Drive-by spatial offset detection for high-speed railway bridges based on fusion analysis of multi-source data from comprehensive inspection train DOI Creative Commons
Chuang Wang, Jiawang Zhan, Nan Zhang

и другие.

Railway Engineering Science, Год журнала: 2025, Номер unknown

Опубликована: Март 26, 2025

Abstract The spatial offset of bridge has a significant impact on the safety, comfort, and durability high-speed railway (HSR) operations, so it is crucial to rapidly effectively detect operational HSR bridges. Drive-by monitoring uneven settlement demonstrates potential due its practicality, cost-effectiveness, efficiency. However, existing drive-by methods for detecting have limitations such as reliance single data source, low detection accuracy, inability identify lateral deformations This paper proposes novel inspection method based multi-source fusion comprehensive train. Firstly, dung beetle optimizer-variational mode decomposition was employed achieve adaptive non-stationary dynamic signals, explore hidden temporal relationships in data. Subsequently, long short-term memory neural network developed feature signal accurate prediction bridge. A dataset track irregularities CRH380A train responses generated using 3D train–track–bridge interaction model, accuracy effectiveness proposed hybrid deep learning model were numerically validated. Finally, reliability further validated by analyzing actual measurement obtained from research findings indicate that approach enables rapid bridge, ensuring long-term safety

Язык: Английский

Drive-by spatial offset detection for high-speed railway bridges based on fusion analysis of multi-source data from comprehensive inspection train DOI Creative Commons
Chuang Wang, Jiawang Zhan, Nan Zhang

и другие.

Railway Engineering Science, Год журнала: 2025, Номер unknown

Опубликована: Март 26, 2025

Abstract The spatial offset of bridge has a significant impact on the safety, comfort, and durability high-speed railway (HSR) operations, so it is crucial to rapidly effectively detect operational HSR bridges. Drive-by monitoring uneven settlement demonstrates potential due its practicality, cost-effectiveness, efficiency. However, existing drive-by methods for detecting have limitations such as reliance single data source, low detection accuracy, inability identify lateral deformations This paper proposes novel inspection method based multi-source fusion comprehensive train. Firstly, dung beetle optimizer-variational mode decomposition was employed achieve adaptive non-stationary dynamic signals, explore hidden temporal relationships in data. Subsequently, long short-term memory neural network developed feature signal accurate prediction bridge. A dataset track irregularities CRH380A train responses generated using 3D train–track–bridge interaction model, accuracy effectiveness proposed hybrid deep learning model were numerically validated. Finally, reliability further validated by analyzing actual measurement obtained from research findings indicate that approach enables rapid bridge, ensuring long-term safety

Язык: Английский

Процитировано

0