Three-dimensional crack identification method and device, electronic equipment, storage medium and product

Abstract

The invention relates to the technical field of oil exploitation and processing, in particular to a three-dimensional crack recognition method and device, electronic equipment, a storage medium and a product, and the three-dimensional crack recognition method comprises the steps of obtaining a three-dimensional grey-scale map of a rock core sample; performing splitting processing on the three-dimensional grey-scale map to obtain a two-dimensional image corresponding to each dimension in three dimensions; performing image recognition on each two-dimensional image, and determining a target sheet-shaped pore in each two-dimensional image; and if the first two-dimensional image and the second two-dimensional image both comprise the target flaky pore, determining that the target flaky pore is a three-dimensional crack, and the first two-dimensional image and the second two-dimensional image belong to two-dimensional images of different dimensions. According to the method, on the premise that the original pore structure is not changed, the reliability and the calculation speed of crack analysis are remarkably improved, the method has wide application value, and powerful data support can be provided for development and research of unconventional oil and gas resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil exploitation and processing, and is a three-dimensional fracture identification method, a three-dimensional fracture identification device, an electronic device, a storage medium and a computer program product. BACKGROUND

[0002] In the development of unconventional oil and gas resources (such as shale gas and tight oil), accurately identifying and analyzing the structure of three-dimensional fractures in rocks is crucial for subsequent evaluation of reservoir characteristics and optimization of exploitation schemes. Currently, existing three-dimensional fracture identification methods are usually based on the ball-and-stick model to analyze and identify three-dimensional fractures. However, the ball-and-stick model simplifies the microstructure of rocks and ignores the complex morphology of pores and fractures, resulting in low reliability of three-dimensional fracture identification.

[0003] The following are related literature on fracture identification technology: Patent application document with publication number CN120065359A discloses a shale gas reservoir fracture identification and evaluation method and device. The method includes: pre-collecting rock sample surface images, training a fracture identification model using the rock sample surface images; obtaining a shale gas reservoir image to be identified; identifying the shale gas reservoir image using the fracture identification model to obtain effective fracture information of the shale gas reservoir; and evaluating the shale gas reservoir based on the effective fracture information of the shale gas reservoir. This patent application document uses a fracture identification model trained using rock sample surface images to identify fractures. The establishment of this fracture identification model requires a large number of images for training.

[0004] Patent application document with publication number CN102867302A discloses a core fracture identification method based on three-dimensional image information processing. The method uses a CT machine to scan the core to be processed, stores the scanned core CT sequence images in a computer, reads the scanned core CT sequence images using a core three-dimensional image fracture identification software, and uses a moving cube algorithm to reconstruct the three-dimensional image of the core CT sequence images. In the reconstructed three-dimensional image, the differences in morphological characteristics of pores, random noise and fractures in the three-dimensional data field are utilized through a series of calculations, acquisitions and screening processes to achieve the purpose of identifying core fractures. This patent application document identifies fractures based on the reconstructed three-dimensional image, which is different from the technical idea of the present technology. SUMMARY

[0005] The present application provides a three-dimensional fracture identification method, device, electronic device, storage medium and product, which overcomes the shortcomings of the prior art and effectively solves the problem of low reliability of three-dimensional fracture identification.

[0006] One of the technical solutions of the present application is realized by the following measures: a three-dimensional fracture identification method, comprising: acquiring a three-dimensional gray image of a core sample; splitting the three-dimensional gray image to obtain a two-dimensional image corresponding to each dimension of the three dimensions; performing image recognition on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image; if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, it is determined that the target sheet-shaped pore is a three-dimensional fracture, and the first two-dimensional image and the second two-dimensional image belong to two-dimensional images of different dimensions.

[0007] The following is a further optimization or / and improvement of one of the above technical solutions of the present application: The above splitting the three-dimensional gray image to obtain a two-dimensional image corresponding to each dimension of the three dimensions comprises: performing binaryzation processing on the three-dimensional gray image to obtain a three-dimensional binaryzation image; splitting the three-dimensional binaryzation image to obtain a two-dimensional image corresponding to each dimension of the three dimensions.

