EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High-Resolution Reconstruction of Temperature Fields Based on Improved ResNet18

Leilei Ma, Jungang Ma, Manlidan Zelminbek, Wenjun Zhang

Sensors · 12.10.2024 · 24 (20) · 6564

DOI: 10.3390/s24206564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.10.2024. Verfasst von Leilei Ma und 3 weiteren Autor:innen. Beteiligte Einrichtung: Xinjiang Uygur Autonomous Region Research Institute Of Measurement & Testing, Urumqi 830011, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xinjiang Uygur Autonomous Region Research Institute Of Measurement & Testing, Urumqi, China, Xinjiang Uygur Autonomous Region Research Institute Of Measurement & Testing, Urumqi, China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-precision measurement of temperature value distributions in production scenarios is of great significance for industrial production, but traditional temperature field reconstruction algorithms rely on the design of manual feature extraction methods with high computational complexity and poor generalization ability. In this paper, we propose a high-precision temperature field reconstruction algorithm based on deep learning, using an efficient adaptive feature extraction method for temperature field reconstruction. We design an improved temperature field reconstruction algorithm based on the ResNet18 neural network; introduce the CBAM attention mechanism in the model; and design a feature pyramid, using M-FPN, a multi-scale feature aggregation network fusing PAN and FPN, to make the extracted feature information propagate multi-dimensionally among different layers to improve the feature characterization ability. Finally, the mean square error is used to guide the model to optimize the training so that the model pays more attention to the data and reduces the large error to ensure that the gap between the predicted value and the real value is small. The experimental results show that the reconstruction accuracy of the improved algorithm presented in this paper is significantly better than that of the original algorithm in the case of typical peaked temperature field distributions.

Schlagwörter

Stichwörter der Autor:innen

deep learningmean square errormulti-scale feature aggregationtemperature field reconstruction

Autor:innen und Institutionen

  • Xinjiang Uygur Autonomous Region Research Institute Of Measurement & Testing, Urumqi 830011, China.

Förderung

  • Xinjiang Uygur Autonomous Region Research Institute Of Measurement & Testing, Urumqi, China
  • Xinjiang Uygur Autonomous Region Research Institute Of Measurement & Testing, Urumqi, China

Zitieren

APA

Ma, L., Ma, J., Zelminbek, M., & Zhang, W. (2024). High-Resolution Reconstruction of Temperature Fields Based on Improved ResNet18. Sensors, 24(20), 6564. https://doi.org/10.3390/s24206564

Vancouver

Ma L, Ma J, Zelminbek M, Zhang W. High-Resolution Reconstruction of Temperature Fields Based on Improved ResNet18. Sensors. 2024;24(20):6564. doi:10.3390/s24206564

BibTeX
@article{Ma2024,
  author = {Ma, Leilei and Ma, Jungang and Zelminbek, Manlidan and Zhang, Wenjun},
  title = {High-Resolution Reconstruction of Temperature Fields Based on Improved ResNet18},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {20},
  pages = {6564},
  doi = {10.3390/s24206564}
}
Kostenlos starten →