EUVIMEDEUVIMED entdecken
Crossref

A cross-condition fault diagnosis method for rolling bearings combining content-conditioned positional encoding and label-conditioned in-context learning

Nengchao Wu, Shengcai Wang, Junjie Bao, Qianxi Zhang, Xinyu Yang, Qing Tao, Haijia Wu, Na Cui, Rangxiang Zhao, Li Liu

Measurement Science and Technology · 13.11.2026 · 37 (45) · 456104

DOI: 10.1088/1361-6501/aebaa5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 10.11.2026. Verfasst von Nengchao Wu und 9 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: The Chongging Municipal Economy and Information Technology Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-condition fault diagnosis for rolling bearings is still a difficult task, mainly because vibration signals acquired under varying operating conditions exhibit distribution differences. To address this issue, this paper proposes a cross-condition fault diagnosis method named content-conditioned positional encoding (CCPE)-label-conditioned in-context learning (LCIC), which combines CCPE and LCIC. The proposed method employs a Transformer-based encoder to extract fault-related features from raw vibration signals, while adaptively enhancing temporal position information according to signal content. Meanwhile, label information from support samples is incorporated into the in-context learning process to improve the modeling of feature-label relationships and support query classification. An auxiliary supervised loss is further introduced to enhance feature discriminability and stabilize training. The effectiveness of the proposed method is verified through cross-condition experiments conducted on the CWRU and TBVD bearing datasets. Ablation studies further confirm the contributions of the main components.

Förderung

  • The Chongging Municipal Economy and Information Technology Commission

Zitieren

APA

Wu, N., Wang, S., Bao, J., Zhang, Q., Yang, X., Tao, Q., Wu, H., Cui, N., Zhao, R., & Liu, L. (2026). A cross-condition fault diagnosis method for rolling bearings combining content-conditioned positional encoding and label-conditioned in-context learning. Measurement Science and Technology, 37(45), 456104. https://doi.org/10.1088/1361-6501/aebaa5

Vancouver

Wu N, Wang S, Bao J, Zhang Q, Yang X, Tao Q, et al. A cross-condition fault diagnosis method for rolling bearings combining content-conditioned positional encoding and label-conditioned in-context learning. Measurement Science and Technology. 2026;37(45):456104. doi:10.1088/1361-6501/aebaa5

BibTeX
@article{Wu2026,
  author = {Wu, Nengchao and Wang, Shengcai and Bao, Junjie and Zhang, Qianxi and Yang, Xinyu and Tao, Qing and Wu, Haijia and Cui, Na and Zhao, Rangxiang and Liu, Li},
  title = {A cross-condition fault diagnosis method for rolling bearings combining content-conditioned positional encoding and label-conditioned in-context learning},
  journal = {Measurement Science and Technology},
  year = {2026},
  volume = {37},
  number = {45},
  pages = {456104},
  doi = {10.1088/1361-6501/aebaa5}
}
Kostenlos starten →