y J et al 2020 Anal. Methods 12 3530 doi: 10.1039/D0AY00905A
[18]	Duan F J et al 2018 Spectrochim. Acta Part B: At. Spectrosc. 143 12 doi: 10.1016/j.sab.2018.02.010
[19]	Lu S Z et al 2018 Spectrochim. Acta Part B: At. Spectrosc. 150 49 doi: 10.1016/j.sab.2018.10.006
[20]	Huang L X et al 2019 J. Anal. At. Spectrom. 34 460 doi: 10.1039/C8JA00442K
[21]	Li M G et al 2022 J. Anal. At. Spectrom. 37 1099 doi: 10.1039/D2JA00048B
[22]	Zhao Q et al 2023 Spectrochim. Acta Part: A. Mol. Biomol. Spectrosc. 287 122053 doi: 10.1016/j.saa.2022.122053
[23]	Song X Y et al 2022 Optik 249 168214 doi: 10.1016/j.ijleo.2021.168214
[24]	Song W R et al 2022 Spectrochim. Acta Part B: At. Spectrosc. 195 106490 doi: 10.1016/j.sab.2022.106490
[25]	Song W R et al 2022 Expert Syst. Appl. 205 117756 doi: 10.1016/j.eswa.2022.117756
[26]	Feng J et al 2011 Anal. Bioanal. Chem. 400 3261 doi: 10.1007/s00216-011-4865-y
[27]	Hou Z Y et al 2022 Spectrochim. Acta Part B: At. Spectrosc. 191 106406 doi: 10.1016/j.sab.2022.106406
[28]	Song W R et al 2021 Fuel 306 121667 doi: 10.1016/j.fuel.2021.121667
[29]	Menze B H, Petrich W and Hamprecht F A 2007 Anal. Bioanal. Chem. 387 1801 doi: 10.1007/s00216-006-1070-5
[30]	Menze B H et al 2009 BMC Bioinformatics 10 213 doi: 10.1186/1471-2105-10-213
[31]	Wold S, Sjöström M and Eriksson L 2001 Chemometr. Intell. Lab. Syst. 58 109 doi: 10.1016/S0169-7439(01)00155-1
[32]	Mehmood T and Ahmed B 2016 J. Chemom. 30 4 doi: 10.1002/cem.2762

[1]	Luyun JIANG, Yutong CHEN, Chentao MAO, Jianhui HAN, Anmin CHEN, Jifei YE. Performance optimization of ammonium dinitramide-based liquid propellant in pulsed laser ablation micro-propulsion using LIBS[J]. Plasma Science and Technology, 2025, 27(1): 015503. DOI: 10.1088/2058-6272/ad92f8
[2]	Junwei JIA, Zhifeng LIU, Congyuan PAN, Huaqin XUE. Detection of Al, Mg, Ca, and Zn in copper slag by LIBS combined with calibration curve and PLSR methods[J]. Plasma Science and Technology, 2024, 26(2): 025507. DOI: 10.1088/2058-6272/ad1045
[3]	Jiajia HOU (侯佳佳), Lei ZHANG (张雷), Yang ZHAO (赵洋), Zhe WANG (王哲), Yong ZHANG (张勇), Weiguang MA (马维光), Lei DONG (董磊), Wangbao YIN (尹王保), Liantuan XIAO (肖连团), Suotang JIA (贾锁堂). Mechanisms and efficient elimination approaches of self-absorption in LIBS[J]. Plasma Science and Technology, 2019, 21(3): 34016-034016. DOI: 10.1088/2058-6272/aaf875
[4]	Xiaomeng LI (李晓萌), Huili LU (陆慧丽), Jianhong YANG (阳建宏), Fu CHANG (常福). Semi-supervised LIBS quantitative analysis method based on co-training regression model with selection of effective unlabeled samples[J]. Plasma Science and Technology, 2019, 21(3): 34015-034015. DOI: 10.1088/2058-6272/aaee14
[5]	Haobin PENG (彭浩斌), Guohua CHEN (陈国华), Xiaoxuan CHEN (陈小玄), Zhimin LU (卢志民), Shunchun YAO (姚顺春). Hybrid classification of coal and biomass by laser-induced breakdown spectroscopy combined with K-means and SVM[J]. Plasma Science and Technology, 2019, 21(3): 34008-034008. DOI: 10.1088/2058-6272/aaebc4
[6]	Shuxia ZHAO (赵书霞), Lei ZHANG (张雷), Jiajia HOU (侯佳佳), Yang ZHAO (赵洋), Wangbao YIN (尹王保), Weiguang MA (马维光), Lei DONG (董磊), Liantuan XIAO (肖连团), Suotang JIA (贾锁堂). Accurate quantitative CF-LIBS analysis of both major and minor elements in alloys via iterative correction of plasma temperature and spectral intensity[J]. Plasma Science and Technology, 2018, 20(3): 35502-035502. DOI: 10.1088/2058-6272/aa97ce
[7]	F. MEHARI, M. ROHDE, C. KNIPFER, R. KANAWADE, F. KL¨AMPFL, W. ADLER, N. OETTER, F. STELZLE, M. SCHMIDT. Investigation of Laser Induced Breakdown Spectroscopy (LIBS) for the Differentiation of Nerve and Gland Tissue–A Possible Application for a Laser Surgery Feedback Control Mechanism[J]. Plasma Science and Technology, 2016, 18(6): 654-660. DOI: 10.1088/1009-0630/18/6/12
[8]	LI Xiongwei (李雄威), MAO Xianglei (毛向雷), WANG Zhe (王哲), Richard E. RUSSO. Quantitative Analysis of Carbon Content in Bituminous Coal by Laser-Induced Breakdown Spectroscopy Using UV Laser Radiation[J]. Plasma Science and Technology, 2015, 17(11): 928-932. DOI: 10.1088/1009-0630/17/11/07
[9]	YANG Guang (杨光), QIAO Shujun (乔淑君), CHEN Pengfei (陈鹏飞), DING Yu (丁宇), TIAN Di (田地). Rock and Soil Classification Using PLS-DA and SVM Combined with a Laser-Induced Breakdown Spectroscopy Library[J]. Plasma Science and Technology, 2015, 17(8): 656-663. DOI: 10.1088/1009-0630/17/8/08
[10]	WEN Guanhong(温冠宏), SUN Duixiong(孙对兄), SU Maogen(苏茂根), DONG Chenzhong(董晨钟). LIBS Detection of Heavy Metal Elements in Liquid Solutions by Using Wood Pellet as Sample Matrix[J]. Plasma Science and Technology, 2014, 16(6): 598-601. DOI: 10.1088/1009-0630/16/6/11