[0008] The above splitting the three-dimensional binaryzation image to obtain a two-dimensional image corresponding to each dimension of the three dimensions comprises: splitting the three-dimensional gray image along the x-axis, y-axis and z-axis respectively to obtain at least one two-dimensional image corresponding to the x-axis, at least one two-dimensional image corresponding to the y-axis and at least one two-dimensional image corresponding to the z-axis.

[0009] The above performing image recognition on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image comprises: performing image recognition on a sheet-shaped pore in each two-dimensional image, and in the case of recognizing a sheet-shaped pore, acquiring a minimum circumscribed rectangle of the sheet-shaped pore; if the ratio between the length and the width of the minimum circumscribed rectangle of the sheet-shaped pore is greater than a preset value, the sheet-shaped pore is marked as the target sheet-shaped pore.

[0010] The above if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, it is determined that the target sheet-shaped pore is a three-dimensional fracture, comprises: acquiring three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image; if the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image match the three-dimensional coordinates of the target sheet-shaped pore in the second two-dimensional image successfully, it is determined that the target sheet-shaped pore is a three-dimensional fracture.

[0011] After determining that the target sheet-shaped pore is a three-dimensional crack, the method further comprises: acquiring a length, a width and a crack direction corresponding to the three-dimensional crack; displaying the three-dimensional crack and the length, the width and the crack direction corresponding to the three-dimensional crack.

[0012] The second technical solution of the present application is implemented by the following measures: a three-dimensional crack identification device for implementing the three-dimensional crack identification method, comprising: an acquisition module configured to acquire a three-dimensional gray-scale image of a core sample; a processing module configured to split the three-dimensional gray-scale image to obtain a two-dimensional image corresponding to each dimension of the three dimensions; an identification module configured to perform image identification on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image; a determination module configured to determine that the target sheet-shaped pore is a three-dimensional crack if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, the first two-dimensional image and the second two-dimensional image belonging to two-dimensional images of different dimensions.

[0013] The third technical solution of the present application is implemented by the following measures: an electronic device, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the three-dimensional crack identification method when executing the computer program.

[0014] The fourth technical solution of the present application is implemented by the following measures: a storage medium, the computer readable storage medium storing a computer program, and the computer program implementing the three-dimensional crack identification method when executed by a processor.

[0015] The fifth technical solution of the present application is implemented by the following measures: a computer program product, instructions in the computer program product being executed by an electronic device to cause the electronic device to execute the three-dimensional crack identification method.

[0016] The application obtains a three-dimensional gray scale image of a core sample, splits the three-dimensional gray scale image to obtain a two-dimensional image corresponding to each dimension of the three dimensions, and then performs image recognition on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image. If the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, the target sheet-shaped pore is determined to be a three-dimensional crack. Through the foregoing steps, image recognition is performed on each two-dimensional image to determine the target sheet-shaped pore in each two-dimensional image, and the target sheet-shaped pore is determined to be a three-dimensional crack when the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore. In this way, whether the target sheet-shaped pore is a three-dimensional crack can be determined according to the morphology of the target sheet-shaped pore in the plurality of two-dimensional images, thereby improving the reliability of three-dimensional crack identification. BRIEF DESCRIPTION OF DRAWINGS

[0017] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 1 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0018] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 2 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0019] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 2 In FIG. 1, (a) is a top view of a micron CT three-dimensional image of a core sample; The left image of (b) is a partial enlarged view of (a); The right image of (b) is a partial enlarged view of (d); (c) is a gray scale histogram of (a); (d) is a two-dimensional image.

[0020] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 3 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0021] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 4 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0022] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 5 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0023] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 6 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0024] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 7 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0025] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 8 FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application.

[0026] FIG. 1 is a flowchart of a three-dimensional crack identification method provided by an embodiment of the application. Figure 9This is a schematic diagram of the structure of the three-dimensional crack recognition device provided in the embodiments of this application.

[0027] Appendix Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0028] The present invention is not limited to the following embodiments, and the specific implementation can be determined according to the technical solution of the present invention and the actual situation.

[0029] In this invention, it should be noted that the terms "first," "second," "third," etc., are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the modules or elements referred to must have a specific order and operation, nor should they be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. They are used to distinguish similar objects.

[0030] First, let's analyze some of the terms used in this application: Three-dimensional cracks: Cracks are naturally occurring discontinuities in rocks, formed by tectonic deformation or physical diagenesis. Three-dimensional cracks, however, are cracks with a defined shape and size in three-dimensional space.

