白云岩砂化特征超前动态评价方法

By employing a combined missile-electric technology and an intelligent classification model, the challenge of advanced dynamic evaluation of dolomite sandification characteristics was solved, enabling advanced prevention and control during tunnel construction and improving construction safety and stability.

CN120779494BActive Publication Date: 2026-07-17CHANGJIANG RIVER SCI RES INST CHANGJIANG WATER RESOURCES COMMISSION

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHANGJIANG RIVER SCI RES INST CHANGJIANG WATER RESOURCES COMMISSION
Filing Date
2025-06-13
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies make it difficult to accurately determine the distribution range of dolomite sandification and the groundwater occurrence environment, which makes it difficult to guarantee the stability of the surrounding rock during tunnel construction, and frequently leads to geological disasters such as deformation, instability and sand inrush.

Method used

Using a method based on indoor experiments and geophysical exploration, dynamic and electrical parameters of dolomite are extracted through a combined missile-electric technology. Combined with radial basis function neural networks and autoencoder models, a dynamic evaluation and intelligent classification method for the sandification degree of dolomite is constructed to achieve advanced prevention and control during tunnel construction.

Benefits of technology

It improved the advanced detection capability for the construction of dolomite sandification tunnels, reduced construction risks, and ensured the safety and stability of tunnel construction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120779494B_ABST
    Figure CN120779494B_ABST
Patent Text Reader

Abstract

一种白云岩砂化特征超前动态评价方法,包括:基于室内试验确定白云岩砂化程度分级的细观与宏观阈值作为岩石试验静参数;基于弹‑电联合的地球物理超前探测提取白云岩岩体的动力学参数和电性参数作为超前探测动参数;将岩石试验静参数与超前探测动参数进行主成分分析和相关性分析,利用RBFNN构建白云岩砂化动‑静参数定量化转换模型;以岩石试验静参数为输入,砂化程度等级为输出,训练智能分级评价模型;将超前探测动参数经定量化转换模型映射为岩石试验静参数,将映射的岩石试验静参数输入智能分级评价模型进行验证与迭代优化,输出砂化程度分级结果。本发明可实现对隧道施工掌子面前方白云岩砂化超前的防控,避免砂化涌砂崩塌地灾发生。
Need to check novelty before this filing date? Find Prior Art