基于 IRIV-SA 的乙烯 FTIR 光谱波数优选

doi:10.3969/j.issn.1007-5461.2023.03.010

摘要/Abstract

摘要： 利用傅里叶变换红外光谱 (FTIR) 技术能够对有机物的成分及含量进行快速无损测量。作为重要的有机化工原料, 乙烯在塑料、醇类和纤维等大宗化学品的制造中有着广泛的应用, 但同时由于其易挥发性, 乙烯对环境和人体有着潜在的危害。为提高FTIR技术检测乙烯浓度模型的精度, 综合迭代保留信息变量法 (IRIV) 和模拟退火算法 (SA) 的优点, 提出了改进的IRIV-SA红外光谱波数优选算法。该方法在IRIV算法稳定选取大量光谱特征波数的基础上, 利用SA进一步筛选少量有效特征波数, 从而降低模型复杂度, 提高有机物光谱检测精度。实验首先利用IRIVSA对乙烯红外光谱的浓度进行波数选取, 最终获取的特征波数由全光谱的271个变量降低至 5 个变量, 再利用特征波数进行建模, 结果表明其验证集相关系数、均方根误差为0.9989和0.3943, 预测集相关系数、均方根误差为0.9978 和0.6652, 较全光谱建模精度有大幅提高。为进一步验证该算法的有效性, 同时建立IRIV、SA、CARS (自适应重加权采样算法)、SPA (连续投影算法) 以及IRIV-CARS、IRIV-SPA波数选取模型对相同数据集进行对比实验, 比对结果表明IRIV-SA算法优于上述 6 种波数选取方法, 是一种更有效的特征波数优选方法。

关键词: 傅里叶变换红外光谱, 乙烯, 波数优选, 迭代保留信息变量, 模拟退火算法

Abstract: Fourier transform infrared spectroscopy (FTIR) can rapidly and nondestructively measure the composition and content of organic matter. As an important organic chemical raw material, ethylene is widely used in the manufacturing of bulk chemicals such as plastics, alcohols and fibers. However, due to its volatility, ethylene is harmful to the environment and human body. To improve the accuracy of FTIR in the detection model of ethylene concentration, an improved IRIV-SA infrared spectral wavenumber optimization algorithm is proposed based on the advantages of iteratively retains informative variables method (IRIV) and simulated annealing algorithm(SA). On the basis of stable selection of a large number of spectral characteristic wavenumbers by IRIV algorithm, this method uses SA to further screen a small number of effective characteristic wavenumbers, so as to reduce the complexity of the model and improve the detection accuracy of organic matter spectrum. In the experiment, IRIV-SA is used to select the wavenumber of the concentration of ethylene infrared spectrum at first, and the number of characteristic wavenumbers obtained is reduced from 271 to 5, then the characteristic wavenumber is used for modeling. The results show that the correlation coefficient and root mean square error of validation set are 0.9989 and 0.3943, and the correlation coefficient and root mean square error of prediction set are 0.9978 and 0.6652, which indicates that the modeling accuracy of the proposed algorithm is significantly improved compared with that of the whole spectrum modeling. To further verify the effectiveness of the improved algorithm, IRIV, SA, CARS (competitive adaptive reweighted sampling algorithm), SPA (successive projections algorithm), IRIV-CARS and IRIV-SPA wavenumber selection models are established for comparative experiments on the same data set. The comparison results show that IRIV-SA algorithm is superior to the above six wavenumber selection methods, and is an effective feature wavenumber selection method.

Key words: Fourier transform infrared spectroscopy, ethylene, wavenumber selection, iteratively retains informative variables, simulated annealing algorithm

中图分类号:

O657.33

张梦思 , 鞠薇 , 程志友 , 任慧东 . 基于 IRIV-SA 的乙烯 FTIR 光谱波数优选[J]. 量子电子学报, 2023, 40(3): 383-391.

ZHANG Mengsi , JU Wei , CHENG Zhiyou , REN Huidong. FTIR spectral wavenumber optimization for ethylene based on IRIV-SA[J]. Chinese Journal of Quantum Electronics, 2023, 40(3): 383-391.