[0031] 3D grayscale image: A 3D grayscale image is a special image representation method that extends the concept of grayscale images to three-dimensional space. Specifically, a 3D grayscale image displays the distribution of grayscale values ​​in a three-dimensional form. It maps each pixel of the image to a three-dimensional space using the grayscale values ​​as height (or depth) information, thus forming a three-dimensional grayscale distribution map. This representation method can more intuitively show the distribution of grayscale values ​​in a grayscale image, facilitating deeper image analysis and processing.

[0032] Pores are the spaces within a rock that are not filled with solid material. They can be filled with air, water, or other fluids, and are an important parameter describing the internal structure and reservoir properties of a rock. The degree of development, size, and connectivity of pores have a significant impact on the evaluation and development of oil and gas reservoirs.

[0033] Rock skeleton: The rock skeleton is mainly composed of various mineral grains. These mineral grains play a supporting role in the rock and form its basic framework. Different types of rocks have different mineral compositions.

[0034] The present invention will be further described below with reference to embodiments: Example 1: As Figure 1 As shown, a three-dimensional crack identification method includes the following steps: In step 101, a three-dimensional gray-scale image of the core sample is obtained. In step 102, the three-dimensional gray-scale image is split to obtain a two-dimensional image corresponding to each dimension. In step 103, image recognition is performed on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image. In step 104, if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, the target sheet-shaped pore is determined to be a three-dimensional fracture, and the first two-dimensional image and the second two-dimensional image belong to two-dimensional images of different dimensions.

[0035] Specifically, the core sample includes pores and rock matrix. The core sample can be scanned by a computer tomography device (such as a computer tomography (CT)) to obtain a three-dimensional gray-scale image of the core sample. At this time, the three-dimensional gray-scale image includes pore information and rock matrix information. The pore information includes a gray-scale value and three-dimensional coordinates corresponding to the pores, and the rock matrix information includes a gray-scale value and three-dimensional coordinates corresponding to the rock matrix. The computer tomography device can use a micron computer tomography device to achieve high-precision scanning of the core sample. Subsequently, the three-dimensional gray-scale image can be split based on three dimensions to obtain a two-dimensional image corresponding to each dimension. In this way, subsequent processing can be performed on each two-dimensional image to fully utilize information in different directions and improve the comprehensiveness and accuracy of three-dimensional fracture identification.

[0036] Through multi-directional two-dimensional slice processing (two-dimensional image), high-precision and high-efficiency fracture identification is achieved. This method significantly improves the reliability and calculation speed of fracture analysis without changing the original pore structure, has wide application value, and can provide strong data support for the development and research of unconventional oil and gas resources.

[0037] After obtaining the two-dimensional image corresponding to each dimension, image recognition can be performed on each two-dimensional image by a pore recognition algorithm to determine the target sheet-shaped pore in each two-dimensional image. For example, the pore recognition algorithm can use a threshold segmentation method, a clustering algorithm, an edge detection algorithm, or other algorithms capable of identifying sheet-shaped pores in a two-dimensional image, without limitation.

[0038] To improve the accuracy of three-dimensional crack identification, information of the target sheet-like pore in different directions can be used to determine whether the target sheet-like pore is a three-dimensional crack. Specifically, in the case that the target sheet-like pore is included in both the first two-dimensional image and the second two-dimensional image, the target sheet-like pore can be determined to be a three-dimensional crack, wherein the first two-dimensional image and the second two-dimensional image belong to different two-dimensional images of different dimensions, and the first two-dimensional image or the second two-dimensional image can be a two-dimensional image of one dimension or a two-dimensional image including two different dimensions, i.e., in the case that the target sheet-like pore is included in two-dimensional images of at least two of the three dimensions, the target sheet-like pore can be determined to be a three-dimensional crack. In this way, the possibility of false detection or missed detection of three-dimensional cracks in a single direction can be reduced, and the reliability of the identification result can be improved.

[0039] The present application determines the target sheet-like pore in each two-dimensional image by image recognition, and determines the target sheet-like pore to be a three-dimensional crack when the target sheet-like pore is included in both the first two-dimensional image and the second two-dimensional image. In this way, whether the target sheet-like pore is a three-dimensional crack can be determined according to the morphology of the target sheet-like pore in multiple two-dimensional images, thereby improving the reliability of three-dimensional crack identification.

