基于聚类的多参数联合隧道探测方法、系统及装置
By employing a multi-parameter joint detection method, combining minimum support functional and FCM clustering, the problem of unclear inversion imaging in tunnel detection using induced polarization and hydrological methods was solved, enabling precise characterization of the water-bearing structure boundary in front of the tunnel and improving the accuracy and stability of the detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANDONG UNIV
- Filing Date
- 2023-08-21
- Publication Date
- 2026-07-17
AI Technical Summary
In tunnel detection, the induced polarization method is sensitive to water body response but not to boundaries. The hydrological flow field permeability coefficient detection data has poor sensitivity, resulting in unclear inversion imaging and multiple solutions, making it difficult to accurately characterize the boundaries of anomalies.
A cluster-based multi-parameter joint detection method is adopted. Multiple sets of observation data are obtained through the geoelectric model. Combined with multi-parameter inversion of resistivity, polarizability and permeability coefficient, the model is iterated and the membership degree is updated using the minimum support functional and FCM clustering method. The weights of each parameter are balanced to solve the homogenization problem in the inversion process and achieve accurate boundary characterization.
It improves the accuracy of detecting water-bearing structures ahead of tunnels, solves the problem of unclear boundary characterization in the joint inversion of induced polarization and hydrological methods, and realizes the stability and effect improvement of multi-parameter inversion.
Smart Images
Figure CN117034637B_ABST