EUVIMEDEUVIMED entdecken
Crossref

Staged domain adaptation with transformer for bearing remaining useful life prediction

Lixiao Cao, Zijian Lu, Zong Meng, Dengyun Sun, Wei Cao, Jimeng Li, Fengjie Fan

ISA Transactions · 2026-05 · 172 · 246-259

DOI: 10.1016/j.isatra.2026.03.024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2026-05. Verfasst von Lixiao Cao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Measurement Technology and Instrumentation of Hebei Province, Yanshan University, Qinhuangdao, 066004, Hebei Province, China; Key L…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hebei Provincial Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of Remaining Useful Life (RUL) is essential to optimize operational efficiency in engineered maintenance systems. Conventional transfer learning approaches often suffer from negative transfer when applied across the entire equipment lifecycle, primarily due to stage-specific distribution shifts. Forcing global alignment between early-stage normal data and late-stage fault data distorts the degradation trajectory, leading to significant prediction errors. Additionally, health indicators are difficult to accurately model in the bearing degradation process. To address this, we propose a Stage-Aware Adversarial Domain Adaptation Framework. Unlike conventional methods that treat the lifecycle as homogeneous, our approach introduces a theoretically grounded staging mechanism driven by CAE-derived Health Indicators (HI). By explicitly decoupling domain alignment into distinct degradation phases, we ensure feature alignment occurs only within semantically consistent operational regimes. Furthermore, domain adversarial neural networks (DANN) and maximum mean discrepancy (MMD) enhance cross-phase adaptability. The experimental results have been validated with two datasets, and show an improvement in prediction accuracy above 10% compared to both traditional and transfer learning methods, offering new methods for domain alignment for transfer learning in this field.

Schlagwörter

Stichwörter der Autor:innen

Domain adaptationRemaining useful life predictionRoll bearingStage classificationTransfer learning

Autor:innen und Institutionen

  • Key Laboratory of Measurement Technology and Instrumentation of Hebei Province, Yanshan University, Qinhuangdao, 066004, Hebei Province, China; Key Laboratory of Intelligent Control and Neural Information Processing, Mi…

Förderung

  • National Natural Science Foundation of China
  • Hebei Provincial Natural Science Foundation

Zitieren

APA

Cao, L., Lu, Z., Meng, Z., Sun, D., Cao, W., Li, J., & Fan, F. (2026). Staged domain adaptation with transformer for bearing remaining useful life prediction. ISA Transactions, 172, 246-259. https://doi.org/10.1016/j.isatra.2026.03.024

Vancouver

Cao L, Lu Z, Meng Z, Sun D, Cao W, Li J, et al. Staged domain adaptation with transformer for bearing remaining useful life prediction. ISA Transactions. 2026;172:246-259. doi:10.1016/j.isatra.2026.03.024

BibTeX
@article{Cao2026,
  author = {Cao, Lixiao and Lu, Zijian and Meng, Zong and Sun, Dengyun and Cao, Wei and Li, Jimeng and Fan, Fengjie},
  title = {Staged domain adaptation with transformer for bearing remaining useful life prediction},
  journal = {ISA Transactions},
  year = {2026},
  volume = {172},
  pages = {246--259},
  doi = {10.1016/j.isatra.2026.03.024}
}
Kostenlos starten →