doi:10.1017/dce.2021.16engSancarlos, AbelCameron, MorganLe Peuvedic, Jean-MarcGroulier, JulietteDuval, Jean-LouisCueto, EliasChinesta, FranciscoLearning stable reduced-order models for hybrid twinsART-2021-130232The 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 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.2021http://zaguan.unizar.es/record/11901910.1017/dce.2021.16http://zaguan.unizar.es/record/119019oai:zaguan.unizar.es:119019info:eu-repo/grantAgreement/ES/MINECO-CICYT/DPI2017-85139-C2-1-Rinfo:eu-repo/grantAgreement/ES/UZ/ESI-ENSAM-Simulated RealityData-Centric Engineering 2 (2021), e10 [20 pp.]byhttp://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccess