A method and device for generating opening information of a rock mass structural plane and a storage medium

Abstract

The application provides a rock mass structure surface opening degree information generation method, device and storage medium, and relates to the rock mass exploration technical field.The rock mass structure surface opening degree information generation method comprises the following steps: obtaining point cloud information of a rock mass structure surface; determining a reference surface according to point cloud coordinates; generating a combined elevation corresponding to each preset sub-region based on the reference surface and the point cloud coordinates, to obtain a combined elevation matrix; dividing the combined elevation matrix into at least four sub-matrices, and arranging the maximum combined elevation in each sub-matrix in descending order to form a combined elevation sequence; selecting the third combined elevation in the combined elevation sequence as a reference elevation, and obtaining opening degree information based on the reference elevation, the combined elevation matrix and an analysis strategy.The size of the combined elevation can reflect the distribution trend of the opening degree, the third combined elevation as the reference elevation represents at least three-point contact of the rock mass, and the reliability and accuracy of the opening degree information are ensured, so that the opening degree information can be quickly obtained without registration of the point cloud.

Description

Technical Field

[0001] This invention relates to the field of rock mass exploration technology, and more specifically, to a method, apparatus, and storage medium for generating rock mass structural plane opening information. Background Technology

[0002] The opening of the structural planes of a rock mass is generally used to describe the degree of opening of joints and fissures in the rock mass. Since the rock masses are not in complete contact, the area of ​​the contact surface is generally smaller than the area of ​​the non-contact surface. Fissures will form in the non-contact areas of the rock mass. The size of the fissures is generally expressed by the opening of the structural planes of the rock mass. The opening of the structural planes of a rock mass is closely related to the permeability characteristics of the rock mass and has important applications in the exploration and acquisition of geological and mineral resources.

[0003] Traditional methods for measuring the opening of rock mass structural planes require water injection into the rock mass, indirectly estimating the opening through seepage. This process is complex and has low accuracy. With the continuous development of laser scanning technology, methods for calculating the opening by acquiring point cloud data of rock mass structural planes using scanning equipment have emerged. Compared to traditional methods, this is more convenient and significantly improves accuracy. However, in existing technologies, the point cloud data of the two structural planes constituting rock mass fractures must be acquired separately. After acquisition, precise registration of the point clouds of the two structural planes is required; otherwise, accurate opening information cannot be obtained. This consumes enormous computing power, resulting in low efficiency in generating opening information. Summary of the Invention

[0004] The problem addressed by this invention is how to improve the generation efficiency of rock mass structural surface opening information.

[0005] To address the above problems, this invention provides a method for generating rock mass structural plane aperture information, comprising the following steps:

[0006] Obtain point cloud information of rock mass structural surfaces, wherein the point cloud information includes the hanging wall point cloud, the footwall point cloud, and point cloud coordinates;

[0007] A reference plane is determined based on the point cloud coordinates. The reference plane includes a first reference plane and a second reference plane, wherein the upper disk point cloud and the lower disk point cloud are located between the first reference plane and the second reference plane.

[0008] Based on the reference plane and the point cloud coordinates, a combined elevation corresponding to each preset sub-region is generated to obtain a combined elevation matrix. The combined elevation includes the first elevation of the upper plate point cloud in the sub-region to the first reference plane, and the second elevation of the lower plate point cloud in the sub-region to the second reference plane.

[0009] The combined elevation matrix is ​​divided into at least four sub-matrices, and the largest combined elevation in each sub-matrix is ​​arranged in descending order to form a combined elevation sequence.

[0010] The third combined elevation in the combined elevation sequence is selected as the reference elevation, and the opening information of the rock mass structural surface is obtained based on the reference elevation, the combined elevation matrix and the preset analysis strategy. The analysis strategy includes setting the opening value of the sub-region corresponding to the combined elevation that is less than or equal to the reference elevation to zero.

[0011] Optionally, the point cloud coordinates include upper disk point cloud coordinates and lower disk point cloud coordinates; determining the reference plane based on the point cloud coordinates includes:

[0012] Obtain the maximum coordinate value of the upper disk point cloud coordinates in the vertical direction, and use it as the first target value;

[0013] Obtain the minimum coordinate value of the lower disk point cloud coordinates in the vertical direction, and use it as the second target value;

[0014] The first reference plane and the second reference plane are determined based on the first target value and the second target value, respectively, wherein the coordinate value of any point on the first reference plane in the vertical direction is equal to the first target value, and the coordinate value of any point on the second reference plane in the vertical direction is equal to the second target value.

[0015] Optionally, before generating the combined elevation corresponding to each preset sub-region based on the reference plane and the point cloud coordinates to obtain the combined elevation matrix, the method further includes:

[0016] Based on a preset partitioning strategy, the regions where the upper disk point cloud and the lower disk point cloud are located are divided into grids to obtain a first grid set and a second grid set with the same row and column dimensions. The partitioning strategy includes using an orthogonal partitioning method for grid partitioning.

[0017] The row and column values ​​corresponding to each first grid and each second grid in the first grid set and the second grid set are obtained respectively, and multiple sub-regions are determined based on the row and column values, wherein the row and column values ​​corresponding to the first grid and the second grid in each sub-region are the same.

[0018] Optionally, the step of generating a combined elevation matrix for each preset sub-region based on the reference surface and the point cloud coordinates includes:

[0019] Based on the point cloud coordinates, the first grid coordinates corresponding to the first grid and the second grid coordinates corresponding to the second grid are obtained;

[0020] Based on the vertical distance from the first grid coordinates to the first reference plane, the first elevation corresponding to each sub-region is obtained;

[0021] Based on the vertical distance from the second grid coordinates to the second reference plane, the second elevation corresponding to each sub-region is obtained;

[0022] The first elevation and the second elevation corresponding to each sub-region are merged to obtain multiple combined elevations, which constitute the combined elevation matrix.

[0023] Optionally, obtaining the first grid coordinates corresponding to the first grid and the second grid coordinates corresponding to the second grid based on the point cloud coordinates includes:

[0024] The coordinates of the first grid are determined based on the first number of upper disk point clouds falling into each of the first grids and the coordinates of the upper disk point clouds;

[0025] Wherein, when the first quantity is equal to 1, the coordinates of the upper disk point cloud corresponding to the upper disk point cloud are used as the first grid coordinates;

[0026] When the first quantity is greater than 1, the average value of the coordinates of the multiple upper disk point clouds corresponding to the multiple upper disk point clouds in the first grid is taken as the coordinates of the first grid.

[0027] When the first quantity is less than 1, the coordinates of the first grid are obtained according to the coordinates of the upper disk point cloud corresponding to the upper disk point cloud within a preset range around the first grid.

[0028] The coordinates of the second grid are determined based on the second number of lower disk point clouds falling into each second grid and the coordinates of the lower disk point clouds.

