一种基于多源数据和数物融合实验的病害发育评估方法
Through multi-source data and data-physical fusion experiments, combined with deep learning and TCI circle theory, we have achieved full-dimensional collection, intelligent quantification, and accurate prediction of tunnel lining defects. This has solved the problems of the single nature of tunnel defect detection and the lack of scientific theory in prediction, improved detection efficiency and accuracy, ensured the safety of tunnel structures, and extended their service life.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG UNIV OF SCI & TECH
- Filing Date
- 2026-05-13
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for detecting tunnel lining defects are limited, lack precision and efficiency in quantifying defects, lack scientific theoretical support for defect development prediction, lack physical experimental verification of prediction results, rely on experience for disease prevention and control measures with poor specificity, and are disconnected from actual engineering practices.
By employing multi-source data and data-physical fusion experiments, comprehensive disease information is acquired through multi-source disease collection equipment. Deep learning algorithms are used for disease identification and quantification. The development direction and location of the main disease are predicted by combining TCI circle theory. The prediction results are verified through dynamic-static load pressure tests, thus achieving closed-loop management throughout the entire process.
It has achieved comprehensive and seamless collection of tunnel lining defects, intelligent, efficient and accurate quantification of defects, and precise prediction and scientific prevention and control of major defects, thereby improving detection efficiency and accuracy, ensuring tunnel structural safety, extending service life and reducing operation and maintenance costs.
Smart Images
Figure CN122171557B_ABST