Method for evaluating reservoir productivity based on shale whole-core ct image

Abstract

A method for evaluating reservoir productivity based on CT images of shale whole-core samples is disclosed. The method includes: acquiring a 3D labeled image of the shale whole-core sample from the target reservoir, where the 3D labeled image includes labels for each phase within the shale whole-core sample, obtained from the CT image of the shale whole-core sample; calculating multidimensional feature parameters of the fracture network in the shale whole-core sample based on voxels labeled as fracture facies in the 3D labeled image, obtaining a multidimensional feature parameter set corresponding to the fracture network; determining a target weight coefficient set based on the target geological application scenario corresponding to the target reservoir; the weight coefficient set contains the weights corresponding to each feature parameter in the multidimensional feature parameter set; and weighting and summing the feature parameters in the multidimensional feature parameter set according to the weights corresponding to each feature parameter in the target weight coefficient set to obtain the productivity evaluation of the target reservoir. This method aims to improve the accuracy of reservoir productivity evaluation.

Description

Technical Field

[0001] This application relates to the field of reservoir analysis, and in particular to a method for evaluating reservoir productivity based on whole-core CT images of shale. Background Technology

[0002] Reservoir productivity assessment is a core step in shale oil and gas exploration and development, directly determining the formulation of exploration and development plans, the evaluation of resource potential, and the level of development efficiency. Shale whole core samples are the most direct and authentic physical data for obtaining subsurface reservoir information. The fracture network within shale whole core samples is a key space for oil and gas occurrence and flow; accurate quantitative characterization of this network is the foundation for reservoir evaluation, productivity prediction, and development plan optimization.

[0003] In related technologies, reservoir productivity evaluation methods mostly rely on core experimental analysis. Such methods require sampling and preparation of whole shale cores, which is not only time-consuming, labor-intensive, and costly, but also easily damages the original structure of the core during the sampling process, leading to deviations between the experimental results and the actual situation of the reservoir. This results in poor accuracy of the evaluation results and cannot meet the needs of actual geological exploration and development. Summary of the Invention

[0004] The main objective of this application is to propose a method, apparatus, electronic device, and storage medium for evaluating reservoir productivity based on shale whole-core CT images, aiming to solve the problem of low accuracy in existing reservoir productivity evaluation methods.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for evaluating reservoir productivity based on whole-core CT images of shale, the method comprising: A three-dimensional label map of a whole shale core in a target reservoir is obtained. The three-dimensional label map includes labels for each phase in the whole shale core. The three-dimensional label map is obtained from CT images of the whole shale core. Based on the voxels labeled as fracture facies in the three-dimensional label map, multidimensional feature parameters are calculated for the fracture network of the shale whole core to obtain the multidimensional feature parameter set corresponding to the fracture network; the multidimensional feature parameter set includes at least two of the following feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness. Based on the target geological application scenario corresponding to the target reservoir, a target weight coefficient set is determined; the weight coefficient set includes the weights corresponding to each feature parameter in the multidimensional feature parameter set; Based on the weights corresponding to each feature parameter in the target weight coefficient set, the feature parameters in the multidimensional feature parameter set are weighted and summed to obtain the productivity evaluation of the target reservoir.

[0006] In some implementations, the three-dimensional labeled map of the whole shale core in the target reservoir includes: Obtain a three-dimensional grayscale image of the whole shale core from the target reservoir; The gray values ​​in the three-dimensional grayscale image are calculated to obtain the gray value distribution histogram of the three-dimensional grayscale image; The three-dimensional grayscale image is segmented based on the grayscale distribution histogram to obtain the three-dimensional label image.

[0007] In some embodiments, segmenting the three-dimensional grayscale image based on the grayscale distribution histogram to obtain the three-dimensional label map includes: The phases in the three-dimensional grayscale image are determined based on the peaks in the grayscale distribution histogram; the phases are used to characterize the components in the three-dimensional grayscale image. The number of phases is used as the number of clusters, and the gray value corresponding to the peak is used as the initial cluster center. The three-dimensional grayscale image is clustered and segmented to obtain the three-dimensional label map. Each voxel in the three-dimensional label map is assigned a label corresponding to the phase of the voxel.

[0008] In some implementations, the crack orientation parameters are calculated through the following steps: For each crack voxel in the 3D label image, obtain the normal vector of each crack voxel; the crack voxel is the voxel labeled as the crack phase in the 3D label image. The fracture orientation parameters are determined based on the angle between the normal vector of each fracture voxel and the preset coordinate axis; the fracture orientation parameters are used to characterize the concentration of fracture development direction.

