Quantitative analysis of steel samples using laser-induced breakdown spectroscopy with an artificial neural network incorporating a genetic algorithm

Kuohu Li, Lianbo Guo, Jiaming Li, Xinyan Yang, Rongxing Yi, Xiangyou Li, Yongfeng Lu, Xiaoyan Zeng

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In this work, a genetic algorithm (GA) was employed to select the intensity ratios of the spectral lines belonging to the target and domain matrix elements, then these selected line-intensity ratios were taken as inputs to construct an analysis model based on an artificial neural network (ANN) to analyze the elements copper (Cu) and vanadium (V) in steel samples. The results revealed that the root mean square errors of prediction (RMSEPs) for the elements Cu and V can reach 0.0040 wt. % and 0.0039 wt. %, respectively. Compared to 0.0190 wt. % and 0.0201 wt. % of the conventional internal calibration approach, the reduction rates of the RMSEP values reached 78.9% and 80.6%, respectively. These results indicate that the GA combining ANN can excellently execute the quantitative analysis in laser-induced breakdown spectroscopy for steel samples and further improve analytical accuracy.

Original languageEnglish (US)
Pages (from-to)935-941
Number of pages7
JournalApplied optics
Volume56
Issue number4
DOIs
StatePublished - Feb 1 2017

Fingerprint

Laser induced breakdown spectroscopy
laser-induced breakdown spectroscopy
root-mean-square errors
genetic algorithms
Mean square error
quantitative analysis
Genetic algorithms
steels
Neural networks
Steel
predictions
Chemical analysis
Vanadium
vanadium
line spectra
Calibration
Copper
copper
matrices

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Cite this

Quantitative analysis of steel samples using laser-induced breakdown spectroscopy with an artificial neural network incorporating a genetic algorithm. / Li, Kuohu; Guo, Lianbo; Li, Jiaming; Yang, Xinyan; Yi, Rongxing; Li, Xiangyou; Lu, Yongfeng; Zeng, Xiaoyan.

In: Applied optics, Vol. 56, No. 4, 01.02.2017, p. 935-941.

Research output: Contribution to journalArticle

Li, Kuohu ; Guo, Lianbo ; Li, Jiaming ; Yang, Xinyan ; Yi, Rongxing ; Li, Xiangyou ; Lu, Yongfeng ; Zeng, Xiaoyan. / Quantitative analysis of steel samples using laser-induced breakdown spectroscopy with an artificial neural network incorporating a genetic algorithm. In: Applied optics. 2017 ; Vol. 56, No. 4. pp. 935-941.
@article{4615252a7b2d4e3ab76b5d055bb6e2f5,
title = "Quantitative analysis of steel samples using laser-induced breakdown spectroscopy with an artificial neural network incorporating a genetic algorithm",
abstract = "In this work, a genetic algorithm (GA) was employed to select the intensity ratios of the spectral lines belonging to the target and domain matrix elements, then these selected line-intensity ratios were taken as inputs to construct an analysis model based on an artificial neural network (ANN) to analyze the elements copper (Cu) and vanadium (V) in steel samples. The results revealed that the root mean square errors of prediction (RMSEPs) for the elements Cu and V can reach 0.0040 wt. {\%} and 0.0039 wt. {\%}, respectively. Compared to 0.0190 wt. {\%} and 0.0201 wt. {\%} of the conventional internal calibration approach, the reduction rates of the RMSEP values reached 78.9{\%} and 80.6{\%}, respectively. These results indicate that the GA combining ANN can excellently execute the quantitative analysis in laser-induced breakdown spectroscopy for steel samples and further improve analytical accuracy.",
author = "Kuohu Li and Lianbo Guo and Jiaming Li and Xinyan Yang and Rongxing Yi and Xiangyou Li and Yongfeng Lu and Xiaoyan Zeng",
year = "2017",
month = "2",
day = "1",
doi = "10.1364/AO.56.000935",
language = "English (US)",
volume = "56",
pages = "935--941",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "The Optical Society",
number = "4",

}

TY - JOUR

T1 - Quantitative analysis of steel samples using laser-induced breakdown spectroscopy with an artificial neural network incorporating a genetic algorithm

AU - Li, Kuohu

AU - Guo, Lianbo

AU - Li, Jiaming

AU - Yang, Xinyan

AU - Yi, Rongxing

AU - Li, Xiangyou

AU - Lu, Yongfeng

AU - Zeng, Xiaoyan

PY - 2017/2/1

Y1 - 2017/2/1

N2 - In this work, a genetic algorithm (GA) was employed to select the intensity ratios of the spectral lines belonging to the target and domain matrix elements, then these selected line-intensity ratios were taken as inputs to construct an analysis model based on an artificial neural network (ANN) to analyze the elements copper (Cu) and vanadium (V) in steel samples. The results revealed that the root mean square errors of prediction (RMSEPs) for the elements Cu and V can reach 0.0040 wt. % and 0.0039 wt. %, respectively. Compared to 0.0190 wt. % and 0.0201 wt. % of the conventional internal calibration approach, the reduction rates of the RMSEP values reached 78.9% and 80.6%, respectively. These results indicate that the GA combining ANN can excellently execute the quantitative analysis in laser-induced breakdown spectroscopy for steel samples and further improve analytical accuracy.

AB - In this work, a genetic algorithm (GA) was employed to select the intensity ratios of the spectral lines belonging to the target and domain matrix elements, then these selected line-intensity ratios were taken as inputs to construct an analysis model based on an artificial neural network (ANN) to analyze the elements copper (Cu) and vanadium (V) in steel samples. The results revealed that the root mean square errors of prediction (RMSEPs) for the elements Cu and V can reach 0.0040 wt. % and 0.0039 wt. %, respectively. Compared to 0.0190 wt. % and 0.0201 wt. % of the conventional internal calibration approach, the reduction rates of the RMSEP values reached 78.9% and 80.6%, respectively. These results indicate that the GA combining ANN can excellently execute the quantitative analysis in laser-induced breakdown spectroscopy for steel samples and further improve analytical accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85011865894&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011865894&partnerID=8YFLogxK

U2 - 10.1364/AO.56.000935

DO - 10.1364/AO.56.000935

M3 - Article

C2 - 28158095

AN - SCOPUS:85011865894

VL - 56

SP - 935

EP - 941

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 4

ER -