Rock quality determination method and apparatus, and computer device and storage medium

Abstract

A rock quality determination method and apparatus, and a computer device and a storage medium. The rock quality determination method comprises: acquiring a rock outcrop image; inputting the rock outcrop image into an intelligent identification model for fracture network trace identification, so as to obtain a fracture network trace map corresponding to the rock outcrop image; classifying fracture nodes in the fracture network trace map, so as to obtain types of the fracture nodes; and on the basis of the types of the fracture nodes, determining rock quality parameters corresponding to the rock outcrop image.

Description

Method, device, computer equipment and storage medium for determining rock quality

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 202311806094.7, filed on December 26, 2023, entitled “Method, device, computer equipment and storage medium for determining rock quality,” 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, computer equipment, and storage medium for determining rock quality. Background Art

[0004] Fractured rock masses are often cut by multiple sets of structural planes, forming steep slopes that are difficult to measure and access. Due to internal and external geological forces, defects such as cracks, pores, joints, faults, and microcracks develop on and within the rock surface. Under load and weathering, these defects evolve, leading to collapse and landslides.

[0005] Therefore, the assessment of rock quality has become an urgent problem to be solved. Currently, the method for determining rock quality is mainly completed through long-term field surveys by experienced geologists, expensive drill core analysis and tedious geological statistical measurements.

[0006] Therefore, the above-mentioned method for determining rock quality has the problems of low timeliness and poor safety.

[0007] Summary of the Invention

[0008] Based on this, it is necessary to provide a rock quality determination method, device, computer equipment and storage medium that can improve the efficiency of rock quality determination and ensure the safety of the measurement process in order to address the above technical problems.

[0009] In the first aspect, the present application provides a method for determining rock quality, including: obtaining a rock outcrop image; inputting the rock outcrop image into an intelligent recognition model to perform crack network trajectory identification, and obtaining a crack network trace diagram corresponding to the rock outcrop image; classifying each crack node in the crack network trace diagram to obtain the type of each crack node; and determining the rock quality parameters corresponding to the rock outcrop image according to the type of each crack node.

[0010] In one embodiment, the intelligent recognition model includes a positioning model and a segmentation model. The rock outcrop image is input into the intelligent recognition model to perform fracture network trajectory recognition, and a fracture network trace map corresponding to the rock outcrop image is obtained, including:

[0011] Input the rock outcrop image into the positioning model to locate the crack position and obtain a positioning image;

[0012] The positioning image is input into the segmentation model to perform fracture area image segmentation, and the fracture network trace map corresponding to the rock outcrop image is obtained.

[0013] In one embodiment, the above-mentioned inputting the positioning image into the segmentation model to perform crack area image segmentation to obtain a crack network trace map corresponding to the rock outcrop image includes: inputting the positioning image into the segmentation model to perform crack area image segmentation to obtain a segmented image; binarizing the segmented image to obtain a binary image corresponding to the segmented image; refining the crack network lines in the binary image to obtain a processed binary image; and connecting the crack network lines in the binary image to obtain a crack network trace map.

[0014] In one embodiment, the above-mentioned classification of each crack node in the crack network trace diagram to obtain the type of each crack node includes: obtaining the nodes of each crack network line in the crack network trace diagram; corresponding to the case where the node is a node on the boundary of the crack network trace diagram and the pixel value of the node is a first value, determining the sum of the pixel values ​​of other nodes adjacent to the node; corresponding to the sum of the pixel values ​​of other nodes adjacent to the node being determined as the first value, the node is a node of the first type; corresponding to the sum of the pixel values ​​of other nodes adjacent to the node being determined as a second value, the node is a node of the second type.

[0015] In one embodiment, if the above-mentioned node is a node on a non-boundary of a fracture network trace graph, the above-mentioned classification of each fracture node in the fracture network trace graph to obtain the type of each fracture node includes: when the pixel value of the node is the first value, determining the sum of the pixel values ​​of other nodes adjacent to the node; when the sum of the pixel values ​​of other nodes adjacent to the node is determined to be the first value, the node is a node of the first type; when the sum of the pixel values ​​of other nodes adjacent to the node is determined to be the second value, the node is a node of the second type; when the sum of the pixel values ​​of other nodes adjacent to the node is determined to be the third value, the node is a node of the third type; when the sum of the pixel values ​​of other nodes adjacent to the node is determined to be the fourth value, the node is a node of the fourth type; when the sum of the pixel values ​​of other nodes adjacent to the node is determined to be the parameter greater than the fourth value, the node is a node of the fifth type.

[0016] In one embodiment, the above-mentioned determination of rock quality parameters corresponding to the rock outcrop image based on the type of each fracture node includes: converting the types of all nodes into branch forms to obtain target branch parameters corresponding to the types of all nodes; and determining the rock quality parameters corresponding to the target branch parameters based on the correspondence between the branch parameters and the rock quality parameters.

[0017] In one embodiment, the corresponding relationship between the branch parameter and the rock quality parameter is: RQD=-12.826V+88.295

[0018] Among them, V represents the rock vulnerability index, N B represents the target branch parameter corresponding to the type of all nodes, and RQD represents the rock quality parameter.

[0019] In one embodiment, the above method also includes: identifying the rock outcrop image to obtain the type of the rock outcrop image; if the type is a block type or a pore type, identifying the blocks or pores in the rock outcrop image to obtain rock quality parameters; if the type is a fracture type, inputting the rock outcrop image into the intelligent recognition model to perform fracture network trajectory recognition to obtain a fracture network trace diagram corresponding to the rock outcrop image.

[0020] In one embodiment, the intelligent recognition model includes a positioning model and a segmentation model; before inputting the rock outcrop image into the intelligent recognition model to perform fracture network trajectory identification and obtain a fracture network trace map corresponding to the rock outcrop image, the method further includes: obtaining a sample data set of fracture structure; inputting the sample data set into the initial positioning model and the initial segmentation model respectively for training to obtain the trained positioning model and the trained segmentation model.

