Rock mass structure network connectivity index determining method and apparatus, and device

Abstract

A rock mass structure network connectivity index determining method and apparatus, and a device. The rock mass structure network connectivity index determining method comprises: identifying cracks in a target rock to obtain a crack rock image of the target rock; determining a surface crack density, a surface crack strength, and a surface crack intersection density of the target rock on the basis of the crack rock image; and determining a network connectivity index of the target rock on the basis of the surface crack density, the surface crack strength, and the surface crack intersection density.

Description

Method, device and equipment for determining rock mass structure network connectivity index

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 202311809228.0, filed on December 26, 2023, entitled “Method, device and apparatus for determining rock structure network connectivity index,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of rock mass engineering technology, and in particular to a method, device and equipment for determining a rock mass structure network connectivity index. Background Art

[0004] Under the influence of natural and human factors, cracks may form on the rock surface, causing the rock structure to lose stability, leading to geological disasters and unpredictable dangers. In this case, it is particularly important to assess rock stability based on the cracks on the rock.

[0005] In related technologies, when evaluating rock stability, precise exploration instruments are used to sample and measure rocks with cracks. The degree of influence of cracks on rock stability is quantified as the Network Connectivity Index (NCI), and the rock stability is evaluated based on the NCI.

[0006] However, the method of obtaining the network connectivity index in the related art has the problems of high measurement risk and low measurement efficiency.

[0007] Summary of the Invention

[0008] Based on this, it is necessary to provide a method, device and equipment for determining the rock structure network connectivity index to address the above technical problems, which can reduce measurement risks and improve measurement efficiency.

[0009] In the first aspect, the present application provides a method for determining the network connectivity index of a rock structure, the method comprising: identifying cracks in a target rock to obtain a crack rock image of the target rock; determining the surface crack density, surface crack strength and surface crack intersection density of the target rock based on the crack rock image; and determining the network connectivity index of the target rock based on the surface crack density, surface crack strength and surface crack intersection density.

[0010] In one embodiment, the surface crack density, surface crack strength and surface crack intersection density of the target rock are determined based on the crack rock image, including: obtaining a crack trace skeleton image of the target rock based on the crack rock image; obtaining a ratio parameter between the image size and the actual size in the crack trace skeleton image; and determining the surface crack density, surface crack strength and surface crack intersection density based on the crack trace skeleton image and the ratio parameter.

[0011] In one embodiment, a crack trace skeleton image of a target rock is obtained based on a crack rock image, including: inputting the crack rock image into an image recognition model to obtain a binary crack rock image; grayscale processing is performed on the binary crack rock image to obtain a grayscale image; and corrosion processing is performed on the grayscale image to obtain a crack trace skeleton image.

[0012] In one embodiment, the surface crack density, surface crack strength and surface crack intersection density are determined based on the crack trace skeleton image and the scale parameter, including: determining the physical area and crack length of the crack trace skeleton image according to the scale parameter; determining the surface crack strength according to the crack length and the physical area, determining the surface crack density according to the physical area and the number of cracks in the crack trace skeleton image; and determining the surface crack intersection density according to the physical area and the number of intersecting cracks in the trace skeleton image.

[0013] In one embodiment, the surface fracture density is determined based on the physical area and the number of fractures in the fracture trace skeleton image, including: obtaining a connected component graph of the fractured rock image; correcting the number of fractures based on the number of fracture groups in the connected component graph; and determining the surface fracture density as the ratio of the corrected number of fractures to the physical area.

[0014] In one embodiment, the network connectivity index of the target rock is determined based on the surface crack density, surface crack strength and surface crack intersection density, including: obtaining boundary crack criterion parameters of the fractured rock image; correcting the surface crack intersection density according to the boundary crack criterion parameters; and determining the network connectivity index of the target rock according to the surface crack density, surface crack strength and the corrected surface crack intersection density.

[0015] In one embodiment, the boundary crack criterion parameters include the number of upper boundary crack endpoints, the number of lower boundary crack endpoints, the number of left boundary crack endpoints, and the number of right boundary crack endpoints; the surface crack intersection density is corrected according to the boundary crack criterion parameters, including: determining the number of upper and lower boundary cracks according to the number of upper boundary crack endpoints, the number of lower boundary crack endpoints, and the height-to-length ratio of the crack rock image; and determining the number of left and right boundary cracks according to the number of left boundary crack endpoints, the number of right boundary crack endpoints, and the length-to-height ratio of the crack rock image; determining the ratio of the sum of the number of upper and lower boundary cracks and the number of left and right boundary cracks to the physical area of ​​the crack rock image as the compensation density of the surface crack intersection density; and correcting the surface crack intersection density by superimposing the compensation density and the surface crack intersection density.

[0016] In one embodiment, the network connectivity index of the target rock is determined based on the surface crack density, the surface crack strength and the corrected surface crack intersection density, including: determining the connectivity coefficient based on the corrected surface crack intersection density and the surface crack density; and determining the product of the connectivity coefficient and the surface crack strength as the network connectivity index of the target rock.

[0017] In one embodiment, the network connectivity index NCI is: in represents the corrected intersection density of the surface cracks; P 20 represents the surface crack density; represents the connectivity coefficient.

[0018] In one embodiment, obtaining the fracture trace skeleton image of the target rock based on the fracture rock image includes: sliding a preset filter kernel on the fracture rock image according to a preset step size to achieve noise reduction of the fracture rock image and obtain the fracture trace skeleton image of the target rock.

[0019] In one embodiment, the correction of the number of cracks according to the number of crack groups in the connected component graph includes: corresponding to the number of cracks N f With the number of crack groups N c In the same case, the number of cracks N f Or the number of crack groups N c Determined as the corrected number of cracks; corresponding to the number of cracks N f Less than the number of crack groups N c In the same case, the number of cracks N c Determined as the corrected number of cracks; corresponding to the number of cracks N f Greater than the number of crack groups N cIf they are equal, the number of adhesion cracks that meet the preset conditions in the connected component graph is determined, the number of adhesion cracks is subtracted from the number of cracks and then added 1 to obtain the corrected number of cracks.

[0020] In one embodiment, the number of upper and lower boundary cracks is: H s (X t +X b ) / W s , where H s is the rock physical height of the fracture, W s is the rock physical width of the fracture, X t is the number of upper boundary crack endpoints of the crack rock image, X b is the number of the lower boundary crack endpoints of the crack rock image; the number of the left and right boundary cracks is: W s (X l +X r ) / H s , where X l is the number of left boundary crack endpoints of the crack rock image, X r is the number of right boundary crack endpoints of the fracture rock image.

