We develop advanced statistical and machine learning frameworks to tackle uncertainty and complexity in structural dynamics.
Want to know more?
- We introduce hierarchical Bayesian models for non-stationary system identification, enabling robust parameter estimation under operational variability.
- We integrate Gaussian Process Regression, tensor-based approaches, and physics-informed learning to enhance predictive accuracy and uncertainty quantification.
- These methods underpin applications such as Digital Twins, virtual sensing, and condition monitoring, providing scalable solutions for real-world engineering systems.