Real-time detection of methane concentration based on TDLAS technology and 1D-WACNN

Abstract

In order to further reduce the cost of manually screening suitable second harmonic signals for curve fitting when detecting methane concentration by tunable diode laser absorption spectroscopy (TDLAS) technology, as well as the influence of certain human factors on the amplitude screening of second harmonic signals, and improve the detection accuracy, a one-dimensional wide atrous convolutional neural network (1D-WACNN) method for methane concentration detection is proposed, and a real-time detection system based on TDLAS technology to acquire signal and Jetson Nano to process signal is built. The results show that the accuracy of this method is 99.96%. Compared with other methods, this method has high accuracy and is suitable for real-time detection of methane concentration.

References

[1] Kwasny M, Bombalska A. Optical methods of methane detection[J]. Sensors, 2023, 23: 2834. Bibcode: ,

[2] Yang K, Zhang L, Wu X S, et al. . Methane concentration detection system for cigarette smoke based on TDLAS technology[J]. Spectroscopy and spectral analysis, 2015, 35(12): 3310

[3] Noel S, Bramstedt K, Rozanov A, et al. . Stratospheric methane profiles from sciamachy solar occultation measurements derived with onion peeling DOAS[J]. Atmospheric measurement techniques, 2011, 4: 2567-2577. Bibcode: ,

[4] Tan T, Lebron G. Determination of carbon dioxide, carbon monoxide, and methane concentrations in cigarette smoke by fourier transform infrared spectroscopy[J]. Journal of chemical education, 2011, 89(3): 383-386. Bibcode: ,

[5] Zhou Z, Cheng Y, Yin S F, et al. . Simulation analysis and experimental study of high precision laser methane telemetry parameters for non-cooperative target[J]. Journal of optoelectronics·laser, 2023, 34(08): 861-871 (in Chinese)

[6] Liu Y, Wu J N, Chen M M, et al. . Trace methane gas detector based on TDLAS-WMS[J]. Spectroscopy and spectral analysis, 2016, 36(01): 279-282

[7] CHEN X Y, CHEN H Y. Improved LMS adaptive algorithm for noise reduction in TDLAS methane detection[J/OL]. Laser journal, 2023, [2023-10-13]. http://kns.cnki.net/kcms/detail/50.1085.TN.20230807.1439.002.html. (in Chinese)

[8] Terbe D, Orz L, Zarandy Á. Classification of holograms with 3D-CNN[J]. Sensors, 2022, 22: 8366. Bibcode: ,

[9] Zhang T J. Flow measurement of natural gas in pipeline based on 1D-convolutional neural network[J]. International journal of computational intelligence systems, 2020, 13: 1198-1206.

[10] Lu C S, Bian Y M, Hu X, et al. . Mixed gas concentration inversion based on the ultraviolet absorption spectrum by a hierarchical convolutional neural network[J]. Journal of applied spectroscopy, 2022, 89: 751-760. Bibcode: ,

[11] Lv C G, Gu Y W, Zhao X Y, et al. . Mixed gas concentration inversion based on the hierarchical feature fusion convolutional neural network[J]. Optics communications, 2023, 536: 129369.

[12] Xiao B W, Yan C M. A lightweight global awareness deep network model for flame and smoke detection[J]. Optoelectronics letters, 2023, 19(10): 614-622. Bibcode: ,

[13] Cui H B, Wang F, Hu S Y, et al. . Determination of methane during anaerobic digestion by tunable diode laser absorption spectroscopy (TDLAS)[J]. Instrumentation science & technology, 2023, 51(5): 44-55.

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

[15] Song X D, Cong Y Y, Song Y F, et al. . A bearing fault diagnosis model based on CNN with wide convolution kernels[J]. Ambient intelligence and humanized computing, 2022, 13: 4041-4056.

[16] Li Z Q, Jiang J, Chen X, et al. . Dense-scale dynamic network with filter-varying atrous convolution for semantic segmentation[J]. Applied intelligence, 2023, 53(22): 26810-26826.

[17] Li K, Liu Z D. MCANet: multi-scale contextual feature fusion network based on atrous convolution[J]. Multimedia tools and applications, 2023, 82(22): 1-24.

[18] Uyanik H, Şentvrk E, Akpinar M, et al. . A multi-input convolutional neural networks model for earthquake precursor detection based on ionospheric total electron content[J]. Remote sensing, 2023, 15(24): 5690. Bibcode: ,