Method and system for quantizing integrity of rasterized rock mass based on excavation and drilling images

Abstract

The invention discloses a rasterized rock mass integrity quantification method and system based on excavation and drilling images, and relates to the technical field of tunnel rock mass integrity analysis, and the method comprises the steps: obtaining a tunnel excavation tunnel face image and a rock mass drilling image; preprocessing the acquired image, inputting the preprocessed image into a rock mass fracture identification model, identifying fractures, and determining geometric features and pixel coordinates of each fracture; according to the geometrical characteristics and pixel coordinates of the fissures, fitting to obtain fissure surfaces, determining plane equations and spatial positions of the fissure surfaces, then calculating spatial connectivity between adjacent fissure surfaces, and analyzing coplanarity of a plurality of fissure surfaces; a rock mass area is divided into adaptive uneven three-dimensional grids, geometric features, spatial positions and spatial connectivity of fractures are mapped to each grid unit, and fracture density, fracture connectivity and integrity index values of each grid unit are calculated. According to the method, accurate quantitative analysis of rock mass integrity can be realized, and the calculation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel rock mass integrity analysis, and in particular to a rasterized rock mass integrity quantification method and system based on excavation and drilling images. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Rock mass integrity refers to the ability of rock mass to maintain its integrity and stability under the action of external forces. As an important structural feature of rock mass, crack distribution, size, shape, connectivity and other factors are directly related to the integrity assessment of rock mass. Traditional rock mass integrity analysis methods mainly rely on manual measurement, two-dimensional analysis or simple crack number statistics, which is difficult to fully and accurately reveal the distribution of cracks in three-dimensional space and the impact on the overall performance of rock mass. Especially under complex geological conditions, this method is often unable to fully and accurately reveal the true situation of cracks due to its limitations.

[0004] Therefore, the traditional two-dimensional fracture analysis method has the problems of large computational complexity and large two-dimensional plane limitations in analyzing the geometric morphology of fractures, evaluating the spatial connectivity of fracture systems and rock mechanics. Especially when faced with calculating large-scale and high-density geological data, there are problems such as low efficiency and data bias, which makes it impossible to accurately analyze the fractures in the rock mass, and thus unable to accurately quantify the integrity of the rock mass.

[0005] With the development of computer image processing technology, 3D modeling technology and spatial data analysis methods, current research attempts to use more advanced 3D technology to analyze rock mass fractures, such as automatically extracting the geometric features of fractures based on digital image processing technology, and then using 3D reconstruction technology to construct a 3D model of fractures. However, the existing 3D fracture analysis methods have shortcomings such as low data processing efficiency, lack of fracture connectivity analysis, and lack of spatial quantitative models. They are also unable to quickly and accurately quantify rock mass integrity. Summary of the invention

[0006] To address the deficiencies of the above-mentioned prior art, the present invention provides a rasterized rock integrity quantification method and system based on excavation and drilling images, which extracts the geometric features and pixel coordinates of cracks from excavation face images and rock drilling images, thereby fitting the spatial position of the cracks, analyzing the spatial distribution characteristics and spatial connectivity of the cracks, and then using a rasterization method to integrate the feature data of rock cracks in different dimensions into a unified spatial framework, thereby more comprehensively quantifying the three-dimensional crack characteristics and obtaining more accurate raster comprehensive crack characteristics, thereby achieving accurate quantitative analysis of rock integrity and improving computational efficiency.

[0007] In a first aspect, the present invention provides a method for quantifying rock mass integrity based on rasterized excavation and borehole images.

