Dragos, KosmasKosmasDragosSmarsly, KayKaySmarsly2025-10-272025-10-272025-0711th International Conference on Experimental Vibration Analysis for Civil Engineering Structures, EVACES 2025978-3-031-96110-6978-3-031-96109-0978-3-031-96111-3978-3-031-96112-0https://hdl.handle.net/11420/58266Since the introduction of wireless technologies in structural health monitoring (SHM), researchers have focused on exploiting the computational capabilities of wireless sensor nodes via embedded computing approaches that enable on-board data analysis, in lieu of wirelessly transmitting large amounts of data. Embedded computing for wireless SHM has largely been based on data-driven analysis methods, which only implicitly account for the physics governing the structural behavior. However, the increasing digitalization of societal activities, including structural maintenance, is frequently associated with digital twinning, which builds upon continuous exchange of data between the digital and the physical world and, often, upon physics-based modeling. In this context, this paper presents an approach for integrating digital twins into wireless SHM systems. Given the distributed nature of wireless sensor networks, characterized by the quasi-independent operation of wireless sensor nodes, the digital twins are designed in a decentralized manner, leveraging the computational power of wireless sensor nodes. In particular, the decentralized digital twins are represented by partial finite element (FE) models of a structure being monitored that are embedded in the wireless sensor nodes and “live” and “evolve” in tandem with the structure. The wireless sensor nodes use the partial FE models and structural response data locally collected to collaboratively assess the structural condition. The proposed approach is validated via laboratory tests, the results of which showcase the capability of the approach to yield reliable estimates of the structural condition.enDigital twinningembedded computingfinite element methodmodel-order reductionstructural health monitoringsurrogate modelingwireless sensor networksTechnology::690: Building, ConstructionConference Paper10.1007/978-3-031-96110-6_103Conference Paper