[0040] In an embodiment, the three-dimensional gray-scale image is split to obtain a two-dimensional image corresponding to each of the three dimensions, including: The three-dimensional gray-scale image is binarized to obtain a three-dimensional binarized image; The three-dimensional binarized image is split to obtain a two-dimensional image corresponding to each of the three dimensions.

[0041] The three-dimensional gray-scale image is split to obtain a two-dimensional image corresponding to each of the three dimensions. Specifically, first, to improve the efficiency of subsequent image recognition of the two-dimensional image, the three-dimensional gray-scale image can be binarized by threshold segmentation to obtain a three-dimensional binarized image. That is, the gray-scale value of each voxel in the three-dimensional gray-scale image can be compared with a preset threshold, and a first identifier (e.g., the first identifier can be 1) can be used to mark the voxel with a gray-scale value greater than the preset threshold, and a second identifier (e.g., the second identifier can be 0) can be used to mark the voxel with a gray-scale value less than or equal to the preset threshold, thereby obtaining the three-dimensional binarized image. The preset threshold can be adjusted according to actual conditions, which is not limited herein. Subsequently, the three-dimensional binarized image can be split based on the three dimensions of the three-dimensional binarized image, thereby obtaining a two-dimensional image corresponding to each of the three dimensions. In this way, subsequent processing can be performed for each two-dimensional image, thereby fully utilizing information in different directions to improve the comprehensiveness and accuracy of three-dimensional crack identification.

[0042] For example,Figure 2 (a) is a top view of a micro-CT three-dimensional image of a certain core sample, Figure 2 (b) is a left view of Figure 2 (a) is a local enlarged view of Figure 2 (c) is Figure 2 (a) is a gray scale histogram. For Figure 2 After threshold segmentation of (a), white is marked as pore (i.e., first mark), and black is marked as skeleton (i.e., second mark), forming Figure 2 (d).

[0043] Embodiment 3: As an optimization of the above-mentioned embodiment 2, the three-dimensional binarized image is subjected to splitting processing to obtain a two-dimensional image corresponding to each of the three dimensions, including: The three-dimensional binarized image is subjected to splitting processing along the x-axis, y-axis and z-axis respectively to obtain at least one two-dimensional image corresponding to the x-axis, at least one two-dimensional image corresponding to the y-axis and at least one two-dimensional image corresponding to the z-axis.

[0044] Specifically, the three dimensions are the x-axis, y-axis and z-axis, wherein the x-axis, y-axis and z-axis are perpendicular to each other. When the three-dimensional binarized image is subjected to splitting processing along the x-axis, for each coordinate value on the x-axis, all coordinate values on the y-axis and z-axis corresponding to the coordinate value on the x-axis are extracted to generate a two-dimensional image. When there is only one coordinate value on the x-axis in the three-dimensional gray scale image, one two-dimensional image corresponding to the x-axis can be obtained by splitting. When there are multiple coordinate values on the x-axis in the three-dimensional gray scale image, multiple two-dimensional images corresponding to the x-axis can be obtained after multiple splitting processing. In this way, at least one two-dimensional image corresponding to the x-axis can be obtained.

[0045] Similarly, when the three-dimensional binarized image is subjected to splitting processing along the y-axis, for each coordinate value on the y-axis, all coordinate values on the x-axis and z-axis corresponding to the coordinate value on the y-axis are extracted to generate a two-dimensional image. When there is only one coordinate value on the y-axis in the three-dimensional gray scale image, one two-dimensional image corresponding to the y-axis can be obtained by splitting. When there are multiple coordinate values on the y-axis in the three-dimensional gray scale image, multiple two-dimensional images corresponding to the y-axis can be obtained after multiple splitting processing. In this way, at least one two-dimensional image corresponding to the y-axis can be obtained.

[0046] When the three-dimensional binarized image is split along the z-axis, for each coordinate value on the z-axis, all coordinate values on the x-axis and y-axis corresponding to the coordinate value on the z-axis are extracted to generate a two-dimensional image. When there is only one coordinate value on the z-axis in the three-dimensional gray image, a two-dimensional image corresponding to the z-axis can be obtained by splitting. When there are multiple coordinate values on the z-axis in the three-dimensional gray image, multiple two-dimensional images corresponding to the z-axis can be obtained by multiple splitting. In this way, at least one two-dimensional image corresponding to the z-axis can be obtained.

