Mine modeling method, device, equipment and medium
By constructing a fusion model of faults and thin-layer ore strands, and using graph convolutional networks and convolutional neural networks to identify mine features, the problem of low model accuracy in traditional mine modeling methods is solved, achieving efficient and accurate mine modeling and improving the accuracy of resource assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PANZHIHUA IRON & STEEL RES INST OF PANGANG GROUP
- Filing Date
- 2025-12-25
- Publication Date
- 2026-05-05
AI Technical Summary
Traditional mine modeling methods are inefficient and highly subjective, making it difficult to accurately depict the fault relationships in layered volcanic rock mines. This results in low model accuracy, difficulty in efficiently integrating multi-source heterogeneous geological data, and difficulty in accurately expressing the coupling relationship between thin-layered ore strands and complex faults, thus affecting resource assessment and model accuracy.
By acquiring topographic data of the goaf, a fault model is constructed using interpolation. A thin ore strip model is constructed by combining the spectral characteristics of the thin ore strip and then fused together. Graph convolutional networks and convolutional neural networks are used to identify the locations of faults and ore strips. Unstructured tetrahedral networks are used to check the model topology and construct an adaptive three-dimensional mesh model.
It improves the accuracy of mine models, enhances the precision of thin-layer ore boundary identification, and realizes the automatic identification of fault spatial distribution and thin-layer ore distribution patterns, replacing traditional manual interactive modeling and improving the model's refinement and accuracy.
Smart Images
Figure CN121978771A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of geological exploration technology, specifically to a method, apparatus, equipment, and medium for modeling mines. Background Technology
[0002] With the rapid rise and development of my country's modern information technology-driven real economy, the country has clearly put forward the digital mine development strategy. The purpose of this strategy is to gain a more comprehensive understanding of real-world mines and to reproduce relevant phenomena and structural characteristics using computer technology, which is a crucial foundation for the construction of digital mining areas. Utilizing information science and technology and 3D visualization platforms to improve the shortcomings of the traditional mining industry has become an important research area in mining science and technology, and a problem urgently needing to be solved in the development of the coal mining industry.
[0003] In related technologies, traditional mine modeling relies on manual interactive interpretation, which has problems such as low efficiency and strong subjectivity. Especially for layered volcanic rock mines, the complex relationship of fault cutting through strata is difficult to accurately depict manually, resulting in large deviations between the model and the actual geological structure. The resolution for thin layered mineral strips at the millimeter to centimeter level is insufficient, making it difficult to support refined resource assessment. Furthermore, multi-source heterogeneous geological data (such as borehole, geophysical exploration, and remote sensing) are difficult to integrate efficiently, and the coupling relationship between thin layered mineral strips (thickness <1m) and complex fault structures is difficult to accurately express, resulting in low accuracy of the constructed mine model. Summary of the Invention
[0004] In view of this, the present invention provides a method, apparatus, equipment, and medium for modeling mines to solve the technical problem of low accuracy in the constructed mine models.
[0005] In a first aspect, the present invention provides a method for modeling a mine, the method comprising: acquiring topographic data of a goaf; constructing a fault model based on the topographic data using an interpolation method; constructing a thin-layer ore strip model based on the topographic data using the spectral characteristics of thin-layer ore strips; and fusing the fault model and the thin-layer ore strip model to determine a mine model corresponding to the goaf.
[0006] In conjunction with the first aspect, in one possible implementation of the first aspect, a fault model is constructed based on topographic data using an interpolation method, including: determining fault attribute data of the goaf based on topographic data; inputting the fault attribute data into a trained graph convolutional network to determine the fault location; determining the rock strata interface based on the fault location using an interpolation method; and constructing a fault model based on the rock strata interface and topographic data.
[0007] In conjunction with the first aspect, in one possible implementation of the first aspect, the method further includes: using radial basis functions to calculate the deformation weight of the fault on the surrounding rock strata; and adjusting the fault model based on the deformation weight.
[0008] In conjunction with the first aspect, in one possible implementation of the first aspect, a thin-layer ore model is constructed based on topographic data and utilizing the spectral characteristics of the thin-layer ore, including: identifying sensitive areas of the ore based on topographic data and utilizing the spectral-geometric characteristics of the thin-layer ore; and constructing a thin-layer ore model based on the sensitive areas using a trained convolutional neural network.
[0009] In conjunction with the first aspect, in one possible implementation of the first aspect, the fault model and the thin ore strip model are fused to determine the mine model corresponding to the goaf, including: using an unstructured tetrahedral network to perform topology error checking on the fault region corresponding to the fault model and the thin ore strip region corresponding to the thin ore strip model to determine the mine model corresponding to the goaf.
