大跨径桥梁钢箱梁疲劳损伤局部与整体协同评估方法及系统
By deploying strain sensors on the steel box girder of a long-span bridge and optimizing the support vector machine model using cross-correlation methods and genetic algorithms, the problem of assessing the impact of local fatigue cracks on the overall structure of the steel box girder was solved. This enabled accurate fatigue crack diagnosis and safety level assessment, improving the scientific rigor and timeliness of the assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Filing Date
- 2025-10-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are insufficient to accurately diagnose local fatigue crack damage in steel box girders of long-span bridges and its impact on overall structural safety, resulting in unscientific and untimely assessments and a lack of a unified indicator system and evaluation model.
Strain sensors are used to monitor the strain response of steel box girders. The strain data are aligned using a cross-correlation method, and the strain ratio and stiffness ratio are calculated. The support vector machine model is optimized by combining a genetic algorithm to quantify the type and safety level of fatigue cracks, thereby achieving a synergistic assessment of local damage and overall performance.
It enables accurate diagnosis and safety assessment of fatigue cracks in steel box girders, breaking through the limitations of traditional assessment methods, providing a scientific basis for decision-making, and improving the accuracy and timeliness of assessment.
Smart Images
Figure CN121350797B_ABST