Abstract (EN):
In long-span suspension bridges, premature failure of bearings or expansion joints has been a concern during the bridge service life. To implement a reasonable inspection strategy of these critical components, cumulative displacement must be considered for assessing their life consumption and health state. As suspension bridges are subjected to simultaneous multiple loads, it is important to investigate the contributions of different loads to cumulative displacement. This paper develops an approach to interpreting cumulative displacement through the physics-based characterisation of multiple loads in a machine learning framework. The approach correlates wind, temperature, train, and roadway traffic with bridge response using Structural Health Monitoring (SHM) data from a long-span road-rail suspension bridge located in Portugal. The effects of the different loads on the cumulative displacement are quantified both globally and individually with SHapley Additive exPlanations (SHAP). The SHAP interpretation reveals that the trainload is the most influential parameter in the cumulative displacement of bearings and expansion joints, followed by roadway traffic. Besides, cumulative displacement increases with the trainloads and roadway traffic. Wind and temperature proved less important in explaining the cumulative displacement. The contribution of trainloads to the daily cumulative displacement is also calculated to verify its dominating influence. The results can guide the maintenance of relevant bridge components to avoid premature damage.
Idioma:
Inglês
Tipo (Avaliação Docente):
Científica
Nº de páginas:
11