时间域迁移物理引导深度学习的桥梁动态可靠性分析方法
By employing a time-domain transfer physics-guided deep learning approach, combined with transfer component analysis and the Monte Carlo method, the problem of insufficient accuracy and efficiency of traditional methods in the dynamic reliability analysis of railway bridges is solved, achieving efficient and reliable safety assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN JIAOTONG UNIVERSITY
- Filing Date
- 2026-04-17
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional methods for dynamic reliability analysis of railway bridges are insufficient in terms of accuracy and efficiency, making it difficult to meet the real-time requirements of railway transportation safety management. Furthermore, data-driven models lack reliability in bridge structural safety assessment.
A time-domain transfer physics-guided deep learning approach is adopted. By establishing the vibration equation and initial boundary conditions of the railway bridge, and combining transfer component analysis and physics-driven model, the deep learning model is used to predict the bridge amplitude, and the Monte Carlo method is combined to conduct dynamic reliability analysis.
It improves the computational efficiency and accuracy of dynamic reliability analysis of railway bridges, solves the problem of insufficient prediction accuracy in the long time domain, and provides a reliable basis for safety assessment.
Smart Images
Figure CN122046516B_ABST