CN-122024053-A - Rock brittle fracture prediction method, apparatus, device and readable storage medium

CN122024053ACN 122024053 ACN122024053 ACN 122024053ACN-122024053-A

Abstract

The application relates to the technical field of geological monitoring, and discloses a rock brittle fracture prediction method, a rock brittle fracture prediction device, rock brittle fracture prediction equipment and a readable storage medium. The method comprises the steps of monitoring target rock, collecting surface images of the target rock, determining displacement field data of surface feature points of the target rock based on the surface images, determining displacement aggregation strength based on the displacement field data, extracting the target surface feature points from the surface images based on the displacement field data, determining displacement field trend quantization indexes based on the target surface feature points and the displacement aggregation strength, and predicting whether brittle failure of the target rock occurs based on the displacement field trend quantization indexes. By observing the displacement of the surface feature points of the rock, the displacement field trend quantization index is constructed for predicting the brittle failure of the rock, and the accuracy of the brittle failure prediction of the rock can be remarkably improved.

Inventors

WANG JIANCHAO
HE FEI
XU QIANG
CHEN GUOQING
Jiang Houhao
TAN LINYUN
HAN SHIDONG
ZHANG YIHAI
WANG XIBAO
CHEN XI

Assignees

成都理工大学

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A method of rock brittle failure prediction, the method comprising: monitoring a target rock, collecting a surface image of the target rock, and determining displacement field data of surface feature points of the target rock based on the surface image; Determining a displacement aggregation intensity based on the displacement field data, and extracting target surface feature points from the surface image based on the displacement field data; Determining a displacement field trend quantization index based on the target surface feature points and the displacement aggregation strength; based on the displacement field trend quantization index, predicting whether brittle failure of the target rock occurs.
2. The method of claim 1, wherein the step of determining displacement field data for surface feature points of the target rock based on the surface image comprises: Determining the displacement variation of the surface feature points of the target rock based on the surface image; and generating displacement field data of the surface feature points of the target rock based on the displacement variation.
3. The method of claim 1, wherein the step of determining a displacement aggregate strength based on the displacement field data comprises: constructing a target covariance matrix based on the displacement field data; And determining the displacement aggregation strength based on the target covariance matrix.
4. The method of claim 1, wherein the step of extracting target surface feature points from the surface image based on the displacement field data comprises: Based on the displacement field data, counting the displacement value of each surface characteristic point in the surface image and a target surface characteristic point cluster, wherein the target surface characteristic point cluster is a point cluster formed by surface characteristic points with the displacement value larger than a first displacement threshold value; Calculating a target proportion based on the number of the target surface characteristic point clusters; A target surface feature point is extracted from the surface image based on the displacement value of each surface feature point and the target scale.
5. The method of claim 1, wherein the step of determining a displacement field trend quantization index based on the target surface feature points and the displacement aggregate intensity comprises: Determining a target surface feature point set centroid based on the target surface feature points; Acquiring a predicted critical time point and a displacement field characteristic scale of the displacement field data; And determining a displacement field trend quantization index based on the target surface feature point set centroid, the prediction critical time point, the displacement field feature scale and the displacement aggregation strength.
6. The method of claim 1, wherein the surface images are acquired in real time over time, each of the surface images corresponding to one of the displacement field trend quantization indices, the step of predicting whether the target rock is subject to brittle failure based on the displacement field trend quantization indices comprising: generating a displacement field trend quantization index change curve based on the displacement field trend quantization index corresponding to each surface image; calculating a second derivative of the displacement field trend quantization index change curve, and comparing the second derivative with a preset threshold; If the second derivative is smaller than a preset threshold value, predicting that brittle fracture of the target rock occurs; and if the second derivative is not smaller than a preset threshold value, predicting that brittle fracture of the target rock does not occur.
7. The method for predicting brittle failure of rock according to claim 6, characterized in that the method further comprises: If the target rock is predicted to be subjected to brittle fracture, carrying out dangerous warning; And if the target rock is predicted not to be subjected to brittle fracture, continuously monitoring the target rock.
8. A rock brittle fracture prediction means, characterized in that the rock brittle fracture prediction means comprises: The acquisition module is used for monitoring the target rock, acquiring a surface image of the target rock and determining displacement field data of surface feature points of the target rock based on the surface image; An extraction module for determining a displacement aggregation strength based on the displacement field data and extracting a target surface feature point from the surface image based on the displacement field data; The determining module is used for determining a displacement field trend quantization index based on the target surface feature points and the displacement aggregation strength; and the prediction module is used for predicting whether the brittle failure of the target rock occurs based on the displacement field trend quantization index.
9. A computer device, characterized in that it comprises a processor and a memory, the memory storing a computer program, the processor being adapted to execute the computer program to implement the rock brittle fracture prediction method according to any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when run on a processor, performs the rock brittle fracture prediction method according to any of claims 1-7.

