EUVIMEDEUVIMED entdecken
Crossref

Neural-network-based multi-spectral thermometry and emissivity reconstruction in cavity high-temperature environments

Xinyu Mao, Qi Xie

Applied Optics · 01.09.2025 · 64 (25) · 7304

DOI: 10.1364/ao.567549 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Optics, online erschienen am 21.08.2025. Verfasst von Xinyu Mao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a neural-network-assisted framework for accurate radiation thermometry in high-temperature cavities, overcoming challenges from unknown emissivity and multi-reflection effects. The method combines Monte Carlo ray-tracing with deep learning through: (1) physics-informed training data including diffuse/specular reflections, (2) alternating neural networks for decoupled temperature/emissivity prediction, and (3) full multi-reflection modeling. Validated with zirconia in a graphite cavity within the 1273–1673 K temperature range and 2–16 µm spectral range, it achieves 0.7% temperature error (9 K, compared to real temperature) and 0.05–0.1 emissivity error in 2–16 µm, outperforming first-order methods (neglecting multiple reflections) by 5%–27% (peak at 2 µm) in emissivity reconstruction. The framework maintains

Zitieren

APA

Mao, X., & Xie, Q. (2025). Neural-network-based multi-spectral thermometry and emissivity reconstruction in cavity high-temperature environments. Applied Optics, 64(25), 7304. https://doi.org/10.1364/ao.567549

Vancouver

Mao X, Xie Q. Neural-network-based multi-spectral thermometry and emissivity reconstruction in cavity high-temperature environments. Applied Optics. 2025;64(25):7304. doi:10.1364/ao.567549

BibTeX
@article{Mao2025,
  author = {Mao, Xinyu and Xie, Qi},
  title = {Neural-network-based multi-spectral thermometry and emissivity reconstruction in cavity high-temperature environments},
  journal = {Applied Optics},
  year = {2025},
  volume = {64},
  number = {25},
  pages = {7304},
  doi = {10.1364/ao.567549}
}
Kostenlos starten →