[0021] In one embodiment, the corrected surface crack intersection density is:

[0022] in, is the corrected surface crack intersection density, X int is the number of intersecting fractures in the non-boundary area of ​​the fractured rock image, X int / (H s W s ) is the surface crack intersection density before correction.

[0023] In a second aspect, the present application also provides a device for determining a rock mass structure network connectivity index, which includes: a crack identification module, a parameter determination module and an index calculation module.

[0024] The crack identification module is used to identify cracks in the target rock and obtain a crack rock image of the target rock.

[0025] The parameter determination module is used to determine the surface crack density, surface crack intensity and surface crack intersection density of the target rock based on the crack rock image.

[0026] The index calculation module is used to determine the network connectivity index of the target rock based on the surface crack density, surface crack intensity and surface crack intersection density.

[0027] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method in any one of the embodiments of the first aspect are implemented.

[0028] In a fourth aspect, the present application further provides a non-volatile computer-readable storage medium having a computer program stored thereon, which implements the steps of the method in any one of the embodiments of the first aspect when the computer program is executed by a processor.

[0029] In a fifth aspect, the present application further provides a computer program product comprising executable instructions, which, when executed by a processor, implement the steps of the method in any one of the embodiments of the first aspect above.

[0030] The above-mentioned rock mass structure network connectivity index determination method, device and equipment obtains the target rock's crack rock image by identifying the cracks in the target rock, and then determines the target rock's surface crack density, surface crack strength and surface crack intersection density based on the crack rock image. Finally, based on the surface crack density, surface crack strength and surface crack intersection density, the target rock's network connectivity index is determined. In this method, considering the potential risks brought by the presence of cracks in the target rock, the target rock is analyzed based on the crack rock image obtained by identifying the target rock, and then the network connectivity index is determined. This is equivalent to a non-contact measurement method, which has a lower risk factor than the manual measurement method in the traditional scheme. Moreover, based on the acquisition of the crack rock image, the cracks are quantitatively evaluated from multiple dimensions to determine the target rock's surface crack density, surface crack strength and surface crack intersection density, restore the interaction of the target rock cracks in the real scene, objectively and quantitatively determine the factors affecting the cracks on the target rock, and then accurately determine the target rock's network connectivity index. In addition, the method for determining the network connectivity index in this method has clear steps and is suitable for deployment on various mobile computer devices. It can analyze fractured rock images anytime and anywhere, and can scientifically, objectively, accurately and efficiently evaluate the degree of network connectivity of geological discontinuities in fractured rock masses. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] FIG1 is a diagram showing the internal structure of a computer device according to an embodiment of the present application;

[0033] FIG2 is a schematic diagram of the structure of a rock bridge and a crack in one embodiment of the present application;

[0034] FIG3 is a flow chart of a method for determining a rock mass structure network connectivity index in one embodiment of the present application;

[0035] FIG4 is a schematic flow chart of the rock physical parameter acquisition step in one embodiment of the present application;

[0036] FIG5 is a schematic flow chart of the steps of acquiring a crack trace skeleton image in one embodiment of the present application;

[0037] FIG6 is a schematic flow chart of the rock physical parameter acquisition step in another embodiment of the present application;

[0038] FIG7 is a schematic flow chart of the rock physical parameter acquisition step in another embodiment of the present application;

[0039] FIG8 is a schematic flow chart of a trace recognition step in one embodiment of the present application;

[0040] FIG9 is a schematic flow chart of the rock physical parameter acquisition step in another embodiment of the present application;

[0041] FIG10 is a schematic flow chart of a rock physical parameter correction step in one embodiment of the present application;

[0042] FIG11 is a flow chart of a method for determining a rock mass structure network connectivity index in another embodiment of the present application;

[0043] FIG12 is a flow chart of a method for determining a rock mass structure network connectivity index in another embodiment of the present application;

[0044] FIG13 is a schematic diagram of a visualization of a fractured rock image in one embodiment of the present application;

[0045] FIG14 is a schematic diagram showing a visualization of a binary fractured rock image in one embodiment of the present application;

[0046] FIG15 is a schematic diagram showing a visualization of a crack trace skeleton image in one embodiment of the present application;

[0047] FIG16 is a schematic diagram showing a visualization of a connected component graph in one embodiment of the present application;

[0048] FIG17 is a schematic diagram of a visualization of an endpoint search graph in one embodiment of the present application;

[0049] FIG18 is a visualization diagram of the steps of processing a fractured rock image corresponding to window number 1 in one embodiment of the present application;

[0050] FIG19 is a visualization diagram of the fracture rock image processing steps corresponding to window number 2 in another embodiment of the present application;

[0051] FIG20 is a visualization diagram of the fracture rock image processing steps corresponding to window number 3 in another embodiment of the present application;

[0052] FIG21 is a visualization diagram of the fracture rock image processing steps corresponding to window number 4 in another embodiment of the present application;

[0053] FIG22 is a visualization diagram of the fracture rock image processing steps corresponding to window number 5 in another embodiment of the present application;

[0054] FIG23 is a structural block diagram of a device for determining a rock mass structure network connectivity index in one embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0056] The network connectivity index determination method provided in an embodiment of the present application can be applied to image processing software. The image processing software can be deployed on a computer device, which can be a server. Its internal structure diagram can be shown in Figure 1. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data used to calculate the rock mass structure network connectivity index. The I / O interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining the rock mass structure network connectivity index.

[0057] Those skilled in the art will understand that the structure shown in FIG1 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0058] In the field of rock engineering technology, a rock bridge is an undamaged rock section that separates geological discontinuities. Its formation depends on the connectivity of the internal fracture network of the rock mass and the physical properties of the rock itself. The concept of rock bridge has always been the core of rock stability research.

[0059] Please refer to Figure 2, which shows a schematic diagram of the rock bridge and crack structure. Geological cracks can be divided into positive rock bridges and negative rock bridges based on their potential connection paths. Positive rock bridges promote downslope sliding, while negative rock bridges effectively maintain slope stability. Based on this, related technologies use the Network Connectivity Index (NCI) to quantify the impact of positive rock bridges on rock mass strength and assess rock mass stability. A higher NCI indicates a greater impact of positive rock bridges on rock mass strength and, consequently, a more unstable rock mass.

[0060] In actual scenarios, in order to fully understand the impact of geological discontinuities on the mechanical strength of rock masses, a large number of in-situ field tests and indoor tests are usually required to collect and calibrate geological parameters. This poses a huge challenge for timely warning of the long-term stability of fractured rock masses and the potential destructive behavior of rock bridges on rock masses.

[0061] Given the uncertainty and high-risk characteristics of the stability of dangerous rock masses, there is an urgent need for a valuable reference scheme for the stability assessment and support design of dangerous rock masses, which can not only quickly estimate the risk of potential rock bridges and the long-term stability of the rock mass, but also provide an effective solution in reducing manpower, material and time costs.

