.png){kind=icon}
.png){kind=icon}
Return
Spectrally normalised Wasserstein generative adversarial imputation framework for multi-modal SHM data recovery in digital-twin systems
.png){kind=icon}
OA
AI
S
S
N
T
DOI：10.1016/j.aei.2026.104734.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes SN-WGAIN-GP, a deep learning framework for imputing SHM data under random and continuous missing scenarios. • Integrates different strategies for stable and efficient adversarial training of the proposed model. • Employs Monte Carlo dropout, Gaussian noise, and critic-guided pooling methods for uncertainty-aware multiple imputation. • Validated on LUMO and Canton Tower datasets across varying noise levels and temporal resolutions. • Achieves RMSE < 0.10 and PCC > 0.95 under severe missingness, outperforming other benchmark imputation models.
Keywords:
Wasserstein Generative Adversarial Network
Structural Health Monitoring
Spectral Normalisation
Two Time-scale Update Rule
Multiple Imputation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.9
Papers:
4.0K
Citations:
1.7W
Organization
Cited Papers