[0029] Optionally, after dividing the combined elevation matrix into at least four sub-matrices and arranging the largest combined elevation in each sub-matrix in descending order to form a combined elevation sequence, the method further includes:

[0030] Obtain the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence;

[0031] Determine whether the location distribution of the three sub-regions meets a preset distribution condition, wherein the distribution condition includes that the distance between any two sub-regions is greater than a preset distance threshold;

[0032] If not, then subtract the preset number from the current number of submatrices to obtain the target number, wherein the target number is greater than or equal to four;

[0033] The combined elevation matrix is ​​divided into the target number of sub-matrices, and the step of obtaining the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence is returned until the distribution condition is met.

[0034] Optionally, after selecting the third combined elevation in the combined elevation sequence as the reference elevation, and obtaining the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix, and a preset analysis strategy, the method further includes:

[0035] The positions of the upper plate point cloud and the lower plate point cloud are adjusted according to a preset position adjustment rule, and the point cloud information is updated. The position adjustment rule includes shifting the upper plate point cloud horizontally by a preset distance.

[0036] Based on the updated point cloud information, virtual opening information corresponding to the rock mass structural surface after the position adjustment is obtained, including obtaining the virtual opening information according to the position adjustment rules and the opening information.

[0037] Optionally, after obtaining the virtual aperture information corresponding to the rock mass structural surface after adjustment based on the updated point cloud information, the method further includes:

[0038] Based on the updated point cloud information, image information of the rock mass structure surface is generated, and the virtual aperture information and the corresponding image information are associated to obtain a set of training data, wherein the image information includes three-dimensional image information;

[0039] Returning to the steps of adjusting the positions of the upper plate point cloud and the lower plate point cloud according to the preset position adjustment rules and updating the point cloud information, multiple sets of training data are obtained to form a training dataset;

[0040] The pre-built initial evaluation model is trained based on the training dataset to obtain the evaluation model;

[0041] The target image information corresponding to the target rock mass structural surface is input into the evaluation model to obtain the target opening information corresponding to the target rock mass structural surface.

[0042] This invention accurately reflects the morphology of rock mass structural surfaces by acquiring the upper and lower hanging wall point clouds and their corresponding point cloud coordinates, providing a reliable data foundation for subsequently generating the opening information of the rock mass structural surfaces. Based on the point cloud coordinates, a first and second reference plane are determined, placing the upper and lower hanging wall point clouds between the first and second reference planes, providing a reference plane for subsequently obtaining the elevation of the point clouds. Based on the reference planes and point cloud coordinates, a combined elevation is generated for each sub-region. The combined elevation includes the first elevation of the upper hanging wall point cloud to the first reference plane and the second elevation of the lower hanging wall point cloud to the second reference plane within the sub-region. The magnitude of the combined elevation reflects the relative positional relationship between the upper and lower hanging wall point clouds; that is, the larger the combined elevation, the closer the upper and lower hanging wall point clouds are, and vice versa. This allows the resulting combined elevation matrix to reflect the relative distribution trend of rock mass structural surface apertures, eliminating the need for registration of the hanging wall and footwall point clouds. This saves computational power and improves processing efficiency. Dividing the combined elevation matrix into at least four sub-matrices and arranging the largest combined elevations within each sub-matrix in descending order forms a combined elevation sequence. This allows us to determine the distribution of the closest positions between the hanging wall and footwall structural surfaces within each sub-matrix, i.e., the locations where the rock mass structural surface aperture value is most likely to be zero. This provides a reliable reference for generating subsequent rock mass structural surface aperture information. For two structural surfaces, to maintain a relatively stable positional relationship, there must be at least three contact points or contact areas between them. In this invention, the sub-regions corresponding to the first three combined elevations in the combined elevation sequence represent the areas where the hanging wall and footwall structural surfaces should actually be in contact. Theoretically, the actual aperture value corresponding to the first three combined elevations in the combined elevation sequence should be zero to ensure the relative stability of the rock mass structure. Therefore, by selecting the third combined elevation in the combined elevation sequence as the reference elevation, the opening information of the rock mass structural plane can be quickly obtained based on the reference elevation, the combined elevation matrix, and the preset analysis strategy. The sub-region corresponding to the combined elevation lower than the reference elevation should be the contact area of ​​the structural plane, and the corresponding opening value should be zero. This embodiment eliminates the need for complex registration operations between the hanging wall and footwall point clouds. It can quickly and reliably estimate the true opening of the rock mass structural plane based on the combined elevation of the point cloud relative to the reference plane, thus improving the efficiency of opening information generation.

[0043] The present invention also provides a device for generating rock mass structural plane aperture information, comprising:

[0044] The acquisition module is used to acquire point cloud information of rock mass structural surfaces, including the hanging wall point cloud, the footwall point cloud, and point cloud coordinates.

[0045] A first processing module is used to determine a reference plane based on the point cloud coordinates. The reference plane includes a first reference plane and a second reference plane, wherein the upper disk point cloud and the lower disk point cloud are located between the first reference plane and the second reference plane.

[0046] The second processing module is used to generate a combined elevation corresponding to each preset sub-region based on the reference plane and the point cloud coordinates, to obtain a combined elevation matrix, wherein the combined elevation includes the first elevation of the upper plate point cloud in the sub-region to the first reference plane, and the second elevation of the lower plate point cloud in the sub-region to the second reference plane.

[0047] A partitioning module is used to divide the combined elevation matrix into at least four sub-matrices and arrange the largest combined elevation in each sub-matrix in descending order to form a combined elevation sequence.

[0048] The generation module is used to select the third combined elevation in the combined elevation sequence as the reference elevation, and obtain the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix and the preset analysis strategy. The analysis strategy includes setting the opening value of the sub-region corresponding to the combined elevation that is less than or equal to the reference elevation to zero.

[0049] The device for generating rock mass structural surface opening information provided by this invention has essentially the same advantages as the method for generating rock mass structural surface opening information compared to the prior art, and will not be elaborated further here.

[0050] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for generating rock mass structural surface aperture information as described above.

[0051] The advantages of the computer-readable storage medium and the method for generating the rock mass structural surface opening information provided by this invention are basically the same as those of the prior art, and will not be repeated here. Attached Figure Description

[0052] Figure 1 This is a flowchart of a method for generating rock mass structural surface aperture information according to an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of the lower disk point cloud according to an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of the structure of a certain section in the rock mass structure according to an embodiment of the present invention;

[0055] Figure 4 This is a schematic diagram of mesh division according to an embodiment of the present invention. Detailed Implementation

[0056] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0057] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0058] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0059] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0060] In the attached diagram, the Z-axis represents the vertical direction, i.e., up and down, with the positive direction of the Z-axis (where the arrow points) indicating up and the negative direction indicating down. The X-axis represents the horizontal direction, designated as left and right, with the positive direction of the X-axis (where the arrow points) indicating right and the negative direction indicating left. The Y-axis represents the front and back direction, with the positive direction of the Y-axis (where the arrow points) indicating front and the negative direction indicating back. It should be noted that the aforementioned representations of the Z, Y, and X axes are merely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation; therefore, they should not be construed as limitations on the invention.