[0047] After the three-dimensional binarized image is split along the x-axis, y-axis and z-axis respectively, at least one two-dimensional image corresponding to the x-axis, at least one two-dimensional image corresponding to the y-axis and at least one two-dimensional image corresponding to the z-axis can be obtained for subsequent image recognition.

[0048] In an embodiment 4, as an optimization of the above-mentioned embodiments, image recognition is performed on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image, including: Image recognition is performed on the sheet-shaped pore in each two-dimensional image, and in the case where the sheet-shaped pore is identified, a minimum circumscribed rectangle of the sheet-shaped pore is obtained, as shown in Figure 2 (b); If the ratio between the length and the width of the minimum circumscribed rectangle of the sheet-shaped pore is greater than a preset value, the sheet-shaped pore is marked as the target sheet-shaped pore.

[0049] Specifically, the sheet-shaped pore in each two-dimensional image can be identified by a pore recognition algorithm. For example, if the two-dimensional image is obtained by splitting the three-dimensional binarized image, and the two-dimensional image includes a first mark and a second mark, the sheet-shaped pore in the two-dimensional image can be identified according to the first mark and the second mark in the two-dimensional image. For the sheet-shaped pore in each two-dimensional image, a minimum circumscribed rectangle of the sheet-shaped pore, i.e., a minimum rectangle that can completely enclose the sheet-shaped pore, can be obtained. For example, the minimum circumscribed rectangle of the sheet-shaped pore can be constructed by a minimum circumscribed rectangle algorithm. In this way, the length and the width of the minimum circumscribed rectangle of the sheet-shaped pore can be obtained, and the ratio between the length and the width of the minimum circumscribed rectangle of the sheet-shaped pore can be determined. If the ratio is greater than a preset value, the sheet-shaped pore can be marked as the target sheet-shaped pore. The preset value can be determined according to actual conditions, for example, the preset value can be 5, 7 or other values. Through the foregoing steps, the morphology of the sheet-shaped pore can be accurately captured without simplifying or modifying the original pore structure, ensuring the authenticity of the recognition result and the integrity of the data, and reducing the impact on the recognition result caused by simplifying the morphology of the sheet-shaped pore.

[0050] Embodiment 5: As an optimization of the above-mentioned embodiments, if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, the method further includes: obtaining the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image; if the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image match the three-dimensional coordinates of the target sheet-shaped pore in the second two-dimensional image, determining that the target sheet-shaped pore is a three-dimensional fracture.

[0051] Multiple target sheet-shaped pores can be identified in each two-dimensional image, so the three-dimensional coordinates of each target sheet-shaped pore in each two-dimensional image can be used to match the target sheet-shaped pores in different two-dimensional images to determine the same sheet-shaped pores in different two-dimensional images, thereby improving the reliability of three-dimensional fracture identification. Specifically, the three-dimensional gray-scale image includes three-dimensional coordinates, and the two-dimensional images obtained by splitting the three-dimensional gray-scale image still retain the information of the three-dimensional coordinates. At this time, the first two-dimensional image and the second two-dimensional image both include the three-dimensional coordinates of at least one target sheet-shaped pore. Therefore, the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image can be obtained, and the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image can be matched with the three-dimensional coordinates of the target sheet-shaped pore in the second two-dimensional image. If the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image match the three-dimensional coordinates of any target sheet-shaped pore in the second two-dimensional image, the target sheet-shaped pore can be determined to be a three-dimensional fracture. In this way, the identification of the three-dimensional fracture can be completed, and the reliability of three-dimensional fracture identification can be improved.

[0052] Embodiment 6: As an optimization of the above-mentioned embodiments, after determining that the target sheet-shaped pore is a three-dimensional fracture, the method further includes: obtaining the length, width, and fracture direction corresponding to the three-dimensional fracture; displaying the three-dimensional fracture and the length, width, and fracture direction corresponding to the three-dimensional fracture.

