| ELECTROMAGNETISM, OPTICS, ACOUSTICS, HEAT TRANSFER, CLASSICAL MECHANICS, AND FLUID DYNAMICS |
Prev
Next
|
|
|
Effect of the target positions on the rapid identification of aluminum alloys by using filament-induced breakdown spectroscopy combined with machine learning |
| Xiaoguang Li(李晓光)1, Xuetong Lu(陆雪童)2, Yong Zhang(张勇)1, Shaozhong Song(宋少忠)3,†, Zuoqiang Hao(郝作强)4, and Xun Gao(高勋)2,‡ |
1 School of Electrical Information, Changchun Guanghua University, Changchun 130033, China;
2 School of Physics, Changchun University of Technology, Changchun 130600, China;
3 School of Information Engineering, Jilin Engineering Normal University, Changchun 130052, China;
4 School of Physics and Electronic Sciences, Shandong Normal University, Jinan 250358, China |
|
|
|
|
Abstract Filament-induced breakdown spectroscopy (FIBS) combined with machine learning algorithms was used to identify five aluminum alloys. To study the effect of the distance between focusing lens and target surface on the identification accuracy of aluminum alloys, principal component analysis (PCA) combined with support vector machine (SVM) and K-nearest neighbor (KNN) was used. The intensity and intensity ratio of fifteen lines of six elements (Fe, Si, Mg, Cu, Zn, and Mn) in the FIBS spectrum were selected. The distances between the focusing lens and the target surface in the pre-filament, filament, and post-filament were 958 mm, 976 mm, and 1000 mm, respectively. The source data set was fifteen spectral line intensity ratios, and the cumulative interpretation rates of PC1, PC2, and PC3 were 97.22%, 98.17%, and 95.31%, respectively. The first three PCs obtained by PCA were the input variables of SVM and KNN. The identification accuracy of the different positions of focusing lens and target surface was obtained, and the identification accuracy of SVM and KNN in the filament was 100% and 90%, respectively. The source data set of the filament was obtained by PCA for the first three PCs, which were randomly selected as the training set and test set of SVM and KNN in 3:2. The identification accuracy of SVM and KNN was 97.5% and 92.5%, respectively. The research results can provide a reference for the identification of aluminum alloys by FIBS.
|
Received: 22 August 2021
Revised: 06 November 2021
Accepted manuscript online:
|
|
PACS:
|
42.62.Fi
|
(Laser spectroscopy)
|
| |
52.38.Hb
|
(Self-focussing, channeling, and filamentation in plasmas)
|
|
| Fund: Project supported by the Natural Science Foundation of Jilin Province,China (Grant No.2020122348JC). |
Corresponding Authors:
Shaozhong Song,E-mail:songsz@jlenu.edu.cn;Xun Gao,E-mail:lasercust@163.com
E-mail: songsz@jlenu.edu.cn;lasercust@163.com
|
| About author: 2021-11-10 |
Cite this article:
Xiaoguang Li(李晓光), Xuetong Lu(陆雪童), Yong Zhang(张勇),Shaozhong Song(宋少忠), Zuoqiang Hao(郝作强), and Xun Gao(高勋) Effect of the target positions on the rapid identification of aluminum alloys by using filament-induced breakdown spectroscopy combined with machine learning 2022 Chin. Phys. B 31 054212
|
[1] Noll R, Fricke-Begemann C, Connemann S, Meinhardt C and Sturm V 2018 J. Anal. At. Spectrom. 33 945
[2] Chen C T, Banaru D, Sarnet T and Hermann J 2018 Spectrochim. Acta, Part B 150 77
[3] Byram C, Moram S S B, Shaik A K and Soma V R 2017 Chem. Phys. Lett. 685 103
[4] Rethfeld B, Ivanov D S, Garcia M E and Anisimov S I 2017 J. Phys. D: Appl. Phys. 50 193001
[5] Labutin T A, Lednev V N, Ilyin A A, et al. 2015 Journal of Analytical Atomic Spectrometry 31 90
