back to list

Research Project: DAMOCLES: Data-Augmented Modeling Of Constitutive Laws for Engineering Systems

Description

The modeling of complex engineering systems is highly challenging. Physics-based models require a cautious application of constitutive assumptions, whereas data-based models require vast amounts of data. DAMOCLES targets a breakthrough in the constitutive modeling of such systems in different physical domains by developing a unified multi-tool framework that combines the favorable characteristics of physics-based and data-based approaches.

The core step of DAMOCLES is to merge the state of the art in port-Hamiltonian Neural Networks, Robust Bayesian Uncertainty Quantification and Evolutionary Optimization to cover the entire spectrum from purely data-driven to completely physics-based modeling. The challenges are tied to data-availability. Flexible, data-driven approaches are available for data-rich cases, but these lack good generalization properties due to being physics-agnostic. For data-scant cases, existing approaches for the training and calibration of physics-based models are unreliable.

DAMOCLES is an EAISI EMDAIR Project involving the Departments of Mathematics & Computer Science, Mechanical Engineering, and Electrical Engeneering.

The DAI cluster is involved in DAMOCLES Work Package 2, Robust Bayesian Uncertainty Quantification. Its main research question is: When can we feasibly specify the most complex constitutive model for which the data provides evidence? And, if the best trade-off is computationally infeasible with the state of the art, can robust uncertainty models and efficient approximate inference techniques be developed to make it feasible?

Details
Principal Investigator
Erik Quaeghebeur
Involved members:
Rodrigo Lima De Souza E Silva
Link
Learn more