[0009] In some implementations, the crack connectivity parameter is calculated by the following steps: Three-dimensional connectivity analysis was performed on all the crack voxels in the three-dimensional label map to identify multiple connected crack clusters; the crack voxels in the connected crack clusters were interconnected. The largest connected fracture cluster among the plurality of connected fracture clusters is identified as the target connected fracture cluster; The ratio of the volume of the connected fracture cluster to the total volume of all fractures in the three-dimensional label map is determined as the fracture connectivity parameter; the fracture connectivity parameter is used to characterize the ability of the fracture network to form effective seepage channels.

[0010] In some implementations, the surface roughness of the crack is calculated by the following steps: Obtain the height of each point on the crack surface in the 3D label image; The average height of the crack surface is determined based on the height of each point on the crack surface. The surface roughness of the crack is determined based on the difference between the height of each point on the crack surface and the average height of the crack surface; the surface roughness of the crack is used to characterize the degree of unevenness of the crack surface.

[0011] In some implementations, determining the target weight coefficient set based on the target geological application scenario corresponding to the target reservoir includes: Based on the target geological application scenario, the target weight coefficient set is obtained by matching from a preset geological knowledge base; The geological knowledge base stores multiple geological application scenarios and a set of weight coefficients corresponding to each geological application scenario. The weight of the target parameter in the set of weight coefficients corresponding to each geological application scenario is higher than the weight of the target parameter in the set of weight coefficients corresponding to other geological application scenarios. The target parameter corresponding to each geological application scenario is a parameter in the set of weight coefficients that matches the geological application scenario.

[0012] To achieve the above objectives, a second aspect of this application proposes a device for evaluating reservoir productivity based on whole-core CT images of shale rocks, the device comprising: The image acquisition module is used to acquire a three-dimensional label map of a whole shale core in the target reservoir. The three-dimensional label map includes labels for each phase in the whole shale core. The three-dimensional label map is obtained from the CT image of the whole shale core. The parameter calculation module is used to calculate the multidimensional feature parameters of the fracture network of the shale whole core based on the voxels labeled as fracture phase in the three-dimensional label map, and obtain the multidimensional feature parameter set corresponding to the fracture network. The multidimensional feature parameter set includes at least two of the following feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness. The weight determination module is used to determine the target weight coefficient set based on the target geological application scenario corresponding to the target reservoir; the weight coefficient set includes the weights corresponding to each feature parameter in the multidimensional feature parameter set; The evaluation calculation module is used to perform weighted summation of the feature parameters in the multidimensional feature parameter set according to the weights corresponding to each feature parameter in the target weight coefficient set, so as to obtain the productivity evaluation of the target reservoir.

[0013] To achieve the above objectives, a third aspect of this application proposes an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method for evaluating reservoir productivity based on shale whole-core CT images described in the first aspect.

[0014] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for evaluating reservoir productivity based on shale whole-core CT images as described in the first aspect.

[0015] To achieve the above objectives, embodiments of this application may provide a computer program product, wherein the instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to implement the method for evaluating reservoir productivity based on shale whole-core CT images as described in the first aspect.

[0016] This application proposes a method for evaluating reservoir productivity based on CT images of shale whole-core samples. This method involves acquiring a 3D labeled image of the shale whole-core sample from the target reservoir. The 3D labeled image includes labels for each phase within the shale whole-core sample and is derived from the CT image of the shale whole-core sample. Based on voxels labeled as fracture phases in the 3D labeled image, multidimensional feature parameters are calculated for the fracture network in the shale whole-core sample, resulting in a multidimensional feature parameter set corresponding to the fracture network. This multidimensional feature parameter set quantitatively characterizes the fracture network from multiple dimensions, including geometric morphology, topology, and fluid flow capacity. A target weight coefficient set is determined based on the target geological application scenario corresponding to the target reservoir. By dynamically determining the weights of each feature parameter according to different target geological application scenarios, the final comprehensive evaluation can flexibly adapt to specific engineering needs. Finally, based on the weights corresponding to each feature parameter in the target weight coefficient set, the feature parameters in the multidimensional feature parameter set are weighted and summed to obtain the productivity evaluation of the target reservoir. Therefore, by using a multidimensional feature parameter set, the limitations of single-index evaluation are overcome. It can comprehensively and accurately quantify the complex geometric morphology and flow characteristics of fracture networks, and dynamically determine the weight of each feature parameter according to different target geological application scenarios. Finally, the multidimensional feature parameters are transformed into intuitive comprehensive evaluation indicators through weighted summation, so as to achieve a leap from "static single-parameter calculation" to "multidimensional intelligent evaluation", effectively improving the accuracy of target reservoir productivity evaluation. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the method for evaluating reservoir productivity based on whole-core CT images of shale provided in this application embodiment; Figure 2 This is a schematic diagram illustrating the implementation process of a method for evaluating reservoir productivity based on whole-core CT images of shale, provided in an embodiment of this application. Figure 3 This is a schematic diagram of a three-dimensional grayscale image clustering and segmentation process provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating a feature parameter calculation provided in an embodiment of this application; Figure 5 This is a schematic diagram illustrating the calculation process of a comprehensive evaluation index provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of the device for evaluating reservoir productivity based on shale whole-core CT images provided in this application embodiment; Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] Fracture and pore networks in reservoir rocks are key spaces for oil and gas occurrence and flow. Accurate quantitative characterization of these networks is fundamental for reservoir evaluation, production prediction, and development scheme optimization. Computed tomography (CT) scanning technology, as a powerful non-destructive three-dimensional imaging method, has been widely used to obtain the microstructure of the interior of shale core samples.