[0061] like Figure 1As shown, the present invention provides a method for generating rock mass structural plane aperture information, comprising the following steps:

[0062] S1: Obtain point cloud information of rock mass structural surfaces. The point cloud information includes the hanging wall point cloud, footwall point cloud, and point cloud coordinates.

[0063] Specifically, the hanging wall point cloud and footwall point cloud referred to in this invention are not absolute vertical positions. Rock mass structural surfaces (such as fissures) typically contain two relatively distributed structural surfaces. In this embodiment, the relatively convex structural surface is defined as the hanging wall structural surface, and the corresponding point cloud is the hanging wall point cloud; the relatively concave structural surface is defined as the footwall structural surface, and the corresponding point cloud is the footwall point cloud. A schematic diagram of the footwall point cloud is shown below. Figure 2 As shown.

[0064] It should be understood that when the horizontal plane is used as a reference (i.e., the plane formed by the X and Y axes), the orientation of two relatively distributed structural planes in the rock mass may be parallel to the horizontal plane or at a certain angle. For ease of understanding and description, in this embodiment, after obtaining the upper and lower hanging wall point clouds, the overall orientation of the upper and lower hanging wall point clouds can be adjusted using processing software such as AutoCAD, for example, by rotating them as a whole by a certain angle so that the overall orientation is basically parallel to the horizontal plane. The point cloud data obtained by equipment such as 3D laser scanning contains the 3D coordinate information corresponding to each point cloud, based on which the point cloud coordinates (x, y, z) corresponding to each point cloud can be determined.

[0065] In this embodiment, obtaining the disk cloud and lower disk cloud and their corresponding point cloud coordinates on the rock mass structural surface can accurately reflect the morphology of the rock mass structural surface, providing an accurate and reliable data foundation for the subsequent generation of the opening information of the rock mass structural surface.

[0066] S2: Determine the reference plane based on the point cloud coordinates. The reference plane includes a first reference plane and a second reference plane, wherein the upper plate point cloud and the lower plate point cloud are located between the first reference plane and the second reference plane.

[0067] Specifically, the reference plane in this invention is set according to the point cloud coordinates and is parallel to the horizontal plane. Since the trends of the two structural planes corresponding to the upper and lower plate point clouds in this embodiment are basically parallel to the horizontal plane, the regions where the upper and lower plate point clouds are located can be surrounded by the first and second reference planes parallel to the horizontal plane. The reference plane can be represented in the point cloud using four calibration points. For example, the maximum value of the z-axis coordinate corresponding to the upper plate point cloud is obtained as the target value, and the first reference plane is defined using four vertices A, B, C, and D, where the z-axis coordinates of the four vertices A, B, C, and D are greater than or equal to the target value.

[0068] In this embodiment, a first reference plane and a second reference plane are determined based on the point cloud coordinates, so that the upper and lower point clouds are located between the first and second reference planes, providing a reference for obtaining the elevation of the point cloud in the future.

[0069] S3: Generate the combined elevation corresponding to each preset sub-region based on the datum plane and point cloud coordinates to obtain the combined elevation matrix. The combined elevation includes the first elevation of the upper plate point cloud in the sub-region to the first datum plane, and the second elevation of the lower plate point cloud in the sub-region to the second datum plane.

[0070] Specifically, in this embodiment, each preset sub-region includes both a portion of the upper plate point cloud and a portion of the lower plate point cloud. The region between the first and second reference planes can be divided equidistantly to obtain multiple sub-regions. For example, the region between the first and second reference planes can be divided into M sub-regions along the X-axis and N sub-regions along the Y-axis, resulting in M*N sub-regions. Based on the point cloud coordinates of the upper plate point cloud within each sub-region, the first elevation of the upper plate point cloud to the first reference plane can be obtained. For example, if the point cloud coordinates of the upper plate point cloud within the sub-region are (0, 2, 5), and the first reference plane corresponds to a horizontal plane with a z-axis coordinate value of 20, then the first elevation of the upper plate point cloud is 15. Similarly, the second elevation of the lower plate point cloud within the sub-region to the second reference plane can be obtained. The combined elevation includes a first elevation and a second elevation. The first elevation reflects the vertical distance of the upper plate cloud to the first datum plane within the sub-region, while the second elevation reflects the vertical distance of the lower plate cloud to the second datum plane within the sub-region. Since both the upper and lower plate clouds are located between the first and second datum planes, a larger combined elevation indicates that the distance between the upper and lower plate clouds is closer, i.e., a smaller aperture. After obtaining the combined elevation, the combined elevation matrix can be obtained based on the position of the corresponding sub-region. For example, if the combined elevation is denoted as H, the sub-region in the second row and third column (i.e., the second sub-region in the X-axis direction and the third sub-region in the Y-axis direction) can be denoted as H0. 23 Based on this, the location of each sub-region corresponding to the combined elevation and the corresponding elevation value can be associated, thereby obtaining the combined elevation matrix.

[0071] It should be understood that, since no registration operation was performed on the upper and lower plate point clouds when generating the combined elevation of each sub-region in this embodiment, the resulting combined elevation matrix can reflect the relative distribution trend of the rock mass structural surface opening.

[0072] Optionally, the point cloud can be preprocessed before calculating the first and second elevations, such as by point cloud trimming and point cloud coordinate simplification. Since 3D laser scanning and other equipment often collect point cloud information from other irrelevant areas when acquiring the structural surfaces of the hanging wall and footwall of a rock mass, this data can be trimmed to simplify the point cloud data and reduce wasted computing power. Simultaneously, the point cloud coordinates can also be simplified, further reducing data processing difficulty and saving computing power. Taking the simplification method of the hanging wall point cloud as an example, the minimum value of the X-axis coordinate in the hanging wall point cloud is denoted as x. min The minimum value of the Y-axis coordinate is denoted as y. min The simplified target point cloud coordinates satisfy:

[0073] x i ′=x i -x min ;

[0074] y i ′=y i -y min ;

[0075] z i ′=z i ;

[0076] Among them, (x i y i , z i (x) represents the point cloud coordinates before simplification. i ′,y i ′,z i ′) represents the simplified target point cloud coordinates.

[0077] In this embodiment, a combined elevation corresponding to each sub-region is generated based on the reference plane and point cloud coordinates. The combined elevation includes the first elevation of the upper plate point cloud to the first reference plane and the second elevation of the lower plate point cloud to the second reference plane within the sub-region. The magnitude of the combined elevation reflects the relative positional relationship between the upper plate point cloud and the lower plate point cloud. That is, the larger the combined elevation, the closer the upper plate point cloud and the lower plate point cloud are, and vice versa. This allows the obtained combined elevation matrix to reflect the relative distribution trend of the rock mass structural surface opening in general. The relative distribution of the rock mass structural surface opening can be grasped without registering the upper plate point cloud and the lower plate point cloud, which is beneficial to saving computing power and improving processing efficiency.

[0078] S4: Divide the combined elevation matrix into at least four submatrices, and sort the largest combined elevations in each submatrix in descending order to form a combined elevation sequence.