[0010] In conjunction with the first aspect, in one possible implementation of the first aspect, the topographic data of the goaf area is obtained, including: inputting the collected multi-source data into a three-dimensional modeling system, combining it with historical mining data corresponding to the goaf area, and constructing an initial point cloud model; and unifying the data coordinate system of the initial point cloud model.
[0011] In conjunction with the first aspect, one possible implementation of the first aspect includes: acquiring actual mining data; and using variance analysis to compare the actual data with the mining data and adjust the mine model.
[0012] Secondly, the present invention provides a mine modeling device, the device comprising: an acquisition module for acquiring topographic data of a goaf; a fault model construction module for constructing a fault model based on the topographic data using an interpolation method; a thin ore strip model construction module for constructing a thin ore strip model based on the topographic data using the spectral characteristics of the thin ore strip; and a determination module for fusing the fault model and the thin ore strip model to determine the mine model corresponding to the goaf.
[0013] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the mine modeling method of the first aspect or any corresponding embodiment described above.
[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the mine modeling method of the first aspect or any corresponding embodiment thereof.
[0015] The technical solution of this invention has the following advantages: This invention provides a method, apparatus, equipment, and medium for modeling mines. The method involves acquiring topographic data of a goaf; constructing a fault model based on the topographic data using interpolation; constructing a thin-layer ore vein model based on the spectral characteristics of the thin-layer ore veins; and fusing the fault model and the thin-layer ore vein model to determine the mine model corresponding to the goaf. In this process, the fault model is constructed using topographic data and interpolation to form fault constraint surfaces. Furthermore, by utilizing the spectral characteristics of the thin-layer ore veins to construct a thin-layer ore vein model, the accuracy of thin-layer ore vein boundary identification is enhanced. Based on this, the spatial distribution of faults and the distribution patterns of thin-layer ore veins are identified, replacing traditional manual interactive modeling, constructing an adaptive 3D mesh model, and improving the accuracy of the constructed mine model. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating a mine modeling method according to an embodiment of the present invention; Figure 2 This is a structural block diagram of a mine modeling device provided according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0019] According to an embodiment of the present invention, a method for modeling a mine is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0020] This embodiment provides a method for modeling a mine, such as... Figure 1As shown, the method includes the following steps: S101. Obtain topographic data of the mined-out area.
[0021] S102. Based on terrain data, a fault model is constructed using interpolation.
[0022] S103. Based on topographic data, construct a thin-layer ore model using the spectral characteristics of thin-layer ore.
[0023] S104. Merge the fault model and the thin-layer ore strip model to determine the mine model corresponding to the goaf.
[0024] This invention provides a method, apparatus, equipment, and medium for modeling mines. The method involves acquiring topographic data of a goaf; constructing a fault model based on the topographic data using interpolation; constructing a thin-layer ore vein model based on the spectral characteristics of the thin-layer ore veins; and fusing the fault model and the thin-layer ore vein model to determine the mine model corresponding to the goaf. In this process, the fault model is constructed using topographic data and interpolation to form fault constraint surfaces. Furthermore, by utilizing the spectral characteristics of the thin-layer ore veins to construct a thin-layer ore vein model, the accuracy of thin-layer ore vein boundary identification is enhanced. Based on this, the spatial distribution of faults and the distribution patterns of thin-layer ore veins are identified, replacing traditional manual interactive modeling, constructing an adaptive 3D mesh model, and improving the accuracy of the constructed mine model.
[0025] In one alternative implementation, a fault model is constructed based on terrain data using an interpolation method, including: Based on topographic data, fault attribute data of the goaf is determined; the fault attribute data is input into a trained graph convolutional network to determine the fault location; based on the fault location, the rock strata interface is determined using interpolation; based on the rock strata interface and topographic data, a fault model is constructed.
[0026] Specifically, fault attribute data includes: fault coordinates, inflection point coordinates, extension depth, profile morphology, borehole number (i.e., stratigraphic information), strike, dip, etc.
[0027] Specifically, inputting fault attribute data into a trained graph convolutional network to determine fault location means that after the fault attributes, such as fault coordinates, inflection point coordinates, extension depth, profile shape, borehole number (i.e., stratigraphic information), strike, and dip, are presented in three dimensions in the software, the graph convolutional network (GCN) is applied to predict the location of unmarked faults.
[0028] Specifically, determining the rock strata interface based on the fault location and using interpolation means using the fault as the boundary and employing the Kriging interpolation method to supplement the rock mass data on both sides of the fault to clarify the rock strata interface.
[0029] Specifically, constructing a fault model based on rock interface and topographic data refers to generating fault constraint surfaces based on borehole displacement anomalies and seismic profile data.
