A soluble rock stratum tunnel health diagnosis method, device, equipment and storage medium

By constructing a coupled knowledge graph and parallel network model of karst-lining-surrounding rock, the problem of insufficient integration of multi-source data in existing technologies has been solved, enabling real-time, accurate diagnosis and dynamic early warning of karst disasters, and improving the safety and operation and maintenance efficiency of tunnels.

CN121479200BActive Publication Date: 2026-07-21CHINA RAILWAY ERYUAN ENGINEERING GROUP CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA RAILWAY ERYUAN ENGINEERING GROUP CO LTD
Filing Date
2025-11-13
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing tunnel health diagnostic technologies cannot effectively integrate multi-source sensing data, making it difficult to achieve comprehensive monitoring and accurate diagnosis of karst disasters. They also lack dynamic adjustment capabilities, resulting in insufficient accuracy and reliability of diagnostic results and an inability to identify early signs and take emergency measures in a timely manner.

Method used

A coupled knowledge graph of karst-lining-surrounding rock is constructed. By combining a parallel coupled model of fuzzy Bayesian network, convolutional neural network and long short-term memory network, multi-source sensing data fusion analysis and online learning are carried out to diagnose the risk of karst water inrush and mud inrush in real time. Intelligent identification and dynamic early warning are achieved through dynamic weight adjustment and early warning level classification.

Benefits of technology

It enables real-time, accurate diagnosis and dynamic early warning of karst disasters, improves tunnel safety and operation and maintenance efficiency, and can perform deep fusion of multi-source monitoring data and intelligent identification of disaster mechanisms under complex soluble rock strata conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121479200B_ABST
    Figure CN121479200B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of tunnel engineering safety monitoring, and in particular to a soluble rock stratum tunnel health diagnosis method, device, equipment and storage medium. It comprises: searching for a karst-lining-surrounding rock coupling knowledge graph to determine whether there is a disaster node that matches the real-time acquired tunnel multi-source perception data; if there is, diagnosis is carried out according to the karst water-rock coupling mechanism embedded in the node; if there is not, a preset karst disaster fusion model is called to carry out online learning and dynamic diagnosis, and a disaster node is added in the knowledge graph. The fusion model extracts features such as the karst water chemical ion concentration change rate, the surrounding rock effective porosity mutation gradient and the lining behind cavity volume growth rate, outputs the karst water and mud gushing risk probability distribution based on the parallel coupling architecture of multiple neural network models, and automatically filters out or marks the high-risk perception data according to the threshold, which can accurately identify the karst water and mud gushing risk of the soluble rock stratum tunnel and carry out real-time early warning.
Need to check novelty before this filing date? Find Prior Art