基于变量选择技术的FTIR光谱识别算法研究

doi:10.3969/j.issn.1007-5461.2021.03.003

量子电子学报 ›› 2021, Vol. 38 ›› Issue (3): 281-289.doi: 10.3969/j.issn.1007-5461.2021.03.003

基于变量选择技术的FTIR光谱识别算法研究

沈先春1;2;3, 徐亮1;3∗, 孙永丰1;2;3, 胡运优1;2;3, 金岭1;3, 杨伟锋1;3 , 徐寒扬1;3 , 刘建国1;3 , 刘文清1;3

1 中国科学院合肥物质科学研究院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽合肥230031; 2 中国科学技术大学, 安徽合肥230026; 3 安徽省环境光学监测技术重点实验室, 安徽合肥230031

收稿日期:2020-05-28 修回日期:2020-06-01 出版日期:2021-05-28 发布日期:2021-05-28
通讯作者: E-mail: xuliang@aiofm.ac.cn
作者简介:沈先春( 1992 - ), 安徽安庆人, 研究生, 主要从事傅里叶变换红外光谱分析方法方面的研究。E-mail: xcshen@aiofm.ac.cn
基金资助:
Supported by Key Research Project of Frontier Science of Chinese Academy of Sciences (中国科学院前沿科学重点研究项目, QYZDYSSW- DQC016), Key Research and Development Plan of Anhui Province of China (安徽省重点研究和开发计划, 1804d08020300), Special Project of National Natural Science Foundation of China (国家自然科学基金专项项目, 41941011), National Key Research and Development Plan (国家重点研发计划, 2016YFC0803001-08)

FTIR spectrum recognition algorithm based on variable selection technology

SHEN Xianchun1;2;3, XU Liang1;3∗, SUN Yongfeng1;2;3, HU Yunyou1;2;3, JIN Ling1;3, YANG Weifeng1;3, XU Hangyang1;3, LIU Jianguo1;3, LIU Wenqing1;3

1 Key Laboratory of Environmental Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China; 2 University of Science and Technology of China, Hefei 230026, China; 3 Key Laboratory of Optical Monitoring Technology for Environment, Hefei 230031, China

Received:2020-05-28 Revised:2020-06-01 Published:2021-05-28 Online:2021-05-28

摘要/Abstract

摘要： 将变量选择方法中SFS、LASSO 和Elastic Net 三种不同方法与广义交互验证准则相结合, 实现对FTIR 光谱气体成分变量的初步筛选, 再采用循环迭代CLS 方法对初步筛选的变量中浓度小于0 的成分进行循环剔除, 然后根据变量在测量向量中的方向占比对选择的变量进行精选, 最终得到目标气体成分。为了验证各识别算法的识别性能, 分别进行了CH4 和SF6 外场排放实验, 两组实验结果表明建立的识别算法应用于气体目标识别的效率高、识别准确率高, 且能够识别出干扰成分H2O。此算法为被动FTIR 技术在危险气体泄露预警监测中的应用提供了方法基础。

关键词: 光谱学, 气体识别方法, 变量选择技术, 光谱分析

Abstract: Qualitative spectrum recognition algorithm is the basis of application of passive Fourier transform infrared spectroscopy (FTIR) in monitoring and early warning of toxic and hazardous gases. Three different methods, SFS, LASSO and Elastic Net, are used to perform preliminary selection of gas component variables in the FTIR spectrum by combining with the generalized cross-validation criteria. Then, the cyclic iterative CLS method is used to perform cyclic elimination of the components with concentrationless than 0 in the preliminary screened variables. Finally, the direction proportion of the variables in the measurement vector is used to further select from the selected variables to get the target gas composition. In order to verify the performance of each recognition algorithm, the simulation experiments of CH4 and SF6 field emission are carried out respectively. The experimental results show that the established recognition algorithm can identify the target components quickly and effectively, the recognition response time is second level, the recognition accuracy is as high as 99%, and it can also accurately identify the interference component H2O. It is shown that the proposed algorithm provides a method basis for the application of passive FTIR technology in emergency monitoring and warning of dangerous gas leakage.

Key words: spectroscopy, gas identification method, variable selection method, spectral analysis

中图分类号:

O433.4

沈先春, 徐亮, ∗, 孙永丰, 胡运优, 金岭, 杨伟锋, , 徐寒扬, , 刘建国, , 刘文清, . 基于变量选择技术的FTIR光谱识别算法研究[J]. 量子电子学报, 2021, 38(3): 281-289.

SHEN Xianchun, XU Liang, ∗, SUN Yongfeng, HU Yunyou, JIN Ling, YANG Weifeng, XU Hangyang, LIU Jianguo, LIU Wenqing, . FTIR spectrum recognition algorithm based on variable selection technology[J]. Chinese Journal of Quantum Electronics, 2021, 38(3): 281-289.