[0008] A rasterized rock mass integrity quantification method based on excavation and borehole images, comprising:

[0009] Acquire tunnel excavation face images and rock mass drilling images;

[0010] Preprocessing the acquired images;

[0011] The preprocessed image is input into the rock mass fracture identification model to identify the fractures and determine the geometric features and pixel coordinates of each fracture;

[0012] According to the geometric characteristics and pixel coordinates of the cracks, the crack surface is fitted, the plane equation and spatial position of the crack surface are determined, and then the spatial connectivity between adjacent crack surfaces is calculated, and the coplanarity of multiple crack surfaces is analyzed;

[0013] The rock mass area is divided into adaptive non-uniform three-dimensional grids, the geometric characteristics, spatial positions, and spatial connectivity of the fractures are mapped to each grid unit, and the fracture density, fracture connectivity, and integrity index value of each grid unit are calculated.

[0014] In a second aspect, the present invention provides a rasterized rock mass integrity quantification system based on excavation and borehole images.

[0015] A rasterized rock mass integrity quantification system based on excavation and borehole images, comprising:

[0016] An image acquisition module is used to acquire tunnel excavation face images and rock mass drilling images;

[0017] An image preprocessing module, used for preprocessing the acquired image;

[0018] A fracture identification module is used to input the preprocessed image into the rock fracture identification model, identify fractures and determine the geometric features and pixel coordinates of each fracture;

[0019] The crack feature analysis module is used to fit the crack surface according to the geometric features and pixel coordinates of the crack, determine the plane equation and spatial position of the crack surface, calculate the spatial connectivity between adjacent crack surfaces, and analyze the coplanarity of multiple crack surfaces;

[0020] The gridded rock mass integrity quantification module is used to divide the rock mass area into an adaptive non-uniform three-dimensional grid, map the geometric characteristics, spatial position, and spatial connectivity of the cracks to each grid unit, and calculate the crack density, crack connectivity, and integrity index value of each grid unit.

[0021] In a third aspect, the present invention also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing the above-mentioned rasterized rock integrity quantification method based on excavation and drilling images when executing the executable instructions stored in the memory.

[0022] In a fourth aspect, the present invention further provides a computer-readable storage medium storing executable instructions for causing a processor to execute the executable instructions to implement the above-mentioned rasterized rock integrity quantification method based on excavation and drilling images.

[0023] In a fifth aspect, the present invention also provides a computer program product, which includes executable instructions stored in a computer-readable storage medium; wherein, when the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned rasterized rock integrity quantification method based on excavation and drilling images is implemented.

[0024] One or more of the above technical solutions have the following beneficial effects:

[0025] 1. The present invention provides a rasterized rock mass integrity quantification method and system based on excavation and drilling images, extracts the geometric features and pixel coordinates of cracks from the excavation face image and the rock mass drilling image, fits the crack plane through the pixel coordinates of the end points of the crack, obtains the plane equation of the crack in three-dimensional space, and determines the spatial position of the crack based on the equation, thereby effectively solving the limitations of the two-dimensional space plane, and determines the spatial expansion form of the crack by expanding the three-dimensional space; according to the three-dimensional spatial position of the crack, it is judged whether adjacent cracks overlap or intersect within a certain range, if the two crack planes coincide or have common points, it is considered that they have a certain connectivity, thereby analyzing the spatial distribution characteristics and spatial connectivity of the cracks, and compared with the traditional two-dimensional method, the accuracy of the connectivity judgment can be effectively improved; finally, the rasterization method is used to integrate the feature data of different dimensions of rock mass cracks into a unified spatial framework, and by assigning values ​​to the rock mass characteristics of each grid unit, a more comprehensive and accurate quantitative analysis of rock mass integrity is achieved, which can effectively reduce the computational workload and improve the computational efficiency compared with the traditional method.

[0026] 2. The present invention fully considers the low grayscale and high linearity characteristics of rock fractures. By adopting a generalized gamma correction algorithm to perform contrast enhancement processing on the image to correct the image, and adopting a grayscale transfer criterion to enhance the continuity of the fractures, the present invention can optimize the problems of missing fractures, fractures and high noise caused by uneven image contrast, and facilitate the subsequent accurate identification and extraction of fractures.

