Fast Identification of Plastics with Laser-Induced Breakdown Spectroscopy

Qian Qian Sun, Min Du, Lian Bo Guo, Zhong Qi Hao, Rong Xing Yi, Jia Ming Li, Jian Guo Liu, Meng Shen, Xiang You Li, Xiao Yan Zeng, Yong Feng Lu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Laser-induced breakdown spectroscopy (LIBS) combined with support vector machine (SVM) was adopted to identify 20 kinds of different colored industrial plastics from different manufacturers in open air. The experimental parameters of spectral acquisition were optimized firstly. 100 spectra recorded under optimum conditions were randomly and equally divided into training set and test set. 6 non-metallic characteristic spectral lines were used to avoid the interference with metallic lines. And the training time of SVM model was reduced. The results show that 996 of 1000 test spectra were identified correctly and the average classification accuracy is reached to 99.6%. The classification efficiency is improved with 6 non-metallic characteristic spectral lines. The research demonstrates that, when fewer of major non-metallic characteristic spectral lines are used, laser-induced breakdown spectroscopy technique with support vector machine can identify more kinds of plastics with high accuracy and efficiency.

Original languageEnglish (US)
Pages (from-to)2205-2209
Number of pages5
JournalGuang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis
Volume37
Issue number7
DOIs
StatePublished - Jul 1 2017

Fingerprint

Laser induced breakdown spectroscopy
laser-induced breakdown spectroscopy
Support vector machines
line spectra
plastics
Plastics
education
acquisition
interference
air
Air

Keywords

  • Characteristic spectral lines of non-metallic elements
  • Laser-induced breakdown spectroscopy
  • Plastics identification
  • Support vector machine

ASJC Scopus subject areas

  • Instrumentation
  • Spectroscopy

Cite this

Fast Identification of Plastics with Laser-Induced Breakdown Spectroscopy. / Sun, Qian Qian; Du, Min; Guo, Lian Bo; Hao, Zhong Qi; Yi, Rong Xing; Li, Jia Ming; Liu, Jian Guo; Shen, Meng; Li, Xiang You; Zeng, Xiao Yan; Lu, Yong Feng.

In: Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis, Vol. 37, No. 7, 01.07.2017, p. 2205-2209.

Research output: Contribution to journalArticle

Sun, Qian Qian ; Du, Min ; Guo, Lian Bo ; Hao, Zhong Qi ; Yi, Rong Xing ; Li, Jia Ming ; Liu, Jian Guo ; Shen, Meng ; Li, Xiang You ; Zeng, Xiao Yan ; Lu, Yong Feng. / Fast Identification of Plastics with Laser-Induced Breakdown Spectroscopy. In: Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis. 2017 ; Vol. 37, No. 7. pp. 2205-2209.
@article{bd4a1addd3964745bb7a6842ba5946fc,
title = "Fast Identification of Plastics with Laser-Induced Breakdown Spectroscopy",
abstract = "Laser-induced breakdown spectroscopy (LIBS) combined with support vector machine (SVM) was adopted to identify 20 kinds of different colored industrial plastics from different manufacturers in open air. The experimental parameters of spectral acquisition were optimized firstly. 100 spectra recorded under optimum conditions were randomly and equally divided into training set and test set. 6 non-metallic characteristic spectral lines were used to avoid the interference with metallic lines. And the training time of SVM model was reduced. The results show that 996 of 1000 test spectra were identified correctly and the average classification accuracy is reached to 99.6{\%}. The classification efficiency is improved with 6 non-metallic characteristic spectral lines. The research demonstrates that, when fewer of major non-metallic characteristic spectral lines are used, laser-induced breakdown spectroscopy technique with support vector machine can identify more kinds of plastics with high accuracy and efficiency.",
keywords = "Characteristic spectral lines of non-metallic elements, Laser-induced breakdown spectroscopy, Plastics identification, Support vector machine",
author = "Sun, {Qian Qian} and Min Du and Guo, {Lian Bo} and Hao, {Zhong Qi} and Yi, {Rong Xing} and Li, {Jia Ming} and Liu, {Jian Guo} and Meng Shen and Li, {Xiang You} and Zeng, {Xiao Yan} and Lu, {Yong Feng}",
year = "2017",
month = "7",
day = "1",
doi = "10.3964/j.issn.1000-0593(2017)07-2205-05",
language = "English (US)",
volume = "37",
pages = "2205--2209",
journal = "Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis",
issn = "1000-0593",
publisher = "Science Press",
number = "7",

}

TY - JOUR

T1 - Fast Identification of Plastics with Laser-Induced Breakdown Spectroscopy

AU - Sun, Qian Qian

AU - Du, Min

AU - Guo, Lian Bo

AU - Hao, Zhong Qi

AU - Yi, Rong Xing

AU - Li, Jia Ming

AU - Liu, Jian Guo

AU - Shen, Meng

AU - Li, Xiang You

AU - Zeng, Xiao Yan

AU - Lu, Yong Feng

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Laser-induced breakdown spectroscopy (LIBS) combined with support vector machine (SVM) was adopted to identify 20 kinds of different colored industrial plastics from different manufacturers in open air. The experimental parameters of spectral acquisition were optimized firstly. 100 spectra recorded under optimum conditions were randomly and equally divided into training set and test set. 6 non-metallic characteristic spectral lines were used to avoid the interference with metallic lines. And the training time of SVM model was reduced. The results show that 996 of 1000 test spectra were identified correctly and the average classification accuracy is reached to 99.6%. The classification efficiency is improved with 6 non-metallic characteristic spectral lines. The research demonstrates that, when fewer of major non-metallic characteristic spectral lines are used, laser-induced breakdown spectroscopy technique with support vector machine can identify more kinds of plastics with high accuracy and efficiency.

AB - Laser-induced breakdown spectroscopy (LIBS) combined with support vector machine (SVM) was adopted to identify 20 kinds of different colored industrial plastics from different manufacturers in open air. The experimental parameters of spectral acquisition were optimized firstly. 100 spectra recorded under optimum conditions were randomly and equally divided into training set and test set. 6 non-metallic characteristic spectral lines were used to avoid the interference with metallic lines. And the training time of SVM model was reduced. The results show that 996 of 1000 test spectra were identified correctly and the average classification accuracy is reached to 99.6%. The classification efficiency is improved with 6 non-metallic characteristic spectral lines. The research demonstrates that, when fewer of major non-metallic characteristic spectral lines are used, laser-induced breakdown spectroscopy technique with support vector machine can identify more kinds of plastics with high accuracy and efficiency.

KW - Characteristic spectral lines of non-metallic elements

KW - Laser-induced breakdown spectroscopy

KW - Plastics identification

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85030645365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030645365&partnerID=8YFLogxK

U2 - 10.3964/j.issn.1000-0593(2017)07-2205-05

DO - 10.3964/j.issn.1000-0593(2017)07-2205-05

M3 - Article

AN - SCOPUS:85030645365

VL - 37

SP - 2205

EP - 2209

JO - Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis

JF - Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis

SN - 1000-0593

IS - 7

ER -