A Rasterized Rock Mass Integrity Quantification Method and System Based on Excavation and Drilling Images

Abstract

The application discloses a kind of based on excavation and drilling image gridding rock mass integrity quantification method and system, it is related to tunnel rock mass integrity analysis technical field, including: obtaining tunnel excavation face image and rock mass drilling image;After the image obtained is preprocessed, then input to rock mass fissure identification model, identify fissure and determine the geometric feature and pixel coordinates of each fissure;According to the geometric feature and pixel coordinates of fissure, fissure surface is obtained by fitting, determine the plane equation and spatial position of fissure surface, then calculate the spatial connectivity between adjacent fissure surfaces, analyze the coplanarity of multiple fissure surfaces;Rock mass region is divided into adaptive non-uniform three-dimensional grid, the geometric feature, spatial position, spatial connectivity of fissure are mapped to each grid cell, and the fissure density, fissure connectivity and integrity index value of each grid cell are calculated.The present application can realize accurate quantitative analysis of rock mass integrity, improve the calculation efficiency.

Description

Technical Field

[0001] This invention relates to the field of tunnel rock mass integrity analysis technology, and in particular to a rasterized rock mass integrity quantification method and system based on excavation and borehole images. Background Technology

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

[0003] Rock mass integrity refers to the ability of a rock mass to maintain its integrity and stability under external forces. Fractures, as an important structural feature of rock masses, have distribution, size, morphology, and connectivity that directly affect rock mass integrity assessment. Traditional rock mass integrity analysis methods mainly rely on manual measurement, two-dimensional analysis, or simple fracture counts, which are insufficient to comprehensively and accurately reveal the distribution of fractures in three-dimensional space and their impact on the overall performance of the rock mass. Especially under complex geological conditions, this method, due to its limitations, often fails to fully and accurately reveal the true state of fractures.

[0004] Therefore, traditional two-dimensional fracture analysis methods suffer from problems such as large computational load and significant limitations of the two-dimensional plane in analyzing fracture geometry, assessing the spatial connectivity of fracture systems, and rock mechanics. In particular, when dealing with large-scale, high-density geological data, they suffer from low efficiency and data bias, making it impossible to accurately analyze fractures in rock masses and thus impossible to accurately quantify rock mass integrity.

[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 technologies to analyze rock mass fractures. For example, methods based on digital image processing technology can automatically extract the geometric features of fractures, and then 3D reconstruction technology can be used to construct a 3D model of the fractures. However, existing 3D fracture analysis methods have shortcomings such as low data processing efficiency, lack of fracture connectivity analysis, and lack of spatial quantification models. They also cannot quickly and accurately quantify the integrity of rock masses. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a rasterized rock mass integrity quantification method and system based on excavation and borehole images. The method extracts the geometric features and pixel coordinates of fractures from excavation face images and rock borehole images, uses this information to fit the spatial location of the fractures, and analyzes their spatial distribution characteristics and spatial connectivity. Then, a rasterization method is used to integrate the feature data of rock mass fractures from different dimensions into a unified spatial framework. This allows for a more comprehensive quantification of three-dimensional fracture features, resulting in more accurate rasterized composite fracture features, enabling accurate quantitative analysis of rock mass integrity and improving computational efficiency.

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

[0008] A method for quantifying the integrity of rasterized rock mass based on excavation and borehole images includes:

[0009] Acquire images of the tunnel face and boreholes in the rock mass;

[0010] The acquired images are preprocessed;

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

[0012] Based on the geometric features and pixel coordinates of the crack, the crack surface is fitted to determine the plane equation and spatial position of the crack surface. Then, the spatial connectivity between adjacent crack surfaces is calculated, and the coplanarity of multiple crack surfaces is analyzed.

[0013] The rock mass region is divided into an adaptive non-uniform three-dimensional grid. The geometric features, spatial location, and spatial connectivity of the fractures are mapped to each grid cell. The fracture density, fracture connectivity, and integrity index values ​​of each grid cell are calculated.

[0014] Secondly, 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] The image acquisition module is used to acquire images of the tunnel excavation face and rock boreholes;

[0017] The image preprocessing module is used to preprocess the acquired images;

[0018] The fracture recognition module is used to input the preprocessed image into the rock fracture recognition 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 based on 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 rasterized rock mass integrity quantification module is used to divide the rock mass region into an adaptive non-uniform three-dimensional raster grid, map the geometric features, spatial location, and spatial connectivity of fractures to each raster cell, and calculate the fracture density, fracture connectivity, and integrity index value of each raster cell.