[0030] In this process, a three-dimensional point cloud database was established, a fault topology analysis framework was built, the spatial distribution of faults was extracted, and the fault slip distance compensation relationship was introduced to dynamically correct the connection relationship of mineral strips on both sides of the fault and quantify the impact of fault displacement on the continuity of rock strata.
[0031] In one alternative implementation, the method further includes: Using radial basis functions, the deformation weight of the fault on the surrounding rock strata is calculated; based on the deformation weight, the fault model is adjusted.
[0032] Specifically, after determining the fault constraint surface, the radial basis function (RBF) is used to calculate the deformation weight of the fault on the surrounding rock strata, thereby dynamically adjusting the curvature of the stratigraphic interface with the calculated deformation weight to achieve iterative updating of the fault constraint surface.
[0033] In one alternative implementation, a thin-layer ore model is constructed based on topographic data and utilizing the spectral characteristics of the thin-layer ore, including: Based on topographic data, sensitive areas of thin-layer ore strips are identified by utilizing their spectral-geometric properties. Based on these sensitive areas, a thin-layer ore strip model is constructed using a trained convolutional neural network.
[0034] Specifically, since ore strips below the minimum mineable thickness are usually discontinuous and easily confused with interbedded rocks, which is detrimental to resource calculation and mining, it is necessary to manually identify thin ore strips in each borehole profile. In this process, sensitive areas of the ore strips are identified through spectral-geometric joint features.
[0035] Specifically, constructing a thin-layer ore strip model based on sensitive areas and utilizing a trained convolutional neural network refers to increasing the voxel resolution to 0.1m × 0.1m × 0.05m in the ore strip region. Thin-layer ore strip extraction is achieved by segmenting core images and geophysical data using a U-Net network. The software inputs attributes such as the borehole number traversed by the ore strip (i.e., stratigraphic information), thickness, morphology, strike, dip, and surrounding rock type, and labels the spatial location of the thin-layer ore strip. A convolutional neural network (CNN) is then used to train the thin-layer ore body feature classification, thus completing the construction of the thin-layer ore strip model.
[0036] In this process, a multi-scale convolutional network is used to distinguish between ore strands and surrounding rock, enhancing the boundary identification accuracy of thin-layer ore strands (0.2-1m thick), correcting the thin-layer interpolation algorithm, and increasing the thickness stability of ore strands in sparse borehole areas, thereby achieving automatic delineation of thin-layer (<1m) ore bodies.
[0037] In one optional implementation, the fault model and the thin ore strip model are fused to determine the mine model corresponding to the goaf, including: using an unstructured tetrahedral network to perform topology checking on the fault region corresponding to the fault model and the thin ore strip region corresponding to the thin ore strip model to determine the mine model corresponding to the goaf.
[0038] Specifically, the fault model and the thin-layer ore strip model are fused through an implicit surface algorithm, and adaptive mesh generation is performed. In this process, an unstructured tetrahedral mesh is used to refine the mesh to sub-meter resolution in the fault and thin-layer regions. The model topology is checked and logically corrected in conjunction with the goaf area.
[0039] In this process, by integrating geological exploration data (drilling, geophysical exploration, UAV oblique photography, etc.) with historical mining data, and using machine learning algorithms such as random forest algorithms, the spatial distribution of faults and the distribution patterns of thin mineral strips are automatically identified, thereby replacing traditional manual interactive modeling and constructing an adaptive three-dimensional mesh model, that is, a mine model corresponding to the goaf.
[0040] In one optional implementation, acquiring topographic data of the goaf includes: The collected multi-source data is input into the 3D modeling system and combined with the historical mining data corresponding to the goaf area to construct an initial point cloud model; the data coordinate system of the initial point cloud model is unified.
[0041] Specifically, the multi-source data includes: high-precision DEM generated by UAV oblique photogrammetry, borehole core data, geophysical inversion data, and geophysical exploration data. The MapGIS mine management and 3D modeling software is used to input borehole core attributes (including borehole coordinates, length, number of runs, stratification information, lithology, grade, and sample information), geophysical inversion data, geophysical exploration data, and historical mining data to construct an initial point cloud model for the database. An interpolation algorithm is then used to enhance the data richness.
[0042] Specifically, the data coordinate system of the unified initial point cloud model is represented by the following formula: , ,
[0043] in, X ` i Representing the unified x Axis coordinates X i Indicates the original mine x Axis coordinates Y ` i Representing the unified y Axis coordinates Yi Indicates the original mine y Axis coordinates H ` i This represents the unified coordinate elevation. H i This indicates the original mine's coordinates and elevation. a , b , c , d , e, f These represent the corresponding average simplified transformation coefficients.