[0027] 3. Unlike traditional methods that focus on the analysis of single crack characteristics, the analysis method proposed in the present invention is based on the three-dimensional spatial geometric relationship and spatial connectivity characteristics of cracks, which can systematically evaluate the spatial connectivity of cracks in large-scale areas. By defining the coplanarity index of cracks (including the normal vector angle and the minimum spatial distance, etc.), it can be determined whether the cracks form a connected network in three-dimensional space, thereby more accurately revealing the spatial distribution and structural characteristics of the cracks.

[0028] 4. The present invention adopts a grid-based quantitative analysis method. According to the scale of the rock mass area, a three-dimensional grid is defined and adaptively divided. Rock mass characteristics are assigned to each divided grid unit. By quantifying the crack characteristics of the grid unit (such as length, width, inclination, etc.) and performing mean or weighted sum operations, the comprehensive crack characteristics of the grid unit are obtained, thereby realizing quantitative analysis of the integrity of the rock mass. By converting the crack characteristics of the rock mass into efficient quantitative data, crack identification no longer relies on traditional manual interpretation or simple inclination and dip threshold judgment, and it is possible to accurately identify the geometric shape of the cracks, judge the distribution shape of the cracks on the tunnel rock face and analyze the characteristic value data, which is conducive to improving the ability to identify the degree of rock mass fragmentation, significantly improving the accuracy and efficiency of crack identification, and providing data support for improving the grouting speed of broken rock mass.

[0029] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1 A flowchart of a method for quantifying the integrity of a rock mass based on rasterized excavation and drilling images according to an embodiment of the present invention;

[0032] Figure 2 It is a grayscale histogram obtained after grayscale processing in the embodiment of the present invention. DETAILED DESCRIPTION

[0033] It should be noted that the following detailed descriptions are exemplary only, are intended to describe specific embodiments, are intended to provide further explanation of the present invention, and are not intended to limit exemplary embodiments according to the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those of ordinary skill in the art to which the present invention belongs. In addition, it should also be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0034] Embodiment 1

[0035] This embodiment provides a method for quantifying rock mass integrity based on rasterized excavation and drilling images. Figure 1 As shown, the specific steps include:

[0036] Step S1, acquiring tunnel excavation face images and rock mass drilling images.

[0037] In this embodiment, geological exploration is first conducted on the rock mass in the tunnel excavation area to obtain excavation face images, rock mass borehole images, and other actual underground engineering detection data, wherein the borehole image refers to a planar unfolded image of the rock mass borehole.

[0038] Step S2: pre-process the acquired image.

[0039] Considering that the original image may be affected by factors such as noise, lighting, and resolution, resulting in errors in subsequent image recognition, this embodiment performs preprocessing such as denoising and enhancement on the collected image data to improve the recognition accuracy of subsequent crack features.

[0040] Specifically, for the excavation face images and drilling images, considering the low grayscale and high linearity characteristics of rock cracks, a targeted crack identification optimization method is used to preprocess the images, that is, the generalized gamma correction algorithm is used to correct the images, and then the grayscale transfer criterion is used to enhance the continuity of the cracks in the image, so as to solve the problems of crack missing, fracture and high noise caused by uneven image contrast, and facilitate the accurate extraction of cracks in subsequent images.

[0041] Step S2.1, use a generalized gamma correction algorithm to perform contrast enhancement processing on the image to correct the image. The generalized gamma correction algorithm is different from the general full grayscale spatial enhancement algorithm. This algorithm analyzes the pre-peak grayscale histogram of the image and adaptively determines the correction parameters to achieve effective processing of crack pixels, including:

[0042] Step S2.1.1: grayscale and pixelate the image. For the processed image, min To the maximum gray level i max , count the number of pixels at each gray level i and construct a gray level histogram, such as Figure 2 As shown, there are 255 gray levels in total. The number of pixels at each gray level is counted and a gray histogram is drawn. For the constructed gray histogram, the histogram is truncated at the peak frequency to obtain a gray level i and the corresponding frequency Pre-peak data

[0043] Step S2.1.2: Pre-peak data Perform multi-segment line fitting to identify the crack area, transition area and rock wall area in the histogram, and obtain the endpoint values ​​of each area, such as the gray level i corresponding to the right endpoint of the crack area and transition area f 、i t And other rough partition information.

