Application of standard gas validation and supporting vector machine in spectral fidelity improvement

Wen-hai JI; Di SONG; Xiao-cui LÜ; Guo-lin LI

doi:10.3788/OPE.20192710.2144

您当前的位置：

首页 >

文章列表页 >

Application of standard gas validation and supporting vector machine in spectral fidelity improvement

Modern Applied Optics | 更新时间：2020-08-13

- Application of standard gas validation and supporting vector machine in spectral fidelity improvement
- Optics and Precision Engineering Vol. 27, Issue 10, Pages: 2144-2153(2019)
- 作者机构：
  
  中国石油大学(华东) 信息与控制工程学院，山东青岛 266580
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20192710.2144
  CLC： O433.4
- Received：08 May 2019，
  
  Accepted：24 June 2019，
  
  Published：15 October 2019
- 稿件说明：
移动端阅览
Wen-hai JI, Di SONG, Xiao-cui LÜ, et al. Application of standard gas validation and supporting vector machine in spectral fidelity improvement[J]. Optics and precision engineering, 2019, 27(10): 2144-2153.
DOI：

Wen-hai JI, Di SONG, Xiao-cui LÜ, et al. Application of standard gas validation and supporting vector machine in spectral fidelity improvement[J]. Optics and precision engineering, 2019, 27(10): 2144-2153. DOI： 10.3788/OPE.20192710.2144.

摘要

鉴于光谱分析仪在使用过程中会发生谱图微缓形变，造成光谱保真度下降，本文提出一种结合标气定期校验和最小二乘支持向量机(LS-SVM)的方法。在校验时，比较相同标准气体的当前光谱和出厂标定时的光谱，利用LS-SVM算法计算谱图形变，并根据形变分析结果进行复原。由于形变具有长期累积性和不可控性，所以用激光器驱动电流的可控性变化引起的谱图变化模拟形变。采用TDLAS技术实验，检测烯烃裂解炉清焦过程中的CO和CO

，使用20 m光程的Herriot气室和中心波长为1 580 nm的DFB激光器。共采集了50组不同形变程度的光谱，根据LS-SVM算法的形变分析结果，利用插值法还原谱图。对比了该方法与不复原以及传统寻峰复原方法的气体浓度分析精度，发现当分析仪存在复杂形变时，利用LS-SVM算法和插值法复原的方法比传统的寻峰方法精度提高2~3倍。实验结果验证了LS-SVM算法的谱图形变分析能力以及插值法复原的有效性。

Abstract

The output of spectroscopy analyzer undergoes slow and subtle distortion when operational for a long period. This results in degradation of the spectral fidelity and it adversely affects the analyzing accuracy. A design based on combination of periodic validation with standard gas and Least Square Supporting Vector Machine (LS-SVM) algorithm was proposed to overcome this issue. For validation

the current spectra and factory calibration spectra of the same standard validation gas were compared. The LS-SVM method was employed to calculate the spectra deformation and the deformation value was further used to restore the spectra. Because of the chronic accumulation and non-controllable characteristic

the deformation was simulated by changing the diode laser driving current. The simultaneous detection of CO and CO

in the olefin cracking furnace decoking process was chosen as the application example. Tunable Diode Laser Spectroscopy (TDLAS) platform was employed with a 20 m Herriot cell and a 1 580 nm DFFB. In total

50 spectra with different deformation levels were collected. The spectra were restored with an interpolation method based on the LS-SVM model output. Accuracy of the gas concentration calculation was compared with no restoration and traditional peak tracking restoration methods; we found that when the analyzer has a complex deformation

accuracy of the LS-SVM algorithm and the interpolation recovery method is 2—3 times higher than that of the traditional peak tracking method. The experiment result proves the effectiveness of the LS-SVM algorithm and the interpolation restoration method.

关键词

Keywords

references

阚瑞峰, 刘文清, 张玉钧, 等.可调谐二极管激光吸收光谱法测量环境空气中的甲烷含量[J].物理学报, 2005, 54(4):1927-1930.

KAN R F, LIU W Q, ZHANG Y J, et al .. Absorption measurements of ambient methane with tunable diode laser[J]. Acta Physica Sinica , 2005, 54(4): 1927-1930. (in Chinese)

刘文清, 崔志成, 刘建国, 等.大气痕量气体测量的光谱学和化学技术[J].量子电子学报, 2004, 21(2): 202-210.

LIU W Q, CUI Z CH, LIU J G, et al .. Measurement of atmospheric trace gases by spectroscopic and chemical techniques[J]. Chinese Journal of Quantum Electronics , 2004, 21(2): 202-210. (in Chinese)

张帅, 刘文清, 张玉钧, 等.基于激光吸收光谱技术天然气管道泄漏定量遥测方法的研究[J].物理学报, 2012, 61(5): 50701-050701.

