Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025IEEE Transactions on Neural Networks and Learning SystemsOpen Access

Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

ZWZhihao WenYFYuan FangPWPengcheng Wei

Discussion

Loading...

Member takes

Overview

This approach demonstrates improved remaining useful life prediction using a temporal graph model, leveraging heterogeneous sensors.

Key Points

  • The novel model improves remaining useful life prediction by capturing temporal and spatial dynamics in sensor data.
  • Empirical findings show up to 31.6% improvement on the N-CMAPSS dataset, highlighting effective prediction capacity.
  • Temporal graph neural networks effectively utilize heterogeneous sensor data to enhance model performance.
  • Feature-wise linear modulation helps address sensor diversity, resulting in better learning of data characteristics.

Cite This Study

Wen et al. (2025) studied this question.

synapsesocial.com/papers/68c1a8fe54b1d3bfb60e1af3https://doi.org/10.1109/tnnls.2025.3592788
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. 1Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction2024 · 2 citations
  2. 2Spatio-Temporal Propagation: An Extended Message Passing Graph Neural Network for Remaining Useful Life Prediction2024 · 4 citations
  3. 3Transformer Encoder Enhanced by an Adaptive Graph Convolutional Neural Network for Prediction of Aero-Engines’ Remaining Useful Life2024 · 15 citations
  4. 4A Static-Dynamic Hybrid Graph Neural Network Model Incorporating Physical Information for Remaining Useful Life Prediction of Aircraft Engines2025 · 1 citations
  5. 5Memory-augmented spatio-temporal graph networks for federated cross-domain remaining useful life prediction2026