Cited By

Cited by

Periodical cited type(14)

1.	Zheng, Z.-H., Shi, Y., Du, J. et al. Research on the calorific value detection method and influencing mechanism of solid materials via EDXRF. Spectrochimica Acta - Part B Atomic Spectroscopy, 2025. DOI:10.1016/j.sab.2025.107154
2.	Dong, M., Cai, J., Liu, H. et al. A review of laser-induced breakdown spectroscopy and spontaneous emission techniques in monitoring thermal conversion of fuels. Spectrochimica Acta - Part B Atomic Spectroscopy, 2023. DOI:10.1016/j.sab.2023.106807
3.	Zhang, C., Song, W., Hou, Z. et al. Improving quantitative analysis of cement elements in laser-induced breakdown spectroscopy through combining matrix matching with regression. Journal of Analytical Atomic Spectrometry, 2023, 38(12): 2554-2561. DOI:10.1039/d3ja00306j
4.	Yao, S., Yu, Z., Xu, S. et al. Investigation on Laser-induced Plasma Characterization of Coal Under Argon Atmosphere \| [氩气环境下煤炭的激光诱导等离子体特性研究]. Kung Cheng Je Wu Li Hsueh Pao/Journal of Engineering Thermophysics, 2023, 44(11): 3140-3150.
5.	Dou, Y., Wang, Q., Wang, S. et al. Quantitative Analysis of Coal Quality by a Portable Laser Induced Breakdown Spectroscopy and Three Chemometrics Methods. Applied Sciences (Switzerland), 2023, 13(18): 10049. DOI:10.3390/app131810049
6.	Long, J., Song, W., Hou, Z. et al. A data selection method for matrix effects and uncertainty reduction for laser-induced breakdown spectroscopy. Plasma Science and Technology, 2023, 25(7): 075501. DOI:10.1088/2058-6272/acb6dd
7.	Guan, C., Wu, T., Chen, J. et al. Detection of Carbon Content from Pulverized Coal Using LIBS Coupled with DSC-PLS Method. Chemosensors, 2022, 10(11): 490. DOI:10.3390/chemosensors10110490
8.	Huang, Q., Jiang, Z., Xie, Y. et al. On-line detection method of silicon mass fraction in pig iron based on LIBS spectral line fitting optimization \| [基于LIBS谱线拟合优化的生铁硅质量分数在线检测方法]. Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and Technology), 2022, 53(4): 1167-1178. DOI:10.11817/j.issn.1672-7207.2022.04.002
9.	Zhang, D., Zhang, H., Zhao, Y. et al. A brief review of new data analysis methods of laser-induced breakdown spectroscopy: machine learning. Applied Spectroscopy Reviews, 2022, 57(2): 89-111. DOI:10.1080/05704928.2020.1843175
10.	Liu, K., He, C., Zhu, C. et al. A review of laser-induced breakdown spectroscopy for coal analysis. TrAC - Trends in Analytical Chemistry, 2021. DOI:10.1016/j.trac.2021.116357
11.	Chen, J., Zhan, K., Li, Q. et al. Spectral clustering based on histogram of oriented gradient (HOG) of coal using laser-induced breakdown spectroscopy. Journal of Analytical Atomic Spectrometry, 2021, 36(6): 1297-1305. DOI:10.1039/d1ja00104c
12.	Wang, Y., Li, R., Chen, Y. Accurate elemental analysis of alloy samples with high repetition rate laser-ablation spark-induced breakdown spectroscopy coupled with particle swarm optimization-extreme learning machine. Spectrochimica Acta - Part B Atomic Spectroscopy, 2021. DOI:10.1016/j.sab.2021.106077
13.	Chen, G., Wang, Q., Teng, G. et al. Influence of polarization of laser beam on emission intensity of nanosecond laser-induced breakdown spectroscopy. Proceedings of SPIE - The International Society for Optical Engineering, 2021. DOI:10.1117/12.2607071
14.	Liu, J., Dou, Y., Zuo, G. Design of sea ice monitoring UAV platform based on machine learning. Journal of Physics: Conference Series, 2020, 1654(1): 12067. DOI:10.1088/1742-6596/1654/1/012067