Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means

Yangmin GUO (郭阳敏); Yun TANG (唐云); Yu DU (杜宇); Shisong TANG (唐仕松); Lianbo GUO (郭连波); Xiangyou LI (李祥友); Yongfeng LU (陆永枫); Xiaoyan ZENG (曾晓雁)

doi:10.1088/2058-6272/aaaade

Plasma Science and Technology > 2018 > 20(6): 65505-065505. > DOI: 10.1088/2058-6272/aaaade

Yangmin GUO (郭阳敏), Yun TANG (唐云), Yu DU (杜宇), Shisong TANG (唐仕松), Lianbo GUO (郭连波), Xiangyou LI (李祥友), Yongfeng LU (陆永枫), Xiaoyan ZENG (曾晓雁). Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means[J]. Plasma Science and Technology, 2018, 20(6): 65505-065505. DOI: 10.1088/2058-6272/aaaade

Citation:

PDF (737 KB)

Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means

¹ Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology (HUST), Wuhan 430074, People’s Republic of China
² Department of Electronic and Information Engineering, Hunan University of Science and Engi-neering, Yongzhou 425199, People’s Republic of China
³ College of Communication Engineering, Jilin University, Changchun 130012, People’s Republic of China

Funds: This work is supported by National Natural Science Foundation of China (Nos. 61575073 and 51429501).

More Information

Received Date: December 17, 2017

Graphical Abstract

Abstract

Abstract

Laser-induced breakdown spectroscopy (LIBS) combined with K-means algorithm was employed to automatically differentiate industrial polymers under atmospheric conditions. The unsupervised learning algorithm K-means were utilized for the clustering of LIBS dataset measured from twenty kinds of industrial polymers. To prevent the interference from metallic elements, three atomic emission lines (C I 247.86 nm, H I 656.3 nm, and O I 777.3 nm) and one molecular line C–N (0, 0) 388.3 nm were used. The cluster analysis results were obtained through an iterative process. The Davies–Bouldin index was employed to determine the initial number of clusters. The average relative standard deviation values of characteristic spectral lines were used as the iterative criterion. With the proposed approach, the classification accuracy for twenty kinds of industrial polymers achieved 99.6%. The results demonstrated that this approach has great potential for industrial polymers recycling by LIBS.
- laser-induced breakdown spectroscopy,
- polymers,
- K-means

FullText(HTML)

References (25)

References

[1]	Geyer R, Jambeck J R and Law K L 2017 Sci. Adv. 3 e1700782
[2]	Bhadra J, Al-Thani N and Abdulkareem A 2017 Recycling of polymer-polymer composites Micro and Nano Fibrillar Composites (MFCs and NFCs) from Polymer Blends ed R K Mishra et al (Amsterdam: Elsevier)
[3]	Feldhoff R et al 1997 Appl. Spectrosc. 51 362
[4]	Boeykens S and Vázquez C 2004 Spectrochim. Acta B 59 1189
[5]	Allen V, Kalivas J H and Rodriguez R G 1999 Appl. Spectrosc. 53 672
[6]	Dinger P 1992 BioCycle 33 80
[7]	Fortes F J 2013 Anal. Chem. 85 640
[8]	Hahn D W and Omenetto N 2012 Appl. Spectrosc. 66 347
[9]	Wang Z et al 2014 Front. Phys. 9 419
[10]	Knight A K et al 2000 Appl. Spectrosc. 54 331
[11]	Gaudiuso R et al 2010 Sensors 10 7434
[12]	Wang Q Q et al 2012 Front. Phys. 7 701
[13]	Cheng X et al 2017 Appl. Opt. 56 9144
[14]	Boueri M et al 2011 Appl. Spectrosc. 65 307
[15]	Anzano J et al 2008 Polym. Test. 27 705
[16]	Banaee M and Tavassoli S H 2012 Polym. Test. 31 759
[17]	Yu Y et al 2014 Opt. Express 22 3895
[18]	He L A et al 2016 Plasma Sci. Technol. 18 647
[19]	Costa V C et al 2017 Polym. Test. 59 390
[20]	Maulik U and Bandyopadhyay S 2002 IEEE Trans. Pattern Anal. Mach. Intell. 24 1650
[21]	Baudelet M et al 2007 Spectrochim. Acta B 62 1329
[22]	Multari R A, Cremers D A and Bostian M L 2012 Appl. Opt. 51 B57
[23]	Luo Q et al 2006 Appl. Phys. B 82 105
[24]	Hartigan J A and Wong M A 1979 Appl. Stat. 28 100
[25]	Chaves R et al 2009 Neurosci. Lett. 461 293