[0021] In one embodiment, the positioning model is a crack structure visual positioning model, and the segmentation model is a multi-scale crack structure geometric segmentation model.

[0022] In one embodiment, the first value is 1 and the second value is 2.

[0023] In one embodiment, the first value is 1, the second value is 2, the third value is 3, and the fourth value is 4.

[0024] On the second aspect, the present application also provides a device for determining rock quality, including: an acquisition module for acquiring a rock outcrop image; an identification module for inputting the rock outcrop image into an intelligent recognition model for crack network trajectory identification, and obtaining a crack network trace map corresponding to the rock outcrop image; a classification module for classifying each crack node in the crack network trace map to obtain the type of each crack node; and a determination module for determining the rock quality parameters corresponding to the rock outcrop image according to the type of each crack node.

[0025] In a third aspect, the present application also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program: obtaining a rock outcrop image; inputting the rock outcrop image into an intelligent recognition model for crack network trajectory identification to obtain a crack network trace map corresponding to the rock outcrop image; classifying each crack node in the crack network trace map to obtain the type of each crack node; and determining the rock quality parameters corresponding to the rock outcrop image according to the type of each crack node.

[0026] Fourthly, the present application also provides a non-volatile computer-readable storage medium having a computer program stored thereon, which implements the following steps when executed by a processor: obtaining a rock outcrop image; inputting the rock outcrop image into an intelligent recognition model to perform fracture network trajectory recognition, and obtaining a fracture network trace diagram corresponding to the rock outcrop image; classifying each fracture node in the fracture network trace diagram to obtain the type of each fracture node; and determining the rock quality parameters corresponding to the rock outcrop image according to the type of each fracture node.

[0027] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the following steps: obtaining a rock outcrop image; inputting the rock outcrop image into an intelligent recognition model for crack network trajectory identification to obtain a crack network trace map corresponding to the rock outcrop image; classifying each crack node in the crack network trace map to obtain the type of each crack node; and determining the rock quality parameters corresponding to the rock outcrop image based on the type of each crack node.

[0028] The rock quality determination method, apparatus, computer equipment, and storage medium described above provide a more accurate assessment basis for rock engineering by obtaining empirical formulas for evaluating the types of fracture nodes and rock instruction parameters. Furthermore, by combining an intelligent recognition model to identify fracture network trajectories in images, rapid and accurate rock quality assessment is achieved. Compared with traditional methods, this method significantly improves the efficiency of rock instruction assessment, ensures real-time data and accurate fracture identification, and reduces on-site work risks through non-contact operation. Furthermore, it provides strong support for the development of intelligent rock engineering survey, design, and monitoring, and is expected to promote technological and economic progress in the entire rock engineering field. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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.

[0030] FIG1 is a schematic diagram of the structure of a computer device according to an embodiment of the present application;

[0031] FIG2 is a schematic flow chart of a method for determining rock quality in one embodiment of the present application;

[0032] FIG3 is a flow chart of a method for determining rock quality in another embodiment of the present application;

[0033] FIG4 is a flow chart of a method for determining rock quality in another embodiment of the present application;

[0034] FIG5 is a flow chart of a method for determining rock quality in another embodiment of the present application;

[0035] FIG6 is a flow chart of a crack network node search algorithm according to one embodiment of the present application;

[0036] FIG7 is a classification criterion for fracture network digital image nodes in one embodiment of the present application;

[0037] FIG8 is a flow chart of a method for determining rock quality in another embodiment of the present application;

[0038] FIG9 is a flow chart of a method for determining rock quality in another embodiment of the present application;

[0039] FIG10 is a correlation function between a fracture network vulnerability index and rock quality parameters in one embodiment of the present application;

[0040] FIG11 is a diagram showing the calculation principle of rock mass quality parameters based on the window line survey method in one embodiment of the present application;

[0041] FIG12 is a flow chart of a method for determining rock quality in another embodiment of the present application;

[0042] FIG13 is a logic diagram of a system for determining rock quality parameters in one embodiment of the present application;

[0043] FIG14 is a structural block diagram of a device for determining rock quality in one embodiment of the present application. DETAILED DESCRIPTION

[0044] 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.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0046] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0047] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] Fractured rock masses are often cut by multiple sets of structural planes, forming steep slopes that are difficult to measure and access. The distribution of these structural planes, the degree of rock fragmentation, and the integrity of the rock are important factors in evaluating rock quality and analyzing its stability. Furthermore, due to internal and external geological stresses, defects such as fissures, pores, joints, faults, and microcracks can develop on the surface and within the rock. Under load and weathering, these defects evolve and eventually cause damage, necessitating an assessment of rock quality.

[0049] However, current rock quality assessment methods are limited to long-term field surveys by experienced geologists, expensive drill core analysis, and tedious geostatistical measurements. These methods require extremely high levels of morphological parameters and physical and mechanical properties of fracture and pore structures. Furthermore, modern advanced exploration techniques rely on expensive measurement equipment and extensive data post-processing and integration. These factors limit the time, manpower, and financial investment, significantly reducing the timeliness of engineering construction and rock mass safety assessments.

[0050] In recent years, a growing number of rock quality assessment methods have emerged, integrating engineering experience and academic research. These include Rock Quality Designation (RQD), Q-classification, the Pxy crack evaluation system, and the RMR rock mass classification method. These methods link failure criteria to field engineering geological observations based on the integrity and fragmentation of the rock mass, visually visualizing information such as crack morphology, infills, and crack system patterns in a semi-empirical and semi-qualitative manner. Furthermore, in slope stability studies based on geological strength indices and network connectivity metrics, a graph theory model approach has demonstrated a significant correlation between the topological structure of the two-dimensional projections of the fracture network and the maximum compressive strength of the rock. This suggests that the geometric structure or topological behavior of the interlocking patterns of rock fractures can be used to measure rock integrity or the degree of block fragmentation, thus forming a rock quality assessment method based on graph theory models.