[0062] With the rapid development of computer vision models and image processing technologies, the recognition, measurement, and parameterization of image data have become an important non-contact monitoring method. Machine vision systems, with their rapid response, large amounts of information, high precision, and non-destructive testing capabilities, have significantly reduced time, labor, and financial costs, becoming a key technology for improving the efficiency of rock mass safety assessments. Using computer vision models to intelligently identify discrete fracture networks in natural rock slopes and using image processing to obtain morphological parameters of geological discontinuities can provide rapid and effective reference data for rock mass quality assessments.

[0063] Based on this, a comprehensive rock modeling approach combining a discrete fracture network model with a geomechanical model is proposed. This approach, in rock mass stability analysis, reveals potential mechanical failure paths and provides a quantitative assessment of rock mass strength directly related to its structural characteristics. By comprehensively considering geological parameters such as fracture intensity, density, length, and aperture, discrete fracture network analysis can be performed within the framework of a rock mass classification system, providing a quantitative method for describing rock mass discontinuities, namely, through the connectivity index of the geological discontinuity network. This approach not only considers pre-existing geological fractures but also intact sections of the rock, describing the natural fracturing and interlocking degree of the rock mass from both structural and mechanical perspectives, thereby illuminating the controlling role of rock bridges in the stability of fractured rock masses.

[0064] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0065] In an exemplary embodiment, as shown in FIG3 , a method for determining a rock mass structure network connectivity index is provided. This method is described using the computer device shown in FIG1 as an example. It is understood that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps S301 to S303.

[0066] S301, identifying cracks in the target rock to obtain a crack rock image of the target rock.

[0067] The computer device is remotely connected to the image acquisition device for communication. The computer device receives the image of the target rock sent by the image acquisition device, and inputs the image of the target rock into the crack recognition model. The crack area in the target rock image is identified by the crack recognition model to obtain at least one crack rock image of the target rock.

[0068] The image acquisition device may be a camera, an unmanned aerial vehicle (UAV) camera system, a ground photogrammetry device, a monitoring system, or other equipment with image acquisition capabilities.

[0069] In another scenario, in addition to remotely receiving images of target rocks taken by an image acquisition device, the computer device can also remotely control the image acquisition device to move and control the image acquisition device to acquire images of cracked rocks in the target rocks.

[0070] For example, the computer device and the image acquisition device share a shooting perspective. If the computer device identifies a crack in the target rock, it controls the image acquisition device to capture an image of the cracked rock and transmits it to the computer device. Accordingly, the computer device controls the image acquisition device to capture the cracked rock image and directly obtains the cracked rock image sent by the image acquisition device.

[0071] S302: Determine the surface crack density, surface crack strength, and surface crack intersection density of the target rock based on the crack rock image.

[0072] The surface crack density is the average number of cracks per unit area of ​​the target rock; the surface crack intensity is the average crack length per unit area of ​​the target rock; and the surface crack intersection density is the number of intersecting cracks per unit area of ​​the target rock. It should be noted that the surface crack density, surface crack intensity, and surface crack intersection density are all numerical values ​​in real-world scenarios and have dimensions with actual physical meaning.

[0073] The cracked rock image is inputted in parallel into a surface crack density recognition model, a surface crack strength recognition model, and a surface crack intersection density recognition model to obtain the surface crack density output by the surface crack density recognition model, the surface crack strength output by the surface crack strength recognition model, and the surface crack intersection density output by the surface crack intersection density recognition model. Of course, a hybrid model can also be used to recognize the cracked rock image and directly output the surface crack density, surface crack strength, and surface crack intersection density of the target rock, but this embodiment of the present application does not limit this.

[0074] S303: Determine the network connectivity index of the target rock based on the surface fracture density, the surface fracture strength, and the surface fracture intersection density.

[0075] The surface crack density, surface crack strength and surface crack intersection density are taken as independent variables, and the network connectivity index is taken as the dependent variable. The network connectivity index of the target rock is obtained according to the logical calculation formula of surface crack density, surface crack strength and surface crack intersection density and network connectivity index.

[0076] In the embodiment of the present application, the calculation formula of the network connectivity index NCI is as follows: NCI=I 20 ×P 21 / P 20 (1)

[0077] In the above formula, I 20 is the surface crack intersection density, P 21 is the surface crack strength, P 20 is the surface crack density.

[0078] In an embodiment of the present application, by identifying the cracks in the target rock, a crack rock image of the target rock is obtained, and then based on the crack rock image, the surface crack density, surface crack strength and surface crack intersection density of the target rock are determined, and finally based on the surface crack density, surface crack strength and surface crack intersection density, the network connectivity index of the target rock is determined. In this method, taking into account the potential risks brought by the presence of cracks in the target rock, the target rock is analyzed based on the crack rock image obtained by identifying the target rock, and then the network connectivity index is determined, which is equivalent to a non-contact measurement method. Compared with the manual measurement method in the traditional scheme, the risk factor is lower. Moreover, on the basis of obtaining the crack rock image, the cracks are quantitatively evaluated from multiple dimensions, the surface crack density, surface crack strength and surface crack intersection density of the target rock are determined, the interaction of the target rock cracks in the real scene is restored, and the influencing factors of the cracks on the target rock are objectively and quantitatively determined, and then the network connectivity index of the target rock is accurately determined. In addition, the method for determining the network connectivity index in this method has clear steps and is suitable for deployment on various mobile computer devices. It can analyze fractured rock images anytime and anywhere, and can scientifically, objectively, accurately and efficiently evaluate the degree of network connectivity of geological discontinuities in fractured rock masses.

[0079] Based on the fractured rock image, there are various ways to obtain the fracture parameters of the target rock, such as analyzing the fractured rock image based on one or more models as described in the aforementioned embodiments. However, considering factors such as color aberration and unclear cracks in the fractured rock image, it is necessary to correct the fractured rock image to improve the accuracy of the surface fracture density, surface fracture intensity, and surface fracture intersection density.

[0080] In an exemplary embodiment, as shown in FIG4 , determining the surface fracture density, surface fracture intensity, and surface fracture intersection density of the target rock based on the fractured rock image includes steps S401 to S403 .

[0081] S401, obtaining a crack trace skeleton image of the target rock according to the crack rock image.

[0082] A preset filter kernel is slid across the fractured rock image at a preset step size to reduce noise in the image and obtain a crack trace skeleton image of the target rock. In this case, since the crack trace skeleton image is a de-noised cracked rock image, the cracks in the image are clearer, facilitating subsequent crack counting in the fracture trace skeleton image.

[0083] S402 , obtaining a ratio parameter between the image size and the actual size in the crack trace skeleton image.