[0079] Specifically, each combined elevation represents the relative distance between the hanging wall and footwall point clouds within a sub-region. The combined elevation matrix is ​​divided into at least four sub-matrices, each representing a partial distribution trend of the rock mass structural plane aperture. The largest combined elevation within each sub-matrice indicates the location with the smallest aperture within that region, which is the area where the hanging wall and footwall structural planes are most likely to contact.

[0080] In this embodiment, the combined elevation matrix is ​​divided into at least four sub-matrices. Each sub-matrix represents the distribution trend of a portion of the rock mass structural surface aperture. The combined elevations in each sub-matrix are arranged in descending order to form a combined elevation sequence. This allows us to understand the distribution of the closest locations between the hanging wall and footwall structural surfaces within the region corresponding to each sub-matrix, which is the distribution of locations where the rock mass structural surface aperture value is most likely to be zero. This provides a reliable reference for the subsequent generation of rock mass structural surface aperture information.

[0081] S5: Select the third combined elevation in the combined elevation sequence as the reference elevation, and obtain the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix and the preset analysis strategy. The analysis strategy includes setting the opening value of the sub-region corresponding to the combined elevation that is less than or equal to the reference elevation to zero.

[0082] Specifically, for rock mass structural planes, the contact area between the hanging wall and footwall structural planes is usually smaller than the non-contact area. For two structural planes to maintain a relatively stable positional relationship, at least three contact points or contact areas are required between them. Based on this, the sub-regions corresponding to the first three combined elevations in the combined elevation sequence represent the areas that should actually be in contact. That is, the actual aperture value corresponding to the sub-regions corresponding to the first three combined elevations should be 0. Since the combined elevation sequence is arranged in descending order, the third combined elevation among the first three determines the critical state between contact and non-contact. Using this as the reference elevation represents the minimum combined elevation required for the hanging wall and footwall structural planes to contact each other, the aperture information of the rock mass structural planes can be obtained without registration.

[0083] In one embodiment, such as Figure 3As shown in the figure, this is a slice of the rock mass structural plane. F1 represents the first reference plane, F2 represents the second reference plane, J1 represents the hanging wall structural plane containing the hanging wall point cloud, and J2 represents the footwall structural plane containing the footwall point cloud. The cross-section line represents the opening between the hanging wall and footwall structural planes. U1 represents the first elevation corresponding to a sub-region in this slice, D1 represents the second elevation corresponding to that sub-region in this slice, and A1 represents the simulated opening corresponding to that sub-region in this slice. It can be seen from the figure that the larger the sum of the first and second elevations (i.e., the combined elevation), the smaller the structural plane opening; conversely, the smaller the combined elevation, the larger the structural plane opening. When the combined elevation (i.e., the reference elevation) corresponding to a structural plane opening value of 0 is determined, there is no need to register the hanging wall and footwall point clouds. The simulated opening A1 can be corrected to obtain a more accurate and reliable opening value, quickly generating the structural plane opening corresponding to each sub-region, facilitating a comprehensive understanding of the opening information of the rock mass structural planes. For example, in a combined elevation matrix, combined elevations greater than the reference elevation represent the non-contact areas between the hanging wall and footwall structural surfaces. Subtracting the reference elevation from the combined elevation yields a relatively accurate opening value. Combined elevations less than or equal to the reference elevation represent the contact areas between the hanging wall and footwall structural surfaces, corresponding to an opening value of 0. This embodiment eliminates the need for complex registration operations, enabling rapid and reliable estimation of the rock mass structural surface opening based on the combined elevations of the point cloud relative to the reference surface, thus improving the efficiency of opening information generation.

[0084] In this embodiment, acquiring the hanging wall point cloud and footwall point cloud and their corresponding point cloud coordinates on the rock mass structural surface can accurately reflect the morphology of the rock mass structural surface, providing an accurate and reliable data foundation for subsequently generating the opening information of the rock mass structural surface. A first reference plane and a second reference plane are determined based on the point cloud coordinates, placing the hanging wall point cloud and footwall point cloud between the first and second reference planes, providing a reference for subsequently acquiring the elevation of the point clouds. Based on the reference planes and point cloud coordinates, a combined elevation is generated for each sub-region. The combined elevation includes the first elevation of the hanging wall point cloud to the first reference plane and the second elevation of the footwall point cloud to the second reference plane within the sub-region. The magnitude of the combined elevation reflects the relative positional relationship between the hanging wall point cloud and the footwall point cloud; that is, the larger the combined elevation, the closer the hanging wall point cloud and the footwall point cloud are, and vice versa. This allows the resulting combined elevation matrix to reflect the relative distribution trend of rock mass structural surface apertures, eliminating the need for registration between the hanging wall and footwall point clouds, thus saving computational resources and improving processing efficiency. Dividing the combined elevation matrix into at least four sub-matrices and arranging the largest combined elevations within each sub-matrix in descending order to form a combined elevation sequence reveals the distribution of the closest positions between the hanging wall and footwall structural surfaces within each sub-matrix's corresponding region—that is, the distribution of the locations where the rock mass structural surface aperture value is most likely to be zero. This provides a reliable reference for subsequently generating rock mass structural surface aperture information. For two structural surfaces to maintain a relatively stable positional relationship, there must be at least three contact points or contact areas between them. Therefore, the sub-regions corresponding to the first three combined elevations in the combined elevation sequence represent the areas where the hanging wall and footwall structural surfaces should actually be in contact; that is, the actual aperture value corresponding to the sub-regions corresponding to the first three combined elevations in the combined elevation sequence should be zero. Therefore, by selecting the third combined elevation in the combined elevation sequence as the reference elevation, the opening information of the rock mass structural surfaces can be quickly obtained based on the reference elevation, the combined elevation matrix, and the preset analysis strategy. The sub-region corresponding to a combined elevation lower than the reference elevation should be the contact area of ​​the structural surfaces, and the corresponding opening value should be zero. Conversely, the sub-region corresponding to a combined elevation higher than the reference elevation should be the non-contact area of ​​the structural surfaces, and the corresponding opening value is the difference between the combined elevation and the reference elevation. This embodiment eliminates the need for complex registration operations between the hanging wall and footwall point clouds. Based on the combined elevation of the point clouds relative to the reference surface, the true opening of the rock mass structural surfaces can be estimated quickly and reliably, which is beneficial for improving the efficiency of opening information generation.

[0085] Optionally, the point cloud coordinates include the upper disk point cloud coordinates and the lower disk point cloud coordinates; determining the reference plane based on the point cloud coordinates includes:

[0086] Obtain the maximum coordinate value of the upper disk point cloud coordinates in the vertical direction, and use it as the first target value;

[0087] Obtain the minimum coordinate value of the lower disk point cloud coordinates in the vertical direction, and use it as the second target value;

[0088] The first reference plane and the second reference plane are determined based on the first target value and the second target value, respectively, wherein the coordinate value of any point on the first reference plane in the vertical direction is equal to the first target value, and the coordinate value of any point on the second reference plane in the vertical direction is equal to the second target value.

