Analytical-performance improvement of laser-induced breakdown spectroscopy for steel using multi-spectral-line calibration with an artificial neural network

Kuohu Li, Lianbo Guo, Changmao Li, Xiangyou Li, Meng Shen, Zhong Zheng, Yang Yu, Rongfei Hao, Zhongqi Hao, Qingdong Zeng, Yongfeng Lu, Xiaoyan Zeng

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

A multi-spectral-line calibration (MSLC) approach based on an artificial neural network (ANN) was developed to improve the accuracy and precision of steel analysis using laser-induced breakdown spectroscopy (LIBS). The intensity ratios of multiple spectral lines of target and matrix elements were used to train an ANN. The resulting model was able to relate the spectra to the concentrations of target elements more accurately than the conventional internal calibration approach, which led to improvements in the accuracy and precision of the LIBS analysis. This approach was applied to LIBS analysis of steel samples to predict the Cr and Ni concentrations. Compared with a conventional internal calibration approach, the root-mean-square errors of cross-validation for Cr and Ni decreased from 0.018 and 0.067 wt% to 0.010 and 0.023 wt%, respectively, using the proposed MSLC, and the average values of the relative standard deviation for Cr and Ni decreased from 11.3 and 19.5% to 6.4 and 12.9%, respectively.

Original languageEnglish (US)
Pages (from-to)1623-1628
Number of pages6
JournalJournal of Analytical Atomic Spectrometry
Volume30
Issue number7
DOIs
StatePublished - Jul 1 2015
Externally publishedYes

Fingerprint

Laser induced breakdown spectroscopy
Steel
Calibration
Neural networks
Steel analysis
Mean square error

ASJC Scopus subject areas

  • Analytical Chemistry
  • Spectroscopy

Cite this

Analytical-performance improvement of laser-induced breakdown spectroscopy for steel using multi-spectral-line calibration with an artificial neural network. / Li, Kuohu; Guo, Lianbo; Li, Changmao; Li, Xiangyou; Shen, Meng; Zheng, Zhong; Yu, Yang; Hao, Rongfei; Hao, Zhongqi; Zeng, Qingdong; Lu, Yongfeng; Zeng, Xiaoyan.

In: Journal of Analytical Atomic Spectrometry, Vol. 30, No. 7, 01.07.2015, p. 1623-1628.

Research output: Contribution to journalArticle

Li, Kuohu ; Guo, Lianbo ; Li, Changmao ; Li, Xiangyou ; Shen, Meng ; Zheng, Zhong ; Yu, Yang ; Hao, Rongfei ; Hao, Zhongqi ; Zeng, Qingdong ; Lu, Yongfeng ; Zeng, Xiaoyan. / Analytical-performance improvement of laser-induced breakdown spectroscopy for steel using multi-spectral-line calibration with an artificial neural network. In: Journal of Analytical Atomic Spectrometry. 2015 ; Vol. 30, No. 7. pp. 1623-1628.
@article{5c961748cf4349bbaa7395e8dabbb389,
title = "Analytical-performance improvement of laser-induced breakdown spectroscopy for steel using multi-spectral-line calibration with an artificial neural network",
abstract = "A multi-spectral-line calibration (MSLC) approach based on an artificial neural network (ANN) was developed to improve the accuracy and precision of steel analysis using laser-induced breakdown spectroscopy (LIBS). The intensity ratios of multiple spectral lines of target and matrix elements were used to train an ANN. The resulting model was able to relate the spectra to the concentrations of target elements more accurately than the conventional internal calibration approach, which led to improvements in the accuracy and precision of the LIBS analysis. This approach was applied to LIBS analysis of steel samples to predict the Cr and Ni concentrations. Compared with a conventional internal calibration approach, the root-mean-square errors of cross-validation for Cr and Ni decreased from 0.018 and 0.067 wt{\%} to 0.010 and 0.023 wt{\%}, respectively, using the proposed MSLC, and the average values of the relative standard deviation for Cr and Ni decreased from 11.3 and 19.5{\%} to 6.4 and 12.9{\%}, respectively.",
author = "Kuohu Li and Lianbo Guo and Changmao Li and Xiangyou Li and Meng Shen and Zhong Zheng and Yang Yu and Rongfei Hao and Zhongqi Hao and Qingdong Zeng and Yongfeng Lu and Xiaoyan Zeng",
year = "2015",
month = "7",
day = "1",
doi = "10.1039/c5ja00089k",
language = "English (US)",
volume = "30",
pages = "1623--1628",
journal = "Journal of Analytical Atomic Spectrometry",
issn = "0267-9477",
publisher = "Royal Society of Chemistry",
number = "7",

}

TY - JOUR

T1 - Analytical-performance improvement of laser-induced breakdown spectroscopy for steel using multi-spectral-line calibration with an artificial neural network

AU - Li, Kuohu

AU - Guo, Lianbo

AU - Li, Changmao

AU - Li, Xiangyou

AU - Shen, Meng

AU - Zheng, Zhong

AU - Yu, Yang

AU - Hao, Rongfei

AU - Hao, Zhongqi

AU - Zeng, Qingdong

AU - Lu, Yongfeng

AU - Zeng, Xiaoyan

PY - 2015/7/1

Y1 - 2015/7/1

N2 - A multi-spectral-line calibration (MSLC) approach based on an artificial neural network (ANN) was developed to improve the accuracy and precision of steel analysis using laser-induced breakdown spectroscopy (LIBS). The intensity ratios of multiple spectral lines of target and matrix elements were used to train an ANN. The resulting model was able to relate the spectra to the concentrations of target elements more accurately than the conventional internal calibration approach, which led to improvements in the accuracy and precision of the LIBS analysis. This approach was applied to LIBS analysis of steel samples to predict the Cr and Ni concentrations. Compared with a conventional internal calibration approach, the root-mean-square errors of cross-validation for Cr and Ni decreased from 0.018 and 0.067 wt% to 0.010 and 0.023 wt%, respectively, using the proposed MSLC, and the average values of the relative standard deviation for Cr and Ni decreased from 11.3 and 19.5% to 6.4 and 12.9%, respectively.

AB - A multi-spectral-line calibration (MSLC) approach based on an artificial neural network (ANN) was developed to improve the accuracy and precision of steel analysis using laser-induced breakdown spectroscopy (LIBS). The intensity ratios of multiple spectral lines of target and matrix elements were used to train an ANN. The resulting model was able to relate the spectra to the concentrations of target elements more accurately than the conventional internal calibration approach, which led to improvements in the accuracy and precision of the LIBS analysis. This approach was applied to LIBS analysis of steel samples to predict the Cr and Ni concentrations. Compared with a conventional internal calibration approach, the root-mean-square errors of cross-validation for Cr and Ni decreased from 0.018 and 0.067 wt% to 0.010 and 0.023 wt%, respectively, using the proposed MSLC, and the average values of the relative standard deviation for Cr and Ni decreased from 11.3 and 19.5% to 6.4 and 12.9%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84933037299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933037299&partnerID=8YFLogxK

U2 - 10.1039/c5ja00089k

DO - 10.1039/c5ja00089k

M3 - Article

VL - 30

SP - 1623

EP - 1628

JO - Journal of Analytical Atomic Spectrometry

JF - Journal of Analytical Atomic Spectrometry

SN - 0267-9477

IS - 7

ER -