Integration of Exfoliated WS2 /Functionalized MWCNT Nanocomposites for NO2 Sensing Using Machine Learning for Response Prediction | Sciact - CRIS-system of Boreskov Institute of Catalysis

Integration of Exfoliated WS2 /Functionalized MWCNT Nanocomposites for NO2 Sensing Using Machine Learning for Response Prediction Full article

Journal

IEEE Sensors Journal
ISSN: 1530-437X

Output data

Year: 2024, Volume: 24, Number: 22, Pages: 36366-36376 Pages count : 11 DOI: 10.1109/jsen.2024.3470069

Tags

carbon nanotubes, gas sensors, nitrogen dioxide, regression

Authors

Kumar S. ¹ , Kedam N. ² , Maksimovskiy E.A. ³ , Ishchenko A.V. ⁴ , Larina T.V. ⁴ , Chesalov Yu.A. ⁴ , Bannov A.G. ⁵

Affiliations

1	Anhui Institute of Optics and Fine Mechanics, and Key Lab of Photovoltaic and Energy Conservation Materials, Hefei Institutes of Physical Science, Anhui Provincial Key Laboratory of Photonic Devices and Materials, Chinese Academy of Sciences, Hefei, China
2	Department of Thermal Engineering and Thermal Engines, Samara National Research University, Moskovskoye Shosse, 34, Samara, Russia
3	Institute of Inorganic Chemistry SB RAS, Novosibirsk, Russia
4	Boreskov Institute of Catalysis SB RAS, Novosibirsk, Russia
5	Department of Chemistry and Chemical Engineering, Novosibirsk State Technical University, Novosibirsk, Russia

Funding (1)

Ministry of Science and Higher Education of the Russian Federation

FSUN-2023-0008

In order to manage the environment and perform noninvasive disease diagnostics, it is necessary to continuously identify harmful and highly toxic gases, such as nitrogen oxide (NO2). This study demonstrates how to design nanocomposites and build a cost-effective NO 2 gas sensor based on exfoliated tungsten disulphide and functionalized multi-walled carbon nanotubes as a highly efficient sensing material operating at room temperature in humid conditions. The composite sensor’s response under various humidity levels, ranging from 2% to 65%, as well as at different temperatures (25°C to 80°C), was studied. Scanning electron microscopy, Raman spectroscopy, transmission electron microscopy, and energy dispersive X-ray spectroscopy were used to analyze the sensing material. The composite-based sensor showed an improved response Δ R/R0 of 52% at room temperature for 50 ppm NO 2 with good selectivity to other gases (e.g. ammonia, methane, benzene, isobutene, hydrogen). The composite sensor exhibited a low detection limit of 1.39 ppm for NO 2 at room temperature. Furthering this advancement, we delve into the integration of machine learning, specifically the CatBoost regression model, with the NO 2 sensor. This integration elevates the sensor from a conventional passive detector to an advanced analytical system, significantly boosting its predictive accuracy and adaptability for real-time environmental monitoring and nuanced data interpretation, thereby opening new frontiers in sensor technology and applications in environmental monitoring and health diagnostics.

Kumar S. , Kedam N. , Maksimovskiy E.A. , Ishchenko A.V. , Larina T.V. , Chesalov Y.A. , Bannov A.G.
Integration of Exfoliated WS2 /Functionalized MWCNT Nanocomposites for NO2 Sensing Using Machine Learning for Response Prediction
IEEE Sensors Journal. 2024. V.24. N22. P.36366-36376. DOI: 10.1109/jsen.2024.3470069 WOS Scopus РИНЦ OpenAlex

Submitted:	Jul 29, 2024
Accepted:	Sep 26, 2024
Published online:	Nov 14, 2024
Published print:	Nov 15, 2024

Web of science:	WOS:001355285600078
Scopus:	2-s2.0-85206011420
Elibrary:	74612253
OpenAlex:	W4403123523

Пока нет цитирований