[0022] However, objectively and accurately extracting meaningful quantitative parameters from massive amounts of CT image data containing complex noise and artifacts remains a significant challenge. Existing technologies have limitations in two main areas: Limitations of segmentation methods: Traditional image segmentation methods, such as manual thresholding, heavily rely on the operator's experience, are highly subjective, and have poor repeatability. While some automatic segmentation algorithms, such as the classic K-means clustering, can achieve automation, their results are extremely sensitive to the selection of initial parameters (such as the number of clusters and initial centers). Small parameter changes can lead to huge differences in the segmentation results, making them unreliable in geological evaluation applications that require high accuracy and stability.

[0023] Limitations of the evaluation system: More importantly, existing evaluation methods are often "single-parameter" or "low-dimensional." For example, when evaluating a fracture network, only its total porosity or average aperture may be considered. This "seeing the trees but not the forest" approach ignores key factors determining the reservoir's true permeability, such as the spatial orientation of fractures (whether they align with the principal stress direction), topological connectivity (whether they form effective permeability channels), and surface roughness (affecting non-Darcy flow effects). Furthermore, existing technologies often cannot effectively distinguish and evaluate fractures of different origins, such as natural fractures (or sedimentary weak surfaces) reflecting the primary geological environment and artificial hydraulic fractures reflecting reservoir modifiability. The lack of a comprehensive evaluation index that integrates multiple aspects of information leads to significant biases in reservoir understanding, thus affecting the accuracy of development decisions.

[0024] Based on this, embodiments of this application provide a method, apparatus, electronic device, and storage medium for evaluating reservoir productivity based on shale whole-core CT images, aiming to solve the problem of low accuracy in evaluating reservoir productivity based on shale whole-core CT images.

[0025] The method, apparatus, electronic equipment, and storage medium for evaluating reservoir productivity based on shale whole-core CT images provided in this application are specifically described through the following embodiments. First, the method for evaluating reservoir productivity based on shale whole-core CT images in this application embodiment is described.

[0026] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0027] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0028] The method, apparatus, electronic device, and storage medium for evaluating reservoir productivity based on shale whole-core CT images provided in this application relate to the field of reservoir analysis. The method for evaluating reservoir productivity based on shale whole-core CT images provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the method for evaluating reservoir productivity based on shale whole-core CT images, but is not limited to the above forms.

[0029] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0030] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0031] Figure 1 This is a flowchart illustrating the method for evaluating reservoir productivity based on shale whole-core CT images provided in this application embodiment. Please refer to [link / reference]. Figure 1 The method for evaluating reservoir productivity based on shale whole-core CT images provided in this application embodiment may include, but is not limited to, steps S101 to S104.

[0032] Step S101: Obtain a three-dimensional label map of the whole shale core in the target reservoir. The three-dimensional label map includes labels for each phase in the whole shale core. The three-dimensional label map is obtained based on the CT image of the whole shale core.

[0033] In this step, the 3D label map is achieved through 3D scanning and image segmentation of the whole shale core in the target reservoir. Specifically, a high-resolution CT scanning device is used to scan the whole shale core of the target reservoir to obtain the original 3D CT image of the whole shale core. The CT image is then segmented using an image segmentation algorithm to identify and distinguish different phases in the whole shale core, such as fracture phase, matrix phase, and pore phase. A unique label is assigned to each phase, such as label 1 for fracture phase, label 2 for matrix phase, and label 3 for pore phase. Finally, a 3D label map containing the labels of each phase is generated. The 3D label map completely corresponds to the spatial structure of the whole shale core to accurately reflect the spatial distribution characteristics of each phase.

