A method and system for segmenting rock mass on the structural plane of a three-dimensional mesh model of the tunnel face.

By using multimodal sensing equipment and tensor processing, combined with clustering methods, the problem of low accuracy in identifying the structural face of the tunnel surrounding rock was solved. This enabled accurate extraction of structural face vertices and efficient calculation of rock mass parameters, thereby improving the reliability of tunnel stability evaluation.

CN122289678APending Publication Date: 2026-06-26CHINA RAILWAY SIYUAN SURVEY & DESIGN GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CHINA RAILWAY SIYUAN SURVEY & DESIGN GRP CO LTD
Filing Date
2026-03-16
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing technologies have low accuracy in identifying the structural surfaces of tunnel surrounding rock faces, making it difficult to accurately obtain the true shape and parameters of the rock mass structural surfaces. Furthermore, traditional methods are prone to over-segmentation and under-segmentation.

Method used

Multimodal sensing equipment integrating infrared cameras, visible light cameras, and lidar is used, combined with RTK positioning and time synchronization technology, to generate colored three-dimensional mesh model data. Structural surface vertices are extracted through tensile processing and clustering methods to calculate rock mass parameters.

Benefits of technology

It enables accurate identification of the structural surfaces of the tunnel surrounding rock, improves the accuracy of structural surface vertex extraction and rock mass parameter calculation, avoids over-segmentation and under-segmentation, and enhances the reliability of tunnel stability evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122289678A_ABST
    Figure CN122289678A_ABST
Patent Text Reader

Abstract

This invention provides a method for segmenting rock mass structural surfaces in a three-dimensional mesh model of the tunnel face, relating to the fields of three-dimensional laser point cloud processing and tunnel geotechnical engineering. The method involves collecting multimodal sensing data of the tunnel face during excavation, generating a colored three-dimensional mesh model based on this data, and performing tensor quantization on the colored three-dimensional mesh model data. Each vertex of the three-dimensional mesh model is encoded as a normal vector tensor, and the saliency of the vertices is determined based on the tensors to extract the vertex data of the structural surfaces. The structural surface vertices are then clustered, and structural surfaces are extracted from the obtained clustered vertices. Based on the orientation of the structural surfaces, they are grouped, and rock mass parameters are calculated. This invention solves the technical problems in existing technologies where structural surface rock mass segmentation easily leads to over-segmentation or under-segmentation, and where manual geological sketching is inefficient and inaccurate.
Need to check novelty before this filing date? Find Prior Art