[0084] Among them, the scale parameter refers to the ratio between the image length in the fracture trace skeleton image and the actual length, and the unit is pixels per meter. Since the fracture trace skeleton image is obtained based on the fracture rock image, the scale parameter is also the ratio between the image length in the fracture rock image and the actual length.

[0085] When shooting target rock images or crack rock images, due to differences in crack length and complexity, it is necessary to adaptively adjust the focal length of the lens of the shooting equipment to obtain clearer target rock images or crack rock images.

[0086] S403 , determining the surface crack density, surface crack strength, and surface crack intersection density based on the crack trace skeleton image and the scale parameter.

[0087] The fracture trace skeleton image is rendered using proportional parameters to obtain the actual length of the fractures, the total number of fractures, the number of intersecting fractures, and the actual area of ​​the fractured rock region in the actual scene. Based on these parameters, the surface fracture density, surface fracture intensity, and surface fracture intersection density are calculated.

[0088] In the embodiment of the present application, the crack trace skeleton image is used as the basis and rendered using proportional parameters to restore the interaction between the cracks in the target rock in the real scene, and objectively and accurately obtain the surface crack density, surface crack strength and surface crack intersection density parameters related to the cracks in the target rock.

[0089] Another implementation of obtaining the fracture trace skeleton image in S401 in the above embodiment is described below through an embodiment. In an exemplary embodiment, as shown in FIG5 , obtaining the fracture trace skeleton image of the target rock based on the fracture rock image includes steps S501 to S503 .

[0090] S501: Input the fractured rock image into an image recognition model to obtain a binary fractured rock image.

[0091] The image recognition model can be a deep learning computer vision model framework, such as the Unet model. In addition, the image recognition model in the embodiment of the present application uses the Inception ResnetV2 encoder, combined with the scale hybridization module, to enhance the accuracy and robustness of the image recognition model in identifying multi-scale linear crack structures.

[0092] Taking the Unet model as an example of an image recognition model, the crack area in the crack rock image is identified by the Unet model, and a binary crack rock image is output.

[0093] In the binary fracture rock image, the pixel value 255 represents the fracture structure and appears white in the binary fracture rock image, and the pixel value 0 represents the background of the target rock and appears black in the binary fracture rock image.

[0094] S502: grayscale processing is performed on the binary fracture rock image to obtain a grayscale image.

[0095] Among them, the binary fracture rock image is a red, green, and blue (RGB) three-channel image. In order to further improve the quality of the binary fracture rock image, enable the binary fracture rock image to show more details of the fractures, and improve the contrast of the binary fracture rock image, the binary fracture rock image is grayscaled to obtain a grayscale image.

[0096] In the grayscale image, the pixel value 1 represents the fracture structure and appears white in the grayscale image, and the pixel value 0 represents the background of the target rock and appears black in the grayscale image.

[0097] S503: performing corrosion processing on the grayscale image to obtain a crack trace skeleton image.

[0098] The image morphological processing algorithm is used to set the number of image corrosion times and corrosion structural elements, and the grayscale image is corroded to obtain a crack trace skeleton image with a crack width of one pixel.

[0099] In an embodiment of the present application, the contrast between the foreground (cracks) and background (noise) in the crack rock image is improved by sequentially performing binarization, grayscale conversion, and morphological corrosion processing on the crack rock image. The crack trace skeleton image obtained in this way can more clearly and clearly characterize the details of the crack structure in the crack rock image, so as to obtain more accurate crack parameters.

[0100] The following example further illustrates how to obtain the surface crack density, surface crack strength, and surface crack intersection density in S403 of the aforementioned embodiment. In one exemplary embodiment, as shown in FIG6 , determining the surface crack density, surface crack strength, and surface crack intersection density based on a crack trace skeleton image and a scale parameter includes steps S601 and S602.

[0101] S601 : Determine the physical area and crack length of the crack trace skeleton image according to the scale parameter.

[0102] Taking the scale parameter of the crack trace skeleton image as PPM as an example, the unit of PPM is pixels per meter, which is a value less than 1; if the image height is H and the image width is W, then the physical height H of the crack trace skeleton image is s The expression is as follows:

[0103] The physical width W of the crack trace skeleton image s The expression is as follows:

[0104] The expression of the physical area Area of ​​the crack trace skeleton image is as follows: Area = H s ×W s (4)

[0105] Crack length L of the crack trace skeleton image f The expression is as follows:

[0106] In the above expression, M f is the number of pixels occupied by the crack in the crack trace skeleton image.

[0107] S602, determining the surface crack strength according to the crack length and physical area, determining the surface crack density according to the physical area and the number of cracks in the crack trace skeleton image; and determining the surface crack intersection density according to the physical area and the number of intersecting cracks in the trace skeleton image.

[0108] When the number of cracks and the number of intersecting cracks in the crack trace skeleton image are obtained, the ratio of crack length to physical area can be determined as the surface crack intensity; the ratio of the number of cracks to physical area can be determined as the surface crack density; and the ratio of the number of intersecting cracks to physical area can be determined as the surface crack intersection density.

[0109] In an embodiment of the present application, the actual size of the crack corresponding to the crack trace skeleton image and the actual area of ​​the crack rock area are obtained according to the proportional parameters, and the surface crack strength, surface crack density and surface crack intersection density are further determined. The dimensions of each crack parameter determined in this way are consistent with the dimensions of the actual engineering field, which facilitates the test personnel to read each parameter during the test process.

[0110] The fracture trace skeleton image is obtained by performing a series of image processing methods based on the fractured rock image, including binarization, grayscale conversion, and corrosion. Although this processing process can enhance the contrast between cracks and noise in the fracture trace skeleton image, it also loses the actual width of the cracks to a certain extent. In particular, multiple corrosion processes may corrode a single crack into two or even more cracks. The obtained crack count is obviously inaccurate, and the surface crack density obtained based on the crack count is also inaccurate. The following example illustrates another possible method for determining crack density on a surface.

[0111] In an exemplary embodiment, as shown in FIG7 , determining the surface crack density according to the physical area and the number of cracks in the crack trace skeleton image includes steps S701 to S703 .

[0112] S701, obtaining a connected component graph of a fractured rock image.

[0113] Based on the fracture trace skeleton image of the fracture rock image, an 8-neighborhood search algorithm is used. With any point on the non-image boundary as the center and the surrounding 8 neighborhood pixel squares as the search target, the area with a pixel value of 1 is searched to obtain a connected complete trace and a connected component graph.

[0114] Please refer to Figure 8, which is a schematic diagram of the 8-neighborhood search algorithm for obtaining crack traces. Among the nine pixels shown in Figure 8, the pixel points with a pixel value of 1 are connected to construct a trace.