[0021] Thirdly, the present invention also provides an electronic device, comprising: a memory for storing executable instructions; and a processor for implementing the above-described method for quantifying the integrity of rasterized rock mass based on excavation and borehole images when executing the executable instructions stored in the memory.

[0022] Fourthly, the present invention also provides a computer-readable storage medium storing executable instructions for causing a processor to execute the executable instructions to implement the above-described method for quantifying the integrity of rasterized rock mass based on excavation and borehole images.

[0023] Fifthly, the present invention also provides a computer program product comprising executable instructions stored in a computer-readable storage medium; wherein, when the processor of an electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the above-mentioned method for quantifying the integrity of rasterized rock mass based on excavation and borehole images is implemented.

[0024] The above one or more technical solutions have the following beneficial effects:

[0025] 1. This invention provides a rasterized rock mass integrity quantification method and system based on excavation and borehole images. It extracts the geometric features and pixel coordinates of fractures from excavation face images and rock borehole images. By fitting the fracture plane with the endpoint pixel coordinates, it obtains the plane equation of the fracture in three-dimensional space and determines the spatial location of the fracture based on this equation. This effectively overcomes the limitations of two-dimensional planes. The spatial unfolding form of the fracture is determined by unfolding in three-dimensional space. Based on the three-dimensional spatial location of the fracture, it determines whether adjacent fractures overlap or intersect within a certain range. If two fracture planes coincide or have common points, they are considered to have a certain degree of connectivity. This allows for the analysis of the spatial distribution characteristics and spatial connectivity of fractures, effectively improving the accuracy of connectivity judgment compared to traditional two-dimensional methods. Finally, a rasterization method is used to integrate the feature data of rock mass fractures in different dimensions into a unified spatial framework. By assigning values ​​to the rock mass characteristics of each raster unit, a more comprehensive and accurate quantitative analysis of rock mass integrity is achieved. Compared to traditional methods, this effectively reduces the computational workload and improves computational efficiency.

[0026] 2. This invention fully considers the characteristics of rock mass fissures, which are characterized by low grayscale and high linearity. It uses a generalized gamma correction algorithm to enhance the contrast of the image to correct the image, and uses a grayscale transfer criterion to enhance the continuity of the fissures. This can optimize the problems of fissure missing, fracture and high noise caused by uneven image contrast, and facilitate the accurate identification and extraction of subsequent fissures.

[0027] 3. Unlike traditional methods that focus on analyzing single fracture features, the analysis method proposed in this invention, based on the three-dimensional spatial geometric relationship and spatial connectivity characteristics of fractures, can systematically evaluate the spatial connectivity of fractures over a large-scale area. By defining the coplanarity index of fractures (including the angle between normal vectors and the minimum spatial distance, etc.), it can be determined whether fractures form a connected network in three-dimensional space, thereby revealing the spatial distribution and structural characteristics of fractures more accurately.

[0028] 4. This invention employs a gridded quantitative analysis method. Based on the scale of the rock mass region, a three-dimensional grid is defined and adaptively divided. Rock mass characteristics are assigned to each grid cell. By quantifying the fracture characteristics of the grid cell (such as length, width, dip angle, etc.) and performing mean or weighted sum calculations, the comprehensive fracture characteristics of the grid cell are obtained, achieving quantitative analysis of rock mass integrity. By transforming the fracture characteristics of the rock mass into efficient quantitative data, fracture identification no longer relies on traditional manual interpretation or simple dip angle and dip threshold judgments. It can accurately identify the geometric shape of fractures, determine the distribution pattern of fractures at the tunnel face, and analyze characteristic value data. This is beneficial for improving the ability to identify the degree of rock mass fragmentation, significantly improving the accuracy and efficiency of fracture identification, and providing data support for increasing the grouting speed of fractured rock masses.

[0029] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0030] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0031] Figure 1 This is a flowchart of the rasterized rock mass integrity quantification method based on excavation and borehole images as described in an embodiment of the present invention;

[0032] Figure 2 This is a grayscale histogram obtained after grayscale processing in an embodiment of the present invention. Detailed Implementation

[0033] It should be noted that the following detailed descriptions are exemplary and are intended only to describe specific embodiments and to provide further explanation of the invention, and are not intended to limit the scope of exemplary embodiments of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0034] Example 1

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

[0036] Step S1: Obtain images of the tunnel excavation face and rock boreholes.

