PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
September 19, 2025Structural Health Monitoring0 citations

Hybrid CAE-DSVDD Framework for Unsupervised Structural Damage Detection in Bridges

Hybrid CAE-DSVDD for unsupervised vibration-based damage detection in in situ steel truss bridge

View Full Paper
Ask AI
Bookmark
Share

Authors

SPSoyeon ParkSKSun-Joong Kim

Discussion

Loading...

Member takes

Overview

This framework combines convolutional autoencoders and DSVDD to enhance vibration-based damage detection, suggesting improved sensitivity to subtle changes.

Key Points

  • The proposed framework achieved a high F1-score of 98.46% for detecting damage under forced vibration.
  • This approach utilizes a convolutional autoencoder and deep support vector data description for effective anomaly detection.
  • Field monitoring data from a real-world damaged bridge validated the framework's high accuracy for unsupervised detection.
  • Robustness was assessed across various loading conditions, demonstrating its adaptability in real-world infrastructure monitoring.

Cite This Study

Park et al. (2025) studied this question.

synapsesocial.com/papers/68d466c431b076d99fa65eedhttps://doi.org/10.1177/14759217251369727
View Full Paper
Ask AI
Bookmark
Share