人工神经网络在激光诱导击穿光谱数据分析中的应用进展

doi:10.3964/j.issn.1000-0593(2021)07-1998-07

摘要
参考文献
相关文章 (15)

全文: PDF (2210 KB)
输出: BibTeX | EndNote (RIS)

摘要：激光诱导击穿光谱（LIBS）具有实时、远程、多元素同时分析的优点，近年来在工业在线分析领域逐渐受到关注，发挥着重要作用。但基于发射光谱本身的特性，LIBS存在光谱噪声、基线漂移、自吸收和重叠峰等现象；又由于环境变化、激光能量波动、基体效应、样品表面形貌等因素，造成光谱稳定性和重现性差。这些问题导致光谱信息与定性、定量分析之间呈非线性关系，限制了分析灵敏度和准确度。随着LIBS器件稳定性的逐渐改善，LIBS光谱数据分析方法日新月异，人工神经网络（ANN）能跟踪和识别非线性特性，自适应学习LIBS光谱特征，筛除干扰信息，在LIBS数据分析领域的应用得到飞速发展。介绍了LIBS原理、仪器结构和工作流程以及在LIBS光谱分析领域常见的神经网络模型，总结出2015年—2020年LIBS结合常见的ANN模型在地质、合金、有机聚合物、煤炭、土壤及生物等领域的具体应用，指出ANN在数据分析领域的超强能力可有效改进LIBS分析精度，提升光谱数据利用率，降低光谱采集环境要求。针对仍然有待突破的技术难点，展望了ANN在LIBS光谱深度信息挖掘、便携式专用型设备开发、技术联用等方面的发展前景。LIBS日趋成熟，但其数据分析领域仍有广阔发展空间。该综述可为机器学习在LIBS数据分析领域的应用提供参考。

关键词：激光诱导击穿光谱；人工神经网络；数据分析；应用

Abstract：Laser-induced breakdown spectroscopy (LIBS) has the advantages of real-time, rapid, and multi-element simultaneous detection. It has attracted more and more attention in recent years and played an essential role in online industrial analysis. However, based on the emission spectrum characteristics, LIBS has spectral noise, baseline drift, self-absorption, and overlapping peaks, etc. In addition, spectral stability and reproducibility are poor due to environmental changes, laser energy fluctuations, matrix effects, and samples’ surface topography. These result in the nonlinear relationship between spectral information and qualitative and quantitative analysis, limiting the analysis’s sensitivity and accuracy. With the gradual improvement of LIBS devices’ stability, LIBS spectral data analysis methods are also changing with each new day. Artificial neural networks (ANN) can track and identify nonlinear characteristics, adaptive learning of LIBS spectral characteristics, screening out interference information, and its application in LIBS data analysis has been rapidly developed. This paper introduces the principle, instrument structure, and working process of LIBS and common neural network model in the field of LIBS spectrum analysis, summed up the LIBS in 2015—2020 in combination with the common ANN model in geological, alloy and organic polymer, coal, soil and biological areas such as the specific application. It pointed out that ANN’s super ability in the field of data analysis can effectively improve the LIBS analysis accuracy and improve the utilization rate of spectrum data, reducing the spectrum collection and environmental requirements. Given the technical difficulties that still required broken through, ANN’s development prospect in LIBS spectral depth information mining, portable special equipment development, technology combination, and other aspects has prospected. LIBS is becoming more and more mature, but data analysis of this technology still has a broad space for development. This review can provide a reference for the application of machine learning in LIBS data analysis.

Key words：Laser-induced breakdown spectroscopy; Artificial neural network; Data analysis; Application

收稿日期: 2020-07-15 修订日期: 2020-11-21

中图分类号:

O657.3

基金资助: 海关总署科研项目(2019HK074)，国家重点研发计划(2018YFF0215400)资助

通讯作者: 刘曙，安雅睿 E-mail: liu_shu@customs.gov.cn; anyarui@usst.edu.cn

作者简介: 赵文雅，1994年生，上海理工大学理学院化学系硕士研究生 e-mail：182692066@st.usst.edu.cn

引用本文:

赵文雅，闵红，刘曙，安雅睿，俞进. 人工神经网络在激光诱导击穿光谱数据分析中的应用进展[J]. 光谱学与光谱分析, 2021, 41(07): 1998-2004.
ZHAO Wen-ya, MIN Hong, LIU Shu, AN Ya-rui, YU Jin. Application Progress of Artificial Neural Network in Laser-Induced Breakdown Spectral Data Analysis. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(07): 1998-2004.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2021)07-1998-07 或 https://www.gpxygpfx.com/CN/Y2021/V41/I07/1998