[0053] To support subsequent rock mechanics property evaluation and reservoir modeling, after identifying the three-dimensional fracture in the core sample, the length, width, and fracture direction corresponding to the three-dimensional fracture can be obtained according to the image recognition result of the pore identification algorithm, and the three-dimensional fracture can be visualized and displayed. At the same time, the length, width, and fracture direction corresponding to the three-dimensional fracture can be exported for display. In this way, the convenience of users when viewing the related data of the three-dimensional fracture can be improved.

[0054] It should be noted that based on a parallel computing architecture (such as multi-threading or GPU acceleration), the electronic device can perform the processes of the aforementioned three-dimensional gray-scale image splitting, two-dimensional image identification, and three-dimensional fracture identification in parallel to improve processing efficiency.

[0055] Example 7: A three-dimensional crack identification method, comprising the following steps: Step 1, Data Acquisition and Preprocessing: High-precision three-dimensional scanning of core samples was performed using a micron-sized computed tomography (CT) device to obtain a three-dimensional grayscale image containing pore information and rock skeleton information. The three-dimensional grayscale image was then binarized by threshold segmentation, so that the pore information in the three-dimensional grayscale image was marked as 0 and the rock skeleton information was marked as 1, resulting in a three-dimensional binarized image.

[0056] Step 2, Image Processing: The three-dimensional binary image is split into at least one two-dimensional image along the x, y, and z axes respectively, resulting in at least one two-dimensional image corresponding to the x-axis, at least one two-dimensional image corresponding to the y-axis, and at least one two-dimensional image corresponding to the z-axis. like Figure 4 As shown, this two-dimensional image is obtained by splitting a three-dimensional binarized image of a core sample along the z-axis. Figure 3 and Figure 4 The difference is: Figure 3 It is a 2D grayscale image without threshold segmentation. After threshold segmentation, Figure 3 The black parts are marked as pores, and the other parts are marked as the skeleton, forming... Figure 4 , Figure 4 It is a two-dimensional image after thresholding.

[0057] like Figure 6 As shown, this two-dimensional image is obtained by splitting a three-dimensional binarized image of a core sample along the y-axis. Figure 5 and Figure 6 The difference is: Figure 5 It is a 2D grayscale image without threshold segmentation. After threshold segmentation, Figure 5 The black parts are marked as pores, and the other parts are marked as the skeleton, forming... Figure 6 , Figure 6 It is a two-dimensional image after thresholding.

[0058] like Figure 8 As shown, this two-dimensional image is obtained by splitting a three-dimensional binarized image of a core sample along the x-axis. Figure 7 and Figure 8 The difference is: Figure 7 It is a 2D grayscale image without threshold segmentation. After threshold segmentation, Figure 7 The black parts are marked as pores, and the other parts are marked as the skeleton, forming... Figure 8 , Figure 8 It is a two-dimensional image after thresholding.

[0059] Figure 4 , Figure 6 ,Figure 8 In the image, the blue portion represents porosity information.

[0060] For each two-dimensional image, identify sheet-like pore regions (i.e., sheet-like pores) in each two-dimensional image, and construct the minimum bounding rectangle (i.e., minimum bounding rectangle) corresponding to the sheet-like pores. Calculate the ratio between the length and width of each minimum bounding rectangle, and mark the sheet-like pores of the corresponding minimum bounding rectangles that satisfy the preset value as target sheet-like pores according to a preset value (e.g., the ratio is greater than 7).

[0061] Step 3, 3D crack identification: The target sheet-like pore markings in the two-dimensional images obtained by processing along the three directions of x-axis, y-axis and z-axis are summarized; A voting mechanism is employed, requiring a three-dimensional crack to be identified as a target sheet-like pore in at least two directions. This allows for the identification of three-dimensional cracks.

[0062] Compared with existing technologies, the three-dimensional crack identification method provided in this application has the following advantages: (1) For the first time, the three-dimensional grayscale image is split into two-dimensional images along the x-axis, y-axis and z-axis, and the two-dimensional images are processed independently. This can make full use of information from different directions and improve the comprehensiveness and accuracy of three-dimensional crack identification.

[0063] (2) By constructing the minimum bounding rectangle, the shape of the inclined crack can be accurately captured, avoiding the simplification of crack shape by traditional methods.

[0064] (3) By setting the three-dimensional cracks to be identified simultaneously in multiple directions, the possibility of false detection and missed detection of three-dimensional cracks in a single direction can be reduced, thereby improving the reliability of the identification results.