[0051] Furthermore, deep learning-based image recognition models are becoming the most advanced digital image processing technology. Based on this, machine vision technology continues to improve, enabling real-time image information acquisition, target detection, visual navigation, and visual control systems. Machine vision systems offer fast response times, large amounts of information, high precision, and non-destructive testing, significantly improving the efficiency and intelligence of site information acquisition. However, existing methods for evaluating rock quality, the most fundamental and important issue in rock mass engineering surveys, suffer from low evaluation efficiency. This application aims to address this issue.

[0052] Following the above introduction to the background technology for the rock mass determination method provided in the embodiments of the present application, the implementation environment involved in the rock mass determination method provided in the embodiments of the present application will be briefly described below. The rock mass determination method provided in the embodiments of the present application can be applied to a computer device as shown in Figure 1. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output 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 wired or wireless communication. The wireless communication method can be implemented via Wi-Fi, a mobile cellular network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a method for selecting an asteroid. The display unit of the computer device is used to produce a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, a keypad, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0053] 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.

[0054] After introducing the application scenarios of the method for determining rock quality provided by the embodiments of the present application, the following focuses on introducing the method for determining rock quality described in the present application.

[0055] In one embodiment, as shown in FIG2 , a method for determining rock quality is provided. The method is described by taking the computer device in FIG1 as an example, and includes the following steps S201 to S204 .

[0056] S201. Acquire rock outcrop images.

[0057] The rock outcrop image may be an image of the rock exposed to the air.

[0058] In the embodiment of the present application, images of rock outcrops can be obtained through means such as drone remote sensing, image data, or camera photography.

[0059] S202 , inputting the rock mass outcrop image into an intelligent recognition model to perform fracture network trajectory recognition, and obtaining a fracture network trace map corresponding to the rock mass outcrop image.

[0060] The intelligent recognition model can be a recognition model pre-trained based on the localization model and segmentation model, and is used to identify fracture network trajectories in rock outcrop images. The localization model can be a fracture structure visual localization model, such as a Detection Transformer (DETR) model, and the segmentation model can be a multi-scale fracture structure geometric segmentation model, such as a Unet++ model. Optionally, scale hybridization techniques can be used to optimize the accuracy and noise tolerance of the localization model and segmentation model in the multi-scale fracture structure recognition task, thereby obtaining a highly robust intelligent recognition model.

[0061] In an embodiment of the present application, after the rock outcrop image is obtained as described above, the rock outcrop image can be input into a pre-trained intelligent recognition model to perform fracture network trajectory recognition, thereby obtaining a fracture network trace map corresponding to the rock outcrop image.

[0062] S203: Classify each crack node in the crack network trace diagram to obtain the type of each crack node.

[0063] Among them, the fracture nodes refer to the nodes between fractures in the fracture network trajectory.

[0064] In the embodiment of the present application, after the crack network trace diagram is obtained, the type of each crack node in the crack network trace diagram can be analyzed to obtain the type of each crack node in the crack network trace diagram.

[0065] S204: Determine rock quality parameters corresponding to the rock mass outcrop image according to the type of each fracture node.

[0066] In an embodiment of the present application, after obtaining the type of each fracture node in the fracture network trace diagram as described above, the type of each fracture node in the fracture network trace diagram can be converted to obtain the number of network topology branches, and the rock quality parameters corresponding to the rock outcrop image can be determined based on the correspondence between the number of network topology branches and the rock quality parameters.

[0067] The rock quality determination method provided in the embodiment of the present application obtains a rock outcrop image, inputs the rock outcrop image into an intelligent recognition model to perform crack network trajectory identification, obtains a crack network trace diagram corresponding to the rock outcrop image, classifies each crack node in the crack network trace diagram, obtains the type of each crack node, and determines the rock quality parameters corresponding to the rock outcrop image according to the type of each crack node. The above method provides a more accurate evaluation basis for rock engineering by obtaining the type of each crack node and the evaluation empirical formula of the rock instruction parameter. In addition, the crack network trajectory in the image is identified in combination with the intelligent recognition model, which realizes a fast and accurate rock quality assessment. Compared with the traditional method, the method of the present application greatly improves the evaluation efficiency of the rock instruction, ensures the real-time nature of the data and the accuracy of crack identification, and reduces the risk of on-site work by non-contact operation. In addition, it also provides strong support for the development of intelligent rock engineering survey, design and monitoring, and can promote the technological and economic progress of the entire rock engineering field.

[0068] In one embodiment, based on the embodiment shown in Figure 2, the intelligent recognition model includes a positioning model and a segmentation model, which can describe the process of obtaining a fracture network trace map corresponding to a rock outcrop image. As shown in Figure 3, step S203 inputs the rock outcrop image into the intelligent recognition model to perform fracture network trace recognition, thereby obtaining a fracture network trace map corresponding to the rock outcrop image, including steps S301 and S302.

[0069] S301: Input the rock outcrop image into the positioning model to locate the crack position and obtain a positioning image.

[0070] Among them, the positioning model is used to locate the fracture area in the rock outcrop image.

[0071] In an embodiment of the present application, after the rock outcrop image is obtained as described above, the rock outcrop image can be input into a positioning model to locate the crack area in the rock outcrop image, thereby obtaining the position of the crack area in the rock outcrop image, and generating a positioning image of the crack based on the position of the crack area.

[0072] S302: Input the positioning image into a segmentation model to perform image segmentation of the fracture area, and obtain a fracture network trace map corresponding to the rock mass outcrop image.

[0073] Among them, the segmentation model is used to segment the positioning image.

[0074] In the embodiment of the present application, after the positioning image with cracks is obtained as described above, the positioning image with cracks is input into the segmentation model to perform crack area image segmentation to obtain a crack network trace map corresponding to the rock outcrop image.