[0037] In this embodiment, geological exploration is first carried out on the rock mass in the tunnel excavation area to obtain images of the excavation face, rock borehole images, and other actual underground engineering detection data. Among them, the borehole images refer to the planar unfolded images of the rock boreholes.

[0038] Step S2: Preprocess the acquired image.

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

[0040] Specifically, for excavation face images and borehole images, considering the characteristics of rock mass fissures with low grayscale and high linearity, a targeted fissure identification optimization method is adopted 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 fissures in the images. This solves the problems of fissure missing, fracture and high noise caused by uneven image contrast, which facilitates the accurate extraction of fissures in subsequent images.

[0041] Step S2.1: The image is contrast-enhanced using a generalized gamma correction algorithm to correct the image. This generalized gamma correction algorithm differs from generalized full-grayscale enhancement algorithms. It adaptively determines correction parameters by analyzing the image's pre-peak grayscale histogram, enabling effective processing of gap pixels, including:

[0042] Step S2.1.1: Perform grayscale and pixelation processing on the image. For the processed image, start from the smallest grayscale level i min up 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, it has 255 gray levels. The number of pixels at each gray level is counted, and a gray-level histogram is drawn. The constructed gray-level histogram is then truncated at the peak frequency to obtain the histogram containing gray level i and its corresponding frequency. Pre-peak data

[0043] Step S2.1.2: Process the pre-peak data Multisegment line fitting is performed to identify the fracture zone, transition zone, and rock wall surface zone in the histogram, and the endpoint values ​​of each zone are obtained, such as the gray level i corresponding to the right endpoint of the fracture zone and the transition zone. f i t Rough partitioning information.

[0044] Step S2.1.3: Using the endpoint values ​​of the fracture zone, transition zone, and rock wall surface zone as input values, and the values ​​output after optimization by the generalized gamma algorithm as output values, point pairs are formed, such as [(0,0), (i min ,0), (i f i t ), (i t i max The parameters in the generalized gamma correction formula are determined by fitting the values ​​of (255, 255) to the image pixel intensity correction. This formula is then applied 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 partitioning information obtained by segmental linear fitting; α and γ are parameters that control the shape of the curve, α∈[0,255], γ∈[0,10], and when α=0, the curve degenerates into the classic gamma correction.

[0047] Step S2.2: The image is processed to uniformize gray values ​​using a gray-scale transfer algorithm. By transferring gray-scale information between crack pixels, the continuity of the crack is effectively enhanced.

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

[0049] Step S2.2.1: Determine the grayscale transmission direction. By identifying various features of the image, such as color depth, the difference between the image and the background color is determined. Based on these features, a band map with color differences from the background color is generated. This band refers to the vertical direction of the pixel gradient in the image, and the color difference band reflects the magnitude of the difference. Pixel intensities along the band direction are distinguished using a curve fitting method. In this embodiment, the grayscale transmission direction is determined using the Hessian matrix, which can be represented as:

[0050]

[0051] In the above formula, I(x,y) represents the pixel intensity at 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 bands with increasing pixel intensity are bright lines, and the bands with decreasing pixel intensity are dark lines. By assigning brightness values, the eigenvalues ​​of pixel intensity are determined.

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

[0054]

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

[0056] Preferably, since engineering site conditions are usually complex, a single rock mass fracture image is difficult to distinguish the actual brightness change trend on site. Therefore, a specific value is selected as a relaxation condition, and local gray-level minimum and maximum points in an image are selected as the transfer objects to determine bright lines and dark lines, and to identify the fracture pixels contained therein as much as possible.

[0057] Step S3: Input the preprocessed image into the rock mass fracture identification model to identify 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 by acquiring borehole images and excavation face images from borehole television, image processing and computer vision algorithms are then used for image processing. Specifically, the preprocessed images are input into a rock mass fracture identification model trained using transfer learning techniques to automatically identify fracture features in different dimensions, including the fracture's geometric features and pixel coordinates. The fracture's geometric features include its length, width, dip angle, and dip direction. Based on the fracture's endpoint pixel coordinates, a fracture plane (referred to as the fracture surface) can be fitted, thereby determining the fracture's three-dimensional spatial location.