[0034] For example, high-resolution micro-CT can be used to perform full-size three-dimensional scanning of shale core samples to obtain a three-dimensional grayscale image of the shale core; then, image segmentation algorithms, such as threshold segmentation, region growing, and deep learning segmentation algorithms, are used to segment the three-dimensional grayscale image, identify and label different phases, and finally generate a three-dimensional label map containing the labels of each phase.

[0035] Step S102: Based on the voxels labeled as fracture phase in the three-dimensional label map, calculate the multidimensional feature parameters of the fracture network of the shale whole core to obtain the multidimensional feature parameter set corresponding to the fracture network. The multidimensional feature parameter set includes at least two of the following feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness.

[0036] In this step, voxels labeled as fracture phase (i.e., the basic units that constitute fractures in three-dimensional space) are selected from the three-dimensional label map, and multidimensional feature parameters of the fracture network of the whole shale core are calculated based on these fracture voxels, finally obtaining the multidimensional feature parameter set corresponding to the fracture network.

[0037] The multidimensional feature parameter set may include at least two of the following feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness.

[0038] Furthermore, the fracture orientation parameter is used to characterize the concentration of fracture development direction; the fracture connectivity parameter is used to characterize the connectivity between fractures in the fracture network, and the closer its value is to 1, the better the connectivity; the permeability parameter is used to characterize the permeability of the fracture network to fluids; the fracture porosity is used to characterize the volume proportion of fractures in the shale whole core; the average fracture aperture is used to characterize the average width of the fracture; and the fracture surface roughness is used to characterize the unevenness of the fracture surface.

[0039] Step S103: Determine the target weight coefficient set according to the target geological application scenario corresponding to the target reservoir; the weight coefficient set includes the weights corresponding to each feature parameter in the multidimensional feature parameter set.

[0040] In this step, the target geological application scenarios can include, but are not limited to, different geological engineering scenarios such as natural fractured reservoir evaluation and artificial fracturing effect evaluation. Since the influence of each characteristic parameter on the fracture network quality varies under different geological application scenarios, the corresponding weights will differ.

[0041] For example, in the scenario of "natural fracture reservoir evaluation", the weight of relevant parameters of natural fractures that reflect the original geological environment (such as "fracture connectivity parameters") can be increased.

[0042] For the "artificial fracturing effect evaluation" scenario, the weight of relevant parameters of artificial hydraulic fractures that reflect reservoir modifiability (such as "fracture orientation parameters" and "average fracture aperture") can be increased.

[0043] Furthermore, the target weight coefficient set corresponding to the target geological application scenario can be obtained by matching from a pre-set geological knowledge base. The geological knowledge base stores multiple geological application scenarios and the corresponding weight coefficient sets for each geological application scenario.

[0044] In other implementations, the target weight coefficient set corresponding to the target geological application scenario can be determined using methods such as the Analytic Hierarchy Process (AHP), the Delphi method (expert scoring method), and the entropy weight method. For example, when using the Analytic Hierarchy Process, the requirements of the target geological application scenario can be taken as the target layer, and each feature parameter can be taken as the criterion layer. The weight of each parameter can be calculated through steps such as constructing a judgment matrix and consistency verification.

[0045] Step S104: Based on the weights corresponding to each feature parameter in the target weight coefficient set, perform a weighted summation of the feature parameters in the multidimensional feature parameter set to obtain the production capacity of the target reservoir.

[0046] In this step, based on the weights corresponding to each feature parameter in the target weight coefficient set, a weighted summation operation is performed on the corresponding feature parameters in the multidimensional feature parameter set to finally obtain the productivity evaluation result of the shale whole core fracture network. This productivity evaluation result is used to quantitatively indicate the quality of the fracture network; the higher the value, the higher the productivity of the fracture network.

[0047] In other implementations, to eliminate the influence of dimensions, each feature parameter can be normalized before performing a weighted summation operation on the feature parameters in the multidimensional feature parameter set. For example, all parameters can be mapped to the interval of 0-1.

[0048] In some implementation methods, in specific applications, in addition to comprehensive evaluation, the specific parameters of each characteristic parameter can be displayed to technical personnel to provide a comprehensive and quantitative basis for reservoir evaluation.