[0065] (4) During the three-dimensional crack identification process, the original pore structure is not simplified or changed in any way to ensure the authenticity of the identification results and the integrity of the data.

[0066] Example 8: As Figure 9 As shown, a three-dimensional crack identification device 200 for implementing the three-dimensional crack identification method includes: The acquisition module 201 is used to acquire a three-dimensional grayscale image of the core sample; Processing module 202 is used to split the three-dimensional grayscale image to obtain a two-dimensional image corresponding to each of the three dimensions; The recognition module 203 is used to perform image recognition on each of the two-dimensional images and determine the target sheet-like pores in each of the two-dimensional images; The determining module 204 is configured to determine that the target sheet-shaped pore is a three-dimensional fracture if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, the first two-dimensional image and the second two-dimensional image being two-dimensional images of different dimensions.

[0067] Specifically, the processing module 202 includes: The first processing submodule is configured to perform binaryzation processing on the three-dimensional gray-scale image to obtain a three-dimensional binaryzation image. The second processing submodule is configured to perform splitting processing on the three-dimensional binaryzation image to obtain a two-dimensional image corresponding to each of the three dimensions.

[0068] The identifying module 203 includes: The identifying submodule is configured to perform image identification on a sheet-shaped pore in each of the two-dimensional images, and acquire a minimum circumscribed rectangle of the sheet-shaped pore if the sheet-shaped pore is identified. The marking submodule is configured to mark the sheet-shaped pore as the target sheet-shaped pore if a ratio between a length and a width of the minimum circumscribed rectangle of the sheet-shaped pore is greater than a preset value.

[0069] The processing module 202 includes: The third processing submodule is configured to perform splitting processing on the three-dimensional gray-scale image along an x-axis, a y-axis and a z-axis respectively to obtain at least one two-dimensional image corresponding to the x-axis, at least one two-dimensional image corresponding to the y-axis and at least one two-dimensional image corresponding to the z-axis.

[0070] The determining module 204 includes: The first acquiring submodule is configured to acquire a three-dimensional coordinate of the target sheet-shaped pore in the first two-dimensional image. The determining submodule is configured to determine that the target sheet-shaped pore is a three-dimensional fracture if the three-dimensional coordinate of the target sheet-shaped pore in the first two-dimensional image matches a three-dimensional coordinate of a target sheet-shaped pore in the second two-dimensional image.

[0071] The three-dimensional fracture identification apparatus 200 further includes a display module, which includes: The second acquiring submodule is configured to acquire a length, a width and a fracture direction corresponding to the three-dimensional fracture. The display submodule is configured to display the three-dimensional fracture and the length, the width and the fracture direction corresponding to the three-dimensional fracture.

[0072] Embodiment 9: An electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the three-dimensional fracture identification method when executing the computer program.

[0073] The electronic device can be any intelligent terminal including a tablet computer, an on-board computer, etc.

[0074] The hardware structure schematic diagram of the electronic device provided by the embodiments of the present application is shown in Figure 10 The electronic device comprises: The processor 301 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., and is used to execute related programs to implement the technical solutions provided by the embodiments of the present application. The memory 302 can be implemented by a ROM (Read-Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), etc. The memory 302 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 302 and are called and executed by the processor 301 to implement the three-dimensional fracture identification method of the embodiments of the present application. The input / output interface 303 is used to realize information input and output. The communication interface 304 is used to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.). The bus 305 is used to transmit information between various components (for example, the processor 301, the memory 302, the input / output interface 303, and the communication interface 304) of the device. The processor 301, the memory 302, the input / output interface 303, and the communication interface 304 are connected to each other by the bus 305 to realize the communication connection between them in the device.

[0075] Embodiment 10: A storage medium, the storage medium stores a computer program, and the computer program is executed by a processor to implement the three-dimensional fracture identification method.

[0076] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include remotely disposed memory relative to the processor, which can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0077] Embodiment 11: A computer program product, instructions in the computer program product being executed by an electronic device to cause the electronic device to perform the three-dimensional fracture identification method.

[0078] The above technical features respectively constitute embodiments of the present application, which have strong adaptability and implementation effect. Non-essential technical features can be added or removed according to actual needs to meet the needs of different situations.

