EUVIMEDEUVIMED entdecken
Crossref

Physics-Aware Spatiotemporal Graph Attention Network for Variable Frequency Temperature Modulation of MOS Gas Sensors

Guangshun Liu, Yinsheng Chen iD, Mingyang Wang, Zedong Ju, Shuo Cui, Wenjie Zhao iD

ACS Sensors · 2026

DOI: 10.1021/acssensors.6c01383 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Sensors, 2026. Verfasst von Guangshun Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Measurement and Communication Engineering, Harbin University of Science and Technology, Harbin150080, China. Hauptthemen laut MEDLINE: Temperature, Gases, Semiconductors, Electronic Nose. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metal oxide semiconductor (MOS) gas sensors are widely used in industrial mixed-gas detection. However, conventional temperature modulation fails to fully activate their dynamic response characteristics, limiting the performance of electronic nose systems. To address this issue, a variable frequency temperature modulation (VFTM) mechanism is proposed, which jointly regulates heating frequency and duty cycle to enhance sensor–gas physicochemical interactions and obtain richer gas fingerprint information. In light of this, a multitask physics-aware spatiotemporal graph attention network (PST-GAN) is developed for simultaneous gas type recognition and concentration estimation. A physics-aware temporal encoder (PATE) incorporates heating excitation into feature encoding, enabling the network to learn the physical correlations between sensor responses and heating states. Spatiotemporal graph modeling is then performed to jointly characterize temporal dependencies within each sensor and cooperative responses across sensors. These features are hierarchically aggregated through layered graph convolution, while a gating mechanism adaptively fuses temporal and spatial graph features. Finally, a compact electronic nose system is designed and fabricated for mixed-gas detection and verified through experiments. The results show that PST-GAN achieves a recognition accuracy of 99.68% and a mean absolute error of 1.9881 ppm in concentration estimation, demonstrating strong potential for industrial gas detection applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TemperatureGasesSemiconductorsElectronic NoseOxidesGraph Neural Networks

Stichwörter der Autor:innen

MOS sensorsmixed-gas detectionphysics-aware learningspatiotemporal graph attention networkvariable frequency temperature modulation

Substanzen

GasesOxides

Autor:innen und Institutionen

  • School of Measurement and Communication Engineering, Harbin University of Science and Technology, Harbin150080, China.

ORCID-Profile: Yinsheng Chen, Wenjie Zhao

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, G., Chen, Y., Wang, M., Ju, Z., Cui, S., & Zhao, W. (2026). Physics-Aware Spatiotemporal Graph Attention Network for Variable Frequency Temperature Modulation of MOS Gas Sensors. ACS Sensors. https://doi.org/10.1021/acssensors.6c01383

Vancouver

Liu G, Chen Y, Wang M, Ju Z, Cui S, Zhao W. Physics-Aware Spatiotemporal Graph Attention Network for Variable Frequency Temperature Modulation of MOS Gas Sensors. ACS Sensors. 2026. doi:10.1021/acssensors.6c01383

BibTeX
@article{Liu2026,
  author = {Liu, Guangshun and Chen, Yinsheng and Wang, Mingyang and Ju, Zedong and Cui, Shuo and Zhao, Wenjie},
  title = {Physics-Aware Spatiotemporal Graph Attention Network for Variable Frequency Temperature Modulation of MOS Gas Sensors},
  journal = {ACS Sensors},
  year = {2026},
  doi = {10.1021/acssensors.6c01383}
}
Kostenlos starten →