ZHANG SH, LIU W Q, ZHANG Y J, et al .. Research of quantitative remote sensing of natural gas pipeline leakage based on laser absorption spectroscopy[J]. Acta Physica Sinica , 2012, 61(5): 50701-050701. (in Chinese)

张志荣, 孙鹏帅, 庞涛, 等.激光吸收光谱技术在工业生产过程及安全预警标识性气体监测中的应用[J].光学精密工程, 2018, 26(8): 1925-1937.

ZHANG ZH R, SUN P SH, PANG T, et al .. Application of laser absorption spectroscopy for identification gases in industrial production processes and early safety warning[J]. Opt.Precision Eng. , 2018, 26(8): 1925-1937. (in Chinese)

季文海, 吕晓翠, 胡文泽, 等. TDLAS技术在烯烃生产过程中的多组分检测应用[J].光学精密工程, 2018, 26(8): 1837-1845.

JI W H, LÜ X C, HU W Z, et al .. Application of TDLAS technology to multicomponent detection in olefin production process[J]. Opt.Precision Eng. , 2018, 26(8): 1837-1845. (in Chinese)

WANG Y, WEI Y B, CHANG J, et al .. Tunable diode laser absorption spectroscopy-based detection of propane for explosion early warning by using a vertical cavity surface enhanced laser source and principle component analysis approach[J]. IEEE Sensors Journal , 2017, 17(15): 4975-4982.

聂伟, 许振宇, 阚瑞峰, 等.可调谐二极管激光吸收光谱技术测量低温流场水汽露点温度[J].光学精密工程, 2018, 26(8): 1862-1869.

NIE W, XU ZH Y, KAN R F, et al .. Measurement of low water vapor dew-point temperature based on tunable diode laser absorption spectroscopy[J]. Opt.Precision Eng. , 2018, 26(8): 1862-1869. (in Chinese)

袁志国, 杨晓涛, 谢文强, 等.基于TDLAS直接检测法的柴油机NO x 排放在线测试[J].光谱学与光谱分析, 2018, 38(1): 194-199.

YUAN Z G, YANG X T, XIE W Q, et al .. Research on the online test of diesel NO x emission by TDLAS[J]. Spectroscopy and Spectral Analysis , 2018, 38(1): 194-199. (in Chinese)

SUR R, SUN K, JEFFRIES J B, et al .. Scanned-wavelength-modulation-spectroscopy sensor for CO, CO 2 , CH4 and H 2 O in a high-pressure engineering-scale transport-reactor coal gasifier[J]. Fuel , 2015, 150: 102-111.

李春光, 董磊, 王一丁, 等.基于TDLAS和ICL的紧凑中红外痕量气体探测系统[J].光学精密工程, 2018, 26(8): 1855-1861.

LI CH G, DONG L, WANG Y D, et al .. Compact mid-infrared trace has based on TDLAS and detection system ICL[J]. Opt.Precision Eng. , 2018, 26(8): 1855-1861. (in Chinese)

王晓梅, 张玉钧, 刘文清, 等.可调谐二极管吸收光谱痕量气体浓度算法的研究[J].光学技术, 2006(5): 717-719, 722.

WANG X M, ZHANG Y J, LIU W Q, et al .. Study on the arithmetic of trace gas concentration based on tunable diode absorption spectroscopy[J]. Optical Technique , 2006(5): 717-719, 722. (in Chinese)

张琳, 张黎明, 李燕, 等.偏最小二乘法在傅里叶变换红外光谱中的应用及进展[J].光谱学与光谱分析, 2005, 25(10): 1610-1613.

ZHANG L, ZHANG L M, LI Y, et al .. Application and improvement of partial-least-squares in Fourier transform infrared spectroscopy[J]. Spectroscopy and Spectral Analysis , 2005, 25(10): 1610-1613. (in Chinese)

WERLE P W, LECHNER S. Recent findings and approaches for the suppression of fluctuations and background drifts in tunable diode laser spectroscopy[C]//Application of Tunable Diode and Other Infrared Sources for Atmospheric Studies and Industrial Process Monitoring. International Society for Optics and Photonics , 1996, 2834: 68-79.

SAVORANI F, TOMASI G, ENGELSEN S B. i coshift: A versatile tool for the rapid alignment of 1D NMR spectra[J]. Journal of Magnetic Resonance , 2010, 202(2): 190-202.

张军, 朱永, 陈俊清, 等.痕量气体可调谐激光二极管吸收光谱分析系统在线自校准技术研究[J].光谱学与光谱分析, 2010, 30(4): 1030-1034.

ZHANG J, ZHU Y, CHEN J Q, et al .. Study on online self-calibration technique for trace gas analyzer based on tunable diode laser absorption spectroscopy[J]. Spectroscopy and Spectral Analysis, 2010, 30(4): 1030-1034. (in Chinese)

束小文, 张玉钧, 阚瑞峰, 等.基于TDLAS技术的HCl气体在线探测温度补偿方法研究[J].光谱学与光谱分析, 2010, 30(5): 1352-1356.

