Research of Chlorine Concentration Inversion Method Based on 1D-CNN Using Ultraviolet Spectral
JIA Tong-hua1, CHENG Guang-xu1*, YANG Jia-cong1, CHEN Sheng2, WANG Hai-rong3, HU Hai-jun1
1. Department of Process Equipment and Control Engineering, School of Chemical and Technology, Xi'an Jiaotong University, Xi'an 710049, China
2. China Special Equipment Inspection & Research Institute, National Market Supervision Technology, Beijing 100029, China
3. State Key Laboratory of Machinery Manufacturing System, School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China
Abstract：The accurate detection of chlorine leakage in an open environment has been an urgent problem for chlor-alkali manufacturers. Differential optical absorption spectroscopy (DOAS) can realize long-distance measurements of trace polluting gases in the atmosphere. Due to the flat characteristic of the UV absorption spectrum of chlorine, it is impossible to differentiate the absorption characteristics from the noise signal by normal methods. A new algorithm based on a one-dimensional convolutional neural network (1D-CNN) is proposed to solve the problem of poor accuracy caused by noise interference, which can fully use spectral information and extract chlorine absorption characteristics layer by layer. Compared with commonly used models such as least squares (LS), multilayer perceptron (MLP), support vector machine (SVR), and k-nearest neighbor (KNN), the inversion result of this algorithm has the highest accuracy (R2=0.996, RMSE=4.40, MAE=2.64, SMAPE=8.51%). Due to the inevitable random noise in -the system, the preprocessing effects of the S-G filter, Fourier transform, singular value decomposition, and wavelet transform decomposition algorithms are compared. The results show that S-G filtering and wavelet decomposition algorithms can retain the characteristic information of chlorine while removing noise and further improving the model's performance. The concentration inversion model based on 1D-CNN provides a new feasible method for long-distance quantitative detection of chlorine leakage in the open environment.
Key words：Chlorine leakage; Remote detection; UV-DOAS; Deep learning; 1D-CNN
贾彤华，程光旭，杨嘉聪，陈 昇，王海容，胡海军. 基于1D-CNN提取Cl2紫外吸收谱特征的浓度反演方法研究[J]. 光谱学与光谱分析, 2024, 44(11): 3109-3119.
JIA Tong-hua, CHENG Guang-xu, YANG Jia-cong, CHEN Sheng, WANG Hai-rong, HU Hai-jun. Research of Chlorine Concentration Inversion Method Based on 1D-CNN Using Ultraviolet Spectral. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(11): 3109-3119.
[1] SHEN Xin-hua(沈新华). Chemical Management(化工管理), 2016, 20: 309.
[2] LI Wei, ZHANG Shuang-quan, GAO Han-chen, et al(李 伟, 张双全, 高翰晨, 等). Chemical Management(化工管理), 2018, 19: 86.
[3] Zhang Y, Wang Y, Liu Y, et al. Spectrochimca, 2019, Acta Part A 210: 120.
[4] YU Zhi-wei, GUO Jie, HAN Xiao-hong, et al(于志伟, 郭 杰, 韩晓红, 等). China Instrumentation(中国仪器仪表), 2019, 3: 52.
[5] Zhang X, Yang J. Trends in Food Science & Technology, 2021, 112(1), 1.
[6] Puneet M, Dario P. TrAC Trends in Analytical Chemistry, 2022, 157: 116804.
[7] Barbedo Jayme G A. Computers & Electronics in Agriculture, 2023, 210: 1.
[8] Liu J, Hu P, Xue H, et al. Spectroscopy Letters, 2022, 55(4)：229.
[9] Li X, Liu J. Spectroscopy Letters, 2023, 56(4): 204.
[10] Hennrich J, Herff C, Heger D, et al. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), 2015, 11：2844.
[11] Liu J, Gibson S J, Mills J, et al. Chemometrics & Intelligent Laboratory Systems, 2018, 184(2): 52.
[12] Mao Y, Liu C, Xiao D, et al. Journal of Sensors, 2018, 17(2): 1.
[13] Sun Y, Brockhauser S, Hegedüs P. Applied Sciences, 2021, 11(23): 11520.
[14] Sohn W B, Lee S Y, Kim S. Journal of Raman Spectroscope, 2020, 51(3): 414.
[15] Yang Y, Liao J, Li H, et al. Spectroscopy Letters, 2023, 56(1): 28.
[16] Keller-Rudek H, Moortgat G K, Sander R, et al. Earth System Science Data, 2013, 5(2): 365.
[17] Fergusson W C, Slotin L, Style D W G. Transactions of the Faraday Society, 1936, 32：956.
