Three-dimensional visualization reconstruction method for overlying rock mass structure on deep coal mine working face

By combining the mining drilling imager and convolutional neural network system, the three-dimensional geological model is reconstructed using improved Kriging spatial interpolation technology, the problems of insufficient data acquisition accuracy and low model construction efficiency in the rooftop modeling of deep coal mine work faces are solved, and the precise visualization of the rock-covered structure of deep coal mine work faces is achieved, and the safety and efficiency of coal mine mining are improved.

CN119942017AActive Publication Date: 2025-05-06EAST CHINA JIAOTONG UNIVERSITY
4 Cites 5 Cited by

Patent Information

Application Number
CN202510429674.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-08
Publication Date
2025-05-06
Estimated Expiration
2045-04-08

AI Technical Summary

Technical Problem

The prior art has problems such as insufficient data acquisition accuracy, low model construction efficiency and poor adaptability to complex structural areas in the three-dimensional geological structure modeling of the roof of the deep coal mine working face, resulting in significant safety hazards in mining design and roof management.

Method used

By combining the mine drilling imager and convolutional neural network system, the rock formation characteristics of the coal mine working face roof plate are accurately identified and extracted, and the three-dimensional geological model is reconstructed using improved Kriging spatial interpolation technology to achieve accurate visualization of the rock-covered structure of the deep coal mine working face.

Benefits of technology

It improves the safety and efficiency of coal mining, reduces the occurrence of roof accidents and gas accidents, and provides scientific guidance for optimizing drilling construction plans and ensuring safe mining.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a three-dimensional visualization reconstruction method for an overlying rock mass structure on a deep coal mine working face, which comprises the following steps of: 1) arranging a drill hole of a mining drill hole imager on the working face, and collecting and storing basic geological data of an overlying rock layer; 2) outputting a drilling image by the mining drilling imager; 3) based on the constructed convolutional neural network, key geologic features of the borehole image are extracted for classification and identification, and rock stratum, fracture and fault information is obtained; (4) vertical virtual drill holes are transversely and simultaneously formed along the working face of the deep coal mine, stratums are divided, and a three-dimensional geologic model is constructed by using an improved Kriging spatial interpolation method and relying on three-dimensional visualization software; and 5) introducing gas concentration and stress distribution data of the monitoring area of the working face of the deep coal mine, and realizing three-dimensional visualization of the overlying rock mass structure and the risk area on the working face of the deep coal mine through multi-modal data fusion. According to the method, accurate visualization of the overlying rock mass structure of the working face of the deep coal mine can be achieved, and comprehensive geological data support is provided for underground operation.
Need to check novelty before this filing date? Find Prior Art