.png){kind=icon}
.png){kind=icon}
Return
Unsupervised progressive structural damage assessment using a denoising diffusion probabilistic model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.measurement.2025.120074.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Unsupervised DDPM assesses progressive structural damage in real time. • Learns damage-sensitive features from multi-channel vibration signals. • Dual indicators from latent distribution shifts and time-domain generation errors. • Outperforms VAE/GAN/DAE baselines in triple decision-making errors. • Proven effective on a full-scale wooden pavilion and the in-service Z24 Bridge.
Journal
IF:
5.6
Papers:
1.9W
Citations:
5.4W