[1] Fortes F J, Moros J, Lucena P, et al. Analytical Chemistry, 2013, 85(2): 640.
[2] Zhang T, Yan C, Qi J, et al. Journal of Analytical Atomic Spectrometry, 2017, 32(10): 1960.
[3] ZHU Da-qi, SHI Hui（朱大奇, 史慧）. Principle and Applications of Artificial Neural Networks（人工神经网络原理及应用）. Beijing: Science Press（北京: 科学出版社）, 2006. 1.
[4] ZHANG Tian-long, WU Shan, TANG Hong-sheng, et al（张天龙, 吴珊, 汤宏胜, 等）. Chinese Journal of Analytical Chemistry（分析化学）, 2015, 43(6): 939.
[5] Andrade D F, Pereira-Filho E R, Amarasiriwardena D. Applied Spectroscopy Reviews, 2021, 56(2): 98.
[6] Fu X, Li G, Dong D. Frontiers in Physics, 2020, 8: 68.
[7] Guo Y M, Guo L B, Li J M, et al. Frontiers of Physics, 2016, 11(5): 114212.
[8] Hu Y, Li Z, Lu T. Journal of Analytical Atomic Spectrometry, 2017, 32(11): 2263.
[9] Chen S, Cowan C N, Grant P M. IEEE Transactions on Neural Networks, 1991, 2(2): 302.
[10] HOU Yuan-bin, DU Jing-yi, WANG Mei（侯媛彬，杜京义，汪梅）. Neural Networks（神经网络）. Xi’an: Xi’an Electronic Sience & Technology University Press（西安：西安电子科技大学出版社）, 2007. 89.
[11] Huang G, Song S, Gupta JND, et al. IEEE Transactions on Cybernetics, 2014, 44(12): 2405.
[12] Chen J, Pisonero J, Chen S, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2020, 166: 105801.
[13] Alvarez J, Velasquez M, Kumar Myakalwar A, et al. Journal of Analytical Atomic Spectrometry, 2019, 34(12): 2459.
[14] Yang Y, Li C, Liu S, et al. Analytical Methods, 2020, 12(10): 1316.
[15] Lu T, Hu Y, Li Z, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2018, 143: 55.
[16] Ding Y, Yan F, Yang G, et al. Analytical Methods, 2018, 10(9): 1074.
[17] HU Yang, LI Zi-han, LÜ Tao（胡杨, 李子涵, 吕涛）. Laser & Optoelectronics Progress（激光与光电子学进展）, 2017, 54(5): 345.
[18] Campanella B, Grifoni E, Legnaioli S, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2017, 134: 52.
[19] Kong H, Sun L, Hu J, et al. Plasma Science & Technology, 2015, 17(11): 964.
[20] He J, Pan C, Liu Y, et al. Applied Spectroscopy, 2019, 73(6): 678.
[21] Li K, Guo L, Li J, et al. Applied Optics, 2017, 56(4): 935.
[22] Li K, Guo L, Li C, et al. Journal of Analytical Atomic Spectrometry, 2015, 30(7): 1623.
[23] D’Andrea E, Pagnotta S, Grifoni E, et al. Applied Physics B: Lasers and Optics, 2015, 118(3): 353.
[24] Owolabi T O, Gondal M A. Journal of Intelligent & Fuzzy Systems, 2018, 35(6): 6277.
[25] Chen P, Wang X, Li X, et al. Sensors, 2019, 19(5): 1087.
[26] Roh S-B, Park S-B, Oh S-K, et al. Journal of Material Cycles and Waste Management, 2018, 20(4): 1934.
[27] Junjuri R, Gundawar M K. Journal of Analytical Atomic Spectrometry, 2019, 34(8): 1683.
[28] Wei J, Dong J, Zhang T, et al. Analytical Methods, 2016, 8(7): 1674.
[29] Lu Z, Mo J, Yao S, et al. Energy & Fuels, 2017, 31(4): 3849.
[30] Yan C, Qi J, Ma J, et al. Chemometrics and Intelligent Laboratory Systems, 2017, 167: 226.
[31] Xu X, Du C, Ma F, et al. Geoderma, 2019, 355: 113905.
[32] Lu C, Wang B, Jiang X, et al. Plasma Science & Technology, 2019, 21(3): 034014.
[33] KANG Sheng, WEI Zhao-hang, YANG Fan, et al（康盛, 魏兆航, 杨帆, 等）. Agricultural Engineering（农业工程）, 2019, 9(10): 38.
[34] Sun C, Tian Y, Gao L, et al. Scientific Reports, 2019, 9: 11363.
[35] Peng J, Ye L, Shen T, et al. Transactions of the ASABE, 2018, 61(3): 821.
[36] Liu F, Shen T, Wang J, et al. Transactions of the ASABE, 2019, 62(1): 123.
[37] Liu X, Feng X, He Y. Renewable Energy, 2019, 143A(12): 176.
[38] Manzoor S, Ugena L, Tornero-Lopez J, et al. Talanta, 2016, 155: 101.
[39] Prochazka D, Mazura M, Samek O, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2018, 139: 6.
[40] Xu W, Chen S, Tan Y, et al. Journal of Analytical Atomic Spectrometry, 2020, 35(8): 1641.