Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 3, 2026Advanced Engineering InformaticsOpen Access

Memory-augmented spatio-temporal graph networks for federated cross-domain remaining useful life prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

WMWenqing MaShanghai Jiao Tong UniversityTXTangbin XiaShanghai Jiao Tong UniversityWSWujun SiShanghai Jiao Tong University

Discussion

Loading...

Member takes

Implication

Randomized trial demonstrates improved cross-domain RUL prediction in industrial clients, highlighting enhanced model performance.

Key Points

  • This research aims to enhance remaining useful life (RUL) prediction models in a federated learning context while preserving data privacy.
  • Developed a memory-augmented spatio-temporal hierarchical graph network (MA-STHGN) for sensor data modeling.
  • Introduced a dual-memory domain adaptation to align graph representations between different data domains.
  • Integrated a federated averaging algorithm with a reputation module for decentralized model training.
  • Performance of the proposed model improves accuracy in cross-domain RUL prediction compared to traditional methods.
  • Successfully preserves local data privacy while aligning features across domains.
  • Demonstrated effectiveness in mitigating negative transfer and distribution shifts.

Cite This Study

Ma et al. (2026) studied this question.

synapsesocial.com/papers/6a70406d75942ff7265e5727https://doi.org/10.1016/j.aei.2026.105115
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1DDP-FedFV: A Dual-Decoupling Personalized Federated Learning Framework for Finger Vein Recognition2024 · 6 citations
  2. 2Damage propagation modeling for aircraft engine run-to-failure simulation2008 · 1,740 citations
  3. 3Federated transfer learning-based distributed fault diagnosis method for rolling bearings2024 · 17 citations
  4. 4The European Union general data protection regulation: what it is and what it means2019 · 781 citations
  5. 5A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings2018 · 1,918 citations