Research on a mixed model applied to LIBS quantitative analysis

Rui Wang; Xiaohong Ma; Taiyu Zhang; Hui Lv; Xin He

doi:10.1117/12.2666510

4 April 2023 Research on a mixed model applied to LIBS quantitative analysis

Rui Wang, Xiaohong Ma, Taiyu Zhang, Hui Lv, Xin He

Proceedings Volume 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications; 126175G (2023) https://doi.org/10.1117/12.2666510
Event: 9th Symposium on Novel Photoelectronic Detection Technology and Applications (NDTA 2022), 2022, Hefei, China

Abstract

Quantification of Laser-Induced Breakdown Spectroscopy (LIBS) has always been an essential but difficult task since LIBS was concerned with material analysis. A quantitative method based on a physical model is completely interpretable and easy to calculate. However, strict assumptions and conditions limit its accuracy, which brings extra error in the actual scene. Although using a neural network model can quickly get better results than physical models, overfitting and inexplicability prevent it from being used in practical applications. In this work, we proposed a new mixed qualification model, which combined a physical model with a neural network to settle the neural network's problems. The validity of the mixed model was applied to four groups, a total of forty-four soil samples each with different element concentration gradients of lead, copper, manganese, and chromium. The leave-one-out method was used to establish quantitative analysis models for the four elements. The R-squares of the four groups were: Pb, 98.44%, Cu, 99.37%, Mn, 99.35%, Cr 98.95%, and all of them were better than the R-squares of the internal standard method. Compared with the prediction results using only the DenseNet, the Root Mean Square Error (RMSE) of the forty-four samples predicted by the mixed model all decreased to varying degrees.

Citation Download Citation

Rui Wang, Xiaohong Ma, Taiyu Zhang, Hui Lv, and Xin He "Research on a mixed model applied to LIBS quantitative analysis", Proc. SPIE 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications, 126175G (4 April 2023); https://doi.org/10.1117/12.2666510

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Laser induced breakdown spectroscopy

Neural networks

Data modeling

Statistical modeling

Overfitting

Plasma

Chemical elements

Show All Keywords

Keywords/Phrases

Search In:

Publication Years