A Novel Unsupervised Structural Damage Detection Method Based on TCN-GAT Autoencoder

Over the service life of several decades, structural damage detection is crucial for ensuring the safety and durability of engineering structures. However, existing methods often overlook the spatiotemporal coupling in multi-sensor data, hindering the full exploitation of structural dynamic evolutio...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Sensors (Basel, Switzerland) Jg. 25; H. 21; S. 6724
Hauptverfasser:	Ni, Yanchun, Jin, Qiyuan, Hu, Rui
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Switzerland MDPI AG 03.11.2025
Schlagworte:	Accuracy Bridges Civil engineering damage detection Deep learning Environmental engineering Fault diagnosis graph attention network Identification Localization Methods multi-sensor Neural networks Sensors Social networks structural health monitoring temporal convolutional network unsupervised deep learning Wavelet transforms graph attention network damage detection structural health monitoring multi-sensor unsupervised deep learning temporal convolutional network
ISSN:	1424-8220, 1424-8220
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!