Semi-supervised methane gas concentration detection model based on TDLAS technology

Abstract

Because methane is flammable and explosive, the detection process is time-consuming and dangerous, and it is difficult to obtain labeled data. In order to reduce the dependence on marker data when detecting methane concentration using tunable diode laser absorption spectroscopy (TDLAS) technology, this paper designs a methane gas acquisition platform based on TDLAS and proposes a methane gas concentration detection model based on semi-supervised learning. Firstly, the methane gas is feature extracted, and then semi-supervised learning is introduced to select the optimal feature combination; subsequently, the traditional whale optimization algorithm is improved to optimize the parameters of the random forest to detect the methane gas concentration. The results show that the model is not only able to select the optimal feature combination under limited labeled data, but also has an accuracy of 94.25%, which is better than the traditional model, and is robust in terms of parameter optimization.

Keywords

A

References

[1] Nie W, Kan R F, Yang C G. et al.. Progress in the application of tunable diode laser absorption spectroscopy technology. Chinese optics, 2018, 45(09): 9-29[J]

[2] Zhang L, Li X, Wang Z B. et al.. Design of digital phase-locked loop circuit for TDLAS methane telemetry. Sensors and microsystems, 2019, 38(1): 89-92[J]

[3] Yao S C, Guo S J, Yang Y. et al.. Research and application of flue gas ammonia slip detection based on tunable diode laser absorption spectroscopy technology. Chinese journal of photonics, 2023, 52(03): 11-24[J]

[4] Li Z, Zhang Z R, Sun P S. et al.. Multipoint full-range monitoring of methane gas using TDLAS technology. Infrared and laser engineering, 2017, 46(09): 243-249[J]

[5] Deng Y, Tang W, Li Z H. et al.. Research on gas concentration inversion method based on direct absorption peak-to-peak calibration. Laser & optoelectronics progress, 2021, 58(3): 325-332[J]

[6] YAO W. Pipeline laser methane detector based on TDLAS technology for in-situ direct measurement[J]. Journal of physics: conference series, 2022, 2246(1).

[7] Xin F, Li J, Guo J. et al.. Measurement of atmospheric CO₂ column concentrations based on open-path TDLAS. Sensors, 2021, 21(5): 1722. J]

[8] Li Z, Zhang Z R, Sun P S. et al.. Multi-point full-scale monitoring of methane gas using TDLAS technology. Infrared and laser engineering, 2017, 46(09): 243-249[J]

[9] Tian L, Sun J, Chang J. et al.. Retrieval of gas concentrations in optical spectroscopy with deep learning. Measurement, 2021, 182: 109739. J]

[10] Liao H, Zhu W, Zhang B. et al.. Application of natural gas pipeline leakage detection based on improved DRSN-CW. 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT), November 26–28, 2021, Chongqing, China, 2021New YorkIEEE514-518[C]

[11] Goldschmidt J, Nitzsche L, Wolf S. et al.. Rapid quantitative analysis of IR absorption spectra for trace gas detection by artificial neural networks trained with synthetic data. Sensors, 2022, 22(3): 857. J]

[12] WANG W, LIU H, WEI G, et al. Hybrid simulated annealing particle swarm optimization support vector machine based temperature-pressure error compensation approach for TDLAS gas detection[J]. Combustion science and technology, 2023: 1–18.

[13] Luo Q, Zhou J, Li W. et al.. Interference fringe suppression for oxygen concentration measurement using adaptive harmonic feeding generative adversarial network. IEEE sensors journal, 2021, 22(3): 2419-2429. J]

[14] Zuo Z, Ma L, Liang S. et al.. A semi-supervised leakage detection method driven by multivariate time series for natural gas gathering pipeline. Process safety and environmental protection, 2022, 164: 468-478. J]

[15] Cui H, Wang F, Hu S. et al.. Determination of methane during anaerobic digestion by tunable diode laser absorption spectroscopy (TDLAS). Instrumentation science & technology, 2023, 51(5): 544-557. J]

[16] Fu B, Zhang C, Lyu W. et al.. Recent progress on laser absorption spectroscopy for determination of gaseous chemical species. Applied spectroscopy reviews, 2022, 57(2): 112-152. J]

[17] Sheikhpour R, Sarram M A, Gharaghani S. et al.. A survey on semi-supervised feature selection methods. Pattern recognition, 2017, 64: 141-158. J]

[18] Xu J, Tang B, He H. et al.. Semisupervised feature selection based on relevance and redundancy criteria. IEEE transactions on neural networks and learning systems, 2016, 28(9): 1974-1984. J]

[19] Pang Q, Zhang L. A recursive feature retention method for semi-supervised feature selection. International journal of machine learning and cybernetics, 2021, 12(9): 2639-2657. J]

[20] Xiao X W, Xiao D, Lin J G. et al.. A survey of multi-objective optimization problems. Research on computer applications, 2011, 28(03): 805-808[J]

[21] Dokeroglu T, Sevinc E, Kucukyilmaz T. et al.. A survey on new generation metaheuristic algorithms. Computers & industrial engineering, 2019, 137: 106040. J]

RIGHTS & PERMISSIONS

Tianjin University of Technology