基于时空多元数据融合的桥梁响应监测方法及系统
By deploying cameras and accelerometers on the bridge to collect data, a multi-rate Kalman data fusion network and modal neural ordinary differential equations are constructed to reconstruct the bridge's seismic dynamic response. This solves the problems of high cost and limited accuracy of traditional monitoring equipment and enables global response monitoring and condition assessment of the bridge.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NAT ENG LAB FOR HIGH SPEED RAILWAY CONSTR
- Filing Date
- 2026-06-17
- Publication Date
- 2026-07-17
AI Technical Summary
Existing bridge monitoring technologies are insufficient to obtain the overall operational status of long-span bridges, and monitoring data is easily lost under extreme conditions, affecting the determination of structural status. This is especially true for high-speed railway bridges, where traditional measuring equipment is costly and has limited accuracy, making it difficult to achieve global response monitoring.
Visual displacement data is collected by deploying monitoring cameras and acceleration data is collected by accelerometers. A multi-rate Kalman data fusion network is constructed to perform spatiotemporal multivariate data fusion. Combined with modal order reduction theory and neural ordinary differential equations, a bridge seismic dynamic response reconstruction network is constructed to reconstruct the displacement and acceleration response of the test points.
It enables the reconstruction of the overall bridge response information from a small number of measuring points under existing conditions, improving monitoring accuracy and robustness, providing more complete structural condition assessment information, and supporting the assessment of bridge structure seismic performance and post-earthquake damage detection.
Smart Images
Figure CN122409110A_ABST