[0059] The rock mass fracture identification model trained using transfer learning technology refers to a model that, based on the target detection model, utilizes transfer learning to learn and adapt to new rock mass fracture identification tasks with limited data, leveraging existing data and knowledge. This effectively utilizes limited rock mass fracture image resources and improves the model's generalization ability. The training process is as follows:

[0060] First, original rock mass fracture images are acquired, and images that do not contain fracture target features are removed to construct a high-quality rock mass fracture image dataset. The rock mass in the dataset is labeled as background to highlight fracture target features, enhance the model's ability to learn key information, and label their location information. This helps the model to identify fractures more accurately, reduces interference from other factors, and improves the accuracy of determining fracture geometric features and pixel coordinates. Then, the model is pre-trained using this image dataset. Through transfer learning, the optimal model parameters are explored to accelerate model convergence and enrich the rock mass fracture image dataset. Finally, a rock mass fracture recognition model is trained.

[0061] Preferably, the above recognition model can employ edge detection algorithms, such as Canny edge detection, to extract crack features from the image, detect and identify the edges of cracks in the image; then, through a fitting algorithm, the geometric features of the crack, such as the length, width, dip angle and dip direction of the crack, can be extracted from the crack edges.

[0062] Step S4: Based on the geometric features and pixel coordinates of the crack, fit the crack surface to obtain the crack surface, 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.

[0063] In this embodiment, firstly, the rock mass fracture identification model based on transfer learning accurately identifies and extracts fractures in the image. Based on the pixel coordinates of the fracture endpoints and the geometric features of the fracture, the plane where the fracture is located is fitted to obtain the plane equation of the fracture in three-dimensional space. Based on this equation, the spatial orientation of the fracture is determined, that is, the specific coordinate position (i.e., spatial position) and direction of the fracture in three-dimensional space are determined.

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

[0065] Subsequently, the fracture surfaces were identified and extracted from the acquired images and converted into digital attribute representations of the fracture surfaces to form a discontinuous dataset. The fracture surfaces in the discontinuous dataset were clustered, and the coplanarity of the fracture surfaces in the same cluster was verified, resulting in multiple coplanar datasets that reveal the spatial distribution characteristics of fractures. This provides strong support for geological interpretation, fracture network modeling, and rock mass stability analysis.

[0066] Furthermore, verifying the coplanarity of fracture surfaces within the same cluster includes: checking whether adjacent fractures are connected by calculating the angle between the normal vectors of the fracture surfaces and the minimum spatial distance between fractures, evaluating the spatial connectivity of fractures, and thus determining whether fractures are coplanar, thereby further forming an overall characteristic analysis of the fracture group. The minimum spatial distance refers to determining whether adjacent fractures overlap or intersect within a certain range based on the fracture orientation and spatial location in three-dimensional space.

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

[0068]

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

[0070] Based on the coplanarity index CI value calculated above, the coplanarity is judged. If the calculated CI value is close to 1, then the two cracks are considered to be coplanar.

[0071] Step S5: Divide the rock mass region into an adaptive non-uniform three-dimensional grid, map the geometric features, spatial location, and spatial connectivity of the fractures to each grid cell, and calculate the fracture density, fracture connectivity, and integrity index values ​​of each grid cell.

[0072] Specifically, after extracting the fracture features, the studied rock mass area is divided into uniform three-dimensional grid cells. Each grid cell represents an independent spatial unit in the rock mass and has a defined spatial size. Each grid cell will contain the corresponding fracture feature data. The geometric features of the fractures are mapped to the grid cells, and according to the spatial location, size, and characteristics of the fractures, the attributes of the fractures, such as length, width, dip angle, and dip direction, are proportionally allocated to the grid cells containing the fractures.

[0073] Preferably, this embodiment employs an adaptive non-uniform grid partitioning method, which is based on AMR adaptive grid refinement. First, cracks are identified, and then the grid is partitioned to a specific adaptive size based on characteristics such as crack density. Traditional methods of dividing a plane into uniformly sized grids for identification suffer from problems such as large computational load, cumbersome calculations, and the potential for invalid data in some grids or the inability to fully represent crack data within some grids. Compared to this traditional method, this embodiment, through adaptive grid partitioning, reduces the number of grids, effectively reducing computational load and ensuring complete data within each grid, facilitating subsequent analysis and processing.

[0074] Furthermore, the rasterized grid cells are assigned values, and the characteristic values ​​such as the number, size, roughness, and thickness of fractures in each grid cell are calculated. Based on the actual fracture distribution density, size, roughness, thickness, and other characteristics, the rock mass region can be divided into an adaptive non-uniform three-dimensional raster grid, where each grid cell corresponds to an independent spatial unit with clear geometric properties.

