System identification (SID) constitutes a focal point in experimental testing of civil infrastructure as well as in structural health monitoring (SHM). Conventional SID approaches have relied on creating finite element (FE) models of civil infrastructure assets and on calibrating the models against in-situ derived information from testing equipment or against SHM data. FE models are capable of providing valuable information on the structural condition. However, the equations governing the FE method are coupled, usually calling for centralized data collection, which may be unsuitable for modern wireless SHM systems that employ independently operating wireless sensor nodes. In this paper, a SID approach for making full use of FE models on board wireless sensor nodes is presented, based on embedded computing and on reduced-order finite elements. Specifically, FE models of civil infrastructure assets are reduced, using model-order reduction, and partitioned into partial models, which represent different substructures and are computationally efficient for embedment in wireless sensor nodes. Using the partial models and structural response data from the substructures, insights into the structural condition of the civil infrastructure assets are obtained. The proposed approach is suitable for vibration-based SID, applied as part of long-term SHM strategies, and implementable in wireless SHM systems. Validation tests using SHM data recorded from a real-world road bridge showcase the validity of the proposed SID approach.