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

Yangmin Guo, Yun Tang, Yu Du, Shisong Tang, Lianbo Guo, Xiangyou Li, Yongfeng Lu, Xiaoyan Zeng

Research output: Contribution to journalArticle

2 Citations (Scopus)

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.

Original languageEnglish (US)
Article number065505
JournalPlasma Science and Technology
Volume20
Issue number6
DOIs
StatePublished - Jun 2018

Fingerprint

cluster analysis
laser-induced breakdown spectroscopy
polymers
meteorology
recycling
learning
line spectra
standard deviation
interference

Keywords

  • K-means
  • laser-induced breakdown spectroscopy
  • polymers

ASJC Scopus subject areas

  • Condensed Matter Physics

Cite this

Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means. / Guo, Yangmin; Tang, Yun; Du, Yu; Tang, Shisong; Guo, Lianbo; Li, Xiangyou; Lu, Yongfeng; Zeng, Xiaoyan.

In: Plasma Science and Technology, Vol. 20, No. 6, 065505, 06.2018.

Research output: Contribution to journalArticle

Guo, Yangmin ; Tang, Yun ; Du, Yu ; Tang, Shisong ; Guo, Lianbo ; Li, Xiangyou ; Lu, Yongfeng ; Zeng, Xiaoyan. / Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means. In: Plasma Science and Technology. 2018 ; Vol. 20, No. 6.
@article{50898b5bd1a2438bb7b70dbc91342daf,
title = "Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means",
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.",
keywords = "K-means, laser-induced breakdown spectroscopy, polymers",
author = "Yangmin Guo and Yun Tang and Yu Du and Shisong Tang and Lianbo Guo and Xiangyou Li and Yongfeng Lu and Xiaoyan Zeng",
year = "2018",
month = "6",
doi = "10.1088/2058-6272/aaaade",
language = "English (US)",
volume = "20",
journal = "Plasma Science and Technology",
issn = "1009-0630",
publisher = "IOP Publishing Ltd.",
number = "6",

}

TY - JOUR

T1 - Cluster analysis of polymers using laser-induced breakdown spectroscopy with K-means

AU - Guo, Yangmin

AU - Tang, Yun

AU - Du, Yu

AU - Tang, Shisong

AU - Guo, Lianbo

AU - Li, Xiangyou

AU - Lu, Yongfeng

AU - Zeng, Xiaoyan

PY - 2018/6

Y1 - 2018/6

N2 - 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.

AB - 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.

KW - K-means

KW - laser-induced breakdown spectroscopy

KW - polymers

UR - http://www.scopus.com/inward/record.url?scp=85047155454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047155454&partnerID=8YFLogxK

U2 - 10.1088/2058-6272/aaaade

DO - 10.1088/2058-6272/aaaade

M3 - Article

AN - SCOPUS:85047155454

VL - 20

JO - Plasma Science and Technology

JF - Plasma Science and Technology

SN - 1009-0630

IS - 6

M1 - 065505

ER -