Identifying gas mixtures based on acoustic relaxation spectroscopy and attention recurrent neural network

Liu, Shuangling; Mei, Jie; Zhu, Meng; Zhuo, Cheng

doi:10.1016/j.rinp.2023.106558

Cited by 3 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergence of powerful deep learning pattern recognition in gas speciation applications, as explored here, is expected to benefit IR absorption gas sensing by replacing manual feature selection and spectral interpretation with automated processes [ 19 , 20 ]. Using these learning methods, sensors can learn on large quantities of spectral information (features and their shapes) in frequency bands that are arbitrarily selected and/or imposed by hardware or other constraints and make useful predictions on constituent species and their concentrations [ 17 , 18 , 21 , 22 , 23 , 24 , 25 ]. Automated feature extraction, based on compound-distinct spectral fingerprints, followed by deep neural network classification provides a model architecture that can automate gas sensing and supplant the limitations of expert humans in spectral feature selection and spectral interpretation.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Gas Sensing via Infrared Spectroscopy

Chowdhury,

Oehlschlaeger

2024

Sensors

View full text Add to dashboard Cite

Deep learning methods, a powerful form of artificial intelligence, have been applied in a number of spectroscopy and gas sensing applications. However, the speciation of multi-component gas mixtures from infrared (IR) absorption spectra using deep learning remains to be explored. Here, we propose a one-dimensional deep convolutional neural network gas classification model for the identification of small molecules of interest based on IR absorption spectra in flexible user-defined frequency ranges. The molecules considered include ten that are of interest in the atmosphere or in industrial and environmental processes: water vapor, carbon dioxide, ozone, nitrous oxide, carbon monoxide, methane, nitric oxide, sulfur dioxide, nitrogen dioxide, and ammonia. A simulated dataset of IR absorption spectra for mixtures of these molecules diluted in air was generated and used to train a deep learning model. The model was tested against simulated spectra containing noise and was found to provide speciation predictions with accuracy from 82 to 97%. The internal operation of the model was investigated using class activation maps that illustrate how the model prioritizes spectral information for classification. Finally, the model was demonstrated for the prediction of speciation for two synthetic experimental mixture spectra. The proposed model and the dataset generation strategies are generalized and can be implemented for other gases, different frequency ranges, and spectroscopy types. The multi-component speciation method developed herein is the first application of a convolutional neural network model, trained on HITRAN-based simulations, for spectral identification.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning for Gas Sensing via Infrared Spectroscopy

Chowdhury,

Oehlschlaeger

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Gas composition detection based on the measurement of acoustic relaxation absorption and sound speed has been applied to the monitoring of gases [1][2][3][4], combustion systems [5,6], quantum computation [7,8], etc. Compared with other methods including thermal phonon resonance [9] and laser sensing [10,11], the acoustic relaxation method has several advantages such as low cost, fast response, and no necessity for calibration [12,13].…”

Section: Introductionmentioning

confidence: 99%

Extracting relaxational features from measurements of sound speeds for gas sensing

Zhang,

Pan

et al. 2023

J. Inst.

View full text Add to dashboard Cite

In recent years, gas sensing methods by jointly measuring acoustic relaxation absorption and sound speeds have become a research focus in acoustic fields. However, the existing methods are difficult to be employed in practical gas detection due to complex measurement processes and large measurement errors when measuring the sound relaxational absorption. Furthermore, the acoustic relaxation absorption spectrum's small signal is hard to be measured because of the noise and large classical relaxation in the high-frequency range. In this paper, a gas sensing method is proposed by only measuring the sound speeds at the three frequencies, avoiding the problems of measuring the acoustic absorption spectrum. First, sound speeds are measured at three frequency points; second, the relaxation strength and the relaxation time of the acoustic relaxation features are extracted; finally, the absorption spectral peak is acquired and located for gas detection. The simulation results verify the feasibility of our method, and the detection errors from the measurement errors of sound speeds can be eliminated effectively. Thus, our work provides a high-accurate and simple acoustic method for gas sensing.

show abstract