[0089] Specifically, the area between the first and second reference planes covers the regions containing the upper and lower plate point clouds. To reduce the computational cost of the first and second elevations, in principle, the first and second reference planes should be as close to the point clouds as possible, provided that the upper and lower plate point clouds are located between them. The maximum vertical coordinate value (i.e., the maximum Z-axis coordinate value) of the upper plate point cloud is obtained as the first target value. The first reference plane is determined based on this first target value. The vertical coordinate value of any point on the first reference plane is equal to the first target value. For example, if the first target value is 15, then the first reference plane is the horizontal plane with Z = 15. Similarly, the second reference plane can be determined.

[0090] In this embodiment, the coordinate value of any point on the first reference plane in the vertical direction is equal to the first target value, and the coordinate value of any point on the second reference plane in the vertical direction is equal to the second target value. While ensuring that the area between the first and second reference planes covers the area where the upper and lower point clouds are located, the distance between the reference planes and the point clouds is shortened, which helps to reduce the computing power consumption of the first and second elevations and further improve efficiency.

[0091] Optionally, before generating the combined elevation corresponding to each preset sub-region based on the datum plane and point cloud coordinates to obtain the combined elevation matrix, the following steps are also included:

[0092] Based on a preset partitioning strategy, the regions where the upper and lower point clouds are located are divided into grids to obtain a first grid set and a second grid set with the same row and column dimensions.

[0093] Obtain the row and column values ​​corresponding to each first grid and each second grid in the first grid set and the second grid set respectively, and determine multiple sub-regions based on the row and column values, wherein the row and column values ​​corresponding to the first grid and the second grid in each sub-region are the same.

[0094] Specifically, in this embodiment, the regions where the upper and lower plate point clouds are located can be determined by the point cloud coordinates corresponding to the upper and lower plate point clouds. Taking the region where the upper plate point cloud is located as an example, the maximum and minimum values ​​of the X-axis, Y-axis, and Z-axis coordinates corresponding to the upper plate point cloud are obtained respectively, denoted as X. min X max Ymin Y max Z min Z max Based on the aforementioned coordinate values, a cuboid space can be constructed, ensuring that all upper plate point clouds are located within this cuboid space, which is the region where the upper plate point clouds are located. Similarly, the region where the lower plate point clouds are located is obtained. Preferably, to facilitate the subsequent generation of the first and second elevations, the cuboid spaces corresponding to the regions of the upper and lower plate point clouds are of the same size and shape, and are positioned vertically opposite each other along the Z-axis. Based on this, a preset partitioning strategy is used to mesh the regions where the upper and lower plate point clouds are located, resulting in a first mesh set and a second mesh set with the same row and column dimensions. For example, the first mesh set consists of M*N first meshes, and the second mesh set consists of M*N second meshes. In this embodiment, the partitioning strategy refers to a meshing method, including hexahedral partitioning, unstructured meshing, and orthogonal partitioning, etc.; preferably, such as... Figure 4 As shown in the figure, the orthogonal partitioning method is used to divide the region in this embodiment. The white grid area in the figure is a first grid or a second grid. Using orthogonal partitioning helps to ensure that the positions of the first grid and the second grid with the same row and column values ​​correspond accurately.

[0095] In one embodiment, the size of each grid can be determined based on the size of the region where the point cloud is located and the density of the point cloud. Simultaneously, it should be ensured that each grid contains at least one point cloud instance. Taking the grid division of the region containing the above point cloud as an example, the first grid set can be represented as:

[0096] K(m,n)=find(mΔ <x<(m+1)Δ,nΔ<y<(n+1)Δ);

[0097] Where K(m,n) represents the first grid set, Δ represents the size of each grid, m represents the row dimension value corresponding to the first grid, n represents the column dimension value corresponding to the first grid, and (x,y) represents the X-axis and Y-axis coordinates of the upper disk point cloud. Therefore, based on the X-axis and Y-axis coordinates of the upper disk point cloud, the grid in which each upper disk point cloud is located and the corresponding row and column dimensions can be determined.

[0098] In this embodiment, the regions containing the upper and lower disk point clouds are divided into grids to obtain a first grid set and a second grid set with the same row and column dimensions. This is beneficial to improving the efficiency of merging the first and second elevations into a combined elevation and ensuring the accuracy of the combined elevation. The row and column values ​​corresponding to each first grid and each second grid in the first and second grid sets are obtained respectively, and multiple sub-regions are determined based on the row and column values. The row and column values ​​corresponding to the first and second grids in each sub-region are the same, which helps to avoid misalignment when generating the combined elevation, resulting in a large error in the estimation of the opening value.

[0099] Optionally, based on the datum plane and point cloud coordinates, a combined elevation corresponding to each preset sub-region is generated to obtain a combined elevation matrix, including:

[0100] Based on the point cloud coordinates, obtain the first grid coordinates corresponding to the first grid and the second grid coordinates corresponding to the second grid;

[0101] Based on the vertical distance from the first grid coordinates to the first reference plane, the first elevation corresponding to each sub-region is obtained;

[0102] Based on the vertical distance from the second grid coordinates to the second reference plane, the second elevation corresponding to each sub-region is obtained;

[0103] The first and second elevations corresponding to each sub-region are merged to obtain multiple combined elevations, which form a combined elevation matrix.

[0104] Specifically, after gridding, each grid may contain one or more point clouds. Since the point clouds within each grid are relatively close, their coordinates can be simplified into a single grid coordinate. This significantly reduces the amount of data without affecting the distribution of the structural surface opening, thus saving computational resources. The first elevation for each region is obtained based on the vertical distance from the first grid coordinate to the first reference plane (i.e., the difference between the Z-axis coordinate corresponding to the first grid coordinate and the Z-coordinate value corresponding to the first reference plane). Similarly, the second elevation is obtained. The first and second elevations are then merged to obtain multiple combined elevations, forming a combined elevation matrix. For example, by associating the obtained first and second elevations with row and column dimensions, we obtain the first elevation matrix U and the second elevation matrix D.

[0105]

[0106] Where mn represents the row and column values ​​of the first or second elevation.

[0107] By adding the first and second elevation matrices according to the equal values ​​of rows and columns, the combined elevation matrix can be obtained:

[0108]

[0109] In this embodiment, the first grid coordinates corresponding to the first grid and the second grid coordinates corresponding to the second grid are obtained based on the point cloud coordinates. Multiple point cloud coordinates within a grid are simplified into a single grid coordinate, significantly reducing the data volume without affecting the structural surface opening distribution, thus saving computational resources. Based on this, the first and second elevations can be obtained separately using the vertical distance from the grid coordinates to the reference plane. Since the row and column values ​​of each first and second grid are obtained when dividing the sub-regions, the first and second elevations within the same sub-region can be quickly matched based on these values, thereby improving the efficiency and accuracy of generating combined elevations.

[0110] Optionally, the coordinates of the first grid corresponding to the first grid and the coordinates of the second grid corresponding to the second grid are obtained from the point cloud coordinates, including:

[0111] The coordinates of the first grid are determined based on the first number of points in the upper disk that fall into each first grid and the coordinates of the upper disk points.

[0112] When the first quantity is equal to 1, the coordinates of the upper plate point cloud corresponding to the upper plate point cloud are used as the coordinates of the first grid.

