Empowering car design, maintenance and operation from advanced model order reduction and AI technologies

This paper aims at introducing the main technologies enabling the construction of physicsaware digital twins, the so-called Hybrid Twins™, embracing physics-based and data-driven functionalities, both enriching mutually. Both should proceed in almost real-time, and the last being able to proceed in the scarce data limit. When applied to materials, structures and processes, model order reduction technologies enable the construction of parametric solutions (surrogates), whereas data-driven modelling, based in advanced regressions, works with experimental or synthetic data, encompassing rapidity and accuracy, even in the low data limit. This paper describes both the state of the art, as well as an outlook, on the most advanced technologies at the origin of the so-called Hybrid Twin™. In the associated talk, some examples concerning car design, maintenance and operation will be addressed, emphasizing the benefits provided by the tools here described. © 2022 the authors.