参考文献

[1] Wang Z P, Shi R, Zhang T R. Three-phase electrochemistry for green ethylene production [J]. Current Opinion in Electrochemistry, 2021, 30: 100789.
[2] He V C, Wang Y, Chen Y, et al. An ethane-favored metal-organic framework with tailored pore environment used for efficient ethylene separation [J]. Microporous and Mesoporous Materials, 2021, 320: 111096.
[3] Ren T, Patel M K, Blok K. Steam cracking and methane to olefins: Energy use, CO2 emissions and production costs [J]. Energy, 2008, 33(5):817–833.
[4] Niu H, Mo Z W, Shao M, et al. Screening the emission sources of volatile organic compounds (VOCs) in China by multi-effects evaluation [J]. Frontiers of Environmental Science & Engineering, 2016, 10(5): 1– 11.
[5] Wei W, Ren Y T, Yang G, et al. Characteristics and source apportionment of atmospheric volatile organic compounds in Beijing, China [J]. Environmental Monitoring and Assessment, 2019, 191(12): 762.
[6] Akhter F, Siddiquei H R, Mukhopadhyay S C. A Graphene-based Composite for Selective Detection of Ethylene at Ambient Environment [J]. 2021 IEEE Sensors, 2021, 1-4.
[7] Li Z B, Pang W, Liang H B, et al. A novel method to realize multicomponent infrared spectroscopy gas logging based on PSO-split peak fitting-SVM [J]. Journal of Natural Gas Science and Engineering, 2022, 101(07): 104496.
[8] Leite D C, Corrêa A A P, Júnior L C C, et al. Non-destructive genotypes classification and oil content prediction using near-infrared spectroscopy and chemometric tools in soybean breeding program [J]. Journal of Food Composition and Analysis, 2020, 91: 103536.
[9] Shi Y J, Wu H T, Liu W H, et al. The design of wireless electronic nose based on near infrared spectral absorption technology [J]. Infrared and Laser Engineering, 2021.
史屹君，武鸿涛，刘文皓，等. 基于近红外光谱吸收技术的无线电子鼻设计 [J]. 红外与激光工程，2021.
[10] Qu D S, Fan H J, Liu L W, et al. Measurement of gas parameters in supersonic combustion field based on near-infrared spectroscopy [J]. Acta Optica Sinica, 2020, 40(03): 198-205.
屈东胜，樊宏杰，刘连伟，等. 基于近红外光谱的超声速燃烧场气体参数测量研究 [J]. 光子学报，2020，40(03): 198-205.
[11] Zhang J, Yuan S, Zhang J. Detection of sugar degree in strawberry based on wavelet transform-genetic algorithm-partial least squares [J]. Journal of Analytical Science, 2020, 36(01): 111-115.
张娟，原帅，张骏. 基于小波变换-遗传算法-偏最小二乘的草莓糖度检测研究 [J]. 分析科学学报，2020，36(01): 111-115.
[12] Deng H R, Lv C W, Chen D L, et al. Application of ant colony optimization in hyperspectral prediction modeling of soil texture [J]. Chinese Journal of Soil Science, 2021, 52(05): 1063-1068.
邓浩然，吕成文，陈东来，等. 蚁群算法在土壤质地高光谱预测建模中的应用 [J]. 土壤通报，2021，52(05): 1063-1068.
[13] Xu L, Zhu W H, Yao H B, et al. Prediction of acetic acid concentration in Chinese liquors based on fluorescence spectrum and simulated annealing algorithm [J]. Spectroscopy and Spectral Analysis, 2021, 41(07): 2159-2165.
许蕾，朱卫华，姚红兵，等. 基于荧光光谱—模拟退火法年份白酒中乙酸浓度预测研究 [J]. 光谱学与光谱分析，2021，41(07): 2159-2165.
[14] Huang J S, Wang D X, Xiong A H, et al. A hybrid variable selection strategy of near infrared spectroscopy for detection the ratio of tea polyphenols to amino acids in green tea infusion [J]. Acta Agriculturae Universitatis Jiangxiensis, 2020, 42(06): 1270-1276.