[0113] When the first quantity is greater than 1, the average value of the coordinates of the multiple upper disk point clouds corresponding to the multiple upper disk point clouds in the first grid is taken as the coordinates of the first grid.

[0114] When the first quantity is less than 1, the coordinates of the first grid are obtained according to the coordinates of the upper disk point cloud corresponding to the upper disk point cloud within a preset range around the first grid.

[0115] The coordinates of the second grid are determined based on the second number of lower disk point clouds falling into each second grid and the coordinates of the lower disk point clouds.

[0116] Specifically, after gridding, each grid may contain one or more point clouds, and some grids may not contain any point clouds. Based on this, the corresponding grid coordinates can be determined according to the number of point clouds in each grid. Taking the first grid as an example, when the first number of the corresponding upper plate point cloud in the first grid is 1, the coordinates of the first grid are the coordinates of the upper plate point cloud corresponding to that upper plate point cloud; when the first number of the corresponding upper plate point cloud in the first grid is greater than 1, the average of the coordinates of multiple upper plate point clouds is taken as the grid coordinate value.

[0117]

[0118] Among them, P (x,y,z) Represents the coordinate values ​​of the first grid, ∑R (xi,yi,zi) This represents the sum of the X, Y, and Z coordinate values ​​corresponding to each upper disk point cloud coordinate falling into the first grid, and N represents the first number of upper disk point clouds falling into the first grid.

[0119] When the first quantity is less than 1, that is, no point cloud coordinates fall in the first grid, the coordinates of the first grid can be obtained from the coordinates of the upper plate point cloud corresponding to the upper plate point cloud within a preset range around the first grid. For example, the coordinates of the upper plate point cloud corresponding to any upper plate point cloud within the preset range can be used as the coordinates of the first grid. Alternatively, the coordinates of the first grid can be obtained by interpolation based on the upper plate point cloud coordinates within the preset range.

[0120] In this embodiment, the grid coordinates are determined based on the number of point clouds falling into each grid and the point cloud coordinates, ensuring the rationality of the first grid coordinates and the second grid coordinates, which helps to improve the accuracy of the opening information.

[0121] Optionally, after dividing the combined elevation matrix into at least four sub-matrices and arranging the largest combined elevations within each sub-matrix in descending order to form a combined elevation sequence, the method further includes:

[0122] Obtain the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence;

[0123] Determine whether the location distribution of the three sub-regions meets the preset distribution conditions, wherein the distribution conditions include the distance between any two sub-regions being greater than a preset distance threshold;

[0124] If not, subtract the preset number from the current number of submatrices to obtain the target number, where the target number is greater than or equal to four;

[0125] Divide the combined elevation matrix into a target number of submatrices and return the steps to obtain the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence, until the distribution conditions are met.

[0126] Specifically, after dividing the combined elevation matrix into at least four sub-matrices and arranging the largest combined elevations within each sub-matrix in descending order, the distribution of the sub-regions corresponding to the first three combined elevations may not reflect reality. For example, dividing the combined elevation matrix into eight sub-matrices results in a relatively concentrated sub-regions corresponding to the first three combined elevations in the combined elevation sequence. While this ensures that at least three points of contact exist between two structural surfaces, it fails to guarantee the stability of the structural surfaces. Consequently, the resulting benchmark elevation is highly likely to be inaccurate and may lead to significant errors in the opening information. This embodiment ensures the rationality of the benchmark elevation by acquiring the three sub-regions corresponding to the first three combined elevations and determining whether their location distribution meets distribution conditions. Distribution conditions may include a distance between any two sub-regions that is greater than a preset distance threshold. The distance threshold can be determined based on the range of the point cloud region; for example, the distance threshold is greater than or equal to the difference between the largest and smallest X-axis coordinate values. The distribution conditions can include three sub-regions connected in pairs to form an enclosed area. The theoretical centroids of the upper and lower point clouds should be located within the enclosed area. The theoretical centroid can be the center point of the upper and lower point clouds.

[0127] In one embodiment, when the distribution of the three sub-regions does not meet the preset distribution conditions, it is necessary to reduce the number of sub-matrices and re-divide the combined elevation matrix until the three sub-regions obtained after re-division meet the distribution conditions. Theoretically, the more sub-matrices are divided, the closer the final rock mass structural surface opening will be to the actual rock mass structural surface opening. However, this requires repeatedly performing the above steps, which is not conducive to improving efficiency. Preferably, the combined elevation matrix is ​​divided into four sub-matrices on an average basis, so that the three sub-regions obtained can meet the distribution conditions, further improving processing efficiency.

[0128] In this embodiment, obtaining the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence and determining whether they meet the preset distribution conditions ensures that the three sub-regions are spatially mutually exclusive, preventing them from being too concentrated and resulting in poor accuracy of the benchmark elevation. If the conditions are not met, the number of sub-matrices is reduced, and the combined elevation matrix is ​​re-divided until the three sub-regions meet the distribution conditions, thus avoiding large errors in the final generated opening information.

[0129] Optionally, after selecting the third combined elevation in the combined elevation sequence as the reference elevation, and obtaining the opening information of the rock mass structural plane based on the reference elevation, the combined elevation matrix, and the preset analysis strategy, the method further includes:

[0130] The positions of the upper and lower point clouds are adjusted according to the preset position adjustment rules, and the point cloud information is updated. The position adjustment rules include shifting the upper point cloud horizontally by a preset distance.

[0131] Based on the updated point cloud information, the virtual aperture information corresponding to the rock mass structural surface after the position adjustment is obtained, including the virtual aperture information obtained according to the position adjustment rules and aperture information.

[0132] Specifically, after obtaining the opening information of the rock mass structural planes, the upper and lower hanging wall point clouds can be misaligned to simulate the opening conditions of other rock mass structural planes. In this embodiment, the position adjustment rules are not limited to translating or rotating the upper and / or lower hanging wall point clouds in one or more dimensions. For example, the positions of the upper and lower hanging wall point clouds can be adjusted according to preset adjustment rules (such as increasing the X-axis coordinate of the upper hanging wall point cloud by a preset value), and the corresponding point cloud information can be updated. Virtual opening information of the rock mass structural planes can be regenerated based on the updated point cloud information. Based on the original first elevation matrix, the row values ​​of each first elevation can be increased by 1, while the column values ​​remain unchanged, and this can be added to the original second elevation matrix. Missing elements in the matrix can be filled using interpolation, thereby enabling rapid acquisition of virtual opening information of rock mass structural planes under various simulation conditions. Simultaneously, the step of determining the reference surface based on the point cloud coordinates can be returned until the virtual opening information is obtained.

[0133] In this embodiment, after obtaining the opening information of the rock mass structural surface, the upper and lower disk point clouds can be misaligned, and their relative positions can be adjusted according to preset position adjustment rules to simulate various different rock mass structural surface conditions. Based on this, the virtual opening value corresponding to the rock mass structural surface after position adjustment can be quickly generated based on the opening information and adjustment rules, providing rich basic data.