[0075] Optionally, a method for obtaining a fracture network trace map corresponding to a rock outcrop image is provided below. As shown in FIG4 , the above step S302 inputs the positioning image into the segmentation model to perform fracture area image segmentation to obtain a fracture network trace map corresponding to the rock outcrop image, including steps S3021 to S3024.

[0076] S3021. Input the positioning image into the segmentation model to perform crack area image segmentation to obtain a segmented image.

[0077] In the embodiment of the present application, after the positioning image is obtained as described above, the positioning image can be directly input into the segmentation model to perform crack area image segmentation, thereby obtaining multiple segmented images corresponding to the positioning image.

[0078] S3022: Binarize the segmented image to obtain a binary image corresponding to the segmented image.

[0079] In the embodiment of the present application, after the plurality of segmented images corresponding to the positioning image are determined, each segmented image may be binarized to obtain a binarized image corresponding to each segmented image.

[0080] S3023. Perform thinning processing on the crack network lines in the binary image to obtain a processed binary image.

[0081] In the embodiment of the present application, after the above-mentioned binary image is obtained, the Zhang-Suen algorithm can be called to refine the crack network lines in the binary image, and then the binary image after the thinning process is obtained. The Zhang-Suen algorithm is a commonly used image morphology processing algorithm, based on an 8-neighborhood pixel value search method, for realizing image thinning and image skeleton extraction. Optionally, as shown in Figure 6, after the above-mentioned binary image (i.e., the binary image in Figure 6) is obtained, the matrix in the binary image can be marked by the Zhang-Suen algorithm, and each pixel in the binary image can be traversed to determine whether the pixel value of each pixel is 0, and when the pixel value of the pixel is 0, continue to judge whether the pixel meets the thinning condition, and when the pixel meets the thinning condition, the pixel value of the pixel is set to 0, and use the above method to traverse each pixel in the binary image, thereby obtaining the pixel value of each pixel, and construct a marking matrix according to the pixel value of each pixel, and then obtain the binary image after the thinning process.

[0082] S3024. Connect the crack network lines in the binary image after processing to obtain a crack network trace diagram.

[0083] In the embodiment of the present application, after the thinned binary image is obtained, the interconnected crack network lines in the processed binary image are connected to each other, thereby obtaining a crack network trace diagram after the connection processing.

[0084] The method for obtaining a fracture network trace map provided in an embodiment of the present application is based on artificial intelligence technologies such as positioning models and segmentation models, and achieves rapid and accurate acquisition of fracture network trace maps, providing a data basis for subsequent determination of rock quality parameters based on the fracture network trace map.

[0085] In one embodiment, based on the embodiment shown in FIG. 2 or FIG. 3 , the process of obtaining the type of each fracture node can be described. As shown in FIG. 5 , step S203 classifies each fracture node in the fracture network trace diagram to obtain the type of each fracture node, including:

[0086] S401, obtaining nodes of each crack network line in the crack network trace diagram.

[0087] The nodes of each crack network line refer to the intersections between each crack network line.

[0088] In the embodiment of the present application, after the fracture network trace diagram is obtained, a plurality of fracture network lines can be determined from the fracture network trace diagram, and further, nodes of each fracture network line can be determined based on the plurality of fracture network lines.

[0089] S402: If the node is a node on the boundary of the fracture network trace graph, and the pixel value of the node is a first value, determine the sum of the pixel values ​​of other nodes adjacent to the node.

[0090] The first value is 1. It should be noted that in the crack network trace diagram, the pixel value of the position where the crack exists is 1, and the pixel value of the position where the crack does not exist is 0.

[0091] In the embodiment of the present application, the nodes of the crack network line are nodes on the boundary of the crack network trace graph, and the nodes of the crack network line are nodes on the non-boundary of the crack network trace graph. First, for the nodes of the crack network line are nodes on the boundary of the crack network trace graph, when the pixel value of the node on the boundary itself is the first value, the sum of the pixel values ​​of other nodes adjacent to the node on the boundary is determined. Optionally, the present application adopts an eight-neighborhood search, that is, there are eight adjacent nodes of the node not on the boundary, three adjacent nodes at the top corners of the crack network trace graph, and five adjacent nodes on the boundary and not at the top corners. As shown in Figure 7, a classification criterion for each node in the crack network trace graph is provided.

[0092] S403: If the sum of the pixel values ​​of other nodes adjacent to the node is a first value, the node is a first type of node.

[0093] Among them, the first type of node is an I-type node.

[0094] In the embodiment of the present application, when the sum of the pixel values ​​of other nodes adjacent to the node on the boundary of the crack network trace graph is obtained as the first value, the node on the boundary of the crack network trace graph is considered to be a first type of node.

[0095] S404: If the sum of the pixel values ​​of other nodes adjacent to the node is a second value, the node is a node of the second type.

[0096] The second value is 2, and the second type of node is a T-type node.

[0097] In the embodiment of the present application, if the sum of the pixel values ​​of other nodes adjacent to the node on the boundary of the crack network trace graph obtained above is the second value, the node on the boundary of the crack network trace graph is considered to be a node of the second type.

[0098] The method for obtaining the type of each fracture node provided in the embodiment of the present application provides an implementation method for determining the type of boundary nodes. The type of boundary nodes is determined by determining the pixel values ​​of the intersection points of each fracture network line and the pixel values ​​of other nodes adjacent to the intersection points, thereby providing a data basis for subsequently determining rock quality parameters based on the type of boundary nodes.

[0099] In one embodiment, based on the embodiment shown in FIG5 , if the node is a node on a non-boundary portion of the fracture network trace graph, the process of obtaining the type of each fracture node can be described. As shown in FIG8 , the above-mentioned step S203 classifies each fracture node in the fracture network trace graph to obtain the type of each fracture node, including steps S405 to S410.

