Learning stable reduced-order models for hybrid twins

TL;DR

This paper develops a method for creating stable, fast, and accurate reduced-order models within the Hybrid Twin framework, combining physics-based models with data-driven corrections for real-time applications.

Contribution

It introduces a novel approach to compute stable, data-driven corrections in Hybrid Twins, ensuring stability and low computational cost.

Findings

Proposes a new stability-guaranteed correction method.

Achieves real-time, accurate model updates.

Ensures low computational overhead for stability.

Abstract

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.