EUVIMEDEUVIMED entdecken
Crossref

Dual-head temporal modeling with causal normalization for cross-turbine gearbox fault early warning

Min Xu, Yongchao Zhu, Ye Zhou, Jianjun Tan, Taixu Jin, Lei Rao

Structural Health Monitoring · 13.08.2026

DOI: 10.1177/14759217261472396 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Structural Health Monitoring, online erschienen am 13.08.2026. Verfasst von Min Xu und 5 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Scientific Research Plan Projects of Shaanxi Education Department, the National Key R&D Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wind turbine gearboxes operate under fluctuating loads and widely varying conditions, which make cross-turbine generalization of supervisory control and data acquisition (SCADA)-based fault early warning difficult. In this article, a novel framework that combines uncertainty-aware residual modeling, dual-stream temporal representation, and causal amplitude normalization is introduced. Specifically, the raw oil-sump temperature is first mapped to a standardized residual through probabilistic regression, which mitigates load-dependent threshold drift. The residual is then routed into a dual-head architecture that models shift-type (mean-elevation) and compress-type (variance-contraction) degradation separately, which suppresses the false-alarm surge caused by conflating the two mechanisms. Finally, a four-layer progressive alarm engine with causal rolling p99 normalization and a training-free gating controller generates episode-level warnings without any target-domain retraining. The key innovation lies in combining mechanism-decoupled risk heads with self-referential normalization, which together enable direct deployment on unseen turbines of the same wind farm and turbine platform without fault-type prior knowledge. Evaluation on 2 years of SCADA data from five 2 MW onshore turbines, including a zero-shot blind-test turbine, shows that the deployable configuration achieves an early warning time of 39.2 h, a false alarm rate of 0.18 episodes/day, and an event recall of 1, demonstrating more stable cross-turbine generalization than the evaluated fixed-threshold and single-head baselines.

Förderung

  • Scientific Research Plan Projects of Shaanxi Education Department
  • the National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Xu, M., Zhu, Y., Zhou, Y., Tan, J., Jin, T., & Rao, L. (2026). Dual-head temporal modeling with causal normalization for cross-turbine gearbox fault early warning. Structural Health Monitoring. https://doi.org/10.1177/14759217261472396

Vancouver

Xu M, Zhu Y, Zhou Y, Tan J, Jin T, Rao L. Dual-head temporal modeling with causal normalization for cross-turbine gearbox fault early warning. Structural Health Monitoring. 2026. doi:10.1177/14759217261472396

BibTeX
@article{Xu2026,
  author = {Xu, Min and Zhu, Yongchao and Zhou, Ye and Tan, Jianjun and Jin, Taixu and Rao, Lei},
  title = {Dual-head temporal modeling with causal normalization for cross-turbine gearbox fault early warning},
  journal = {Structural Health Monitoring},
  year = {2026},
  doi = {10.1177/14759217261472396}
}
Kostenlos starten →