[0044] Step S2.1.3: The endpoint values ​​of the fissure zone, transition zone, and rock face zone are not input, and the output values ​​after optimization by the generalized gamma algorithm are used as output values ​​to form point pairs such as [(0,0), (i min ,0),(i f ,i t ), (i t ,i max ), (255, 255)] to fit, and then determine the parameters in the generalized gamma correction formula, and apply the formula to image pixel intensity correction. The correction formula can be expressed as:

[0045]

[0046] In the above formula, the parameters α and γ are determined by using the histogram partition information obtained by fragment linear fitting; α and γ are parameters that control the shape of the curve, α∈[0,255], γ∈[0,10], when α=0, the curve degenerates into the classic gamma correction.

[0047] Step S2.2: Use the grayscale transfer algorithm to perform grayscale value homogenization on the image, and effectively enhance the continuity of the cracks by transferring grayscale value information between crack pixels.

[0048] Considering that the grayscale value of a crack pixel is affected by a series of factors such as the crack distribution density, crack thickness, and crack edge friction on its path, this embodiment uses a grayscale transfer algorithm to process the image. When its grayscale value is high and the grayscale value of the pixel on its adjacent path is low, its grayscale value is reduced to a certain extent to improve the degree of uniformity of the crack grayscale value. The process of the grayscale transfer algorithm is as follows:

[0049] Step S2.2.1, determine the grayscale transfer direction. By identifying multiple features of the image, such as color depth features, etc., determine the difference between the image and the background color, and generate a stripe diagram with a color difference from the background color based on the color depth and other features, wherein the stripe refers to the vertical direction of the pixel gradient in the image, and the color difference stripe reflects the size of the difference. The pixel intensity along the stripe direction is distinguished by the fitting curve method. In this embodiment, the grayscale transfer direction is determined by the Hessian matrix, which can be expressed as:

[0050]

[0051] In the above formula, I(x,y) represents the pixel intensity at the pixel point (x,y).

[0052] Step S2.2.2, determine the pixel intensity division assignment through the eigenvalues ​​λ1 and λ2 of the Hessian matrix, as shown in Table 1 below. The strips with an increasing trend in pixel intensity are bright lines, and the strips with a decreasing trend in pixel intensity are dark lines. By assigning brightness, the eigenvalue of pixel intensity is determined.

[0053] Table 1 Pixel intensity division assignment corresponding to the eigenvalues ​​of the Hessian matrix

[0054]

[0055] Through the above method, the change direction of pixel intensity is obtained, the transfer pixel is determined, and the local grayscale minimum point is selected as the transfer object to include all possible crack pixels.

[0056] Preferably, under normal circumstances, the conditions at the engineering site are complex, and a single rock fracture image is difficult to distinguish the actual brightness change trend at the site. Therefore, a specific value is selected as the relaxation condition, and the local grayscale minimum and maximum points in an image are selected as the transfer objects to judge the bright lines and dark lines, and identify the contained fracture pixels as much as possible.

[0057] Step S3: input the preprocessed image into the rock mass fracture recognition model to identify the fractures and determine the geometric features and pixel coordinates of each fracture.

[0058] In this embodiment, after completing the above-mentioned image acquisition and preprocessing of the borehole images and excavation face images obtained by the borehole television, image processing and computer vision algorithms are used for image processing, that is, the preprocessed images are input into the rock mass fracture recognition model trained based on the transfer learning technology, and the characteristics of the fractures in different dimensions are automatically identified, including the geometric characteristics and pixel coordinates of the fractures. Among them, the geometric characteristics of the fractures include the length, width, inclination and inclination of the fractures. Based on the pixel coordinates of the endpoints of the fractures, the fracture plane (referred to as the fracture plane) can be fitted, and then the three-dimensional spatial position of the fracture can be determined.