[6] Freeman J R, Harilal S S, Diwakar P K, Verhoff B and Hassanein A 2013 Spectrochim. Acta, Part B 87 43
[7] Deng Y P, Zhu J B, Ji Z G, Liu J S and Chin S L 2006 Opt. Lett. 31 546
[8] Zhao S Y, Gao X, Song X W, Yao S and Lin J Q 2019 OSA Continuum 2 116
[9] Gao X, Du C, Li C, Liu L, Song C, Hao Z Q and Lin J Q 2014 Acta Phys. Sin. 63 095203 (in Chinese)
[10] Abdul K S And Venugopal R S 2019 OSA Continuum 2 554
[11] Li H L,Zang H W,Xn H L,Sun H B, Baltuška A and Polynkin P 2019 Glob Chall 3 1800070
[12] Xu H L, Liu W and Chin S L 2006 Opt. Lett. 31 1540
[13] Hartig K C, Ghebregziabher I and Jovanovic I 2017 Sci. Rep. 7 43852
[14] Fu Y, Hou M Y, Zang H W, Li H, Chin S L and Xu H 2019 Spectrochim. Acta, Part B 155 107
[15] Abdul K S, Nageswara R E, Hamad S and Byram C 2018 Opt. Express 26 8069
[16] Abdul K S, Ajmathulla and Venugopal R S. 2018 Opt. Lett. 43 3465
[17] Rajendhar J and Manoj K G 2019 J. Anal. At. Spectrom. 34 1683
[18] Narla L M and Rao S V 2020 Appl. Phys. B 126 18
[19] Kalam S A, Rao S V B M, Jayananda M and Rao S V 2020 J. Anal. At. Spectrom. 35 3007
[20] Wang W, Sun L X, Wang G D, Zhang P and Dong W 2020 J. Anal. At. Spectrom. 35 357
[21] Harilal S S, Diwakar P K, Polek M P and Phillips M C 2015 Opt. Express 23 15608
[22] Harilal S S, Yeak J and Phillips M C 2015 Opt. Express 23 27113
[23] Yao S, Zhang J, Gao X, Zhao S Y and Lin J Q 2018 Opt. Commun. 425 152
[24] Xu W P, Chen A M, Wang Q Y, Zhang D, Wang Y, Li S Y, Jiang Y F and Jin M X 2019 J. Anal. At. Spectrom. 34 1018
[25] Harilal S S, Yeak J, Brumfield B E and Phillips M C 2016 Opt. Express 24 17941
[26] Lu X T, Zhao S Y, Gao X, Guo K M and Lin J Q 2020 Chin. Phys. B 29 124209
[27] Daniel D, Alejandro M and Hahn D W 2019 Appl. Spectrosc. 74 42
[28] Sitangshu C, Manjeet S, Bishnu P B, Uday K S, Suraj P and Arnab S 2019 Anal. Bioanal. Chem. 411 2855
[29] Li W T, Zhu Y N, Li X, Hao Z Q, Guo L B, Li X Y, Zeng X Y and Lu Y F 2018 J. Anal. At. Spectrom. 33 461
[30] Pathak A K, Singh A, Kumar R and Rai A K 2018 Natl. Acad. Sci. Lett. 42 87
[31] Liu X D, Feng X P and He Y 2019 Renew. Energ. 143 176
[32] Lu Y Y, Boukharouba K, Boonaert J, Fleury A and Lecoeuche S 2014 Neurocomputing 126 132
[33] Jia J W, Fu H B, Hou Z Y, Wang D H, Ni Z B and Dong F Z 2018 Plasma Sci. Technol. 21 034003
[34] Wang Q Q, Teng G, Li C Y, Zhao Y and Peng Z 2019 J. Hazard. Mater. 369 423
[35] Chen X, Li X H, Yu X, Chen D Y and Liu A C 2018 Spectrochim. Acta, Part B 139 63
[36] Lu X N, Deng L, Du J C and Vienna J D 2020 J Non Cryst Solids 553 120490
[37] Guo L B, Hao R F, Hao Z Q, Li K H and Zeng X Y 2013 Acta Phys. Sin. 62 224211 (in Chinese)
[38] Jin J, Chen Y, Pei L S, Hu C J, Ma X X and Chen C X 2000 Acta Phys. Sin. 49 1689 (in Chinese)
[39] Couairon A and Mysyrowicz A 2007 Phys. Rep. 441 47
[40] Li S Y, Guo F M, Song Y, Chen A M and Jin M X 2014 Phys. Rev. A 89 023809
[41] Anabitarte F, Mirapeix J, Portilla O, Lopez-Higuera J and Cobo A 2012 IEEE. Sens. J. 12 64
[42] Campanella B, Grifoni E, Legnaioli S, Lorenzetti G, Pagnotta S, Sorrentino F and Palleschi V 2017 Spectrochim. Acta, Part B 134 52
[43] Liu W, Théberge F, Arévalo E, Gravel J F and Chin S L 2005 Opt. Lett. 30 2602
[44] Valenzuela A, Munson C, Porwitzky A, Weidman M and Richardson M 2014 Appl. Phys. B 116 485
[45] Zhu X Q, Xu T, Lin Q Y, Liang L, Niu G H, Lai H J, Xu M J, Wang X, Li H and Duan Y X 2014 Spectrochim. Acta, Part B 93 8 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
