一种基于破岩机理的TBM跨洞径围岩类别实时判别方法及系统
By using DFPI and DTPI feature indices based on rock breaking mechanisms and a Bayesian classification model, the problems of insufficient timeliness and interpretability of traditional TBM surrounding rock classification methods are solved, and real-time, robust discrimination and parameter optimization of TBM surrounding rock categories are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JIAOTONG UNIV
- Filing Date
- 2025-11-07
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional TBM surrounding rock classification methods rely on sampling and manual interpretation, which lacks continuity and timeliness, making it difficult to meet real-time control requirements. Pure data-driven methods are constrained by the scarcity of labels and cross-equipment and geological domain deviations in the early stages of engineering, resulting in insufficient interpretability.
Based on the rock breaking mechanism, we construct the DFPI and DTPI rock breaking characteristic indices. Combining the MMD method and Bayesian classification model, we reduce the impact of equipment size and operational disturbances through data preprocessing, achieving transferability across tunnel diameters and engineering projects. We introduce an online identification framework based on Bayesian discrimination and threshold rules to provide real-time and robust surrounding rock category identification.
It enables continuous, traceable, and updatable determination of surrounding rock types, improves the real-time performance and robustness of TBM parameter optimization and risk collaborative decision-making, and reduces the impact of changes in equipment and geological conditions.
Smart Images
Figure CN121614972B_ABST