参考文献 22

[1]	Sch¨afer K, Heland J, Lister D H, et al. Nonintrusive optical measurements of aircraft engine exhaust emissions and comparison
	with standard intrusive techniques [J]. Applied Optics, 2000, 39(3): 441-455.
[2]	Xie P H, Liu W Q, Wei Q N. Spectroscopic remote techniques for atmospheric pollution monitoring [J]. Chinese Journal of
	Quantum Electronics, 2000, 17(5): 385-394.
	谢品华, 刘文清, 魏庆农, 等. 大气环境污染气体的光谱遥感监测技术[J]. 量子电子学报, 2000, 17(5): 385-394.
[3]	Xu L, Gao M G, Liu J G, et al. Multi-gas monitoring by open path FTIR in Yanshan petro-chemical area during Beijing
	Olympic games [J]. Journal of Atmospheric and Environmental Optics, 2009, 4(5): 376-381.
	徐亮, 高闽光, 刘建国, 等. 北京奥运期间石化工业区多组分污染气体的开放光程FTIR 监测[J]. 大气与环境光学学报,
20	09, 4(5): 376-381.
[4]	Ben-David A. Remote detection of biological aerosols at a distance of 3 km with a passive Fourier transform infrared (FTIR)
	sensor [J]. Optics Express, 2003, 11(5): 418-429.
[5]	Chen S Y, Gao M G, Xu L, et al. Remote sensing of CH4 column concentration in the atmosphere based on direct-sun infrared
	absorption spectroscopy [J]. Chinese Journal of Quantum Electronics, 2014, 31(1): 18-24.
	程巳阳, 高闽光, 徐亮, 等. 基于直射太阳光红外吸收光谱技术的大气中CH4 柱浓度遥测研究[J]. 量子电子学报, 2014,
31	(1): 18-24.
[6]	Feng M C, Xu L, Liu W Q, et al. Investigation of detecting biological aerosol by passive Fourier transform infrared spectroscopy
	technology based on MODTRAN model [J]. Acta Physica Sinica, 2016, 65(1): 014210.
	冯明春, 徐亮, 刘文清, 等. 基于MODTRAN 模型使用被动傅里叶变换红外光谱技术对生物气溶胶的探测研究[J]. 物理
	学报, 2016, 65(1): 014210.
[7]	Delaney M F, Warren F V, Hallowell J R. Quantitative evaluation of library searching performance [J]. Analytical Chemistry,
19	83, 55(12): 1925-1929.
[8]	Visser T, Luinge H J, Maas J V D. Neural Networks as a Tool for Identity Confirmation of IR Spectra [C]. Progress in Fourier
	Transform Spectroscopy, Springer Vienna, 1997: 287-288.
[9]	Fox R C. Computer searching of infrared spectra using peak location and intensity data [J]. Analytical Chemistry, 1976, 48(4):
71	7-721.
[10]	NydenMR, Pallister J E, Sparks D T, et al. Computer-assisted spectroscopic analysis using orthonormalized reference spectra.
	Part II: Application to the identification of pure compounds [J]. Applied Spectroscopy, 1987, 41(1): 63-66.
[11]	Ruyken M M A, Visser J A, Smilde A K. Online detection and identification interferents in multivariate predictions of organic
	gases using FT-IR spectroscopy [J]. Analytical Chemistry, 1995, 67(13): 2170-2179.
[12]	Lavine B K, Nuguru K, Mirjankar N, et al. Pattern recognition assisted infrared library searching [J]. Applied Spectroscopy,
20	12, 66(8): 917-925.
[13]	Zhou Y, Liu T B, Li J R, et al. Rapid identification of edible oil and swill-cooked dirty oil by using near-infrared spectroscopy
	and sparse representation classification [J]. Analytical Methods, 2015, 7(6): 2367-2372.
[14]	Bai P, Xie W J, Liu J H. Application of mixture gas spectral recognition with support vector machine [J]. Opto-Electronic
	Engineering, 2006, 33(8): 37-43.
	白鹏, 谢文俊, 刘君华. 支持向量机在混合气体种类光谱识别中的应用[J]. 光电工程, 2006, 33(8): 37-43.
[15]	Liu F, Wang J D. Using genetic algorithm to identify completely unknown system in FTIR spectra analysis [J]. Journal of
	Environmental Science and Health: Part A, 2004, 39(6): 1525-1533.
[16]	Tang J, Alelyani S, Liu H. Feature selection for classification: A review [OL]. Documentaci´on Administrativa, 2014.
[17]	Tibshirani R. Regression shrinkage and selection via the LASSO: A retrospective [J]. Journal of the Royal Statistical Society:
	Series B (Statistical Methodology) 2011, 73(3): 273-282.
[18]	Zou H, Hastie T, Tibshirani R. On the“Degrees of freedom”of the Lasso [J]. The Annals of Statistics, 2007, 35(5): 2173-2192.
[19]	Xue F, Liu J Q, Li Z F, et al. A novel GCV-based criterion for parametric PSF estimation [C]. 2014 12th International
	Conference on Signal Processing (ICSP), 2014: 743-746.
[20]	Griffith D W T. Synthetic calibration and quantitative analysis of gas-phase FT-IR spectra [J]. Applied Spectroscopy, 1996,
50	(1): 59-70.
[21]	Shen X C, Xu L, Ye S B, et al. Automatic baseline correction method for the open-path Fourier transform infrared spectra by
	using simple iterative averaging [J]. Optics Express, 2018, 26(10): A609- A614.
[22]	Shen X C. Study on the Qualitative Method and Application of Passive FTIR Telemetry of Gas [D]. Hefei: University of Science
	and Technology of China, 2020.
	沈先春. 气体目标FTIR 被动遥测识别方法及应用研究[D]. 合肥: 中国科学技术大学, 2020.