[0049] In this implementation, a three-dimensional label map of the shale whole core in the target reservoir is obtained. The three-dimensional label map includes labels for each phase in the shale whole core and is derived from the CT image of the shale whole core. Based on the voxels labeled as fracture phases in the three-dimensional label map, multi-dimensional feature parameters are calculated for the fracture network of the shale whole core, resulting in a multi-dimensional feature parameter set corresponding to the fracture network. The multi-dimensional feature parameter set is used to quantitatively characterize the fracture network from multiple dimensions such as geometric morphology, topology, and fluid flow capacity. Based on the target geological application scenario corresponding to the target reservoir, a target weight coefficient set is determined. By dynamically determining the weight of each feature parameter according to different target geological application scenarios, the final comprehensive evaluation can flexibly adapt to specific engineering needs. Based on the weights corresponding to each feature parameter in the target weight coefficient set, the feature parameters in the multi-dimensional feature parameter set are weighted and summed to obtain the productivity evaluation of the target reservoir. Therefore, by using a multidimensional feature parameter set, the limitations of single-index evaluation are overcome. It can comprehensively and accurately quantify the complex geometric morphology and flow characteristics of fracture networks, and dynamically determine the weight of each feature parameter according to different target geological application scenarios. Finally, the multidimensional feature parameters are transformed into intuitive comprehensive evaluation indicators through weighted summation, so as to achieve a leap from "static single-parameter calculation" to "multidimensional intelligent evaluation", effectively improving the accuracy of target reservoir productivity evaluation.

[0050] In some implementations, obtaining the three-dimensional label map of the whole shale core in step S101 may include the following steps S201 to S203: Step S201: Obtain a three-dimensional grayscale image of the whole shale core in the target reservoir; Step S202: Calculate the gray values ​​in the three-dimensional grayscale image to obtain the gray value distribution histogram of the three-dimensional grayscale image; Step S203: Segment the three-dimensional grayscale image according to the grayscale distribution histogram to obtain the three-dimensional label image.

[0051] Step S203 may include the following: The phases in the three-dimensional grayscale image are determined based on the peaks in the grayscale distribution histogram; the phases are used to characterize the components in the three-dimensional grayscale image. The number of phases is used as the number of clusters, and the gray value corresponding to the peak is used as the initial cluster center. The three-dimensional grayscale image is clustered and segmented to obtain the three-dimensional label map. Each voxel in the three-dimensional label map is assigned a label corresponding to the phase of the voxel.

[0052] In this implementation, a high-resolution micro-CT device can be used to scan the entire shale core of the target reservoir to obtain a three-dimensional grayscale image of the entire shale core. All voxels in the three-dimensional grayscale image are traversed, and the number of voxels corresponding to each grayscale value is counted. A graph is then plotted with the grayscale value on the x-axis and the number of voxels on the y-axis to obtain a grayscale distribution histogram.

[0053] Furthermore, in the principle of CT imaging, the gray value of a voxel is directly proportional to the density of the material. Shale core samples are typically composed of materials with varying densities. For example, the rock skeleton has the highest density and the largest gray value, corresponding to a tall peak on the right side of the histogram; fractures and pores are usually filled with air or fluid, have the lowest density and the smallest gray value, corresponding to a peak or tail on the left side of the histogram; and infilling minerals (such as pyrite and calcite) have densities between those of the skeleton and fluids, potentially forming an independent peak in the middle of the histogram.

[0054] Therefore, each prominent peak actually corresponds to a specific phase in the shale core. By counting the number of peaks in the histogram, the number of different phases contained within the shale core can be determined. For example, if the histogram shows three distinct peaks, it indicates that the shale core image contains three main phases (such as matrix, fractures, and high-density minerals).

[0055] Furthermore, after determining the phase types and their corresponding gray values, clustering algorithms, such as K-Means clustering and ISODATA algorithm, are used to segment the three-dimensional grayscale image to obtain a three-dimensional label map.

[0056] For example, the K-Means clustering algorithm is used for clustering and segmentation: Step 1 Initialization: Using k as the number of clusters and C1, C2, ..., Ck as the initial cluster centers, perform K-means clustering on the 3D grayscale image. Here, K is the number of major peaks in the histogram, and C1, C2, ..., Ck are the grayscale values ​​corresponding to each peak. By directly assigning the grayscale values ​​(x-axis values) corresponding to each peak to the corresponding cluster centers, compared to randomly selecting center points, the true distribution of the data can be reflected more accurately, significantly accelerating the convergence speed of the algorithm and avoiding getting trapped in local optima.

[0057] The second step is clustering iteration: traverse each voxel in the 3D grayscale image, calculate the distance (which can be Euclidean distance) between the voxel's grayscale value and each cluster center (C1, C2, ..., CK). Assign the voxel to the category (i.e., phase) represented by the nearest cluster center.

[0058] After all voxels are assigned, the average gray value of all voxels in each category is calculated, and this average value is used as the new cluster center to update the cluster centers.

