远程LIBS结合GA-arPLS的爆炸物识别研究

doi:10.3964/j.issn.1000-0593(2024)11-3199-07

Abstract
References
Related Citation (15)

Download: PDF (8895 KB)
Export: BibTeX | EndNote (RIS)

Abstract This study proposes a remote LIBS baseline correction preprocessing method based on genetic algorithm (GA) optimized nonweighted penalty least squares (arPLS) to ensure public safety and prevent terrorist attacks. It combines this method with an ANN classification model to accurately identify four types of explosives (TNT, RDX, HMX, and CL-20) at a distance of 6 m. The GA-arPLS algorithm's foundation is adding a fitness function to arPLS, which allows it to assess the fitting baseline and choose the best option in the candidate parameter space for fitting the LIBS baseline. On the one hand, it is primarily caused by the instrument's inherent dark current noise, bremsstrahlung, or environmental factors. This is because LIBS spectral signals typically include noise signals such as continuous radiation and atomic and molecular emission lines, which cover a wide range of light bands in LIBS spectra. Therefore, in long-distance environments, it is necessary to improve the ability to identify characteristic spectral lines through GA-arPLS preprocessing; on the other hand, it is difficult to capture small differences between the characteristic spectra of similar explosives for classification when qualitatively analyzing organic compounds of similar elements directly through LIBS spectroscopy. As a result, spectral analysis accuracy needs to be raised. This study used the LIBS dataset as input for closest neighbor classification (KNN) and support vector machine (SVM) before and after GA-arPLS correction. SVM's classification accuracy increased by 8.4%, whereas the KNN model's accuracy increased by 8.7%. The classification accuracy demonstrates that the GA-arPLS baseline correction preprocessing method can effectively reduce the continuous background of remote LIBS spectra. Meanwhile, the artificial neural network (ANN) constructedclassification model achieves the optimal classification recognition effect by improving the recognition accuracy of similar explosives from 89.2% to 100%. Studies have demonstrated that this baseline correction preprocessing technique successfully lowers the noise interference and continuous background radiation of remote LIBS and enhances the robustness and predictive power of the remote LIBS classification model. The research findings are anticipated to increase the precision and effectiveness of remote LIBS in explosive detection to better respond to possible explosive threats.

Key words：Remote laser-induced breakdown spectroscopy; Explosives identification; GA-arPLS preprocessing; Artificial neural network algorithm; Baseline correction method

Received: 2023-09-06 Accepted: 2024-03-25

ZTFLH:

O657.31

Corresponding Authors: CHEN Yuan-yuan E-mail: chenyy@nuc.edu.cn

Cite this article:

YAN Hong-yu,ZHAO Yu,CHEN Yuan-yuan, et al. Explosive Residue Identification Study by Remote LIBS Combined With GA-arPLS[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3199-3205.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)11-3199-07 OR https://www.gpxygpfx.com/EN/Y2024/V44/I11/3199

[1] Félix, Zapata, María, et al. Applied Spectroscopy Reviews, 2016, 51(3): 227.
[2] Gillibert R, Huang J Q, Zhang Y, et al. TrAC Trends in Analytical Chemistry, 2018, 105: 166.
[3] Thomas S W I, Joly G D, Swager T M. Chem. Inform., 2007, 38(31).
[4] Anilanmert, Beril, Cengiz, et al. Chemicke Zvesti, 2017, 71(5): 971.
[5] Fraissard J, Lapina O. Springer Netherlands, 2009, 10: 1007.
[6] Hee-Jung Im, Hyun-Je Cho, ByoungChul Song, et al. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2006, 566(2): 422.
[7] Cremers D A, Radziemski L J. Remote LIBS Measurements. John Wiley & Sons Ltd, 2013.
[8] Sylvain Grégoire, Boudinet M, Frédéric Pelascini, et al. Analytical & Bioanalytical Chemistry, 2011, 400(10): 3331.
[9] Capitelli F, Colao F, Provenzano M R, et al. Geoderma, 2002, 106(1): 45.
[10] Barbini R, Colao F, Lazic V, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2002, 57(7): 1203.
[11] Lopez-Moreno C, Amponsah-Manager K, Smith B, et al. Journal of Analytical Atomic Spectrometry, 2005, 20(6): 552.
[12] Chauhanm D K, Tripathi D K, Rai N K, et al. Food Biophysics, 2011，(6): 416.
[13] Frank C, Lucia D, Russell S, et al. Applied Optics, 2003, 42(30): 6148.
[14] De Lucia, Frank C, Jemifer L, et al. Applied Optics, 2012, 51(7): B83.
[15] Serrano J, Moros J, Sánchez, et al. Analytica Chimica Acta, 2014, 806: 107.
[16] Junjuri R, Prakash G A, Kumar G M. Optik-International Journal for Light and Electron Optics, 2020, 204: 16396.
[17] Wang Qianqian, Geer, et al. Journal of Hazardous Materials, 2019, 638: 423.
[18] GU Tian-yu, ZHANG Da-cheng, FENG Zhong-qi, et al(谷天予，张大成，冯中琦，等). Modern Applied Physics(现代应用物理), 2023, 14(2): 106.
[19] Anandan B, Manikandan M. Materials Today Communications, 2023, 34：105286.
[20] De Lucia F, Gottfried J. Propellants Explosives Pyrotechnics, 2010, 35(3): 268.
[21] De Lucia F, Gottfried J L. Journal of Physical Chemistry A, 2013, 117(39): 9555.
[22] Park, Aaron, Ahn, et al. The Analyst: The Analytical Journal of the Royal Society of Chemistry: A Monthly International Publication Dealing with All Branches of Analytical Chemistry, 2015, 1401: 250.