Return
A multi-label and multi-stage damage identification method for complex structures
DOI:10.1016/j.oceaneng.2025.123938.png)
Abstract
En 中文
• Multi-label framework for accurate multi-location damage identification in structural health monitoring. • Residual-attention feature extractor enhances damage detection precision and robustness. • Method outperforms LSTM, TCN, GNN baselines in accuracy and generalization on real structures.
Journal
IF:
5.5
Papers:
7.2K
Citations:
7.6W
Organization
No organization information available
Cited Papers
Structural damage severity classification from time-frequency acceleration data using convolutional neural networks
STRUCTURES
IF4.3
Damage identification for jacket-supported offshore wind turbines with limited measurements
Measurement
IF0