[0100] S405: If the node is a node on a non-boundary portion of the fracture network trace graph, and the pixel value of the node is a first value, determine the sum of the pixel values ​​of other nodes adjacent to the node.

[0101] In an embodiment of the present application, for a node of a crack network line that is not on the boundary of a crack network trace graph, if the pixel value of the non-boundary node itself is a first value, the sum of the pixel values ​​of other nodes adjacent to the non-boundary node is determined. Optionally, the present application employs an eight-neighborhood search, i.e., there are eight adjacent nodes for a node not on the boundary, three adjacent nodes for a node at a vertex of the crack network trace graph, and five adjacent nodes for a node not on the boundary but at a vertex.

[0102] S406: If the sum of the pixel values ​​of other nodes adjacent to the node is a first value, the node is a first type of node.

[0103] In the embodiment of the present application, when the sum of the pixel values ​​of other nodes adjacent to the non-boundary node in the crack network trace graph obtained above is the first value, the non-boundary node in the crack network trace graph is considered to be a first type of node.

[0104] S407: If the sum of the pixel values ​​of other nodes adjacent to the node is a second value, the node is a node of the second type.

[0105] In an embodiment of the present application, when the sum of the pixel values ​​of other nodes adjacent to the non-boundary node in the crack network trace graph is obtained as the second value, and it is determined whether the nodes with pixel values ​​of other adjacent nodes having the first value are on the same side, and when the nodes with pixel values ​​of other adjacent nodes having the first value are on the same side, the non-boundary node in the crack network trace graph is considered to be a second type of node.

[0106] S408: If the sum of the pixel values ​​of other nodes adjacent to the node is a third value, the node is a node of the third type.

[0107] The third value is 3, and the third type of node is a Y-type node.

[0108] In the embodiment of the present application, when the sum of the pixel values ​​of other nodes adjacent to the non-boundary node in the crack network trace graph obtained above is the second value, the non-boundary node in the crack network trace graph is considered to be a third type of node.

[0109] S409: If the sum of the pixel values ​​of other nodes adjacent to the node is a fourth value, the node is a node of the fourth type.

[0110] The fourth value is 4, and the fourth type of node is an X-type node.

[0111] In an embodiment of the present application, when the sum of the pixel values ​​of other nodes adjacent to the non-boundary node in the crack network trace diagram is obtained as the fourth value, and it is determined whether there is a node among the other adjacent nodes that has two values ​​of the first value on one side and is not connected, and when it is determined that there is a node among the other adjacent nodes that has two values ​​of the first value on one side and is not connected, the non-boundary node in the crack network trace diagram is considered to be a node of the fourth type.

[0112] S410: If the sum of the pixel values ​​of other nodes adjacent to the node is greater than the parameter of the fourth value, the node is a node of the fifth type.

[0113] Among them, the fifth type of node is a D-type node.

[0114] In an embodiment of the present application, when the sum of the pixel values ​​of other nodes adjacent to the non-boundary node in the crack network trace diagram is greater than the parameter of the fourth value, the non-boundary node in the crack network trace diagram is considered to be a fifth type of node.

[0115] The method for obtaining the types of each fracture node provided in the embodiment of the present application provides an implementation method for determining the type of non-boundary nodes. The type of non-boundary nodes is determined by determining the pixel values ​​of the intersection points of each fracture network line and the pixel values ​​of other nodes adjacent to the intersection points, thereby providing a data basis for subsequently determining rock quality parameters based on the type of non-boundary nodes.

[0116] In one embodiment, based on the embodiment shown in Figure 2, the process of determining the rock quality parameters corresponding to the rock outcrop image can be described. As shown in Figure 9, the above-mentioned step S204 determines the rock quality parameters corresponding to the rock outcrop image according to the type of each fracture node, including steps S501 and S502.

[0117] Step S501: convert the types of all nodes into branch forms to obtain target branch parameters corresponding to the types of all nodes.

[0118] The target branch parameter is the number of network topology branches (N B ).

[0119] In the embodiment of the present application, after the types of all nodes are obtained as described above, the node-branch model can be used to convert the types of all nodes into branch forms, and the target branch parameters corresponding to the types of all nodes are statistically obtained.

[0120] Step S502: Based on the correspondence between the branch parameters and the rock quality parameters, determine the rock quality parameters corresponding to the target branch parameters.

[0121] The corresponding relationship between the branch parameters and the rock quality parameters can be expressed by the following formulas (1) and (2): RQD=-12.826V+88.295 (2)

[0122] Among them, V represents the rock vulnerability index, N B It represents the target branch parameter corresponding to the type of all nodes, and RQD represents the rock quality parameter.

[0123] In the embodiment of the present application, after obtaining the target branch parameters corresponding to the types of all nodes, the rock quality parameters corresponding to the target branch parameters can be determined based on the correspondence between the branch parameters and the rock quality parameters. It should be noted that the rock fragility index (V) and the target branch parameter (N B) empirical formula The goodness of fit is 0.997. The linear mapping function of the rock quality parameter (RQD) and rock vulnerability index (V) based on the window line method, RQD = -12.826V + 88.295, has a goodness of fit of 0.637 (for example, as shown in Figure 10). The goodness of fit of the two basically meets the correlation requirements for quantitative rock quality assessment.

[0124] The rock quality parameter determination method provided in the embodiment of the present application determines the rock quality parameter corresponding to the target branch parameter through the evaluation empirical formula between the branch parameter and the rock quality parameter, providing a more accurate evaluation basis for rock engineering.