[0115] To more clearly contrast the cracks shown in the connected component map with those shown in the crack trace skeleton image, the connected component map can be inverted. This inverted color process will cause the cracks to appear black and the background to appear white. Furthermore, the different cracks in the connected component map can be randomly filled with different colors, resulting in a connected component map with a white background and different cracks in different colors.

[0116] S702: Modify the number of cracks according to the number of crack groups in the connected component graph.

[0117] The number of cracks is obtained by computer equipment based on the crack trace skeleton image statistics, denoted as N f The number of crack groups is obtained by the computer equipment based on the statistics of the connected areas in the connected component graph, denoted as N c .

[0118] In this embodiment of the present application, by comparing the number of cracks (N f ) and the number of connected fracture groups in the connected component graph (N c ), the number of cracks in the crack trace skeleton image (N f ) to make corrections. There are three situations:

[0119] (1)N f With N c If they are equal, it means that there is no adhesion of cracks in the crack trace skeleton image, and there is no need to correct the number of cracks. Then, N f or N c Determined as the corrected number of cracks.

[0120] (2)N f Less than N c, which means that some cracks in the crack trace skeleton image are too small and are corroded during the image processing process, resulting in some cracks being missed. Then the number of connected cracks N is set to c Determined as the corrected number of cracks.

[0121] (3)N f Greater than N c , which means that there are multiple cracks in the crack trace skeleton image, which are decomposed by multiple corrosion of a real crack, resulting in the number of cracks N in the crack trace skeleton image. f If it is too high, the number of connected cracks N c The corrected number of cracks is determined. In another scenario, the corrected number of cracks can be obtained by determining the number of adhesion cracks that meet the preset conditions in the connected component graph, subtracting the number of adhesion cracks from the number of cracks and adding 1. The preset condition is that there are two cracks in the connected component graph that are close to each other and are in a connected component. For example, if the number of adhesion cracks is x, the corrected number of cracks is: N f -x+1.

[0122] S703: Determine the ratio of the corrected number of cracks to the physical area as the surface crack density.

[0123] In an embodiment of the present application, the number of cracks obtained based on the crack trace skeleton image is corrected according to the number of crack groups in the connected component graph, thereby avoiding the omission or miscounting of the number of cracks in the crack trace skeleton image, improving the accuracy of the number of cracks, and further improving the accuracy of calculating the surface crack density based on the number of cracks.

[0124] When counting cracks in a fractured rock image, factors such as the image not being a regular rectangle or the cracks in the image being incomplete may result in missed detections of intersecting cracks, leading to lower accuracy in the surface fracture intersection density and, consequently, lower accuracy in the resulting network connectivity index. Based on this, the following describes a method for obtaining the network connectivity index using an example.

[0125] In an exemplary embodiment, as shown in FIG9 , the network connectivity index of the target rock is determined based on the surface fracture density, the surface fracture strength and the surface fracture intersection density, including steps S901 to S903 .

[0126] S901, obtaining boundary crack criterion parameters of the fractured rock image.

[0127] Among them, the boundary crack criterion parameters include the number of upper boundary crack endpoints X of the fracture rock image t , the number of lower boundary crack endpoints X b , the number of left boundary crack endpoints X land the number of right boundary crack endpoints X r .

[0128] S902: Correct the intersection density of surface cracks according to the boundary crack criterion parameters.

[0129] In an exemplary embodiment, as shown in FIG10 , the surface crack intersection density is corrected according to the boundary crack criterion parameters, including steps S1001 to S1003 .

[0130] S1001, determine the number of upper and lower boundary cracks based on the number of upper boundary crack endpoints, the number of lower boundary crack endpoints, and the height-to-length ratio of the crack rock image; and determine the number of left and right boundary cracks based on the number of left boundary crack endpoints, the number of right boundary crack endpoints, and the length-to-height ratio of the crack rock image.

[0131] The expression of the number of upper and lower boundary cracks is: H s (X t +X b ) / W s , where H s is the physical height of the fracture rock, W s is the fracture rock physical width, X t is the number of upper boundary crack endpoints of the fracture rock image, X b is the number of lower boundary crack endpoints of the fracture rock image.

[0132] The expression for the number of cracks on the left and right boundaries is: W s (X l +X r ) / H s , where H s is the physical height of the fracture rock, W s is the fracture rock physical width, X l is the number of left boundary crack endpoints of the crack rock image, X r is the number of right boundary crack endpoints of the fracture rock image.

[0133] S1002: Determine the ratio of the sum of the number of upper and lower boundary cracks and the number of left and right boundary cracks to the physical area of ​​the cracked rock image as the compensation density of the surface crack intersection density.

[0134] The expression of the compensation density of the surface crack intersection density is:

[0135] In the above expression, H s is the physical height of the fracture rock image, W s is the physical width of the fracture rock image, H s W s is the physical area of ​​the fractured rock image.

[0136] S1003, correcting the surface crack intersection density by superimposing the compensation density and the surface crack intersection density.

[0137] The corrected expression of surface crack intersection density is:

[0138] In the above expression, is the corrected surface crack intersection density, X int is the number of intersecting fractures in the non-boundary area of ​​the fractured rock image; X int / (H s W s ) is the surface crack intersection density before correction.

[0139] In the embodiment of the present application, taking into account the shape effect and truncation effect that may occur in the statistical process, the crack intersection density on the boundary is obtained according to the boundary crack criterion parameters, and it is superimposed on the surface crack intersection density to achieve compensation for the surface crack intersection density and improve the accuracy of the surface crack intersection density.

[0140] S903: Determine the network connectivity index of the target rock based on the surface fracture density, the surface fracture intensity, and the corrected surface fracture intersection density.

[0141] The surface crack density, surface crack strength and corrected surface crack intersection density are used as independent variables, and the network connectivity index is used as the dependent variable. The network connectivity index of the target rock is obtained according to the logical calculation formula of the surface crack density, surface crack strength and corrected surface crack intersection density and the network connectivity index.

[0142] In the embodiment of the present application, the surface crack intersection density is corrected according to the boundary crack criterion parameters to improve the accuracy of the surface crack intersection density. On this basis, the network connectivity index determined according to the corrected surface crack intersection density is also more accurate.

[0143] The following further illustrates how to determine the network connectivity index using an example embodiment. In one exemplary embodiment, as shown in FIG11 , the network connectivity index of a target rock is determined based on the surface fracture density, surface fracture intensity, and corrected surface fracture intersection density, including steps S1101 and S1102.

[0144] S1101: Determine the connectivity coefficient based on the corrected surface crack intersection density and surface crack density.

