EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Test-Time Adaptation for Cross-Domain Remaining Useful Life Prediction: When Does It Work and What Should Practitioners Use

JINHE YU, Jianyin Zhao, Yufeng Qin

Eksploatacja i Niezawodność – Maintenance and Reliability · 29.07.2026

DOI: 10.17531/ein/226057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Eksploatacja i Niezawodność – Maintenance and Reliability, online erschienen am 29.07.2026. Verfasst von JINHE YU und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning models for remaining useful life (RUL) prediction degrade under varying operating conditions due to distribution shifts. Test-time adaptation (TTA) addresses this issue by updating a pretrained model using unlabeled target data without source data access; however, it has not been systematically studied for RUL prediction. Four TTA strategies are reformulated and evaluated across six cross-domain scenarios on C-MAPSS. TTA improves performance only when the source has more diverse operating conditions than the target. Restricting adaptation to batch-normalization (BN) affine parameters makes all gradient-based methods produce functionally equivalent outputs (BN affine bottleneck). Gradient-free adaptive BN gives the best risk–benefit trade-off, matching or outperforming them in five of six scenarios. A four-step deployment workflow for cross-domain predictive maintenance is proposed. The direction dependence of TTA effectiveness and the BN affine bottleneck are further confirmed on an LSTM backbone and the N-CMAPSS dataset.

Zitieren

APA

YU, J., Zhao, J., & Qin, Y. (2026). Test-Time Adaptation for Cross-Domain Remaining Useful Life Prediction: When Does It Work and What Should Practitioners Use. Eksploatacja i Niezawodność – Maintenance and Reliability. https://doi.org/10.17531/ein/226057

Vancouver

YU J, Zhao J, Qin Y. Test-Time Adaptation for Cross-Domain Remaining Useful Life Prediction: When Does It Work and What Should Practitioners Use. Eksploatacja i Niezawodność – Maintenance and Reliability. 2026. doi:10.17531/ein/226057

BibTeX
@article{YU2026,
  author = {YU, JINHE and Zhao, Jianyin and Qin, Yufeng},
  title = {Test-Time Adaptation for Cross-Domain Remaining Useful Life Prediction: When Does It Work and What Should Practitioners Use},
  journal = {Eksploatacja i Niezawodność – Maintenance and Reliability},
  year = {2026},
  doi = {10.17531/ein/226057}
}
Kostenlos starten →