Learning stable reduced-order models for hybrid twins

The concept of hybrid twin (HT) has recently received a growing interest thanks to the availability of powerful machine learning techniques. This twin concept combines physics-based models within a model order reduction framework-to obtain real-time feedback rates-and data science. Thus, the main idea of the HTis to develop on-the-fly data-driven models to correct possible deviations between measurements and physics-based model predictions. This paper is focused on the computation of stable, fast, and accurate corrections in the HT framework. Furthermore, regarding the delicate and important problem of stability, a new approach is proposed, introducing several subvariants and guaranteeing a low computational cost as well as the achievement of a stable time-integration.

Automated summary

The concept of hybrid twin (HT) combines physics-based models and data science to correct deviations between measurements and predictions in real-time. This paper focuses on computing stable, fast, and accurate corrections in the HT framework, introducing a new approach to ensure stability.