[0145] The connectivity coefficient is calculated by calculating the ratio of the corrected surface fracture intersection density to the surface fracture density. The connectivity coefficient is positively correlated with the network connectivity index. The larger the connectivity coefficient, the larger the network connectivity index, and correspondingly, the more unstable the target rock.

[0146] The corrected surface crack intersection density is The surface crack density is P 20 For example, the expression of connectivity coefficient is

[0147] S1102: The product of the connectivity coefficient and the surface fracture strength is determined as the network connectivity index of the target rock.

[0148] The corrected surface crack intersection density is The surface crack density is P 20 , surface crack strength example is P 21 , the expression of network connectivity index NCI:

[0149] In an embodiment of the present application, the connectivity coefficient of the target rock is evaluated based on the corrected surface crack intersection density and surface crack density, and then the network connectivity index of the target rock is obtained based on the product of the connectivity coefficient and the surface crack strength, so as to objectively and accurately evaluate the stability of the target rock.

[0150] In an exemplary embodiment, as shown in FIG12 , a method for determining a rock mass structure network connectivity index is provided, and the method includes steps S1201 to S1214 .

[0151] S1201, identifying cracks in the target rock to obtain a crack rock image of the target rock.

[0152] Please refer to FIG13 , which is a visualization diagram of a fractured rock image. In practical applications, the fractured rock image is an RGB three-channel image.

[0153] Optionally, use Matlab image processing software to write a code file for determining the network connectivity index. When running the code file, the calculation code and image data are in the same directory to facilitate common use of the defined function. The data is read using Matlab's default imread() function.

[0154] S1202: Input the fractured rock image into an image recognition model to obtain a binary fractured rock image.

[0155] Please refer to Figure 14, which is a visualization diagram of the binary fracture rock image. In practical applications, the binary fracture rock image is an RGB three-channel image, where the pixel value 255 represents the fracture structure and appears white, and the pixel 0 represents the rock background and appears black.

[0156] Optionally, Matlab image processing software is used for binarization processing, and the three-channel image data is converted into a single-channel binary image using the imbinarize() function, where the method parameter is set to "global".

[0157] S1203: grayscale processing is performed on the binary fracture rock image to obtain a grayscale image.

[0158] Optionally, Matlab image processing software is used for grayscale processing, and the rgb2gray() function provided by Matlab is used to process and identify the binary fracture rock image to obtain a grayscale image.

[0159] S1204: performing corrosion processing on the grayscale image to obtain a crack trace skeleton image.

[0160] Please refer to Figure 15, which is a visualization diagram of the fracture trace skeleton image. In practical applications, the fracture trace skeleton image is a single-channel image, where pixel value 1 represents the fracture structure and appears white, and pixel 0 represents the rock background and appears black.

[0161] Optionally, Matlab image processing software is used for corrosion processing, and the bwmorph() function provided by Matlab is used to implement it, and the method parameters are set to "thin" and the number of corrosion times is 40.

[0162] S1205 , obtaining a ratio parameter between the image size and the actual size in the crack trace skeleton image.

[0163] S1206 , determining the physical area and crack length of the crack trace skeleton image according to the scale parameter.

[0164] S1207, obtaining a connected component graph of the fractured rock image; correcting the number of fractures according to the number of fracture groups in the connected component graph; and determining the ratio of the corrected number of fractures to the physical area as the surface fracture density.

[0165] Please refer to Figure 16, which is a visualization diagram of the connected component graph. In actual application, different cracks in the connected component graph are randomly filled with different colors, and the rock background is white.

[0166] Moreover, when counting the number of crack groups in the connected component graph, endpoint search is performed by traversing all pixel points on the boundary of the connected component image, as shown in FIG17 , which is a visualization diagram of the endpoint search graph; if the connected trace contains only one crack, the endpoint of the crack is set to a circle; if there are two cracks in the connected trace and they are connected, the connection point of the two cracks is set to a cross; if there are two edges in the connected trace and they intersect, the intersection point of the two cracks is set to a five-pointed star.

[0167] Optionally, Matlab image processing software is used to identify and process connected regions, and the bwlabel() function is used to extract the connected component map of the fracture network structure, and the label2rgb() function is used to count the number of connected components and number them.

[0168] S1208 , determining a surface crack density based on the physical area and the number of cracks in the crack trace skeleton image; and determining a surface crack intersection density based on the physical area and the number of intersecting cracks in the trace skeleton image.

[0169] S1209, obtaining boundary crack criterion parameters of the cracked rock image.

[0170] The boundary crack criterion parameters include the number of upper boundary crack endpoints, the number of lower boundary crack endpoints, the number of left boundary crack endpoints, and the number of right boundary crack endpoints.

[0171] S1210, determining the number of upper and lower boundary cracks based on the number of upper boundary crack endpoints, the number of lower boundary crack endpoints, and the height-to-length ratio of the crack rock image; and determining the number of left and right boundary cracks based on the number of left boundary crack endpoints, the number of right boundary crack endpoints, and the length-to-height ratio of the crack rock image.

[0172] S1211: The ratio of the sum of the number of upper and lower boundary cracks and the number of left and right boundary cracks to the physical area of ​​the cracked rock image is determined as the compensation density of the surface crack intersection density.

[0173] S1212, correcting the surface crack intersection density by superimposing the compensation density and the surface crack intersection density.

[0174] S1213: Determine the connectivity coefficient based on the corrected surface crack intersection density and surface crack density.

[0175] S1214: The product of the connectivity coefficient and the surface fracture strength is determined as the network connectivity index of the target rock.

[0176] In an embodiment of the present application, by identifying the cracks in the target rock, a crack rock image of the target rock is obtained, and then based on the crack rock image, the surface crack density, surface crack strength and surface crack intersection density of the target rock are determined, and finally based on the surface crack density, surface crack strength and surface crack intersection density, the network connectivity index of the target rock is determined. In this method, taking into account the potential risks brought by the presence of cracks in the target rock, the target rock is analyzed based on the crack rock image obtained by identifying the target rock, and then the network connectivity index is determined, which is equivalent to a non-contact measurement method. Compared with the manual measurement method in the traditional scheme, the risk factor is lower. Moreover, on the basis of obtaining the crack rock image, the cracks are quantitatively evaluated from multiple dimensions, the surface crack density, surface crack strength and surface crack intersection density of the target rock are determined, the interaction of the target rock cracks in the real scene is restored, and the influencing factors of the cracks on the target rock are objectively and quantitatively determined, and then the network connectivity index of the target rock is accurately determined. In addition, the method for determining the network connectivity index in this method has clear steps and is suitable for deployment on various mobile computer devices. It can analyze fractured rock images anytime and anywhere, and can scientifically, objectively, accurately and efficiently evaluate the degree of network connectivity of geological discontinuities in fractured rock masses.

