荧光寿命衰减曲线结合支持向量机的油种识别

大气与环境光学学报 ›› 2022, Vol. 17 ›› Issue (2): 258-266.

荧光寿命衰减曲线结合支持向量机的油种识别

景敏∗, 陈曼龙, 丁敏, 张琦, 杨帆, 马祯元

陕西理工大学机械工程学院, 陕西汉中, 723001

收稿日期:2020-12-17 修回日期:2022-02-21 出版日期:2022-03-28 发布日期:2022-03-28
通讯作者: E-mail: jingmin@snut.edu.cn E-mail:jingmin@snut.edu.cn
作者简介:景敏 (1978 - ), 女, 陕西汉中人, 博士, 副教授, 硕士生导师, 主要从事激光诱导荧光检测、机器视觉检测等方面的研究。 E-mail: jingmin@snut.edu.cn
基金资助:
Supported by Natural Science Foundation of Shaanxi Provincial Department of Education (陕西省教育厅科学研究项目, 18JK0163), Natural Science Foundation of Shaanxi Provincial Department of Science and Technology (陕西省科技厅科学研究项目, 2019JM-171, 2022JM-383), Natural Science Foundation of Shaanxi University of Technology (陕西理工大学科学研究项目, SLGRCQD2103)

Oil recognition based on fluorescence-lifetime decay curve combined with support vector machine

JING Min∗, CHEN Manlong, DING Min, ZHANG Qi, YANG Fan, MA Zhenyuan

School of Mechanical Engineering, Shaanxi University of Technology, Hanzhong, 723001, China

Received:2020-12-17 Revised:2022-02-21 Published:2022-03-28 Online:2022-03-28
Contact: Min JING E-mail:jingmin@snut.edu.cn

摘要/Abstract

摘要： 作为一种重要检测手段, 主动荧光探测利用荧光寿命参数作为荧光探测的特征参数, 可以解决荧光强度易受外界环境因素影响的问题。基于门控探测法测量荧光寿命的原理, 利用荧光寿命衰减曲线结合非线性最小二乘回归拟合荧光寿命衰减函数来提取荧光平均寿命参数, 利用荧光寿命图谱绘制荧光物质的二维空间分布, 进而提出并实验验证了结合支持向量机利用荧光寿命参数作为特征向量进行油种识别的方法。实验结果表明, 利用荧光平均寿命作为参数, 激发区域中像素点荧光寿命值落入各自置信区间内的概率为 68% 以上, 结合支持向量机进行油种识别, 识别概率在 77% 以上。利用荧光寿命参数进行油种识别具有可行性且具有良好的识别率, 同时结合支持向量机的识别方法所需训练样本少, 因此利用荧光寿命衰减曲线结合支持向量机的油种识别方法有望为环境污染领域油种识别研究提供另一种参考。

关键词: 主动荧光探测, 荧光寿命, 门控探测法, 支持向量机

Abstract: As an important detection method, active fluorescence detection uses fluorescence lifetime as the characteristic parameter of fluorescence detection, which can solve the problem that the fluorescence intensity is easily affected by external environmental factors to a certain extent. Based on the principle of the gated-detection method for measuring fluorescence life, the nonlinear least square regress combined with fluorescence lifetime decay curve is used to fit the fluorescence lifetime decay function to extract the average fluorescence lifetime parameters, and the two-dimensional spatial distribution of fluorescence substances is drawn from the fluorescence life map. Furthermore, a method of oil types recognition using fluorescence lifetime parameter as feature vector is proposed and experimentally verified. The experimental results show that the probability of the pixel point fluorescence lifetime falling into the confidence interval in the excitation region is more than 68% by using the fluorescence average life as a parameter, and the recognition probability is over 77% by using the support vector machine for oil types recognition. It seems that it is feasible and has a good recognition rate to identify oil species by using fluorescence lifetime parameter, and at the same time, less training samples are required for the method combined with support vector machine. Therefore, the oil recognition method based on fluorescence lifetime decay curve combined with support vector machine will provide another reference for oil types recognition research in the field of environmental pollution.

Key words: active fluorescence detection, fluorescence lifetime, time-gated detection, support vector machine

中图分类号:

X831

景敏∗, 陈曼龙, 丁敏, 张琦, 杨帆, 马祯元. 荧光寿命衰减曲线结合支持向量机的油种识别[J]. 大气与环境光学学报, 2022, 17(2): 258-266.

JING Min∗, CHEN Manlong, DING Min, ZHANG Qi, YANG Fan, MA Zhenyuan. Oil recognition based on fluorescence-lifetime decay curve combined with support vector machine[J]. Journal of Atmospheric and Environmental Optics, 2022, 17(2): 258-266.