[0059] Repeat the above allocation and update steps until the change in the location of the cluster centers is less than the preset change threshold, or the maximum number of iterations is reached. At this point, the algorithm converges. It should be noted that the change threshold and the maximum number of iterations can be set according to the actual situation, and are not specifically limited here.

[0060] Step 3: Label Generation. After clustering, each voxel belongs to a specific category. Based on the category, each voxel in the 3D image is assigned a corresponding integer label value. For example, voxels belonging to the lowest gray-level peak category (representing the crack phase) are labeled "1", voxels belonging to the intermediate gray-level category are labeled "2", and voxels belonging to the highest gray-level category (representing the skeleton) are labeled "3".

[0061] In this implementation, the global statistical characteristics of grayscale histograms are used to guide cluster initialization, which can effectively distinguish the complex phase composition inside the shale core of the target reservoir, accurately extract the fracture network, and provide a high-quality data foundation for subsequent feature parameter calculation. This overcomes the fundamental defects of the traditional K-means algorithm, which is sensitive to initial parameters and has unstable results.

[0062] In some implementations, the crack orientation parameters are calculated through the following steps: For each crack voxel in the 3D label image, obtain the normal vector of each crack voxel; the crack voxel is the voxel labeled as the crack phase in the 3D label image. The fracture orientation parameters are determined based on the angle between the normal vector of each fracture voxel and the preset coordinate axis; the fracture orientation parameters are used to characterize the concentration of fracture development direction.

[0063] In this implementation, since the 3D label map is composed of discrete voxels, and each voxel does not have a defined geometric surface, it is necessary to estimate the normal vector of the crack surface through local neighborhood analysis. In this embodiment, the structure tensor method can be used to calculate the normal vector, which has good robustness when processing discrete voxel data.

[0064] The specific process of the structure tensor method may include: 1. Traverse all voxels labeled as fracture phase (i.e., fracture voxels) in the 3D label map. 2. Centered on the current crack voxel, select a neighborhood window of a preset size (e.g., a 3×3×3 or 5×5×5 cube region).

[0065] 3. Within this neighborhood window, calculate the image grayscale gradient using image gradient operators such as the Sobel or Prewitt operators. Alternatively, since it is based on the label map, the covariance matrix can be calculated directly using the distribution of voxel coordinates.

[0066] 4. Construct the structure tensor matrix J. For discrete voxels, this matrix essentially reflects the principal component directions of the crack voxel point cloud distribution within that neighborhood.

[0067] 5. Perform eigenvalue decomposition on the structure tensor matrix to obtain three eigenvalues. , , (Assuming) ≤ ≤ ) and their corresponding eigenvectors , , .

[0068] 6. When the crack exhibits a thin-layered structure, the minimum eigenvalue... corresponding feature vector That is, in the direction perpendicular to the crack surface, this feature vector The normal vector of the current crack voxel is determined. ( x , y , z ).

[0069] By performing steps 1-6 above on each crack voxel, the set of normal vectors for each crack voxel in the entire crack network can be obtained.

[0070] Furthermore, after obtaining the normal vectors, their spatial orientation distribution can be quantified to characterize the concentration of fracture development directions. In a three-dimensional Cartesian coordinate system, the Z-axis is typically set as the vertical direction (i.e., the normal direction of the bedding plane), and the X and Y axes as the horizontal directions. The Z-axis is then used as the principal coordinate axis, i.e., the preset coordinate axis. For each fracture voxel, the angle between its normal vector and the principal coordinate axis is calculated.

[0071] Specifically, the crack orientation parameters can be calculated using the following formula 1:

[0072] In the formula, R Indicates the crack orientation parameters. N This represents the total number of voxels on the surface of the crack. This represents the angle between the normal vector and the principal coordinate axis.

[0073] R The closer it is to 1, the more concentrated the location.

[0074] In some implementations, the crack connectivity parameter can be calculated by the following steps: Three-dimensional connectivity analysis was performed on all the crack voxels in the three-dimensional label map to identify multiple connected crack clusters; the crack voxels in the connected crack clusters were interconnected. The largest connected fracture cluster among the plurality of connected fracture clusters is identified as the target connected fracture cluster; The ratio of the volume of the connected fracture cluster to the total volume of all fractures in the three-dimensional label map is determined as the fracture connectivity parameter; the fracture connectivity parameter is used to characterize the ability of the fracture network to form effective seepage channels.

[0075] In this implementation, all voxels labeled as crack phases are extracted from the 3D label map. These crack voxels are then analyzed using a 3D Connected Component Labeling (3D-CCL) algorithm. In the 3D voxel mesh, the 26-connectivity criterion can be applied, meaning that a voxel is considered directly connected to its 26 neighboring voxels in the front, back, left, right, top, bottom, and diagonal directions. This aligns with the physical characteristics of crack propagation in 3D space.

