Quantitative Study of Laser Methane Concentration Based on Support Vector Machine
CAO Quan-wei1,TU Cheng-xu1,XU Hao-hao2,BAO Fu-bing1,LI Xiang2,SHEN Jia-yuan3
1. School of Metrology and Testing Engineering, China Jiliang University, Hangzhou, Zhejiang 310018, China
2. Zhejiang Zheneng Technology Research Institute Co., Ltd., Hangzhou, Zhejiang 310018, China
3. Zhejiang Zheneng Natural Gas Operation Co., Ltd., Hangzhou, Zhejiang 310000, China
Abstract It is important to detect methane gas and quantify methane concentration accurately based on tunable semiconductor laser absorption spectroscopy (TDLAS).Due to the weak laser methane signal, the traditional methane concentration quantification model has the problem of large quantization error under complex working conditions.To solve this problem, a quantitative regression model of laser methane telemetering concentration was built based on radial basis RBF-nu-SVR, and was compared with the traditional model, polynomial kernel and linear kernel nu support vector regression, BP neural network and other models.In the results, the RBF-nu-SVR model built showed strong generalization performance on the test set.The average absolute percentage error (MAPE) and Pearson correlation coefficient (R2) were 9.155 and 0.99947 respectively, which improved the detection accuracy of TDLAS for methane gas.Because the original data was used, it was unnecessary to extract the second harmonic, thus simplifying the structure.
CAO Quan-wei,TU Cheng-xu,XU Hao-hao, et al. Quantitative Study of Laser Methane Concentration Based on Support Vector Machine[J]. Acta Metrologica Sinica, 2023, 44(6): 981-985.
He D, Peng Z M, Ding Y J. Ignition-delay-time/time-resolved CO2-concentration measurements during the combustion of iC4H10/H2 mixtures ［J］. Fuel, 2021, 284: 118980.
Zhang L W, Pang T, Zhang Z R, et al. A novel compact intrinsic safety full range Methane microprobe sensor using “trans-world” processing method based on near-infrared spectroscopy［J］. Sensors and Actuators B: Chemical, 2021, 334: 129680.
Liang Y T, Chen C F, Tian F C, et al. Methane gas detection technology and its application in coal mines［J］. Coal Science and Technology, 2021, 49 (4): 40-48.
Pei Q B, Yan W C, Shen C, et al. Study on Dew Point Measurement of Natural Gas Based on Tunable Semiconductor Laser Absorption Spectrometry［J］. Acta Metrologica Sinica, 2021, 42 (1): 117-122.
Chen H, Ju Y, Han L, et al. Research on the relationship between modulation depth and center of high order harmonic in tdlas wavelength modulation method ［J］. Spectroscopy and Spectral Analysis, 2021, 41 (12): 3676-3681.
Yan G, Zhang L, Yu L, et al. Mid-Infrared Methane Sensor System for Natural Gas Leakage Detection and Its Application ［J］. Chinese Journal of Lasers, 2022, 49 (18): 118-126.
Kan L L, Ye L, Wang X L, et al. Identification of methane concentration based on TDLAS technology system ［J］. Control and Instruments in Chemical Industry, 2021, 48 (2): 122-127.
Sun X J, Li H, Tang L P, et al. Study on atmosphere volume scattering polarization degree characteristics in visible and infrared band ［J］. Acta Optica Sinica, 2011, 31 (5): 9-14.
［7］
Wei T T, Wu H P, Dong L, et al. Palm-sized methane TDLAS sensor based on a mini-multi-pass cell and a quartz tuning fork as a thermal detector ［J］. Opt Express, 2021, 29 (8): 12357-12364.
［14］
Zhang L, Wang R L, Liu K K. Study on Errors Correction of Infrared Methane Sensor Based on Support Vector Machines ［C］//Second International Conference on Intelligent Computation Technology Automation (ICICTA). Changsha, China, 2009.
Chen H Y, Liu J H, Sheng W M, et al. Application of SVM based on grey wolf optimizer in measurement error analysis of infrared methane sensor ［J］. Acta Metrologica Sinica, 2021, 42 (9): 1244-1249.
Zhang W H, Wang W Q, Zhang L, et al. Methane Gas Detection Based on Tunable Diode Laser Absorption Spectroscopy and Optical Fiber Sensing［C］//7th International Conference on Intelligent Computation Technology and Automation (ICICTA). Changsha, China, 2014.
［17］
Chang C C, Lin C J. Training v-Support Vector Regression: Theory and Algorithms ［J］. Neural Computation, 2002, 14: 1959-1977.
Wang B, Tang X J, Gan Y Y, et al. A TC/WMS-TDLAS mid-infrared detection method for ultra-low concentration carbon isotope methane［J］. Journal of Analytical Atomic Spectrometry, 2022, 37 (12): 2615-2624.
Xu J, Li Y F, Cheng Y, et al. Developmentof methane leakage telemetering system based on TDLAS-WMS ［J］. Laser & Optoelectronics Progress. https://kns.cnki.net/kcms/detail/31. 1690. TN. 20220212. 1750. 010. html. 2022-02-14.
2023, Vol. 44 