Claims

1. A method of three-dimensional fracture identification, characterized by, The method comprises the following steps: obtaining a three-dimensional gray image of a core sample; splitting the three-dimensional gray image to obtain a two-dimensional image corresponding to each dimension; image recognition is performed on each two-dimensional image to determine the target sheet-shaped pore in each two-dimensional image; if the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, it is determined that the target sheet-shaped pore is a three-dimensional fracture, and the first two-dimensional image and the second two-dimensional image belong to two-dimensional images of different dimensions.

2. The three-dimensional fracture identification method of claim 1, wherein, The splitting of the three-dimensional gray image to obtain a two-dimensional image corresponding to each dimension comprises: performing binaryzation processing on the three-dimensional gray image to obtain a three-dimensional binary image; splitting the three-dimensional binary image to obtain a two-dimensional image corresponding to each dimension.

3. The three-dimensional fracture identification method of claim 2, wherein, The splitting of the three-dimensional binary image to obtain a two-dimensional image corresponding to each dimension comprises: splitting the three-dimensional gray image along the x-axis, y-axis and z-axis to obtain at least one two-dimensional image corresponding to the x-axis, at least one two-dimensional image corresponding to the y-axis and at least one two-dimensional image corresponding to the z-axis.

4. The three-dimensional fracture identification method according to claim 1 or 2 or 3, characterized by, The image recognition performed on each two-dimensional image to determine the target sheet-shaped pore in each two-dimensional image comprises: image recognition is performed on the sheet-shaped pore in each two-dimensional image, and in the case that a sheet-shaped pore is recognized, the minimum circumscribed rectangle of the sheet-shaped pore is obtained; if the ratio between the length and the width of the minimum circumscribed rectangle of the sheet-shaped pore is greater than a preset value, the sheet-shaped pore is marked as the target sheet-shaped pore.

5. The three-dimensional fracture identification method according to claim 1 or 2 or 3, characterized by, If the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, it is determined that the target sheet-shaped pore is a three-dimensional fracture, which comprises: obtaining the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image; if the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image match the three-dimensional coordinates of the target sheet-shaped pore in the second two-dimensional image successfully, it is determined that the target sheet-shaped pore is a three-dimensional fracture; or / and, after determining that the target sheet-shaped pore is a three-dimensional fracture, the method further comprises: obtaining the length, width and fracture direction corresponding to the three-dimensional fracture; displaying the three-dimensional fracture and the length, width and fracture direction corresponding to the three-dimensional fracture.

6. The three-dimensional fracture identification method of claim 4, wherein, If the first two-dimensional image and the second two-dimensional image both include the target sheet-shaped pore, it is determined that the target sheet-shaped pore is a three-dimensional fracture, which comprises: obtaining the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image; if the three-dimensional coordinates of the target sheet-shaped pore in the first two-dimensional image match the three-dimensional coordinates of the target sheet-shaped pore in the second two-dimensional image successfully, it is determined that the target sheet-shaped pore is a three-dimensional fracture; or / and, after determining that the target sheet-shaped pore is a three-dimensional fracture, the method further comprises: obtaining the length, width and fracture direction corresponding to the three-dimensional fracture; displaying the three-dimensional fracture and the length, width and fracture direction corresponding to the three-dimensional fracture.

7. A three-dimensional fracture identification device for implementing the three-dimensional fracture identification method according to any one of claims 1 to 6, characterized by, The method comprises the following steps: an obtaining module is configured to obtain a three-dimensional gray image of a core sample; A processing module is configured to split the three-dimensional gray-scale image to obtain a two-dimensional image corresponding to each dimension; An identification module is configured to perform image recognition on each two-dimensional image to determine a target sheet-shaped pore in each two-dimensional image; A determination module is configured to determine that the target sheet-shaped pore is a three-dimensional crack if the target sheet-shaped pore is included in both a first two-dimensional image and a second two-dimensional image, the first two-dimensional image and the second two-dimensional image belonging to different two-dimensional images.

8. An electronic device, comprising: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the three-dimensional crack identification method of any one of claims 1 to 6 when executing the computer program.

9. A storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the three-dimensional crack identification method of any one of claims 1 to 6.

10. A computer program product, characterised in that, The instructions in the computer program product are executed by the electronic device to cause the electronic device to perform the three-dimensional crack identification method of any one of claims 1 to 6.

Images