黄俊仕，王冬欣，熊爱华，等. 基于混合变量选择的绿茶酚氨比近红外光谱检测方法 [J]. 江西农业大学学报，2020，42(06): 1270-1276.
[15] Zhao J Y, Xiong Z X, Ning J M, et al. Wavelet transform combined with SPA to optimize the near-infrared analysis model of caffeine in tea [J]. Journal of Analytical Science, 2021, 37(05): 611-617.
赵静远，熊智新，宁井铭，等. 小波变换结合连续投影算法优化茶叶中咖啡碱的近红外分析模型 [J]. 分析科学学报，2021，37(05): 611-617.
[16] Li C T, Zhang Y Y, Chen H Z, et al. Near-infrared spectral waveband selection for soil potassium based on simulated annealing [J]. Laser & Optoelectronics Progress, 2022, 59(13): 1330002.
李春婷，张优优，陈华舟，等. 基于模拟退火的土壤钾含量近红外光谱波段优选 [J]. 激光与光电子学进展，2022，59(13): 1330002.
[17] Sun X R, Zhou Z J, Liu C L, et al. Near infrared spectroscopic detection of gluten content in wheat flour based on spectral pretreatment and simulated annealing algorithm [J]. Food Science, 2018, 39(02): 222-226.
孙晓荣，周子健，刘翠玲，等. 光谱预处理结合模拟退火算法的小麦粉面筋含量检测 [J]. 食品科学，2018，39(02): 222-226, 2018, 39(02): 222-226.
[18] Yun Y H, Wang W T, Tan M L, et al. A strategy that iteratively retains informative variables for selecting optimal variable subset in multivariate calibration [J]. Analytica Chimica Acta, 2014, 807: 36-43.
[19] Zhang H, Liu G H, Jiang H, et al. Quantitative detection of ethanol solid-state fermentation process parameters based on near infrared spectroscopy [J]. Laser & Optoelectronics Progress, 2017, 54(02): 320-326.
张航，刘国海，江辉，等. 基于近红外光谱技术的乙醇固态发酵过程参数定量检测 [J]. 激光与光电子学进展，2017，54(02): 320-326.
[20] Cheng J H, Chen Z G. Wavelength selection method for near infrared spectroscopy based on iteratively retains informative variables and successive projections algorithm [J]. Chinese Journal of Analytical Chemistry, 2021, 49(08): 1402-1409.
程介虹，陈争光. 基于迭代保留信息变量和连续投影的近红外光谱波长选择方法 [J]. 分析化学，2021，49(08): 1402-1409.
[21] An S Y, Zhang L, Shang X Z, et al. Variable selection method in the NIR quantitative analysis model of total saponins in red ginseng extract [J]. Spectroscopy and Spectral Analysis, 2021, 41(01): 206-209.
安思宇，张磊，尚献召，等. 红参提取物总皂苷近红外定量分析建模中的变量筛选 [J]. 光谱学与光谱分析，2021，41(01): 206-209.
[22] Zhan X R, Zhu X R, Shi X Y, et al. Determination of hesperidin in tangerine leaf by near-infrared spectroscopy with SPXY algorithm for sample subset partitioning and Monte Carlo cross validation [J]. Spectroscopy and Spectral Analysis, 2009, 29(4): 964-968.
展晓日，朱向荣，史新元，等. SPXY 样本划分法及蒙特卡罗交叉验证结合近红外光谱用于橘叶中橙皮苷的含量测定 [J]. 光谱学与光谱分析，2009，29(4): 964-968, 2009, 29(4): 964-968.
[23] Ji R S, Chen X Y, Liu S Z, et al. Nondestructive testing of volatile oil of zanthoxylum bungeanum based on hyperspectral technique and IRIV-FOA-ELM algorithm [J]. Laser & Optoelectronics Progress, 2020, 57(20): 394-400.
纪然仕，陈晓燕，刘素珍，等. 基于高光谱技术和IRIV-FOA-ELM算法的花椒挥发油无损检测 [J]. 激光与光电子学进展，2020，57(20): 394-400.
[24] Huang F, Zhang X K, Sun L, et al. Vibration spectral component analysis based on genetic algorithm and simulated annealing algorithm [J]. Laser & Optoelectronics Progress, 2020, 57(09): 224-231.
黄凡，张旭坤，孙陆，等. 基于遗传算法和模拟退火算法的振动光谱成分分析算法 [J]. 激光与光电子学进展，2020，57(09): 224-231.