基于变量选择技术的FTIR光谱识别算法研究

FTIR spectrum recognition algorithm based on variable selection technology

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 22

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈珂马凤翔赵跃李辰溪安冉朱峰杭忱. 基于光纤光声传感的油中溶解气体分析系统[J]. 量子电子学报, 2023, 40(4): 597-605.
[2]	曹冬梅, 李永放 . 领结状金纳米二聚体耦合共振特性研究[J]. 量子电子学报, 2023, 40(4): 606-613.
[3]	费晔, 孙仲谋, 田东鹏, 刘骁源, 刘玉柱, . 基于激光诱导击穿光谱的果木炭燃烧对空气成分影响的研究[J]. 量子电子学报, 2023, 40(4): 436-446.
[4]	王海青 , 施卫 . THz-ATR 技术检测生物医学样品的研究进展[J]. 量子电子学报, 2023, 40(3): 319-332.
[5]	曾子威 , 李宏光 , 郭宇烽 , 廖文焘 . 隐匿危险品高准确度太赫兹光谱识别方法[J]. 量子电子学报, 2023, 40(3): 340-348.
[6]	白岩冰, 张梦圆, 朱梦琪, 李旭, 闫佳玉, 张存林, 左剑, . α-乳糖一水合物太赫兹动力学研究[J]. 量子电子学报, 2023, 40(3): 349-359.
[7]	葛宏义 , 王飞 , 蒋玉英 , 李丽 , 张元 , 贾柯柯 , . 基于宽度学习的太赫兹光谱图像小麦霉变识别研究[J]. 量子电子学报, 2023, 40(3): 360-368.
[8]	张冉冉 , 应璐娜 , 周卫东. 相关向量机结合主成分分析应用于 LIBS 技术定量分析[J]. 量子电子学报, 2023, 40(3): 376-382.
[9]	杨金, , 王云峰, , 储玲巧 , 蒋华超 , 苏付海 ∗. 少层 PtSe2 中光生载流子超快动力学研究[J]. 量子电子学报, 2023, 40(2): 282-292.
[10]	王泽育, 崔琪, 和小虎, 卢丹华, 邱选兵何秋生, 赖云忠, 李传亮∗. I₂⁺离子低能电子态的计算和光谱研究[J]. 量子电子学报, 2022, 39(4): 477-484.
[11]	徐鹏, 贾韧, 姚关心, 秦正波, 郑贤锋, 杨新艳, 崔执凤, . 混合水溶液中金属元素的偏最小二乘法激光诱导击穿光谱[J]. 量子电子学报, 2022, 39(4): 485-493.
[12]	于玮, 周卓彦, 孙仲谋, 张兴龙, 刘玉柱, . 激光诱导击穿光谱技术实时检测蔷薇属植物[J]. 量子电子学报, 2022, 39(4): 494-501.
[13]	丁伯坤, 邵李刚, 王坤阳, 陈家金, 王贵师, 刘锟, 梅教旭, 谈图, 高晓明, ∗. 基于离轴积分腔的海水溶解气体实时检测技术研究[J]. 量子电子学报, 2022, 39(4): 502-510.
[14]	马凤翔, 赵跃, 崔方晓∗, 李大成. 基于支持向量回归的光声光谱信号温度和湿度校正方法[J]. 量子电子学报, 2022, 39(4): 511-518.
[15]	张云琪, 崔超远, 陈永, 鲁翠萍. 苹果酸度可见-近红外无损测定模型设计与优化[J]. 量子电子学报, 2022, 39(4): 531-540.