EUVIMEDEUVIMED entdecken
Crossref

Aircraft Engine Remaining Useful Life Estimation via a Graph Attention Reconcile Network Model Based on Physical Equations and Sensor Data

Wenyue Cui, Shuo Zhang, Tao Sun, Rui Wang

IEEE Transactions on Reliability · 2025-12 · 74 (4) · 5244-5258

DOI: 10.1109/tr.2025.3626358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Reliability, 2025-12. Verfasst von Wenyue Cui und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Young Elite Scientist Sponsorship Program of China, Association for Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The prediction of remaining useful life (RUL) for aircraft engines stands as a critical process ensuring the safe operation of aircraft. Traditional methods for estimating RUL primarily mine temporal features within data, frequently overlooking the complex interdependencies among multivariate signals. Furthermore, in actual physical systems such as aircraft engines, there is a dynamic linkage among the sensor data. Ignoring these subtleties can result in a reduction of estimation accuracy. Addressing this challenge, the article proposes a novel graph attention reconcile network integrated with priori knowledge to predict aircraft engine RUL. It constructs a time-series graph by fusing sensor data with aerothermodynamics equations. The network employs dual attention mechanisms to capture spatio-temporal features: a spatial attention module to identify relationships between sensors, and a temporal attention module to highlight the importance of different time steps. Additionally, a LSTM layer is incorporated to enhance RUL prediction accuracy. Comparative analysis using the Commercial Modular Aero-Propulsion System Simulation datasets and new Commercial Modular Aero-Propulsion System Simulation datasets demonstrates the superior performance of the proposed model over other prevailing approaches.

Förderung

  • National Natural Science Foundation of China
  • Young Elite Scientist Sponsorship Program of China
  • Association for Science and Technology
  • Major Science and Technology Special Project of Guizhou Province
  • Independent Innovation Special Fund Project of China
  • Aero-Engine Corporation

Zitieren

APA

Cui, W., Zhang, S., Sun, T., & Wang, R. (2025). Aircraft Engine Remaining Useful Life Estimation via a Graph Attention Reconcile Network Model Based on Physical Equations and Sensor Data. IEEE Transactions on Reliability, 74(4), 5244-5258. https://doi.org/10.1109/tr.2025.3626358

Vancouver

Cui W, Zhang S, Sun T, Wang R. Aircraft Engine Remaining Useful Life Estimation via a Graph Attention Reconcile Network Model Based on Physical Equations and Sensor Data. IEEE Transactions on Reliability. 2025;74(4):5244-5258. doi:10.1109/tr.2025.3626358

BibTeX
@article{Cui2025,
  author = {Cui, Wenyue and Zhang, Shuo and Sun, Tao and Wang, Rui},
  title = {Aircraft Engine Remaining Useful Life Estimation via a Graph Attention Reconcile Network Model Based on Physical Equations and Sensor Data},
  journal = {IEEE Transactions on Reliability},
  year = {2025},
  volume = {74},
  number = {4},
  pages = {5244--5258},
  doi = {10.1109/tr.2025.3626358}
}
Kostenlos starten →