[0177] To further verify the network connectivity index determination method provided in the examples of this application, rock sampling was conducted in a study area located at 36.26516804°N, 116.94287360°E, and 210m above sea level, and the network connectivity index determination method was used for processing. The lithology of the study area is mainly Late Mesozoic diorite and Archean granite gneiss, mostly high and steep rock slopes, with strong weathering and obvious erosion on the geological outcrops. A large number of secondary weathering cracks are distributed on the rock surface. The rock mass has an overall blocky structure and extremely complex tectonic processes. A large number of joints, cracks, and faults are distributed on the rock surface. The hydrogeological conditions are good, and many fissure water outcrops and algae can be seen.

[0178] In this example, five rock fracture images were compared, as shown in Figures 18 to 22. For each set of images shown in Figures 18 to 22: (a) is the fractured rock image; (b) is the binarized fractured rock image; (c) is the connected component graph based on the binary recognition results of the statistical window; and (d) is an overlay of the fracture trace skeleton image and the endpoint search graph after image morphology processing. The fracture statistical parameters and network connectivity index obtained after image processing are shown in Table 1. Table 1 shows the statistical results of the physical parameters of the five rock locations.

[0179] Table 1

[0180] In the embodiment of the present application, the trace network obtained based on computer vision model recognition can restore the interaction form of the real fracture network in the actual site to the maximum extent. It is different from the fracture evaluation system based on the simplified trace network model that counts the number and length of fractures from the perspectives of lines, surfaces, and bodies. It reduces the workload and subjectivity brought by manual data processing to a certain extent, and provides a scientific, objective, accurate and efficient method for evaluating the connectivity of the geological discontinuity surface network of fractured rock masses.

[0181] In summary, the rock mass structure network connectivity index determination method proposed in the embodiment of the present application can quickly and accurately evaluate the network connectivity index and other key fracture statistical parameters by using the image data of fractured rocks. This non-contact and rapid method for obtaining the fracture surface density (P 20 ), surface strength (P 21 ) and surface intersection density (I 20 ) significantly reduces the workload of statistical measurements of geological fractures on-site in rock mass engineering projects. Furthermore, by calculating the corrected surface fracture intersection density and obtaining the Network Connectivity Index (NCI) of geological discontinuities, this method improves the timeliness of statistical measurements of geological discontinuities, avoids human errors caused by long-term fatigue work, and avoids measurement errors caused by truncation and shape effects during the statistical process. This improves work efficiency while ensuring real-time data and accurate fracture identification, reducing on-site work risks.

[0182] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0183] Based on the same inventive concept, embodiments of the present application also provide a network connectivity index determination device for implementing the aforementioned network connectivity index determination method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the network connectivity index determination device provided below can be found in the above-mentioned limitations of the network connectivity index determination method and will not be repeated here.

[0184] In an exemplary embodiment, as shown in FIG23 , a device for determining a rock mass structure network connectivity index is provided, including: a crack identification module 2301 , a parameter determination module 2302 and an index calculation module 2303 .

[0185] The crack identification module 2301 is used to identify cracks in the target rock and obtain a crack rock image of the target rock.

[0186] The parameter determination module 2302 is used to determine the surface crack density, surface crack strength and surface crack intersection density of the target rock based on the crack rock image.

[0187] The index calculation module 2303 is used to determine the network connectivity index of the target rock based on the surface fracture density, surface fracture intensity and surface fracture intersection density.

[0188] In an exemplary embodiment, the parameter determination module 2302 includes a trace acquisition unit, a ratio acquisition unit, and a parameter determination unit.

[0189] The trace acquisition unit is used to acquire a crack trace skeleton image of the target rock according to the crack rock image.

[0190] The ratio acquisition unit is used to obtain the ratio parameter between the image size and the actual size in the crack trace skeleton image.

[0191] The parameter determination unit is used to determine the surface crack density, surface crack intensity and surface crack intersection density based on the crack trace skeleton image and the scale parameter.

[0192] In an exemplary embodiment, the trace acquisition unit includes a binarization processing subunit, a grayscale processing subunit, and an corrosion subunit.

[0193] The binarization processing subunit is used to input the fractured rock image into the image recognition model to obtain a binarized fractured rock image.

[0194] The grayscale processing subunit is used to perform grayscale processing on the binary fracture rock image to obtain a grayscale image.

[0195] The corrosion subunit is used to perform corrosion processing on the grayscale image to obtain a crack trace skeleton image.

[0196] In an exemplary embodiment, the parameter determination unit includes a first acquisition subunit and a second acquisition subunit.

[0197] The first acquisition subunit is used to determine the physical area and crack length of the crack trace skeleton image according to the scale parameter.

[0198] The second acquisition subunit is used to determine the surface crack strength based on the crack length and physical area, determine the surface crack density based on the physical area and the number of cracks in the crack trace skeleton image, and determine the surface crack intersection density based on the physical area and the number of intersecting cracks in the trace skeleton image.

[0199] In an exemplary embodiment, the second acquisition subunit is further used to obtain a connected component graph of the fractured rock image; correct the number of fractures according to the number of fracture groups in the connected component graph; and determine the ratio of the corrected number of fractures to the physical area as the surface fracture density.

[0200] In an exemplary embodiment, the index calculation module 2303 includes a criterion acquisition unit, a density correction unit, and an index acquisition unit.

[0201] The criterion acquisition unit is used to obtain boundary crack criterion parameters of the fractured rock image.

[0202] The density correction unit is used to correct the intersection density of surface cracks according to the boundary crack criterion parameters.

[0203] The index acquisition unit is used to determine the network connectivity index of the target rock according to the surface crack density, the surface crack intensity and the corrected surface crack intersection density.

[0204] In an exemplary embodiment, the density correction unit includes a first determination subunit, a second determination subunit, and a density superposition subunit.

[0205] The first determination subunit is used to determine the number of upper and lower boundary cracks based on the number of upper boundary crack endpoints, the number of lower boundary crack endpoints and the height-to-length ratio of the crack rock image, and to determine the number of left and right boundary cracks based on the number of left boundary crack endpoints, the number of right boundary crack endpoints and the length-to-height ratio of the crack rock image.

[0206] The second determining subunit is used to determine the ratio of the sum of the upper and lower boundary crack numbers and the left and right boundary crack numbers to the physical area of ​​the fractured rock image as the compensation density of the surface fracture intersection density.

[0207] The density superposition subunit is used to correct the surface crack intersection density by superimposing the compensation density and the surface crack intersection density.

[0208] In an exemplary embodiment, the index acquisition unit includes a coefficient determination subunit and a connectivity calculation subunit.

