.png){kind=icon}
Return
Time-Filtering Graph Learning With Spatial–Temporal Diffusion for Robust Blade Icing Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/JIOT.2026.3654792.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate detection of wind turbine blade icing is essential for ensuring the safety and efficiency of wind farm operations. Although current machine learning and deep learning approaches are capable of identifying icing states, they still suffer from three major limitations: heavy reliance on manual feature engineering limits the capture of meaningful spatiotemporal dependencies; highly imbalanced data leads to increased false negatives and alarm delays; and sensitivity to data noise often introduces false positives. To address these challenges, this article proposes an imbalance- and noise-resistant TG-Diff network, which achieves accurate and robust icing state classification by effectively integrating spatiotemporal information from multiple sensors. The TG-Diff comprises three core modules: a temporal filtering-based graph learning module (TF-GLM), a temporal–spatial diffusion graph convolutional network (TSD-GCN), and a distance-based classifier (DBC). Specifically, the TF-GLM dynamically infers node relationships to construct robust graph topologies; the TSD-GCN enhances feature representation and suppresses noise through diffusion mechanisms; and the DBC effectively mitigates class imbalance by leveraging distance-based decision boundaries. Experimental results demonstrate that the proposed modules work synergistically to collectively enhance the accuracy and robustness of icing detection in real-world complex environments.
Keywords:
Diffusion graph convolutional networks (DGCNs)
distance-based classification
dynamic graph construction
robust fault detection
spatiotemporal graph neural networks
wind turbine blade icing detection
Journal
IF:
8.9
Papers:
1.4W
Citations:
7.8W
Organization
Cited Papers
ShareSave
ShareSaveShareSaveShareSaveShareSaveLearning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition.png)
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
OAAI
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)IF0
OAAIShareSaveStatistics Pooling Time Delay Neural Network Based on X-Vector for Speaker VerificationICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)IF0
PREAI
ShareSave
View more