参考文献 28

[1]	Alaruri S D. Multiwavelength laser induced fluorescence (LIF) LIDAR system for remote detection and identification of oil
	spills [J]. Optik, 2019, 181: 239-245.
[2]	Jing M, Hua D X, Yue J. Simulation of fluorescence lidar for detecting oil slick [J]. Acta Physica Sinica, 2016, 65(7): 070704.
	景敏, 华灯鑫, 乐静. 荧光激光雷达技术探测水面油污染系统仿真研究 [J]. 物理学报, 2016, 65(7): 070704.
[3]	He S L, Chen X, Li S, et al. Small hyperspectral imagers and lidars and their marine applications [J]. Infrared and Laser
	Engineering, 2020, 49(2): 0203001.
	何赛灵, 陈祥, 李硕, 等. 小型高光谱图谱仪与激光雷达及其海洋应用 [J]. 红外与激光工程, 2020, 49(2): 0203001．
[4]	Zhang Q J, Wang Z G, Wang S S, et al. Dynamic release correlation between extracellular organic components and microcystins
	MC-LR based on three-dimensional fluorescence spectroscopy [J]. Journal of Atmospheric and Environmental Optics, 2020,
15	(4): 285-295.
	张晴静, 王志刚, 王赛赛, 等. 基于三维荧光光谱分析的胞外有机物组分与微囊藻毒素 MC-LR 的动态释放关联性研究
[J]	大气与环境光学学报, 2020, 15(4): 285-295.
[5]	Chen H, Geng D C, Chen T, et al. Second-derivative laser-induced fluorescence spectroscopy combined with chemometrics for
	authentication of the adulteration of camellia oil [J]. CyTA-Journal of Food, 2018, 16(1): 747-754.
[6]	Shen X S, Liu S Y, Yuan B, et al. Measurement of OH reactivity of diesel vehicles exhaust based on LIF method [J]. Journal
	of Atmospheric and Environmental Optics, 2020, 15(4): 269-284.
	沈翔森, 刘硕英, 袁斌, 等. 基于 LIF 方法对柴油车尾气羟基总反应性测量 [J]. 大气与环境光学学报, 2020, 15(4):
26	9-284．
[7]	Zheng Y C, Wang Y Z, Yue C Y. Technical and application development study of space-borne atmospheric environment
	observation lidar [J]. Infrared and Laser Engineering, 2018, 47(3): 0302002.
	郑永超, 王玉诏, 岳春宇. 天基大气环境观测激光雷达技术和应用发展研究 [J]. 红外与激光工程, 2018, 47(3): 0302002．
[8]	Luan X N, Zhang F, Guo J J, et al. Polarization characterization of laser-induced fluorescence from the simulated oil spill
	samples [J]. Spectroscopy and Spectral Analysis, 2017, 37(7): 2092 -2099.
	栾晓宁, 张锋, 郭金家, 等. 模拟溢油样品激光诱导荧光光谱的偏振特性研究 [J]. 光谱学与光谱分析, 2017, 37(7):
20	92-2099.
[9]	Zhou Z Z, Guo L D, Shiller A M, et al. Characterization of oil components from the Deepwater Horizon oil spill in the Gulf of
	Mexico using fluorescence EEM and PARAFAC techniques [J]. Marine Chemistry, 2013, 148: 10-21.
[10]	Liu B X, Li Y, Han L. Identification of oil type using spectral reflectance characteristics [J]. Spectroscopy and Spectral Analysis,
20	16, 36(4): 1100-1103.
	刘丙新, 李颖, 韩亮. 基于光谱反射率数据的水面油种鉴别研究 [J]. 光谱学与光谱分析, 2016, 36(4): 1100-1103.
[11]	Xu J, Wang Y T, Liu X F. A novel pretreatment method of three-dimensional fluorescence data for quantitative measurement
	of component contents in mixture [J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2015, 140:
48	4-488.
[12]	Liu D Q, Luan X N, Han X S, et al. Characterization of time-resolved laser-induced fluorescence from crude oil samples [J].
	Spectroscopy and Spectral Analysis, 2015, 35(6): 1582-1586.
	刘德庆, 栾晓宁, 韩晓爽, 等. 原油样品激光诱导荧光的时间分辨光谱特性研究 [J]. 光谱学与光谱分析, 2015, 35(6):
15	82-1586.
[13]	Xiao X, Zhao N J, Yu S H, et al. Laser induced time-resolved fluorescence spectroscopy characteristics of fluoranthene in
	ethanol with nanosecond laser of 355nm [J]. Spectroscopy and Spectral Analysis, 2016, 36(11): 3497-3500.
	肖雪, 赵南京, 于绍慧, 等. 355 nm 纳秒激光作用下荧蒽的时间分辨荧光光谱特征 [J]. 光谱学与光谱分析, 2016, 36(11):
34	97-3500．
