Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors

doi:10.1021/acs.analchem.1c05059

CIOMP OpenIR

	Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors
	J. C. Sun; L. B. Tian; J. Chang; A. A. Kolomenskii; H. A. Schuessler; J. B. Xia; C. Feng and S. S. Zhang
	2022
发表期刊	Analytical Chemistry
ISSN	0003-2700
卷号	94 期号:4 页码:2321-2332
摘要	Noise significantly limits the accuracy and stability of retrieving gas concentration with the traditional direct absorption spectroscopy (DAS). Here, we developed an adaptively optimized gas analysis model (AOGAM) composed of a neural sequence filter (NSF) and a neural concentration retriever (NCR) based on deep learning algorithms for extraction of methane absorption information from the noisy transmission spectra and obtaining the corresponding concentrations from the denoised spectra. The model was trained on two data sets, including a computationally generated one and the experimental one. We have applied this model for retrieving methane concentration from its transmission spectra in the near-infrared (NIR) region. The NSF was implemented through an encoderdecoder structure enhanced by the attention mechanism, improving robustness under noisy conditions. Further, the NCR was employed based on a combination of a principal component analysis (PCA) layer, which focuses the algorithm on the most significant spectral components, and a fully connected layer for solving the nonlinear inversion problem of the determination of methane concentration from the denoised spectra without manual computation. Evaluation results show that the proposed NSF outperforms widely used digital filters as well as the state-of-the-art filtering algorithms, improving the signal-to-noise ratio by 7.3 dB, and the concentrations determined with the NCR are more accurate than those determined with the traditional DAS method. With the AOGAM enhancement, the optimized methane sensor features precision and stability in real-time measurements and achieves the minimum detectable column density of 1.40 ppm center dot m (1s). The promising results of the present study demonstrate that the combination of deep learning and absorption spectroscopy provides a more effective, accurate, and stable solution for a gas monitoring system.
DOI	10.1021/acs.analchem.1c05059
URL	查看原文
收录类别	sci
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/66390
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	J. C. Sun,L. B. Tian,J. Chang,et al. Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors[J]. Analytical Chemistry,2022,94(4):2321-2332.
APA	J. C. Sun.,L. B. Tian.,J. Chang.,A. A. Kolomenskii.,H. A. Schuessler.,...&C. Feng and S. S. Zhang.(2022).Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors.Analytical Chemistry,94(4),2321-2332.
MLA	J. C. Sun,et al."Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors".Analytical Chemistry 94.4(2022):2321-2332.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Adaptively Optimized（6044KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载