[0209] The coefficient determination subunit is used to determine the connectivity coefficient according to the corrected surface crack intersection density and surface crack density.

[0210] The connectivity calculation subunit is used to determine the product of the connectivity coefficient and the surface fracture strength as the network connectivity index of the target rock.

[0211] Each module in the rock mass structural network connectivity index determination device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0212] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0213] In an exemplary embodiment, a non-volatile computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0214] In an exemplary embodiment, a computer program product is provided, including executable instructions, which implement the steps in the above method embodiments when executed by a processor.

[0215] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0216] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0217] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0218] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for determining the network connectivity index of a rock mass structure, characterized in that, The method includes: Identifying fractures in the target rock to obtain a fracture rock image of the target rock; Determining the surface fracture density, surface fracture intensity, and surface fracture intersection density of the target rock according to the fracture rock image; Determining the network connectivity index of the target rock based on the surface fracture density, the surface fracture intensity, and the surface fracture intersection density.

2. The method according to claim 1, wherein The determining the surface fracture density, surface fracture intensity, and surface fracture intersection density of the target rock according to the fracture rock image includes: Obtaining a fracture trace skeleton image of the target rock according to the fracture rock image; Obtaining a scale parameter between the image size and the actual size in the fracture trace skeleton image; Determining the surface fracture density, the surface fracture intensity, and the surface fracture intersection density based on the fracture trace skeleton image and the scale parameter.

3. The method according to claim 2, wherein The obtaining a fracture trace skeleton image of the target rock according to the fracture rock image includes: Inputting the fracture rock image into an image recognition model to obtain a binary fracture rock image; Performing grayscale processing on the binary fracture rock image to obtain the grayscale image; Performing erosion processing on the grayscale image to obtain the fracture trace skeleton image.

4. The method according to claim 2 or 3, characterized in that, The determining the surface fracture density, the surface fracture intensity, and the surface fracture intersection density based on the fracture trace skeleton image and the scale parameter includes: Determining the physical area and fracture length of the fracture trace skeleton image according to the scale parameter; Determining the surface fracture intensity according to the fracture length and the physical area, determining the surface fracture density according to the physical area and the number of fractures in the fracture trace skeleton image, and determining the surface fracture intersection density according to the physical area and the number of intersecting fractures in the trace skeleton image.

5. The method according to claim 4, characterized in that, The determining the surface fracture density according to the physical area and the number of fractures in the fracture trace skeleton image includes: Obtaining a connected component map of the fracture rock image; Correcting the number of fractures according to the number of fracture groups in the connected component map; Determining the ratio of the corrected number of fractures to the physical area as the surface fracture density.

6. The method according to any one of claims 1-5, characterized in that, The determining the network connectivity index of the target rock based on the surface fracture density, the surface fracture intensity, and the surface fracture intersection density includes: Obtaining a boundary fracture criterion parameter of the fracture rock image; Correcting the surface fracture intersection density according to the boundary fracture criterion parameter; Determining the network connectivity index of the target rock according to the surface fracture density, the surface fracture intensity, and the corrected surface fracture intersection density.

7. The method according to claim 6, wherein The boundary fracture criterion parameter includes the number of upper boundary fracture endpoints, the number of lower boundary fracture endpoints, the number of left boundary fracture endpoints, and the number of right boundary fracture endpoints; The correcting the surface fracture intersection density according to the boundary fracture criterion parameter includes: Determining the number of upper and lower boundary fractures according to the number of upper boundary fracture endpoints, the number of lower boundary fracture endpoints, and the height-length ratio of the fracture rock image; Moreover, determine the left and right boundary fracture numbers according to the number of left boundary fracture endpoints, the number of right boundary fracture endpoints, and the length-height ratio of the fracture rock image; Determine the compensation density of the surface fracture intersection density as the ratio of the sum of the upper and lower boundary fracture numbers and the left and right boundary fracture numbers to the physical area of the fracture rock image; Correct the surface fracture intersection density by superimposing the compensation density and the surface fracture intersection density.

8. The method according to claim 6 or 7, characterized in that, The determining of the network connectivity index of the target rock according to the surface fracture density, the surface fracture strength, and the corrected surface fracture intersection density includes: Determine the connectivity coefficient according to the corrected surface fracture intersection density and the surface fracture density; Determine the product result of the connectivity coefficient and the surface fracture strength as the network connectivity index of the target rock.

9. The method according to claim 8, characterized in that, The network connectivity index NCI is as follows: Among them Represents the corrected intersection density of the surface cracks; P 20 Represents the surface crack density; Denote the connectivity coefficient.

10. The method according to claim 2, characterized in that The obtaining of the fracture trace skeleton image of the target rock according to the fracture rock image includes: Perform a sliding process on the fracture rock image with a preset filter kernel at a preset step length to reduce the noise of the fracture rock image and obtain the fracture trace skeleton image of the target rock.

11. The method according to claim 5, wherein The correction of the fracture number according to the number of fracture groups in the connected component map includes: corresponding to the number of cracks N f and the number of crack groups N c in the case of equality, the number of cracks N f or the number of crack groups N c is determined as the corrected number of cracks; corresponding to the number N of the cracks f less than the number N of the crack groups c in the case of equality, take the number N of the cracks c as the corrected number of cracks; corresponding to the number N of the cracks f greater than the number N of crack groups c in the case of equality, determining the number of adhered cracks in the connected component graph that meet the preset conditions, subtracting the number of adhered cracks from the number of cracks and then adding 1 to obtain the corrected number of cracks.

12. The method according to claim 7, wherein: The number of upper and lower boundary cracks is: H s (X t + X b ) / W s , where H s is the physical height of the cracked rock, W s is the physical width of the cracked rock, X t is the number of upper boundary crack endpoints of the cracked rock image, and X b is the number of lower boundary crack endpoints of the cracked rock image; The number of left and right boundary cracks is: W s (X l +X r ) / H s , where X l is the number of left boundary crack endpoints of the crack rock image, and X r is the number of right boundary crack endpoints of the crack rock image.

13. The method according to claim 12, characterized in that: The corrected surface crack intersection density is as follows: Among them, X is the corrected surface crack intersection density int X is the number of intersecting cracks in the non-boundary area of the crack rock image int / (H s W s ) is the surface crack intersection density before correction 14. A device for determining the network connectivity index of a rock mass structure, characterized in that, The device includes: A fracture identification module for identifying fractures in a target rock to obtain a fracture rock image of the target rock; A parameter determination module for determining the surface fracture density, the surface fracture strength, and the surface fracture intersection density of the target rock according to the fracture rock image; An index calculation module for determining the network connectivity index of the target rock based on the surface fracture density, the surface fracture strength, and the surface fracture intersection density. rock.

15. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 13 are implemented.

Images