[0059] The rock fracture recognition model obtained by training based on the transfer learning technology means that: on the basis of the target detection model, the model can quickly learn and adapt to new rock fracture recognition tasks on less data through the transfer learning method with the help of existing data and knowledge, effectively utilize limited rock fracture image resources, and improve the generalization ability of the model. The training process is as follows:

[0060] Firstly, the original rock fracture images are obtained, and the images that do not contain the target features of fractures are eliminated to construct a high-quality rock fracture image dataset. The rock mass is marked as the background to highlight the target features of fractures, enhance the model's learning ability of key information, and mark its location information. This can help the model to identify fractures more accurately, reduce interference from other factors, and improve the accuracy of determining the geometric features of fractures and pixel coordinates. The image dataset is then used to pre-train the model, and the optimal model parameters are explored through the transfer learning method to achieve the purpose of accelerating the convergence of the model and enriching the rock fracture image dataset. Finally, a rock fracture recognition model is trained.

[0061] Preferably, the above-mentioned recognition model can use an edge detection algorithm, such as Canny edge detection and other methods, to extract crack features from the image, detect and identify the edges of cracks in the image; and then use a fitting algorithm to extract the geometric features of the cracks from the crack edges, such as the length, width, inclination and tendency of the cracks.

[0062] Step S4: According to the geometric features and pixel coordinates of the cracks, the crack surface is fitted, the plane equation and spatial position of the crack surface are determined, and then the spatial connectivity between adjacent crack surfaces is calculated, and the coplanarity of multiple crack surfaces is analyzed.

[0063] In this embodiment, first, the rock fracture recognition model based on transfer learning accurately identifies and extracts the fractures in the image, fits the plane where the fractures are located according to the pixel coordinates of the fracture endpoints and the geometric characteristics of the fractures, and obtains the plane equation of the fracture in three-dimensional space. Based on the equation, the spatial orientation of the fracture is determined, that is, the specific coordinate position (that is, spatial position) and direction of the fracture in three-dimensional space are determined.

[0064] Secondly, considering the existence of crack opening, discrete pixel points in the image are extracted, the crack information is represented by discrete points, and characterized as digital attributes. The standard deviation σ of the normal distance from the discrete pixel point to the best fitting plane is calculated as the discreteness, and the discreteness σ is used as a statistical attribute parameter to represent an attribute of the crack surface position.

[0065] Afterwards, the fracture surfaces are identified and extracted from the acquired images, converted into digital attribute representations of the fracture surfaces to form discontinuous data sets. The fracture surfaces in the discontinuous data sets are clustered, and the coplanarity of the fracture surfaces in the same cluster is verified. Multiple coplanar data sets that reveal the spatial distribution characteristics of fractures are obtained, providing strong support for geological interpretation, fracture network modeling and rock stability analysis.

[0066] Furthermore, the coplanarity of the fracture surfaces in the same cluster is verified, including: checking whether two adjacent fractures are connected by calculating the normal vector angle of the fracture surface and the minimum spatial distance between fractures, evaluating the spatial connectivity of the fractures, and thereby determining whether the fractures are coplanar, and further forming an overall characteristic analysis of the fracture group. Among them, the minimum spatial distance refers to judging whether adjacent fractures overlap or intersect within a certain range based on the fracture orientation and spatial position in three-dimensional space.

[0067] By analyzing the parameters such as the normal vector angle of the crack plane and the minimum distance between cracks, the spatial connectivity between adjacent cracks is calculated. The value of the spatial connectivity can be used to determine the coplanarity of the cracks. Therefore, the calculation result of the spatial connectivity is used as the coplanarity index CI (Coplanarity Index). The calculation formula can be expressed as:

[0068]

[0069] in, and They represent the normal vectors of the two cracks, · represents the vector dot product, d 12 represents the minimum distance between two cracks, d threshold is the set spatial distance threshold.