[0125] In one embodiment, as shown in FIG11 , the window line method for the RQD of the engineering rock mass is calculated by using a discontinuous surface statistical method in which a line is arranged with a fixed arc gradient (5°, 10°, 20°) centered at the measuring point (A or B) in the measuring window. The length Ws and height Hs of the window are additionally statistically calculated. This method can better reflect the comprehensive characteristics of the anisotropy of the fractured rock mass than the RQD calculation method based on the drill core. During measurement and calculation, the statistical threshold is set to 10 cm, that is, the ratio of the cumulative length of the intact rock length greater than 10 cm in the measuring line to the length of the entire measuring line is RQD, and then the average value of the RQD index calculated for each measuring line derived from different measuring points is calculated and recorded as RQDc. The calculation formula for calculating RQD based on the window line method satisfies the following formulas (3) and (4): RQD r =0.9464×RQD C -11.946 (4)

[0126] Among them, N M is the number of all survey lines, RQD i The specific value of RQD calculated for any survey line. In addition, according to a large number of actual engineering applications, the window survey line method usually overestimates the RQD of the rock mass, so it is corrected by formula (3), RQD r is the correction value.

[0127] In one embodiment, based on the embodiment shown in FIG2 , the training method of the intelligent recognition model includes:

[0128] Get a sample dataset of fracture structures.

[0129] The sample dataset refers to an image dataset that needs to provide a clearer description of the crack structure.

[0130] In the embodiment of the present application, sample data sets for training the positioning model and the segmentation model can be obtained from the Internet, long-term collection, project accumulation or public data sets.

[0131] The sample data sets are respectively input into the initial positioning model and the initial segmentation model for training to obtain a trained positioning model and a trained segmentation model.

[0132] The initial positioning model may be a target detection model (Detection Transformer, DETR), and the initial segmentation model may be a Unet++ model.

[0133] In an embodiment of the present application, after the sample data set is obtained as described above, the obtained sample data set can be input into the initial positioning model and the initial segmentation model respectively, and through hyperparameter adjustment and scale hybridization technology, the accuracy and noise tolerance of the initial positioning model and the initial segmentation model in the multi-scale crack structure recognition task can be optimized, thereby obtaining a trained positioning model and a trained segmentation model.

[0134] An intelligent recognition model is determined based on the trained positioning model and the trained segmentation model.

[0135] In an embodiment of the present application, after the trained positioning model and the trained segmentation model are obtained as described above, the trained positioning model and the trained segmentation model are integrated to obtain an intelligent recognition model.

[0136] The training method of the intelligent recognition model provided in the embodiment of the present application uses a sample data set of a fissure structure to train the initial positioning model and the initial segmentation model, thereby maximizing the feature learning ability of the model and providing a basis for obtaining relatively excellent recognition accuracy based on the subsequent intelligent recognition model. In addition, the above method can significantly improve the effective recognition scale interval by 85.7% by adopting scale hybridization technology, and increase the recognition accuracy to a maximum of 0.992. Applying it to the trained model can effectively improve the recognition accuracy of the multi-scale features of the fissure structure and reduce the interference of noise on the model's feature learning ability, such as Gaussian noise, visual blur and distortion caused by insufficient image resolution.

[0137] In one embodiment, based on the embodiment shown in FIG. 2 , as shown in FIG. 12 , the above method further includes step S205 .

[0138] S205: Identify the rock outcrop image to obtain the type of the rock outcrop image.

[0139] Among them, the types of rock outcrop images include matrix blocks, pore structures and fracture structures. The scale of matrix blocks is <10 -2 m, the scale of pore structure>10 -1m.

[0140] In the embodiment of the present application, after the rock outcrop image is obtained as described above, the features of the rock outcrop image may be identified to determine whether the rock outcrop image is a matrix block, a pore structure, or a fracture structure.

[0141] S206: If the type is a block type or a pore type, identify the blocks or pores in the rock outcrop image to obtain rock quality parameters.

[0142] In the embodiment of the present application, when the rock mass outcrop image determined above is of the matrix block type, the rock fragility index (V) is directly set to 0 and directly substituted into the above formula (2) for calculation, thereby obtaining the rock quality parameters of the rock mass outcrop image of the matrix block type; when the rock mass outcrop image determined above is of the pore structure type, the rock fragility index (V) is directly set to 1 and directly substituted into the above formula (2) for calculation, thereby obtaining the rock quality parameters of the rock mass outcrop image of the pore structure type. It should be noted that a rock fragility index (V) of 1 indicates that the rock mass has lost its bearing capacity and the corresponding observation area is in a completely broken state.

[0143] S207: If the type is a crack type, return to execute the above step S202.

[0144] In an embodiment of the present application, when the rock outcrop image determined above is of a fracture type, the fracture type rock outcrop image is input into a pre-trained intelligent recognition model for fracture network trajectory recognition, thereby obtaining a fracture network trace map corresponding to the rock outcrop image.

[0145] The method for processing different types of rock outcrop images provided in the embodiments of the present application refines the method for determining rock quality parameters of rock outcrop images and further improves the accuracy of the determined rock quality parameters.

[0146] In one embodiment, a rock quality determination system is also provided. The system functional modules are shown in Figure 13 and include: an image data acquisition device M1, an information transmission and storage system M2, a fracture structure image intelligent recognition module M3, a fracture network branch number search module M4 based on machine vision, and a rock quality rapid assessment module M5 based on machine vision. The image data acquisition device M1 can be a drone, a surveillance camera, or other data acquisition equipment with a shooting function, and can upload image data to the information transmission and storage system M2 using an SD memory card or a data transmission cable; the information transmission and storage system M2 can be a desktop computer, a notebook computer, an industrial computer, or other computing media that loads deep learning model conditions; the fracture structure image intelligent recognition module M3 is written in Python code and mainly implements the following functions: (1) opening the image storage path, (2) loading the image data to be identified and processed, (3) judging whether the identified structure is a matrix block, a pore structure, or a fracture structure, and outputting the vulnerability index of the rock mass if it is a matrix block or a pore structure. (4) If it is a crack structure, load the crack structure visual positioning model and the multi-scale crack structure geometric segmentation model to obtain the binary trace map of the crack structure; the crack network branch number search module M4 is written by python code, and mainly realizes the following functions: (1) load the crack network binary map, (2) image grayscale processing, (3) set the iteration number NP, (4) apply the image morphology Zhang-Suen algorithm to obtain the crack network skeleton map, (5) mark the crack network connected components, (6) apply the node search algorithm to extract the boundary pixels of the digital image, and obtain the node classification according to the node type judgment condition through the eight-neighborhood search method, (7) count the number of branches N according to the topological structure of the crack network B The rock quality rapid assessment module M5 is written in Python code and mainly implements the following functions: (1) load the number of branches of the fracture network, (2) calculate the number of branches according to the empirical formula Calculate the rock vulnerability reference value, (3) calculate the rock RQD reference value according to the linear mapping function RQD = -12.826V + 88.295, (4) output the rock quality assessment value.

