Research on Measurement Method of δ13C and δ18O Isotopes Abundance in Exhaled Gas Based on the BP Neural Network Model
HUANG Wen-biao1, 2, XIA Hua2*, WANG Qian-jin1, 2, SUN Peng-shuai2, PANG Tao2, WU Bian2, ZHANG Zhi-rong1, 2, 3, 4*
1. Science Island Branch, Graduate School of University of Science and Technology of China, Hefei 230026, China
2. Anhui Provincial Key Laboratory of Photonic Devices and Materials, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
3. Key Lab of Environmental Optics & Technology, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
4. Advanced Laser Technology Laboratory of Anhui Province, National University of Defense Technology, Hefei 230037, China
Abstract：The 13C urea breath test is widely used as the “gold standard” for detecting Helicobacter pylori domestically and internationally. Accurate measurements of carbon and oxygen isotope characteristics in CO2 are significant for disease diagnosis. Tunable diode laser absorption spectroscopy (TDLAS) has been widely used in multiple fields due to its simple structure, fast response speed, and high sensitivity. It is also fully suitable for the measurement and research of gas isotopes. In this study, a quantum cascade laser with a central wavelength of 4.32 μm and a small volume gas absorption cellwith an optical path of 14 cm and volume of 44 mL was used to simultaneously measure the volume concentrations of 16O12C16O，18O12C16O and 16O13C16O in CO2 based on direct absorption spectroscopy. In addition, the noise interference caused by the stability of the light source in the direct absorption spectrum system and gas sample fluctuations were reduced using the Back Propagation (BP) neural network model. The results showed that the measurement accuracy and stability of isotope abundance based on the BP neural network model were better than those of the absorbance peak ratio method. The concentration measurement accuracy of 16O13C16O and 18O12C16O increased by about 1.27 and 1.58 times, respectively. Meanwhile, the Allan variance analysis also showed that when the integration time was 106 s, the accuracy of 13C and 18O isotope abundance using the BP neural network model was 0.97‰ and 1.47‰, respectively, which improved about 2.1 times and 1.2 times compared to the absorbance peak ratio method. This fully proves the feasibility of the isotope abundance measurement method based on the BP neural network model, laying the foundation for developing high-precision isotope abundance sensors.
黄文彪，夏 滑，王前进，孙鹏帅，庞 涛，吴 边，张志荣. 基于BP神经网络模型的呼出气δ13C、δ18O同位素丰度测量方法研究[J]. 光谱学与光谱分析, 2024, 44(10): 2761-2767.
HUANG Wen-biao, XIA Hua, WANG Qian-jin, SUN Peng-shuai, PANG Tao, WU Bian, ZHANG Zhi-rong. Research on Measurement Method of δ13C and δ18O Isotopes Abundance in Exhaled Gas Based on the BP Neural Network Model. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(10): 2761-2767.
[1] Henderson B, Khodabakhsh A, Metsälä M, et al. Applied Physics B, 2018, 124: 1.
[2] Stacewicz T, Bielecki Z, Wojtas J, et al. Opto-Electronics Review, 2016, 24(2): 82.
[3] Ghorbani R, Schmidt F M. Optics Express, 2017, 25(11): 12743.
[4] Franceschi F, Gasbarrini A, Polyzos S A, et al. Helicobacter, 2015, 20: 40.
[5] Som S, De A, Banik G D, et al. Scientific Reports, 2015, 5(1): 10936.
[6] SUN Ming-guo, MA Hong-liang, LIU Qiang, et al(孙明国，马宏亮，刘 强，等). Acta Physica Sinica(物理学报), 2018, 67(6): 146.
[7] Zhou T, Wu T, Wu Q, et al. Optics Express, 2020, 28(8): 10970.
[8] Zhou T, Wu T, Wu Q, et al. Analytical Chemistry, 2020, 92(19): 12943.
[9] Shao L, Mei J, Chen J, et al. Sensors, 2022, 22(4): 1527.
[10] Ghosh C, Mandal S, Banik G D, et al. Scientific Reports, 2016, 6(1): 1.
[11] Berman E S F, Levin N E, Landais A, et al. Analytical Chemistry, 2013, 85(21): 10392.
[12] LI Xiang-xian, XU Liang, GAO Min-guang, et al(李相贤，徐 亮，高闽光，等). Acta Physica Sinica(物理学报), 2015, 64(2): 235.
[13] HOU Yue, HUANG Ke-jin, YU Guan-yi, et al(侯 月，黄克谨，于冠一，等). Infrared and Laser Engineering(红外与激光工程), 2021, 50(4): 73.
[14] ZHANG Tian-yu, LIU Zhi-wei, ZHANG Lei, et al(张天羽，刘志伟，张 磊，等). Acta Optica Sinica(光学学报), 2021, 41(10): 195.
[15] WANG Zhi-fang, WANG Shu-tao, WANG Gui-chuan(王志芳，王书涛，王贵川). Acta Photonica Sinica(光子学报), 2019, 48(4): 147.
[16] Zhou S, Shen C Y, Zhang L, et al. Optics Express, 2019, 27(22): 31874.
[17] Li G L, Li J, Liu Y, et al. Microwave and Optical Technology Letters, 2023, 65(5): 1468.
[18] WANG Biao, LIAN Hou-quan, YU Yong-bo, et al(王 彪，连厚泉，余泳波，等). Laser Journal(激光杂志), 2022, 43(8): 19.
[19] ZHANG Zhi-rong, PANG Tao, SUN Peng-shuai, et al(张志荣，庞 涛，孙鹏帅，等). Chinese Journal of Lasers(中国激光), 2019, 46(12): 265.
[20] Wang Q, Sun P, Zhang Z, et al. Sensors and Actuators B: Chemical, 2022, 369: 132292.
[21] Zhao X H, Sun P S, Zhang Z R, et al. Optics Express, 2022, 30(24): 43464.