SHU X W, ZHANG Y J, KAN R F, et al .. An investigation of temperature compensation of HCL gas online monitoring based on TDLAS method[J]. Spectroscopy and Spectral Analysis , 2010, 30(5): 1352-1356. (in Chinese)

鲍伟义, 朱永, 陈俊, 等.可调谐激光二极管吸收光谱系统信号分析及谱线畸变校正技术研究[J].光谱学与光谱分析, 2011, 31(4): 1015-1019.

BAO W Y, ZHU Y, CHEN J, et al .. Signal analysis and spectrum distortion correction for tunable diode laser absorption spectroscopy system[J]. Spectroscopy and Spectral Analysis , 2011, 31(4): 1015-1019. (in Chinese)

王喆, 汪曣, 张锐, 等.奇异值分解用于可调谐二极管激光吸收光谱技术去除系统噪声[J].光谱学与光谱分析, 2016, 36(10): 3369-3376.

WANG J, WANG Y, ZHANG R, et al .. A singular value decomposition method for tunable diode laser absorption spectroscopy system to remove systematic noises[J]. Spectroscopy and Spectral Analysis , 2016, 36(10): 3369-3376. (in Chinese)

唐七星, 张玉钧, 陈东, 等.调谐激光吸收光谱波长偏移修正算法研究[J].光谱学与光谱分析, 2018, 38(11): 3328-3333.

TANG Q X, ZHANG Y J, CHEN D, et al .. Research on wavelength shift correction algorithm for tunable laser absorption spectrum[J]. Spectroscopy and Spectral Analysis , 2018, 38(11): 3328-3333. (in Chinese)

季文海, 杨雅涵, 任鹏, 等. TDLAS分析仪谱图微缓形变的复原算法[J].光子学报, 2017, 46(8): 812001-0812001.

JI W H, YANG Y H, REN P, et al .. Transfer and restoration algorithm for slow and subtle spectra deformation of TDLAS gas analyzer[J]. Acta Photonica Sinica , 2017, 46(8): 812001-0812001. (in Chinese)

BARMPALEXIS P, KARAGIANNI A, NIKOLAKAKIS I, et al .. Artificial neural networks (ANNs) and partial least squares (PLS) regression in the quantitative analysis of cocrystal formulations by Raman and ATR-FTIR spectroscopy[J] . Journal of Pharmaceutical and Biomedical Analysis , 2018, 158: 214-224.

MALEGORI C, NASCIMENTO MARQUES E J, DE FREITAS S T, et al .. Comparing the analytical performances of Micro-NIR and FT-NIR spectrometers in the evaluation of acerola fruit quality, using PLS and SVM regression algorithms[J]. Talanta , 2017, 165: 112-116.

LE BA TUAN, 肖冬, 毛亚纯, 等.可见、近红外光谱和深度学习CNN-ELM算法的煤炭分类[J].光谱学与光谱分析, 2018, 38(7): 2107-2112.

TUAN L B, XIAO D, MAO Y C, et al .. Coal classification based on visible, near-infrared spectroscopy and CNN-ELM algorithm[J]. Spectroscopy and Spectral Analysis , 2018, 38(7): 2107-2112. (in Chinese)

OWOLABI T O, GONDAL M A. Development of hybrid extreme learning machine based chemo-metrics for precise quantitative analysis of LIBS spectra using internal reference pre-processing method[J]. Analytica Chimica Acta , 2018, 1030: 33-41.

DASHTI A, RIASAT HARAMI H, REZAKAZEMI M, et al .. Estimating CH 4 and CO 2 solubilities in ionic liquids using computational intelligence approaches[J]. Journal of Molecular Liquids , 2018, 271: 661-669.

KONG W J, DING J L. Online learning algorithm for LS-SVM based modeling with time-varying kernels[J]. IFAC-Papers Online , 2018, 51(18): 626-630.

张友卫, 曹硕硕, 魏威, 等.基于UKF-LS-SVM的燃煤机组NO x 排放浓度预测方法[J].自动化仪表, 2018, 39(12):13-17.

ZHANG Y W, CAO S S, WEI W, et al .. NO x emission concentration prediction based on UKF-LS-SVM for coal-fired units[J]. Process Automation Instrumentation , 2018, 39(12): 13-17. (in Chinese)

Views

126

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

High finesse optical feedback cavity ringdown spectroscopy

Near-infrared optical-feedback linear cavity-enhanced absorption spectroscopy

On-line detection of carbon dioxide in large scale offshore by laser technology

Laser spectroscopy applied to combustion diagnostics

Related Author

KAN Ruifeng

HE Yabai

XU Zhenyu

DENG Hao

LIU Ying

MA Guosheng

Wei-guang MA

Gang ZHAO

Related Institution

Anhui Institute of Optics and Fine Mechanics， Hefei Institute of Physical Science， Chinese Academy of Sciences

University of Science and Technology of China

State Key Laboratory of Quantum Optics and Quantum Optics Devices， Institute of Laser Spectroscopy， Shanxi University

Collaborative Innovation Center of Extreme Optics， Shanxi University

Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Sciences, Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