[0070] The coplanarity is judged based on the coplanarity index CI value obtained by the above calculation. If the calculated CI value is close to 1, it is considered that the two cracks are coplanar.

[0071] Step S5, dividing the rock mass area into an adaptive non-uniform three-dimensional grid, mapping the geometric characteristics, spatial position, and spatial connectivity of the fractures to each grid unit, and calculating the fracture density, fracture connectivity, and integrity index value of each grid unit.

[0072] Specifically, after the crack feature extraction is completed, the rock mass area under study is divided into uniform three-dimensional grid units, each grid unit represents an independent spatial unit in the rock mass, has a spatial size definition, and each grid unit will contain the corresponding crack feature data; the geometric characteristics of the crack are mapped to the grid unit, and according to the spatial position, size and characteristics of the crack, the attributes of the crack, such as length, width, inclination, dip, etc., are proportionally allocated to the grid unit containing the crack.

[0073] Preferably, this embodiment adopts an adaptive non-uniform grid division method, which is based on AMR adaptive grid refinement, first identifies cracks, and then performs specific adaptive size grid division according to crack density and other characteristics. The traditional method of dividing the plane into uniform size grids for identification has the problems of large data calculation, cumbersome calculation, and invalid data may exist in some grids, and some crack data may exist in some grids and cannot be fully reflected. Compared with this traditional method, this embodiment can reduce the number of grids and effectively reduce the number of calculations by adaptively dividing the grids, so that complete data exists in the grids, which is convenient for subsequent analysis and processing.

[0074] Furthermore, the grid cells after rasterization are assigned values, and characteristic values ​​such as the number, size, roughness, and thickness of the cracks in each grid cell are calculated; according to the actual crack distribution density, size, roughness, thickness and other characteristics, the rock mass area can be divided into an adaptive non-uniform three-dimensional grid, in which each grid cell corresponds to an independent spatial unit with clear geometric properties.

[0075] On the above basis, according to the spatial position, geometric shape, connectivity and other characteristics of the cracks, the crack density, crack connectivity coefficient and integrity factor of the grid unit are calculated to quantitatively evaluate the integrity of the rock mass.

[0076] Among them, according to the spatial connectivity of the cracks, the crack connectivity coefficient C of each grid unit is calculated f , to assess whether there are through-going fracture channels in the rock mass fractures, the formula is:

[0077]

[0078] Furthermore, the integrity of the rock mass is quantitatively evaluated through the fracture characteristics, grid data and connectivity analysis results of the above process, including:

[0079] (1) Calculate the crack density based on the number of cracks in each grid cell. Where N f is the number of cracks in the grid, and V represents the volume of the grid.

[0080] (2) For each grid unit, according to the crack density D f and connectivity coefficient C f , calculate the integrity factor I f , grid integrity is expressed as a quantitative factor, the formula is:

[0081] I f =1-αD f -βC f ;

[0082] Among them, α and β are adjustment coefficients used to balance the weights of the impact of fracture density and connectivity on integrity.

[0083] Preferably, after completing the quantitative analysis of rock mass fracture characteristics, the final fracture density, fracture connectivity, rock mass integrity and other data are output. Through data visualization technology, based on the fracture density, fracture connectivity and integrity factor of each grid unit obtained by calculation, a rock mass integrity distribution map, fracture distribution map and the like are generated to intuitively display the fracture characteristics and integrity status of the rock mass, and provide a basis for rock mass stability and safety assessment.