[0134] Optionally, after obtaining the virtual aperture information corresponding to the adjusted rock mass structural surface based on the updated point cloud information, the method further includes:

[0135] Based on the updated point cloud information, image information of rock mass structural surfaces is generated, and virtual aperture information is associated with corresponding image information to obtain a set of training data, including three-dimensional image information.

[0136] Return to the steps of adjusting the positions of the upper and lower point clouds according to the preset position adjustment rules and updating the point cloud information to obtain multiple sets of training data, which constitute the training dataset;

[0137] The initial evaluation model is trained based on the training dataset to obtain the evaluation model;

[0138] The target image information corresponding to the target rock mass structural surface is input into the evaluation model to obtain the target opening information corresponding to the target rock mass structural surface.

[0139] Specifically, image information of the rock mass structure can be generated based on the updated point cloud information. For example, point cloud processing software such as 3ds Max can be used to generate a corresponding 3D model from the updated point cloud information, thereby obtaining 3D image information. The 3D image information is then correlated with the corresponding virtual aperture information to obtain a set of training data. Repeating the above steps yields multiple sets of different training data, thus constructing a training dataset. An initial evaluation model can be built based on the image information, such as a convolutional neural network or a ResNet residual network. The initial evaluation model is then trained using the training dataset to obtain the evaluation model. In practical applications, point cloud information of the target rock mass can be acquired using a 3D laser scanning device, converted into target image information, and input into the evaluation model to obtain the target aperture information corresponding to the target rock mass structure.

[0140] In this embodiment, after acquiring point cloud information corresponding to various simulated rock mass structural surfaces, it can be converted into image information and associated with the corresponding virtual aperture information to construct a training dataset. Based on this dataset, a pre-constructed initial evaluation model is trained to obtain the evaluation model. In practical applications, there is no need to perform complex processing on the point cloud of the target rock mass structural surface; the corresponding target aperture information can be estimated based on the image information corresponding to the target rock mass structural surface, which is beneficial to improving the efficiency of on-site handling in rock mass exploration.

[0141] Another embodiment of the present invention provides a device for generating rock mass structural plane aperture information, comprising:

[0142] The acquisition module is used to acquire point cloud information of rock mass structural surfaces. The point cloud information includes the hanging wall point cloud, the footwall point cloud, and point cloud coordinates.

[0143] The first processing module is used to determine the reference plane based on the point cloud coordinates. The reference plane includes a first reference plane and a second reference plane, wherein the upper plate point cloud and the lower plate point cloud are located between the first reference plane and the second reference plane.

[0144] The second processing module is used to generate the combined elevation corresponding to each preset sub-region based on the reference plane and point cloud coordinates, and obtain the combined elevation matrix. The combined elevation includes the first elevation of the upper plate point cloud in the sub-region to the first reference plane, and the second elevation of the lower plate point cloud in the sub-region to the second reference plane.

[0145] The partitioning module is used to divide the combined elevation matrix into at least four sub-matrices and sort the largest combined elevations in each sub-matrix in descending order to form a combined elevation sequence.

[0146] The generation module is used to select the third combined elevation in the combined elevation sequence as the reference elevation, and obtain the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix and the preset analysis strategy. The analysis strategy includes setting the opening value of the sub-region corresponding to the combined elevation that is less than or equal to the reference elevation to zero.

[0147] In this embodiment, the acquisition module accurately reflects the morphology of the rock mass structural surface by acquiring the upper and lower foot cloud points and their corresponding point cloud coordinates, providing an accurate and reliable data foundation for subsequently generating the opening information of the rock mass structural surface. The first processing module determines the first and second reference planes based on the point cloud coordinates, placing the upper and lower foot cloud points between the first and second reference planes, providing a reference for subsequently acquiring the elevation of the point clouds. The second processing module generates the combined elevation corresponding to each sub-region based on the reference planes and point cloud coordinates. The combined elevation includes the first elevation of the upper foot cloud to the first reference plane and the second elevation of the lower foot cloud to the second reference plane within the sub-region. The magnitude of the combined elevation reflects the relative positional relationship between the upper and lower foot cloud points; that is, the larger the combined elevation, the closer the upper and lower foot cloud points are. Conversely, the further away the points are, the more distant they are. This allows the resulting combined elevation matrix to reflect the relative distribution trend of the rock mass structural surface aperture. The relative distribution of the rock mass structural surface aperture can be grasped without registering the hanging wall and footwall point clouds, saving computing power and improving processing efficiency. The partitioning module divides the combined elevation matrix into at least four sub-matrices. The largest combined elevation in each sub-matrix is ​​arranged in descending order to form a combined elevation sequence. This allows us to grasp the distribution of the closest positions between the hanging wall and footwall structural surfaces within the region corresponding to each sub-matrix, i.e., the distribution of the positions where the rock mass structural surface aperture value is most likely to be zero. This provides a reliable reference for subsequent generation of rock mass structural surface aperture information. For two structural surfaces, to maintain a relatively stable positional relationship, there must be at least three contact points or contact areas between the two structural surfaces. Therefore, the sub-regions corresponding to the first three combined elevations in the combined elevation sequence represent the areas where the hanging wall and footwall structural surfaces should actually be in contact, i.e., the actual aperture value corresponding to the sub-regions corresponding to the first three combined elevations in the combined elevation sequence should be zero. Based on this, the generation module selects the third combined elevation in the combined elevation sequence as the reference elevation. It can then quickly obtain the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix, and the preset analysis strategy. The sub-region corresponding to the combined elevation less than the reference elevation should be the contact area of ​​the structural surface, and the corresponding opening value should be zero. In this embodiment, there is no need to perform complex registration operations on the upper and lower plate point clouds. Based on the combined elevation of the point cloud relative to the reference surface, the true opening of the rock mass structural surface can be estimated quickly and reliably, which is beneficial to improving the generation efficiency of opening information.

[0148] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for generating rock mass structural surface aperture information as described above.

[0149] The beneficial effects produced by the computer-readable storage medium provided in this embodiment are basically the same as those of the above-mentioned method for generating rock mass structural surface aperture information, and will not be repeated here.

[0150] The present invention will now describe electronic devices that can serve as servers or clients of the present invention, which are examples of hardware devices that can be applied to various aspects of the present invention. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0151] Electronic devices include a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM can also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0152] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0153] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware or as software functional units.

[0154] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for generating rock mass structural plane aperture information, characterized in that, Includes the following steps: Obtain point cloud information of rock mass structural surfaces, wherein the point cloud information includes the hanging wall point cloud, the footwall point cloud, and point cloud coordinates; A reference plane is determined based on the point cloud coordinates. The reference plane includes a first reference plane and a second reference plane, wherein the upper disk point cloud and the lower disk point cloud are located between the first reference plane and the second reference plane. Based on the reference plane and the point cloud coordinates, a combined elevation corresponding to each preset sub-region is generated to obtain a combined elevation matrix. The combined elevation includes the first elevation of the upper plate point cloud in the sub-region to the first reference plane, and the second elevation of the lower plate point cloud in the sub-region to the second reference plane. The combined elevation matrix is ​​divided into at least four sub-matrices, and the largest combined elevation in each sub-matrix is ​​arranged in descending order to form a combined elevation sequence. The third combined elevation in the combined elevation sequence is selected as the reference elevation, and the opening information of the rock mass structural surface is obtained based on the reference elevation, the combined elevation matrix and the preset analysis strategy. The analysis strategy includes setting the opening value of the sub-region corresponding to the combined elevation that is less than or equal to the reference elevation to zero.