[0076] Specifically, the 3D label map is scanned, and a new cluster number is assigned to each unvisited crack voxel. Using a breadth-first search (BFS) or depth-first search (DFS) algorithm, all neighboring crack voxels satisfying the 26-connectivity criterion are found around the current crack voxel, and they are grouped into the same cluster. This process is recursively executed until all voxels in the cluster have been traversed. The scan continues, searching for the next unclassified crack voxel, and the above steps are repeated until all crack voxels have been traversed.

[0077] Through the above process, the originally independent crack voxels are classified into several independent sets, resulting in multiple connected crack clusters. The voxels within each connected crack cluster are interconnected, while different connected crack clusters are completely isolated from each other.

[0078] Furthermore, after identifying all connected fracture clusters, the geometric properties of each cluster were calculated. Since the 3D label map is composed of discrete voxels, the volume of a connected fracture cluster can be directly characterized by counting the number of voxels contained in the cluster. Specifically, all identified connected fracture clusters were traversed, the number of voxels contained in each connected fracture cluster was counted, and the volume value corresponding to each connected fracture cluster was recorded. The connected fracture cluster with the largest volume value was selected as the target connected fracture cluster. The proportion of the volume of the target connected fracture cluster to the total volume of all fractures in the shale core was calculated to obtain the fracture connectivity parameter, thereby quantifying the connectivity of the fracture network.

[0079] Specifically, the crack connectivity parameter can be calculated using the following formula 2:

[0080] In the formula, B Indicates the crack connectivity parameter. This represents the volume of the target connected fracture cluster. This represents the total volume of all cracks. Among them, B The closer the value is to 1, the better the connectivity.

[0081] In some implementations, the surface roughness of the crack can be calculated by the following steps: Obtain the height of each point on the crack surface in the 3D label image; The average height of the crack surface is determined based on the height of each point on the crack surface. The surface roughness of the crack is determined based on the difference between the height of each point on the crack surface and the average height of the crack surface; the surface roughness of the crack is used to characterize the degree of unevenness of the crack surface.

[0082] In this implementation, since the 3D label map is composed of discrete voxels, and the fracture surface is the contact interface between the fracture phase voxels and the matrix phase voxels, all voxels labeled as fracture phase are traversed, and the voxel labels within their 26 neighborhoods are checked. If a voxel labeled as matrix phase exists within its neighborhood, the fracture voxel is marked as a fracture surface voxel, and its coordinates in 3D space are recorded. x , y , z ).

[0083] Furthermore, to standardize the measurement of "height," a reference benchmark can be established. For cracks with complex morphologies, the least squares method can be used to fit the coordinates of all crack surface voxels to a plane, obtaining an optimally fitted plane P. This plane approximately reflects the average orientation of the crack.

[0084] For each voxel point on the crack surface, its vertical distance to the reference plane is taken as the height of that point. After obtaining the height values ​​of all surface points, their arithmetic mean is calculated to determine the average height of the crack surface. This average height represents the offset of the geometric center of the crack surface relative to the reference plane.

[0085] Furthermore, the root mean square roughness can be used as the surface roughness of the crack. Specifically, the surface roughness of the crack can be calculated using the following formula 3:

[0086] In the formula, Indicates the surface roughness of the crack. A Indicates the surface area of ​​the crack. Indicates the height of a point on the surface. This indicates the average height.

[0087] In some implementations, the permeability parameter can be estimated based on the geometry of the fracture network by means of fluid flow simulation (such as LBM) or empirical formulas (such as the cubic law) to obtain its equivalent permeability.

[0088] In some implementations, the crack porosity can be calculated using the following formula 4:

[0089] In the formula, D represents the crack porosity. Indicates the crack volume. This indicates the total volume of the shale core.

[0090] In some implementations, the average crack aperture is used to represent the average width of the crack. This can be achieved by deploying a distance transformation algorithm within the crack to calculate the distance from each crack center point to the nearest matrix boundary, and then averaging twice the distances from all center points.

[0091] In some implementations, determining the target weight coefficient set based on the target geological application scenario corresponding to the target reservoir in step S103 may include the following: Based on the target geological application scenario, the target weight coefficient set is obtained by matching from a preset geological knowledge base; The geological knowledge base stores multiple geological application scenarios and a set of weight coefficients corresponding to each geological application scenario. The weight of the target parameter in the set of weight coefficients corresponding to each geological application scenario is higher than the weight of the target parameter in the set of weight coefficients corresponding to other geological application scenarios. The target parameter corresponding to each geological application scenario is a parameter in the set of weight coefficients that matches the geological application scenario.