[0147] 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.

[0148] Based on the same inventive concept, embodiments of the present application also provide a rock quality determination device for implementing the aforementioned rock quality determination method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more rock quality determination device embodiments provided below can be found in the limitations of the rock quality determination method described above and will not be further elaborated here.

[0149] In an exemplary embodiment, as shown in FIG14 , a device for determining rock quality is provided, including: an acquisition module 10 , an identification module 11 , a classification module 12 and a determination module 13 .

[0150] The acquisition module 10 is used to acquire rock outcrop images.

[0151] In the recognition module 11 , the user inputs the rock outcrop image into the intelligent recognition model to perform fracture network trajectory recognition, and obtains a fracture network trace map corresponding to the rock outcrop image.

[0152] The classification module 12 is used to classify each fracture node in the fracture network trace diagram to obtain the type of each fracture node.

[0153] The determination module 13 is used to determine the rock quality parameters corresponding to the rock outcrop image according to the type of each fracture node.

[0154] In an exemplary embodiment, the intelligent recognition model includes a positioning model and a segmentation model, and the recognition module 11 includes a positioning unit and a segmentation unit.

[0155] The positioning unit is specifically used to input the rock outcrop image into the positioning model to locate the crack position and obtain a positioning image.

[0156] The segmentation unit is specifically used to input the positioning image into the segmentation model to perform crack area image segmentation, and obtain a crack network trace map corresponding to the rock outcrop image.

[0157] In an exemplary embodiment, the above-mentioned segmentation unit is specifically used to input the positioning image into the segmentation model to perform crack area image segmentation to obtain a segmented image; perform binarization processing on the segmented image to obtain a binary image corresponding to the segmented image; perform refinement processing on the crack network lines in the binary image to obtain a processed binary image; and connect the crack network lines in the binary image after processing to obtain a crack network trace diagram.

[0158] In an exemplary embodiment, the classification module 12 includes: an acquisition unit, a first determination unit, a second determination unit, and a third determination unit.

[0159] The acquisition unit is specifically used to obtain the nodes of each crack network line in the crack network trace diagram.

[0160] The first determining unit is specifically configured to, if the node is a node on a boundary in the fracture network trace graph and the pixel value of the node is a first value, determine the sum of the pixel values ​​of other nodes adjacent to the node.

[0161] The second determining unit is specifically configured to determine that a node is a first type of node if the sum of pixel values ​​of other nodes adjacent to the node is a first value.

[0162] The third determining unit is specifically configured to determine that a node is a node of the second type if the sum of pixel values ​​of other nodes adjacent to the node is a second value.

[0163] In an exemplary embodiment, if the node is a node on a non-boundary portion of the fracture network trace graph, the classification module 12 includes: a fourth determination unit, a fifth determination unit, a sixth determination unit, a seventh determination unit, an eighth determination unit, and a ninth determination unit.

[0164] The fourth determining unit is specifically configured to determine the sum of pixel values ​​of other nodes adjacent to the node when the pixel value of the node is the first value.

[0165] The fifth determining unit is specifically configured to determine that a node is a first type of node if the sum of pixel values ​​of other nodes adjacent to the node is a first value.

[0166] The sixth determining unit is specifically configured to determine that a node is a node of the second type if the sum of pixel values ​​of other nodes adjacent to the node is a second value.

[0167] The seventh determining unit is specifically configured to determine that the node is a node of the third type if the sum of pixel values ​​of other nodes adjacent to the node is a third value.

[0168] The eighth determining unit is specifically configured to determine that the node is a node of the fourth type if the sum of pixel values ​​of other nodes adjacent to the node is a fourth value.

[0169] The ninth determining unit is specifically configured to determine that, if the sum of pixel values ​​of other nodes adjacent to the node is greater than a parameter of a fourth value, the node is a node of the fifth type.

[0170] In an exemplary embodiment, the determination module 13 includes: a conversion unit and a determination unit.

[0171] The conversion unit is specifically used to convert the types of all nodes into branch forms to obtain target branch parameters corresponding to the types of all nodes.

[0172] The determination unit is specifically configured to determine the rock quality parameter corresponding to the target branch parameter based on the corresponding relationship between the branch parameter and the rock quality parameter.

[0173] In an exemplary embodiment, the apparatus further includes: a first identification module, a second identification module, and a third identification module.

[0174] The first recognition module is used to recognize the rock outcrop image and obtain the type of the rock outcrop image.

[0175] The second recognition module is used to identify the blocks or pores in the rock outcrop image if the type is a block type or a pore type, and obtain rock quality parameters.

[0176] The third recognition module is used to return to step S202 to input the rock outcrop image into the intelligent recognition model to perform fracture network trajectory recognition if the type is a fracture type, and obtain a fracture network trace map corresponding to the rock outcrop image.

[0177] Each module in the rock quality determination device described above may be implemented in whole or in part via software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may 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.

