Model-based transfer learning for real-time damage assessment of bridge networks

Abstract

The growing use of permanent monitoring systems has increased data availability, offering new opportunities for structural assessment but also posing scalability challenges, especially across large bridge networks. Managing multiple structures requires tracking and comparing long-term behavior efficiently. To address this, knowledge transfer between similar structures becomes essential. This paper proposes a model-based transfer learning approach using neural network surrogate models, enabling a model trained on one bridge to be adapted to another with similar characteristics. These models capture shared damage mechanisms, supporting a scalable and generalizable monitoring framework. The method was validated using real data from two bridges. The transferred model was integrated into a Bayesian inference framework for continuous damage assessment based on modal features from monitoring data. Results showed high sensitivity to damage location, severity, and extent. This approach enhances real-time monitoring and enables cross-structure knowledge transfer, promoting smart monitoring strategies and improved resilience at the network level.