Learning stable reduced-order models for hybrid twins
This work addresses stability issues in hybrid twins for applications requiring real-time corrections, but it appears incremental as it builds on existing frameworks.
The paper tackles the problem of ensuring stability in hybrid twin models, which combine physics-based models with data-driven corrections for real-time feedback, by proposing a new approach that guarantees stable time-integration with low computational cost.
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 HT is 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 Hybrid Twin framework. Furthermore, regarding the delicate and important problem of stability, a new approach is proposed, introducing several sub-variants and guaranteeing a low computational cost as well as the achievement of a stable time-integration.