Spectrally normalised Wasserstein generative adversarial imputation framework for multi-modal SHM data recovery in digital-twin systems

• 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. Reliable data acquisition is fundamental to the integrity of Structural Health Monitoring (SHM) systems and their integration within digital twin environments. However, data loss caused by sensor malfunction, communication failure, or environmental interference remains a persistent challenge, undermining model fidelity and structural condition assessment accuracy, especially during extreme loading events when continuous monitoring is most critical for digital twin applications. To address this, we propose SN-WGAIN-GP, a novel Spectrally Normalised Wasserstein Generative Adversarial Imputation Network with Gradient Penalty, designed for robust multi-modal time-series data imputation in SHM applications. The framework enhances the adversarial learning process through three key mechanisms: spectral normalisation to enforce Lipschitz continuity and stabilise training; wasserstein distance with gradient penalty to improve convergence and reduce mode collapse; and a two-time-scale update rule to balance generator-critic dynamics and accelerate optimisation. SN-WGAIN-GP operates in both single and multiple-imputation modes. In the latter, it leverages Monte Carlo (MC) dropout, Gaussian noise, and multiple latent noise vectors to generate diverse imputed datasets, followed by critic-weighted softmax pooling for aggregation and Rubin’s rule for quantifying predictive uncertainty. Comprehensive evaluation on two benchmark datasets, the LUMO experimental steel mast and the Canton Tower full-scale instrumented structure, demonstrates that SN-WGAIN-GP consistently outperforms existing GAN-based baseline models across a wide range of missing-data rates, noise levels, and temporal resolutions. Validation through operational modal analysis confirms accurate natural frequency extraction, with imputed responses showing excellent agreement with true responses in both time-domain and frequency spectra. SN-WGAIN-GP maintains correlation coefficients above 0.95 and RMSE below 0.10 even under 90% data loss, while achieving computational efficiency compatible with real-time digital twin deployment. The framework provides a scalable, uncertainty-aware and physically interpretable solution for multi-sensor SHM data imputation under partial observability, advancing the reliability of data-driven digital twins for predictive maintenance, resilience assessment, and intelligent infrastructure management.