Intelligent rock mass structure identification and stability analysis method based on guide hole image

By combining deep learning and Bayesian theory, a three-dimensional discrete fracture network model is automatically identified and constructed, which solves the problem of lagging assessment of surrounding rock stability in raise borehole construction, realizes timely generation of support parameters and dynamic adjustment of the construction process, and improves construction safety and economy.

CN122328095APending Publication Date: 2026-07-03CHINA THREE GORGES CORPORATION
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-30
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing technologies lack intelligent fracture identification and 3D modeling throughout the entire process of reverse drilling, resulting in delayed and inaccurate assessment of surrounding rock stability and difficulty in generating timely and effective support parameters.

Method used

A deep learning model is used to automatically identify crack traces in the borehole wall image, construct a three-dimensional discrete crack network model, identify key blocks and perform probabilistic reliability analysis, generate support parameters, and dynamically update the model through Bayesian theory to achieve a construction closed loop.

Benefits of technology

It improves the accuracy and efficiency of surrounding rock structure identification, realizes transparent quantification of surrounding rock stability assessment and automatic generation of support parameters, and ensures construction safety and economy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122328095A_ABST
    Figure CN122328095A_ABST
Patent Text Reader

Abstract

This invention provides an intelligent rock mass structure identification and stability analysis method based on pilot hole images, belonging to the fields of underground engineering informatization and engineering geology. The method includes: identifying fracture traces and inverting fracture surface attitude based on pilot hole unfolding images to obtain fracture attributes and identification confidence; constructing a three-dimensional discrete fracture network (DFN) model constrained by single-hole observation statistical characteristics, and introducing key blocks into the free surface boundary of the excavated shaft for kinematic screening; mapping the fracture identification confidence to geometric parameter variability and combining it with rock mass mechanics parameters to conduct probabilistic reliability analysis, obtaining the instability probability and reliability index of key blocks and well sections; automatically generating support parameter schemes such as anchor bolts / shotcrete with target reliability as constraints; and using newly revealed information during construction and excavation to perform Bayesian updates on the DFN parameters and trigger cyclic calculations to achieve a closed loop of risk quantification, support decision-making, and on-site feedback.
Need to check novelty before this filing date? Find Prior Art