Description

Rock brittle fracture prediction method, apparatus, device and readable storage medium Technical Field The application relates to the technical field of geological monitoring, in particular to a rock brittle fracture prediction method, a rock brittle fracture prediction device, rock brittle fracture prediction equipment and a readable storage medium. Background Rock brittleness is an inherent property exhibited by rock when broken by stress, and as existing cracks in the rock expand and new cracks are generated, the stress in the rock is continuously redistributed, and high-intensity stress is rapidly and far propagated, so that the rock is broken by brittleness. Hard rock is used as a rock type frequently encountered in underground engineering, the brittle failure of the rock is monitored in real time in the field of underground engineering, and the hard rock plays a key role in the stability evaluation of surrounding rock of the underground engineering and has very wide application. However, the current brittle failure monitoring technology of rock is often limited by the configuration of monitoring points, especially in the vicinity of the recently excavated tunnel working surface, the rapid setting of the monitoring points is challenging, and the technology still has limitation in the aspect of underground engineering rock fracture disaster early warning. Therefore, the existing monitoring technology cannot completely show the damage state in the rock, and the brittle fracture of the rock is difficult to accurately predict. Disclosure of Invention In view of the above, an object of the present application is to overcome the shortcomings in the prior art, and to provide a method for predicting brittle failure of rock, the method comprising: monitoring a target rock, collecting a surface image of the target rock, and determining displacement field data of surface feature points of the target rock based on the surface image; Determining a displacement aggregation intensity based on the displacement field data, and extracting target surface feature points from the surface image based on the displacement field data; Determining a displacement field trend quantization index based on the target surface feature points and the displacement aggregation strength; based on the displacement field trend quantization index, predicting whether brittle failure of the target rock occurs. In an embodiment, the step of determining displacement field data of surface feature points of the target rock based on the surface image comprises: Determining the displacement variation of the surface feature points of the target rock based on the surface image; and generating displacement field data of the surface feature points of the target rock based on the displacement variation. In an embodiment, the step of determining the displacement aggregation strength based on the displacement field data comprises: constructing a target covariance matrix based on the displacement field data; And determining the displacement aggregation strength based on the target covariance matrix. In an embodiment, the step of extracting target surface feature points from the surface image based on the displacement field data comprises: Based on the displacement field data, counting the displacement value of each surface characteristic point in the surface image and a target surface characteristic point cluster, wherein the target surface characteristic point cluster is a point cluster formed by surface characteristic points with the displacement value larger than a first displacement threshold value; Calculating a target proportion based on the number of the target surface characteristic point clusters; A target surface feature point is extracted from the surface image based on the displacement value of each surface feature point and the target scale. In one embodiment, the step of determining a displacement field trend quantization index based on the target surface feature point and the displacement collection intensity includes: Determining a target surface feature point set centroid based on the target surface feature points; Acquiring a predicted critical time point and a displacement field characteristic scale of the displacement field data; And determining a displacement field trend quantization index based on the target surface feature point set centroid, the prediction critical time point, the displacement field feature scale and the displacement aggregation strength. In one embodiment, the surface images are acquired in real time over time, each of the surface images corresponds to one of the displacement field trend quantization indices, and the step of predicting whether brittle failure of the target rock occurs based on the displacement field trend quantization indices comprises: generating a displacement field trend quantization index change curve based on the displacement field trend quantization index corresponding to each surface image; c