[0084] As an implementation method, a message passing neural network (MPNN) is constructed, which can pass information in a graph structure through a message passing mechanism, so that each node can aggregate the information of its neighboring nodes. In this embodiment, the grid divided by the above-mentioned grid is used as an MPNN network node, and each grid is first quantitatively calculated in the above manner, that is, the characteristics of each node, such as the integrity factor, crack density and other characteristic values, are determined and node attributes are assigned; then, data / messages are transmitted as adjacent nodes, and each node receives messages from its neighboring nodes and aggregates them, thereby converging into multiple central nodes (i.e., intersections between unit grids), and the central nodes continue to perform iterative calculations. After multiple rounds of iterations, the nodes continuously update their characteristics and weighted assignments, and gradually integrate the information of more distant neighbors; after multiple iterations, the characteristic values ​​of the nodes obtain global information from a larger range of graph structures, and finally aggregate to obtain an index for judging the degree of integrity of the face. Using the index obtained by the final aggregation, the degree of integrity of the face can be divided, and the division can intuitively present the rock integrity of the face, and provide a quantitative basis for judging the degree of fragmentation of the rock face of the tunnel.

[0085] In addition, the classification of the integrity of the tunnel face and the corresponding characteristic values ​​can provide a certain data basis for the grouting speed. By accurately judging the rock mass with different degrees of fragmentation, engineers can adjust the grouting plan in a targeted manner, such as selecting appropriate grouting materials, grouting pressure and grouting volume, thereby improving the grouting effect, enhancing the stability and safety of the rock mass, and ensuring the smooth progress of tunnel construction.

[0086] Embodiment 2

[0087] This embodiment provides a rasterized rock mass integrity quantification system based on excavation and drilling images, which specifically includes:

[0088] An image acquisition module is used to acquire tunnel excavation face images and rock mass drilling images;

[0089] An image preprocessing module, used for preprocessing the acquired image;

[0090] A fracture identification module is used to input the preprocessed image into the rock fracture identification model, identify fractures and determine the geometric features and pixel coordinates of each fracture;

[0091] The crack feature analysis module is used to fit the crack surface according to the geometric features and pixel coordinates of the crack, determine the plane equation and spatial position of the crack surface, calculate the spatial connectivity between adjacent crack surfaces, and analyze the coplanarity of multiple crack surfaces;

[0092] The gridded rock mass integrity quantification module is used to divide the rock mass area into an adaptive non-uniform three-dimensional grid, map the geometric characteristics, spatial position, and spatial connectivity of the cracks to each grid unit, and calculate the crack density, crack connectivity, and integrity index value of each grid unit.

[0093] Embodiment 3

[0094] This embodiment provides an electronic device, including: a memory, used to store executable instructions; and a processor, used to implement the above method provided in this embodiment when executing the executable instructions stored in the memory.

[0095] Embodiment 4

[0096] This embodiment also provides a computer-readable storage medium storing executable instructions. When the executable instructions are executed by a processor, the processor will be caused to execute the above method provided by this embodiment.

[0097] Embodiment 5

[0098] This embodiment provides a computer program product, which includes an executable instruction, which is a computer instruction; the executable instruction is stored in a computer-readable storage medium. When a processor of an electronic device reads the executable instruction from the computer-readable storage medium and the processor executes the executable instruction, the electronic device executes the above method provided in this embodiment.

[0099] The steps involved in the above embodiments 2 to 5 correspond to the method embodiment 1. For the specific implementation, please refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0100] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0101] The above description is only a preferred embodiment of the present invention. Although the specific implementation mode of the present invention is described in conjunction with the accompanying drawings, it is not a limitation of the protection scope of the present invention. Those skilled in the art should understand that on the basis of the technical solution of the present invention, various modifications or variations that can be made by those skilled in the art without creative work are still within the protection scope of the present invention.

Claims

1. A method for quantifying rock mass integrity based on rasterized excavation and drilling images, characterized in that: include: Acquire tunnel excavation face images and rock mass drilling images; Preprocessing the acquired images; The preprocessed image is input into the rock mass fracture identification model to identify the fractures and determine the geometric features and pixel coordinates of each fracture; According to the geometric characteristics and pixel coordinates of the cracks, the crack surface is fitted, the plane equation and spatial position of the crack surface are determined, and then the spatial connectivity between adjacent crack surfaces is calculated, and the coplanarity of multiple crack surfaces is analyzed; The rock mass area is divided into adaptive non-uniform three-dimensional grids, the geometric characteristics, spatial positions, and spatial connectivity of the fractures are mapped to each grid unit, and the fracture density, fracture connectivity, and integrity index value of each grid unit are calculated.