[0075] Based on the above, according to the spatial location, geometric shape, connectivity and other characteristics of the fractures, the fracture density, fracture connectivity coefficient and integrity factor of the grid cells are calculated, so as to carry out a quantitative assessment of the rock mass integrity.

[0076] Specifically, based on the spatial connectivity of the fractures, the fracture connectivity coefficient C of each grid cell is calculated. f The formula for assessing whether there are continuous fracture channels in rock mass fissures is:

[0077]

[0078] Furthermore, based on the fracture characteristics, raster data, and connectivity analysis results obtained from the above process, the integrity of the rock mass is quantitatively assessed, including:

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

[0080] (2) For each grid cell, based on the crack density D f and connectivity coefficient C f Calculate the integrity factor I f Raster integrity is represented as a quantization factor, with the formula:

[0081] I f =1-αD f -βC f ;

[0082] Here, 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 data such as fracture density, fracture connectivity, and rock mass integrity are output. Through data visualization technology, based on the calculated fracture density, fracture connectivity, and integrity factor of each grid cell, rock mass integrity distribution maps and fracture distribution maps are generated, intuitively displaying the fracture characteristics and integrity status of the rock mass, and providing a basis for rock mass stability and safety assessment.

[0084] As one implementation method, a message-passing neural network (MPNN) is constructed. This network can pass information in a graph structure through a message-passing mechanism, enabling each node to aggregate information from its neighboring nodes. In this embodiment, the grid-based subdivision described above is used as the nodes of the MPNN network. First, each grid is quantized using the aforementioned method, i.e., the characteristics of each node are determined, such as integer factor, fracture density, and other feature values, and node attribute values ​​are assigned. Then, data / messages are passed between adjacent nodes. Each node receives and aggregates messages from its neighboring nodes, thus converging into multiple central nodes (i.e., intersection points between unit grids). The central nodes continue iterative calculations. After multiple iterations, the nodes continuously update their features and assign weighted values, gradually fusing information from more distant neighbors. After multiple iterations, the node's feature values ​​obtain global information from a wider range of graph structures, ultimately aggregating to obtain an index for classifying the integrity level of the tunnel face. Using the finally aggregated index, the integrity level of the tunnel face can be classified. This classification can intuitively present the rock mass integrity status of the tunnel face, providing a quantitative basis for judging the degree of fragmentation of the tunnel rock face.

[0085] Furthermore, the classification of the tunnel face integrity and corresponding characteristic values ​​can provide data for grouting speed. By accurately assessing rock masses with varying degrees of fracture, engineers can adjust grouting plans accordingly, such as selecting appropriate grouting materials, pressures, and volumes, thereby improving grouting effectiveness, enhancing the stability and safety of the rock mass, and ensuring the smooth progress of tunnel construction.

[0086] Example 2

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

[0088] The image acquisition module is used to acquire images of the tunnel excavation face and rock boreholes;

[0089] The image preprocessing module is used to preprocess the acquired images;

[0090] The fracture recognition module is used to input the preprocessed image into the rock fracture recognition 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 based on 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 rasterized rock mass integrity quantification module is used to divide the rock mass region into an adaptive non-uniform three-dimensional raster grid, map the geometric features, spatial location, and spatial connectivity of fractures to each raster cell, and calculate the fracture density, fracture connectivity, and integrity index value of each raster cell.

[0093] Example 3

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

[0095] Example 4

[0096] This embodiment also provides a computer-readable storage medium storing executable instructions, which, when executed by a processor, will cause the processor to execute the method described above in this embodiment.

[0097] Example 5

[0098] This embodiment provides a computer program product including executable instructions, which are computer instructions; the executable instructions are stored in a computer-readable storage medium. When the processor of an electronic device reads the executable instructions from the computer-readable storage medium and executes the executable instructions, the electronic device performs the method described in this embodiment.

[0099] The steps and methods involved in Embodiments 2 to 5 above correspond to those in Embodiment 1. For specific implementation details, please refer to the relevant description section 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 as including any medium capable of storing, encoding, or carrying an instruction set for execution by a processor and enabling the processor to perform any of the methods in this invention.

