Abstract

Modern engineering systems—ranging from bridges to wind energy structures—operate under complex loading and evolving environmental conditions. Ensuring their resilience requires understanding their real-time performance, a goal addressed by Structural Health Monitoring (SHM). SHM follows a hierarchy from damage detection to prognosis, but higher-level tasks demand more than purely data-driven methods. Achieving reliable insights necessitates balancing physics-based models with operational data and expert knowledge while maintaining intuitive system representations. This talk explores how critical infrastructure can be modeled as cyber-physical systems, integrating sensing, modeling, control, and networking to create closed-loop digital twins. We emphasize the role of intuitive representations, such as those driven by physics principles and graph-based representations, in capturing system topology, dependencies, and evolving states. By balancing data-driven augmentation, physics-based modeling, expert insights, and system-wide considerations, we develop augmented twins that accurately represent structures, predict responses beyond measured points, anticipate future performance, and support proactive decision-making across various engineering assets.