Standard

Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning. / Borozdin, Pavel; Erushin, Evgenii; Kozmin, Artem et al.

In: Sensors, Vol. 24, No. 23, 7518, 12.2024.

Research output: Contribution to journal › Article › peer-review

Harvard

Borozdin, P, Erushin, E, Kozmin, A, Bednyakova, A, Miroshnichenko, I, Kostyukova, N, Boyko, A & Redyuk, A 2024, 'Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning', Sensors, vol. 24, no. 23, 7518. https://doi.org/10.3390/s24237518

APA

Borozdin, P., Erushin, E., Kozmin, A., Bednyakova, A., Miroshnichenko, I., Kostyukova, N., Boyko, A., & Redyuk, A. (2024). Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning. Sensors, 24(23), [7518]. https://doi.org/10.3390/s24237518

Vancouver

Borozdin P, Erushin E, Kozmin A, Bednyakova A, Miroshnichenko I, Kostyukova N et al. Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning. Sensors. 2024 Dec;24(23):7518. doi: 10.3390/s24237518

Author

Borozdin, Pavel ; Erushin, Evgenii ; Kozmin, Artem et al. / Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning. In: Sensors. 2024 ; Vol. 24, No. 23.

BibTeX

@article{e9f5c88556a6434bb2e9ee20f60327dc,
title = "Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning",
abstract = "In this study, we address the challenge of estimating the resonance frequency of a photoacoustic detector (PAD) gas cell under varying temperature conditions, which is crucial for improving the accuracy of gas concentration measurements. We introduce a novel approach that uses a long short-term memory network and a self-attention mechanism to model resonance frequency shifts based on temperature data. To investigate the impact of the gas mixture temperature on the resonance frequency, we modified the PAD to include an internal temperature sensor. Our experiments involved multiple heating and cooling cycles with varying methane concentrations, resulting in a comprehensive dataset of temperature and resonance frequency measurements. The proposed models were trained and validated on this dataset, and the results demonstrate real-time prediction capabilities with a mean absolute error of less than 1 Hz for frequency shifts exceeding 30 Hz over four-hour periods. This approach allows continuous, real-time tracking of the resonance frequency without interrupting the laser operation, significantly enhancing gas concentration measurements and contributing to the long-term stabilization of the sensor. The results suggest that the proposed approach is effective in managing temperature-induced frequency shifts, making it a valuable tool for improving the accuracy and stability of gas sensors in practical applications.",
keywords = "accuracy, long short-term memory networks, machine learning, methane, neural networks, optical sensing, photoacoustic gas sensor, photoacoustic spectroscopy, sensitivity enhancement",
author = "Pavel Borozdin and Evgenii Erushin and Artem Kozmin and Anastasia Bednyakova and Ilya Miroshnichenko and Nadezhda Kostyukova and Andrey Boyko and Alexey Redyuk",
note = "This work was supported by the grant for research centers provided by the Analytical Center for the Government of the Russian Federation, in accordance with the subsidy agreement (agreement identifier 000000D730324P540002) and by the agreement with Novosibirsk State University, dated 27 December 2023, No. 70-2023-001318.",
year = "2024",
month = dec,
doi = "10.3390/s24237518",
language = "English",
volume = "24",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "23",

}

RIS

TY - JOUR

T1 - Temperature-Based Long-Term Stabilization of Photoacoustic Gas Sensors Using Machine Learning

AU - Borozdin, Pavel

AU - Erushin, Evgenii

AU - Kozmin, Artem

AU - Bednyakova, Anastasia

AU - Miroshnichenko, Ilya

AU - Kostyukova, Nadezhda

AU - Boyko, Andrey

AU - Redyuk, Alexey

N1 - This work was supported by the grant for research centers provided by the Analytical Center for the Government of the Russian Federation, in accordance with the subsidy agreement (agreement identifier 000000D730324P540002) and by the agreement with Novosibirsk State University, dated 27 December 2023, No. 70-2023-001318.

PY - 2024/12

Y1 - 2024/12

N2 - In this study, we address the challenge of estimating the resonance frequency of a photoacoustic detector (PAD) gas cell under varying temperature conditions, which is crucial for improving the accuracy of gas concentration measurements. We introduce a novel approach that uses a long short-term memory network and a self-attention mechanism to model resonance frequency shifts based on temperature data. To investigate the impact of the gas mixture temperature on the resonance frequency, we modified the PAD to include an internal temperature sensor. Our experiments involved multiple heating and cooling cycles with varying methane concentrations, resulting in a comprehensive dataset of temperature and resonance frequency measurements. The proposed models were trained and validated on this dataset, and the results demonstrate real-time prediction capabilities with a mean absolute error of less than 1 Hz for frequency shifts exceeding 30 Hz over four-hour periods. This approach allows continuous, real-time tracking of the resonance frequency without interrupting the laser operation, significantly enhancing gas concentration measurements and contributing to the long-term stabilization of the sensor. The results suggest that the proposed approach is effective in managing temperature-induced frequency shifts, making it a valuable tool for improving the accuracy and stability of gas sensors in practical applications.

AB - In this study, we address the challenge of estimating the resonance frequency of a photoacoustic detector (PAD) gas cell under varying temperature conditions, which is crucial for improving the accuracy of gas concentration measurements. We introduce a novel approach that uses a long short-term memory network and a self-attention mechanism to model resonance frequency shifts based on temperature data. To investigate the impact of the gas mixture temperature on the resonance frequency, we modified the PAD to include an internal temperature sensor. Our experiments involved multiple heating and cooling cycles with varying methane concentrations, resulting in a comprehensive dataset of temperature and resonance frequency measurements. The proposed models were trained and validated on this dataset, and the results demonstrate real-time prediction capabilities with a mean absolute error of less than 1 Hz for frequency shifts exceeding 30 Hz over four-hour periods. This approach allows continuous, real-time tracking of the resonance frequency without interrupting the laser operation, significantly enhancing gas concentration measurements and contributing to the long-term stabilization of the sensor. The results suggest that the proposed approach is effective in managing temperature-induced frequency shifts, making it a valuable tool for improving the accuracy and stability of gas sensors in practical applications.

KW - accuracy

KW - long short-term memory networks

KW - machine learning

KW - methane

KW - neural networks

KW - optical sensing

KW - photoacoustic gas sensor

KW - photoacoustic spectroscopy

KW - sensitivity enhancement

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85211792251&origin=inward&txGid=d60816f5a9f2813c16463da8caf4213c

UR - https://www.mendeley.com/catalogue/1aff70e8-d8a8-33cb-a298-444224741fa2/

U2 - 10.3390/s24237518

DO - 10.3390/s24237518

M3 - Article

C2 - 39686055

VL - 24

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 23

M1 - 7518

ER -

ID: 61281737