[0178] In an exemplary embodiment, a computer device is provided, which may be a terminal. Its internal structure may be shown in FIG1 . The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer program stored in the non-volatile storage medium. The input / output 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 wired or wireless communication, where the wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements a method for determining rock quality. The display unit of the computer device is used to produce a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0179] In one embodiment of the present application, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0180] In one embodiment of the present application, a 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.

[0181] In one embodiment of the present application, a computer program product is provided, including executable instructions, which implement the steps in the above-mentioned method embodiments when executed by a processor.

[0182] 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.

[0183] 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.

[0184] 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 rock quality, comprising: Obtain rock outcrop images; Inputting the rock mass outcrop image into an intelligent recognition model to perform fracture network trajectory recognition, and obtaining a fracture network trace map corresponding to the rock mass outcrop image; Classifying each crack node in the crack network trace diagram to obtain a type of each crack node; The rock quality parameter corresponding to the rock mass outcrop image is determined according to the type of each fracture node.

2. The method according to claim 1, characterized in that The intelligent recognition model includes a positioning model and a segmentation model. Inputting the rock mass outcrop image into the intelligent recognition model to perform fracture network trajectory recognition, and obtaining a fracture network trace map corresponding to the rock mass outcrop image, includes: Inputting the rock mass outcrop image into the positioning model to locate the crack position and obtain a positioning image; The positioning image is input into the segmentation model to perform fracture area image segmentation, and a fracture network trace map corresponding to the rock mass outcrop image is obtained.

3. The method according to claim 2, characterized in that Inputting the positioning image into the segmentation model to perform fracture area image segmentation to obtain a fracture network trace map corresponding to the rock mass outcrop image includes: Inputting the positioning image into the segmentation model to perform crack region image segmentation to obtain a segmented image; performing a binarization process on the segmented image to obtain a binarized image corresponding to the segmented image; performing thinning processing on the crack network lines in the binary image to obtain a processed binary image; The crack network lines in the processed binary image are connected to obtain the crack network trace map.

4. The method according to any one of claims 1 to 3, characterized in that Classifying each fracture node in the fracture network trace diagram to obtain the type of each fracture node includes: Obtaining nodes of each crack network line in the crack network trace diagram; Corresponding to a case where the node is a node on a boundary of the fracture network trace graph and the pixel value of the node is a first value, determining a sum of pixel values ​​of other nodes adjacent to the node; The sum of pixel values ​​corresponding to other nodes adjacent to the node is determined as the first value, and the node is a node of the first type; The sum of pixel values ​​corresponding to other nodes adjacent to the node is determined as a second value, and the node is a node of the second type.

5. The method according to claim 4, characterized in that Corresponding to the node being a node on a non-boundary portion of the fracture network trace graph, classifying each fracture node in the fracture network trace graph to obtain a type of each fracture node includes: In response to the case where the pixel value of the node is the first value, determining the sum of the pixel values ​​of other nodes adjacent to the node; The sum of pixel values ​​corresponding to other nodes adjacent to the node is determined as the first value, and the node is a node of the first type; The sum of pixel values ​​corresponding to other nodes adjacent to the node is determined as the second value, and the node is a node of the second type; The sum of pixel values ​​corresponding to other nodes adjacent to the node is determined as a third value, and the node is a node of the third type; The sum of pixel values ​​corresponding to other nodes adjacent to the node is determined as a fourth value, and the node is a node of the fourth type; A parameter greater than the fourth value is determined corresponding to the sum of pixel values ​​of other nodes adjacent to the node, and the node is a node of the fifth type.

6. The method according to any one of claims 1 to 5, characterized in that Determining the rock quality parameter corresponding to the rock mass outcrop image according to the type of each fracture node includes: Convert the types of all nodes into branch forms to obtain target branch parameters corresponding to the types of all nodes; Based on the corresponding relationship between the branch parameters and the rock quality parameters, the rock quality parameters corresponding to the target branch parameters are determined.

7. The method according to claim 6, characterized in that: The corresponding relationship between the branch parameters and the rock quality parameters is: RQD=-12.826V+88.295 Among them, V represents the rock vulnerability index, N B represents the target branch parameter corresponding to the type of all nodes, and RQD represents the rock quality parameter.

8. The method according to any one of claims 1 to 7, further comprising: Identifying the rock outcrop image to obtain the type of the rock outcrop image; If the type is a block type or a pore type, identifying the blocks or pores in the rock outcrop image to obtain rock quality parameters; If the type is a fracture type, the step of inputting the rock outcrop image into an intelligent recognition model to perform fracture network trajectory recognition to obtain a fracture network trace map corresponding to the rock outcrop image is performed.

9. The method according to any one of claims 1 to 8, characterized in that: The intelligent recognition model includes a positioning model and a segmentation model; Before inputting the rock mass outcrop image into the intelligent recognition model to perform fracture network trajectory recognition and obtain a fracture network trace map corresponding to the rock mass outcrop image, the method further includes: Obtain a sample dataset of fracture structures; The sample data sets are respectively input into the initial positioning model and the initial segmentation model for training to obtain the trained positioning model and the trained segmentation model.

10. The method according to claim 9, characterized in that: The positioning model is a crack structure visual positioning model, and the segmentation model is a multi-scale crack structure geometric segmentation model.

11. The method according to claim 4, wherein: The first value is 1, and the second value is 2.

12. The method according to claim 5, wherein: The first value is 1, the second value is 2, the third value is 3, and the fourth value is 4.

13. A device for determining rock quality, characterized in that: The device comprises: An acquisition module, used for acquiring rock outcrop images; an identification module, configured to input the rock mass outcrop image into an intelligent identification model to perform fracture network trajectory identification, and obtain a fracture network trace map corresponding to the rock mass outcrop image; a classification module, configured to classify each fracture node in the fracture network trace diagram to obtain a type of each fracture node; The determination module is used to determine the rock quality parameter corresponding to the rock outcrop image according to the type of each fracture node.

14. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.

15. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images