2. A method for quantifying rock mass integrity based on rasterized excavation and drilling images as claimed in claim 1, characterized in that: The pre-processing comprises: The generalized gamma correction algorithm is used to perform contrast enhancement on the image to correct the image; The grayscale transfer algorithm is used to homogenize the grayscale values ​​of the image.

3. A method for quantifying rock mass integrity based on rasterized excavation and drilling images as claimed in claim 1, characterized in that: The geometric characteristics of the fracture include the length, width, dip and inclination of the fracture.

4. A method for quantifying rock mass integrity based on rasterized excavation and drilling images as claimed in claim 1, characterized in that: Calculate the spatial connectivity between adjacent fracture surfaces and analyze the coplanarity of multiple fracture surfaces, including: The angle between the normal vectors of the crack surfaces of two adjacent cracks and the minimum spatial distance between the cracks are calculated to obtain the spatial connectivity between adjacent cracks. The calculation result of the spatial connectivity is used as the coplanarity index CI, and its calculation formula is: in, and They represent the normal vectors of the two cracks, · represents the vector dot product, d 12 represents the minimum distance between two cracks, d threshold is the set spatial distance threshold; According to the coplanarity index value, the coplanarity of two adjacent cracks is determined.

5. A method for quantifying rock mass integrity based on rasterized excavation and drilling images as claimed in claim 1, characterized in that: Calculate the fracture density, fracture connectivity and integrity index values ​​for each grid cell, including: According to the spatial connectivity of the cracks, the crack connectivity coefficient C of each grid cell is calculated. f , the formula is: According to the number of cracks in each grid cell, the crack density D of each grid cell is calculated. f , the formula is: Among them, N f is the number of cracks in the grid, and V represents the volume of the grid.

6. A method for quantifying rock mass integrity based on rasterized excavation and drilling images as claimed in claim 5, characterized in that: Also includes: Calculate the integrity factor I based on the fracture density and connectivity coefficient f , grid integrity is expressed as a quantitative factor, the formula is: I f =1-αD f -βC f ; Among them, α and β are adjustment coefficients.

7. A rasterized rock mass integrity quantification system based on excavation and drilling images, characterized in that: include: An image acquisition module is used to acquire tunnel excavation face images and rock mass drilling images; An image preprocessing module, used for preprocessing the acquired image; A fracture identification module is used to input the preprocessed image into the rock fracture identification model, identify fractures and determine the geometric features and pixel coordinates of each fracture; The crack feature analysis module is used to fit the crack surface according to the geometric features and pixel coordinates of the crack, determine the plane equation and spatial position of the crack surface, calculate the spatial connectivity between adjacent crack surfaces, and analyze the coplanarity of multiple crack surfaces; The gridded rock mass integrity quantification module is used to divide the rock mass area into an adaptive non-uniform three-dimensional grid, map the geometric characteristics, spatial position, and spatial connectivity of the cracks to each grid unit, and calculate the crack density, crack connectivity, and integrity index value of each grid unit.

8. An electronic device, characterized in that: include: A memory for storing executable instructions; The processor is used to implement the rasterized rock mass integrity quantification method based on excavation and drilling images as described in any one of claims 1 to 6 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium, characterized in that: Executable instructions are stored, which are used to cause the processor to execute the executable instructions to implement the rasterized rock mass integrity quantification method based on excavation and drilling images as described in any one of claims 1-6.

10. A computer program product, characterized in that The computer program product includes executable instructions stored in a computer-readable storage medium; When the processor of the electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the rasterized rock integrity quantification method based on excavation and drilling images described in any one of claims 1 to 6 is implemented.

Images