CN-121978771-A - Modeling method, device, equipment and medium for mine

CN121978771ACN 121978771 ACN121978771 ACN 121978771ACN-121978771-A

Abstract

The invention relates to the technical field of geological exploration and discloses a modeling method, device, equipment and medium of a mine, wherein the method comprises the steps of obtaining terrain data of a goaf; the method comprises the steps of constructing a fault model based on topographic data by utilizing an interpolation method, constructing a thin-layer ore strip model based on topographic data by utilizing the spectral characteristics of thin-layer ore strips, fusing the fault model and the thin-layer ore strip model, and determining a mine model corresponding to a goaf. According to the scheme, a fault model is constructed by using topographic data and an interpolation method to form a fault constraint surface, and the thin-layer ore strip model is constructed by using the spectral characteristics of the thin-layer ore strip to enhance the boundary recognition accuracy of the thin-layer ore strip, so that the fault spatial distribution and the thin-layer ore strip distribution rule are recognized on the basis, the traditional manual interaction modeling is replaced, and the self-adaptive three-dimensional grid model is constructed.

Inventors

HE MINGQIAN
YANG DAOGUANG
LI SHUO
CAI XIANYAN

Assignees

攀钢集团攀枝花钢铁研究院有限公司

Dates

Publication Date: 20260505
Application Date: 20251225

Claims (10)

1. A method of modeling a mine, the method comprising: acquiring terrain data of a goaf; constructing a fault model by utilizing an interpolation method based on the topographic data; Based on the topographic data, constructing a thin layer ore strip model by utilizing the spectral characteristics of the thin layer ore strip; and fusing the fault model and the thin-layer mine strip model to determine a mine model corresponding to the goaf.
2. The method of claim 1, wherein constructing a fault model based on the terrain data using interpolation comprises: determining fault attribute data of the goaf based on the terrain data; Inputting the fault attribute data into a trained graph convolution network to determine a fault position; determining a rock stratum interface by an interpolation method based on the fault position; and constructing a fault model based on the rock stratum interface and the topographic data.
3. The method according to claim 2, characterized in that the method further comprises: Calculating deformation weight of the fault to surrounding rock formations by using the radial basis function; And adjusting the fault model based on the deformation weight.
4. The method of claim 1, wherein constructing a thin layer strip model using spectral characteristics of thin layer strips based on the topographical data comprises: Based on the topographic data, identifying a sensitive area of the thin layer ore strip by utilizing the spectrum-geometric characteristic of the thin layer ore strip; Based on the sensitive area, a thin layer ore strip model is constructed by utilizing a trained convolutional neural network.
5. The method of claim 1, wherein the fusing the fault model with the thin layer mine strip model to determine a mine model corresponding to the goaf comprises performing model topology fault detection on a fault region corresponding to the fault model and a thin layer region corresponding to the thin layer mine strip model using an unstructured tetrahedral network to determine a mine model corresponding to the goaf.
6. The method of claim 1, wherein the acquiring terrain data for the goaf comprises: inputting the collected multi-source data into a three-dimensional modeling system, and constructing an initial point cloud model by combining historical mining data corresponding to the goaf; and unifying a data coordinate system of the initial point cloud model.
7. The method according to claim 1, characterized in that the method further comprises: obtaining exploitation actual measurement data; And comparing the measured data with the measured data by using analysis of variance, and adjusting a mine model.
8. An apparatus for automated driving edge scene data generation, the apparatus comprising: The acquisition module is used for acquiring the topographic data of the goaf; the fault model construction module is used for constructing a fault model by utilizing an interpolation method based on the topographic data; The thin-layer ore strip model construction module is used for constructing a thin-layer ore strip model by utilizing the spectral characteristics of the thin-layer ore strip based on the topographic data; And the determining module is used for fusing the fault model and the thin-layer mine strip model and determining a mine model corresponding to the goaf.
9. A computer device, comprising: A memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, perform the method of modeling generation of a mine of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of modeling a mine of any of claims 1 to 7.

Description

Modeling method, device, equipment and medium for mine Technical Field The invention relates to the technical field of geological exploration, in particular to a modeling method, device, equipment and medium for mines. Background With the rapid rise and development of the economy of modern informationized construction entities in China, the country has clearly proposed a digital mine development strategy. The development strategy of the mine is proposed to more comprehensively understand the actual mine, and the related phenomena and structural characteristics of the mine are reproduced by utilizing a computer technology, so that the development strategy of the mine is an important foundation for the construction of a digital mining area. The defects in the traditional mine industry are improved by utilizing information science and technology and a three-dimensional visual platform, so that the method has become important research content of mine science and technology and is also a problem to be solved in the development of the coal mine industry. In the related technology, the traditional mine modeling relies on manual interaction interpretation, and has the problems of low efficiency, strong subjectivity and the like, especially for a layered volcanic mine, the complex relation of faults to stratum cutting is difficult to manually and accurately describe, so that the deviation of a model and an actual geological structure is large, the resolution ratio of a millimeter-to-centimeter-level thin-layer mine strip is insufficient, the support of refined resource assessment is difficult, multi-source heterogeneous geological data (such as drilling, geophysical prospecting and remote sensing) are difficult to efficiently fuse, and the coupling relation of the thin-layer mine strip (the thickness is less than 1 m) and the complex fault structure is difficult to accurately express, so that the accuracy of a constructed mine model is low. Disclosure of Invention In view of the above, the invention provides a modeling method, a device, equipment and a medium for mines, which are used for solving the technical problem of low accuracy of constructed mine models. The invention provides a modeling method of a mine, which comprises the steps of obtaining topographic data of a goaf, constructing a fault model by utilizing an interpolation method based on the topographic data, constructing a thin layer mine strip model by utilizing spectral characteristics of thin layer mine strips based on the topographic data, fusing the fault model and the thin layer mine strip model, and determining the mine model corresponding to the goaf. With reference to the first aspect, in a possible implementation manner of the first aspect, constructing a fault model by interpolation based on the topographic data includes determining fault attribute data of the goaf based on the topographic data, inputting the fault attribute data into a trained graph packing network, determining a fault position, determining a rock stratum interface based on the fault position by interpolation, and constructing the fault model based on the rock stratum interface and the topographic data. With reference to the first aspect, in a possible implementation manner of the first aspect, the method further includes calculating deformation weights of the fault to surrounding rock formations using the radial basis function, and adjusting the fault model based on the deformation weights. With reference to the first aspect, in a possible implementation manner of the first aspect, the thin-layer ore strip model is constructed by utilizing spectral characteristics of the thin-layer ore strip based on the topographic data, and the thin-layer ore strip model is constructed by utilizing spectral-geometrical characteristics of the thin-layer ore strip based on the topographic data, and utilizing a trained convolutional neural network based on the sensitive area. With reference to the first aspect, in one possible implementation manner of the first aspect, the merging of the fault model and the thin layer mine strip model to determine the mine model corresponding to the goaf includes adopting an unstructured tetrahedral network to perform model topology error checking on a fault region corresponding to the fault model and a thin layer region corresponding to the thin layer mine strip model to determine the mine model corresponding to the goaf. With reference to the first aspect, in one possible implementation manner of the first aspect, acquiring the terrain data of the goaf includes inputting the acquired multi-source data into a three-dimensional modeling system, combining historical mining data corresponding to the goaf to construct an initial point cloud model, and unifying a data coordinate system of the initial point cloud model. With reference to the first aspect, in a possible implementation manner of the first aspect, the method further includes acquiring actual measure