[0100] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

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

Claims

1. A method for quantifying integrity of a rock mass based on excavation and drilling images, characterized in that, The method comprises: obtaining tunnel excavation face images and rock mass drilling images; preprocessing the obtained images; inputting the preprocessed images into a rock mass fracture identification model to identify fractures and determine the geometric features and pixel coordinates of each fracture; fitting the fracture surfaces according to the geometric features and pixel coordinates of the fractures to determine the plane equations and spatial positions of the fracture surfaces, and then calculating the spatial connectivity between adjacent fracture surfaces, and analyzing the coplanarity of multiple fracture surfaces, including: The included angle of the fissure face normal vectors of two adjacent fissures and the minimum space distance between the fissures are calculated to obtain the space connectivity between the adjacent fissures, and the space connectivity calculation result is taken as the coplanarity index CI The calculation formula is: ； wherein, denote the normal vectors of the two fractures, respectively, and • denotes the vector dot product, denotes the minimum distance between the two fractures, is a set spatial distance threshold value; judging the coplanarity of two adjacent fractures according to the coplanarity index value. The rock mass region is divided into adaptive non-uniform three-dimensional grid, the geometric characteristics, spatial position and spatial connectivity of the fissure are mapped into each grid unit, the fissure density, fissure connectivity and integrity index value of each grid unit are calculated; the fissure density and connectivity coefficients are calculated according to the fissure density and connectivity The integrity factor is calculated The grid integrity is expressed as a quantitative factor, and the formula is: ； wherein and is an adjustment factor.

2. A method of quantifying the integrity of a rock mass based on images of excavations and boreholes as claimed in claim 1, characterized in that, The preprocessing includes: using a generalized gamma correction algorithm to perform contrast enhancement processing on the images to correct the images; using a gray value transfer algorithm to perform gray value equalization processing on the images.

3. A method of quantifying the integrity of a rock mass based on excavated and drilled images according to claim 1, characterized in that, The geometric features of the fractures include the length, width, dip angle and dip direction of the fractures.

4. A method of quantifying the integrity of a rock mass based on excavated and drilled images according to claim 1, characterized in that, The method further comprises calculating the fracture density, fracture connectivity and integrity index value of each grid cell, including: According to the spatial connectivity of the fissure, a fissure connectivity coefficient of each grid unit is calculated , the formula is: ； According to the number of fissures within each grid cell, the fissure density of each grid cell is calculated , the formula is: ； wherein, is the number of fractures within the grid, represents the volume of the grid.

5. A system for quantifying integrity of a grid-based rock mass based on excavation and borehole images, characterized by, The method comprises: an image acquisition module configured to obtain tunnel excavation face images and rock mass drilling images; an image preprocessing module configured to preprocess the obtained images; a fracture identification module configured to input the preprocessed images into a rock mass fracture identification model to identify fractures and determine the geometric features and pixel coordinates of each fracture; a fracture feature analysis module configured to fit the fracture surfaces according to the geometric features and pixel coordinates of the fractures to determine the plane equations and spatial positions of the fracture surfaces, and then calculate the spatial connectivity between adjacent fracture surfaces, and analyze the coplanarity of multiple fracture surfaces, including: The included angle of the fissure face normal vectors of two adjacent fissures and the minimum space distance between the fissures are calculated to obtain the space connectivity between the adjacent fissures, and the space connectivity calculation result is taken as the coplanarity index CI The calculation formula is: ； wherein, respectively denote the normal vectors of the two fractures, and · denotes the vector dot product, denotes the minimum distance between the two fractures, is a set spatial distance threshold value; judging the coplanarity of two adjacent fractures according to the coplanarity index value. The grid rock mass integrity quantification module is used for dividing the rock mass area into adaptive and non-uniform three-dimensional grid meshes, mapping the geometric features, spatial positions and spatial connectivity of the fractures into each grid cell, and calculating the fracture density, fracture connectivity and integrity index value of each grid cell; according to the fracture density and the connectivity coefficient , the integrity factor is calculated , and the grid integrity is represented as a quantification factor, and the formula is: ； wherein and is an adjustment factor.

6. An electronic device, comprising: The method comprises: a memory configured to store executable instructions; a processor configured to execute the executable instructions stored in the memory to implement the grid-based rock mass integrity quantification method based on excavation and drilling images according to any one of claims 1-4.

7. A computer readable storage medium characterized in that, The memory stores executable instructions configured to cause the processor to execute the executable instructions to implement the grid-based rock mass integrity quantification method based on excavation and drilling images according to any one of claims 1-4.

8. A computer program product, characterised in that, The computer program product comprises 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 grid-based rock mass integrity quantification method based on excavation and drilling images according to any one of claims 1-4 is implemented.

Images