[14]	Han X S, Liu D Q, Luan X N, et al. Discrimination of crude oil samples using laser-induced time-resolved fluorescence
	spectroscopy [J]. Spectroscopy and Spectral Analysis, 2016, 36(2): 445-448.
	韩晓爽, 刘德庆, 栾晓宁, 等. 基于激光诱导时间分辨荧光的原油识别方法研究 [J]. 光谱学与光谱分析, 2016, 36(2):
44	5-448.
[15]	Liu D H, Xiao X M, Cheng P, et al. Study of genetic evolution of oil inclusion and density of surface oil by measurement of
	fluorescence lifetime of crude oil and oil inclusion [J]. Scientia Since (Terrae), 2016, 46(12): 1626-1632.
	刘德汉, 肖贤明, 程鹏, 等. 应用原油和石油包裹体荧光寿命研究石油包裹体的成因演化和对应地面原油的密度 [J]. 中
	国科学: 地球科学, 2016, 46(12): 1626-1632．
[16]	Gao K, Li D D U. Estimating fluorescence lifetimes using extended Kalman filter [J]. Electronics Letters, 2017, 53(15): 1027-
	1029.
[17]	Shao Y X, Yang X P, Wang Z Y, et al. Fluorescence information processing based on wavelet de-noising [J]. Applied Mechanics
	& Materials, 2015, 734: 56-63.
[18]	Liu B X, Li Y, Han L. Identification of oil type using spectral reflectance characteristics [J]. Spectroscopy and Spectral Analysis,
20	16, 36(4): 1100-1103.
	刘丙新, 李颖, 韩亮. 基于光谱反射率数据的水面油种鉴别研究 [J]. 光谱学与光谱分析, 2016, 36(4): 1100-1103．
[19]	Liu X H, Chen S Y, Zhang Y C, et al. Rapid recognition of common machine oils based on laser induced fluorescence [J].
	Spectroscopy and Spectral Analysis, 2014, 34(8): 2148-2151.
	刘晓华, 陈思颖, 张寅超, 等. 基于激光诱导荧光的常见机油快速识别方法 [J]. 光谱学与光谱分析, 2015, 34(8):
21	48-2151.
[20]	Liu X B, Lin D Y, Wu Q Q, et al. Recent progress of fluorescence lifetime imaging microscopy technology and its application
[J]	Acta Physica Sinica, 2018, 67(17): 27-40.
	刘雄波, 林丹樱, 吴茜茜, 等．荧光寿命显微成像技术及应用的最新研究进展 [J]. 物理学报, 2018, 67(17): 27-40.
[21]	Nevin A, Cesaratto A, Bellei S, et al. Time-resolved photoluminescence spectroscopy and imaging: New approaches to the
	analysis of cultural heritage and its degradation [J]. Sensors (Basel, Switzerland), 2014, 14(4): 6338-6355.
[22]	Jing M, Le J, Hua D X, et al. Laser speckle jitter correction in plant fluorescence lifetime extraction [J]. Measurement, 2019,
13	3: 33-40.
[23]	Wan W B, Su J H. Study of laser-induced plant fluorescence lifetime imaging technology for plant remote sensing monitor [J].
	Measurement, 2018, 125: 564-571.
[24]	Zhang Y L, Li D D U. Comment on ′A novel method for fast and robust estimation of fluorescence decay dynamics using
	constrained least-square deconvolution with Laguerre expansion′ [J]. Physics in Medicine and Biology, 2017, 62(4): 1632-
	1636.
[25]	Jing M. Research on Measurement Technique and Application of Laser-induced Fluorescence Lifetime Imaging [D]. Xi′an:
	Xi′an University of Technology, 2019.
	景敏. 基于激光诱导的荧光寿命成像检测技术及应用研究 [D]. 西安: 西安理工大学, 2019.
[26]	Lin X L, Yuan R, Sun Y Q, et al. The basic theory and research progress of support vector machine [J]. Journal of Yangtze
	University (Natural Science Edition), 2018, 15(17): 48-53.
	林香亮, 袁瑞, 孙玉秋, 等. 支持向量机的基本理论和研究进展 [J]. 长江大学学报 (自科版), 2018, 15(17): 48-53．
[27]	Miao Y H, Yang M, Wu G J. Sophisticated vegetation classification based on multi-dimensional features of hyperspectral image
[J]	Journal of Atmospheric and Environmental Optics, 2020, 15(2): 117-124.
	苗宇宏, 杨敏, 吴国俊. 基于高光谱影像多维特征的植被精细分类 [J]. 大气与环境光学学报, 2020, 15(2): 117-124．
[28]	Liu F Y, Wang S H, Zhang Y D. Overview on models and applications of support vector machine [J]. Computer Systems &
	Applications, 2018, 27(4): 1-9.
	刘方园, 王水花, 张煜东. 支持向量机模型与应用综述 [J]. 计算机系统应用, 2018, 27(4): 1-9.