2. The method for generating rock mass structural plane aperture information according to claim 1, characterized in that, The point cloud coordinates include the upper disk point cloud coordinates and the lower disk point cloud coordinates; determining the reference plane based on the point cloud coordinates includes: Obtain the maximum coordinate value of the upper disk point cloud coordinates in the vertical direction, and use it as the first target value; Obtain the minimum coordinate value of the lower disk point cloud coordinates in the vertical direction, and use it as the second target value; The first reference plane and the second reference plane are determined based on the first target value and the second target value, respectively, wherein the coordinate value of any point on the first reference plane in the vertical direction is equal to the first target value, and the coordinate value of any point on the second reference plane in the vertical direction is equal to the second target value.

3. The method for generating rock mass structural surface aperture information according to claim 2, characterized in that, Before generating the combined elevation corresponding to each preset sub-region based on the reference plane and the point cloud coordinates to obtain the combined elevation matrix, the method further includes: Based on a preset partitioning strategy, the regions where the upper disk point cloud and the lower disk point cloud are located are divided into grids to obtain a first grid set and a second grid set with the same row and column dimensions. The partitioning strategy includes using an orthogonal partitioning method for grid partitioning. The row and column values ​​corresponding to each first grid and each second grid in the first grid set and the second grid set are obtained respectively, and multiple sub-regions are determined based on the row and column values, wherein the row and column values ​​corresponding to the first grid and the second grid in each sub-region are the same.

4. The method for generating rock mass structural surface aperture information according to claim 3, characterized in that, The step of generating a combined elevation matrix based on the reference plane and the point cloud coordinates for each preset sub-region, including: Based on the point cloud coordinates, the first grid coordinates corresponding to the first grid and the second grid coordinates corresponding to the second grid are obtained; Based on the vertical distance from the first grid coordinates to the first reference plane, the first elevation corresponding to each sub-region is obtained; Based on the vertical distance from the second grid coordinates to the second reference plane, the second elevation corresponding to each sub-region is obtained; The first elevation and the second elevation corresponding to each sub-region are merged to obtain multiple combined elevations, which constitute the combined elevation matrix.

5. The method for generating rock mass structural surface aperture information according to claim 4, characterized in that, The step of obtaining the first grid coordinates corresponding to the first grid and the second grid coordinates corresponding to the second grid based on the point cloud coordinates includes: The coordinates of the first grid are determined based on the first number of upper disk point clouds falling into each of the first grids and the coordinates of the upper disk point clouds; Wherein, when the first quantity is equal to 1, the coordinates of the upper disk point cloud corresponding to the upper disk point cloud are used as the first grid coordinates; When the first quantity is greater than 1, the average value of the coordinates of the multiple upper disk point clouds corresponding to the multiple upper disk point clouds in the first grid is taken as the coordinates of the first grid. When the first quantity is less than 1, the coordinates of the first grid are obtained according to the coordinates of the upper disk point cloud corresponding to the upper disk point cloud within a preset range around the first grid. The coordinates of the second grid are determined based on the second number of lower disk point clouds falling into each second grid and the coordinates of the lower disk point clouds.

6. The method for generating rock mass structural plane opening information according to claim 1, characterized in that, After dividing the combined elevation matrix into at least four sub-matrices and arranging the largest combined elevation in each sub-matrix in descending order to form a combined elevation sequence, the method further includes: Obtain the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence; Determine whether the location distribution of the three sub-regions meets a preset distribution condition, wherein the distribution condition includes that the distance between any two sub-regions is greater than a preset distance threshold; If not, then subtract the preset number from the current number of submatrices to obtain the target number, wherein the target number is greater than or equal to four; The combined elevation matrix is ​​divided into the target number of sub-matrices, and the step of obtaining the three sub-regions corresponding to the first three combined elevations in the combined elevation sequence is returned until the distribution condition is met.

7. The method for generating rock mass structural plane aperture information according to any one of claims 1-6, characterized in that, After selecting the third combined elevation in the combined elevation sequence as the reference elevation, and obtaining the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix, and the preset analysis strategy, the method further includes: The positions of the upper plate point cloud and the lower plate point cloud are adjusted according to a preset position adjustment rule, and the point cloud information is updated. The position adjustment rule includes shifting the upper plate point cloud horizontally by a preset distance. Based on the updated point cloud information, virtual opening information corresponding to the rock mass structural surface after the position adjustment is obtained, including obtaining the virtual opening information according to the position adjustment rules and the opening information.

8. The method for generating rock mass structural plane opening information according to claim 7, characterized in that, After obtaining the virtual aperture information corresponding to the rock mass structural surface after adjustment based on the updated point cloud information, the method further includes: Based on the updated point cloud information, image information of the rock mass structure surface is generated, and the virtual aperture information and the corresponding image information are associated to obtain a set of training data, wherein the image information includes three-dimensional image information; Returning to the steps of adjusting the positions of the upper plate point cloud and the lower plate point cloud according to the preset position adjustment rules and updating the point cloud information, multiple sets of training data are obtained to form a training dataset; The pre-built initial evaluation model is trained based on the training dataset to obtain the evaluation model; The target image information corresponding to the target rock mass structural surface is input into the evaluation model to obtain the target opening information corresponding to the target rock mass structural surface.

9. A device for generating information on the opening degree of rock mass structural surfaces, characterized in that, include: The acquisition module is used to acquire point cloud information of rock mass structural surfaces, including the hanging wall point cloud, the footwall point cloud, and point cloud coordinates. A first processing module is used to determine a reference plane based on the point cloud coordinates. The reference plane includes a first reference plane and a second reference plane, wherein the upper disk point cloud and the lower disk point cloud are located between the first reference plane and the second reference plane. The second processing module is used to generate a combined elevation corresponding to each preset sub-region based on the reference plane and the point cloud coordinates, to obtain a combined elevation matrix, wherein the combined elevation includes the first elevation of the upper plate point cloud in the sub-region to the first reference plane, and the second elevation of the lower plate point cloud in the sub-region to the second reference plane. A partitioning module is used to divide the combined elevation matrix into at least four sub-matrices and arrange the largest combined elevation in each sub-matrix in descending order to form a combined elevation sequence. The generation module is used to select the third combined elevation in the combined elevation sequence as the reference elevation, and obtain the opening information of the rock mass structural surface based on the reference elevation, the combined elevation matrix and the preset analysis strategy. The analysis strategy includes setting the opening value of the sub-region corresponding to the combined elevation that is less than or equal to the reference elevation to zero.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method for generating rock mass structural surface opening information as described in any one of claims 1-8.

Images