[0044] In one alternative implementation, the method further includes: Obtain actual mining data; use analysis of variance to compare with the actual data and adjust the mine model.
[0045] Specifically, by acquiring actual mining data and comparing it with the actual mining data using Kriging variance analysis, the model is validated and optimized by cross-validating the reserves of industrial blocks. This verifies the accuracy of the virtual exploration data synthesized by Kriging interpolation, fills in data-sparse areas, and achieves iterative optimization of the model by continuously adjusting the interpolation parameters.
[0046] This embodiment also provides a mine modeling device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0047] This embodiment provides a mine modeling device, such as... Figure 2 As shown, it includes: The response module 201 is used for... For details, please refer to the description of step S101 in the above embodiments, which will not be repeated here.
[0048] The sending module 202 is used for... For details, please refer to the description of step S102 in the above embodiments, which will not be repeated here.
[0049] The receiving module 203 is used for... For details, please refer to the description of step S103 in the above embodiments, which will not be repeated here.
[0050] The generation module 204 is used for... For details, please refer to the description of step S104 in the above embodiments, which will not be repeated here.
[0051] The prompt module 205 is used for... For details, please refer to the description of step S105 in the above embodiments, which will not be repeated here.
[0052] In this embodiment, the mine modeling device is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.
[0053] This invention also provides a computer device having the above-described features. Figure 2 The modeling device for the mine shown.
[0054] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 3 As shown, the computer device includes one or more processors 301, memory 302, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 3 Take processor 301 as an example.
[0055] Processor 301 may be a central processing unit, a network processor, or a combination thereof. Processor 301 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.
[0056] The memory 302 stores instructions executable by at least one processor 301 to cause the at least one processor 301 to perform the method shown in the above embodiments.
[0057] Memory 302 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, memory 302 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 302 may optionally include memory remotely located relative to processor 301, and this remote memory may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0058] The memory 302 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 302 may also include combinations of the above types of memory. The computer device also includes a communication interface 303 for communicating with other devices or communication networks.
[0059] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.
[0060] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for modeling a mine, characterized in that, The method includes: Obtain topographic data of the mined-out area; Based on the terrain data, a fault model is constructed using interpolation. Based on the topographic data, a thin-layer mineral strip model is constructed using the spectral characteristics of the thin-layer mineral strips; The fault model and the thin-layer ore strip model are fused to determine the mine model corresponding to the goaf.
2. The method according to claim 1, characterized in that, The construction of a fault model based on the terrain data using interpolation includes: Based on the terrain data, the fault attribute data of the goaf area are determined; The fault attribute data is input into a trained graph convolutional network to determine the fault location. Based on the fault location, the rock strata interface is determined using interpolation. A fault model is constructed based on the rock strata interface and the topographic data.
3. The method according to claim 2, characterized in that, The method further includes: Using radial basis functions, the deformation weight of the fault on the surrounding rock strata is calculated; The fault model is adjusted based on the deformation weights.
4. The method according to claim 1, characterized in that, The process of constructing a thin-layer mineral strip model based on the topographic data and utilizing the spectral characteristics of the thin-layer mineral strip includes: Based on the topographic data, sensitive areas of the ore layer are identified by utilizing the spectral-geometric properties of the thin ore layer. Based on the sensitive region, a thin-layer ore bar model is constructed using a trained convolutional neural network.
5. The method according to claim 1, characterized in that, The step of fusing the fault model and the thin-layer ore strip model to determine the mine model corresponding to the goaf includes: using an unstructured tetrahedral network to perform topology checking on the fault region corresponding to the fault model and the thin-layer region corresponding to the thin-layer ore strip model to determine the mine model corresponding to the goaf.
6. The method according to claim 1, characterized in that, The acquisition of terrain data of the goaf includes: The collected multi-source data is input into the 3D modeling system and combined with historical mining data corresponding to the goaf area to construct an initial point cloud model; Unify the data coordinate system of the initial point cloud model.
7. The method according to claim 1, characterized in that, The method further includes: Obtain actual mining measurement data; The mine model was adjusted by comparing it with the measured data using analysis of variance.
8. A device for generating edge scene data for autonomous driving, characterized in that, The device includes: The acquisition module is used to acquire terrain data of the mined-out area; The fault model construction module is used to construct a fault model based on the terrain data using an interpolation method. The thin-layer mineral strip model construction module is used to construct a thin-layer mineral strip model based on the topographic data and utilizing the spectral characteristics of the thin-layer mineral strip. The determination module is used to fuse the fault model and the thin-layer ore strip model to determine the mine model corresponding to the goaf.
9. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method for modeling and generating the mine according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method of modeling a mine according to any one of claims 1 to 7.