A Machine Learning Model to Predict the Seismic Lifecycle Behavior of a Cross-Sea Cable-Stayed Bridge

Buildings, Год журнала: 2024, Номер 14(5), С. 1190 - 1190

Опубликована: Апрель 23, 2024

Cross-sea cable-stayed bridges encounter challenges associated with cable corrosion and cable-force relaxation during their service life, which significantly affects structural performance seismic response. This study focuses on a cross-sea bridge located in Hainan Province. Utilizing an LSTM deep learning model, this aims to fill the gaps short-term cable-monitoring data from past year using available cable-force-monitoring same period. The authors of interpolated absence sensors employed SARIMA machine time-series-prediction model predict future trends all forces. A finite-element was constructed, dynamic time-history analysis response conducted, considering influence future. findings indicate that LSTM-SARIMA predicted average decrease 11.81% force after 20 years. During lifecycle cables, exerts significant impact variation stress within structure earthquakes, while has more pronounced effect vertical displacement main beam events. Compared when traditional only considers corrosion, maximum negative increases by 29.7% proposed if earthquake intensity is 0.35 g years, indicates can exactly determine behavior bridge, impacts both corrosion.

Язык: Английский

Seismic vulnerability evolution of large cantilever cap bridges due to material degradation

Structures, Год журнала: 2025, Номер 72, С. 108303 - 108303

Опубликована: Янв. 26, 2025

Язык: Английский

Mechanical properties of offshore floating photovoltaic structural coating/carbon steel system in a marine environment

Ocean Engineering, Год журнала: 2025, Номер 323, С. 120585 - 120585

Опубликована: Фев. 10, 2025

Язык: Английский