[0092] In this implementation, a geological knowledge base can be pre-built. The storage structure of the geological knowledge base can be a relational database, key-value pair storage, or other similar formats, without any specific limitations.

[0093] The geological knowledge base stores a large number of data records for geological application scenarios. Each geological application scenario record contains two core parts: a scenario identifier, used to uniquely identify a specific geological research or engineering purpose, such as shale gas production prediction, geothermal reservoir assessment, CO2 geological storage site selection, hydraulic fracturing fracture propagation simulation, and bedrock permeability analysis; and a weight coefficient set, which is a weight allocation scheme for each feature parameter in the multidimensional feature parameter set corresponding to each geological application scenario.

[0094] The geological knowledge base can be constructed based on prior knowledge of petroleum geology and rock mechanics. The weights of target parameters in the weight coefficients set for each geological application scenario are higher than those in other geological application scenarios. Target parameters refer to the feature parameters most closely related to and most influential on that specific geological application scenario. For example, in the shale gas production prediction scenario, fluid flow capacity is key; therefore, permeability and fracture connectivity parameters are target parameters for this scenario, and their corresponding weights in the knowledge base (e.g., 0.4 and 0.3 respectively) are significantly higher than those in other non-key scenarios (e.g., 0.1). In the hydraulic fracturing design scenario, the occurrence of natural fractures has a significant impact on the initiation and extension of artificial fractures; therefore, fracture orientation parameters are target parameters, and their weights are set very high (e.g., 0.5), far exceeding their weights in the production prediction scenario.

[0095] In this implementation, based on specific geological requirements, reasonable weights are assigned to each characteristic parameter quickly and accurately, ensuring that the production capacity evaluation results closely align with the actual engineering needs and improving the relevance and accuracy of the production capacity evaluation results.

[0096] In other implementations, all fracture voxels in the 3D labeled image can be identified to determine multiple fracture clusters. Then, the attitude characteristics of each fracture cluster are analyzed. For example, principal component analysis (PCA) can be used to determine the principal orientation and morphological characteristics (aspect ratio) of each fracture cluster. Fracture clusters that are parallel to each other, have a high development frequency, and small aperture are classified as natural fractures; while those that are relatively fewer in number, intersect the former at a high angle, and have a larger aperture are classified as artificial hydraulic fractures. After obtaining the overall productivity assessment of the fracture network, the contribution ratio of each fracture cluster is determined based on its attitude characteristics.

[0097] The following describes the implementation process of the method for evaluating reservoir productivity based on shale whole-core CT images provided in the embodiments of this application: See also Figure 2 , Figure 2 This is a schematic diagram illustrating the implementation process of the method for evaluating reservoir productivity based on shale whole-core CT images provided in this application embodiment.

[0098] Step 200: Start, process starts, input is the 3D shale whole core CT grayscale image data volume, and the geological application scenario of this task (e.g., "natural fracture reservoir evaluation").

[0099] Step 210: Automated segmentation and crack classification, such as... Figure 3 As shown, this step aims to convert the input grayscale image into a label map that marks different phases (cracks, pores, matrix). Specifically: 212: Calculate the grayscale histogram: Calculate the grayscale value distribution histogram of the entire 3D data volume.

[0100] 214: Histogram Peak Identification: Using a peak detection algorithm, the number of main peaks k in the histogram and the corresponding gray values ​​C1, C2, ..., Ck of each peak are automatically identified. Here, k represents the presence of k main phases in the image.

[0101] 216: Perform K-means clustering: Using k as the number of clusters and C1, C2, ..., Ck as the initial cluster centers, perform K-means clustering segmentation on the image. This histogram-based initialization method overcomes the fundamental defects of the traditional K-means algorithm, which is sensitive to initial parameters and has unstable results.

[0102] 218: Output segmentation results: Output a three-dimensional segmentation label map (i.e., a three-dimensional label map), in which each voxel is assigned a label of its respective phase.

[0103] Step 220: Calculation of multidimensional feature parameters, for example, such as Figure 4 As shown.

[0104] Specifically: Crack azimuth parameters R This parameter is used to quantify the dominant direction of fracture development. First, for each fracture voxel, its normal vector is calculated, and the angle between the normal vector and the principal coordinate axis is obtained. Then, the azimuth concentration is calculated using the following formula. R The closer the value is to 1, the more concentrated the location.

[0105]

[0106] Where N is the total number of voxels on the crack surface.

[0107] Crack connectivity parameters B This parameter is used to evaluate the ability of a fracture network to form effective seepage channels. By performing three-dimensional connected domain analysis on all fracture voxels, the largest single connected fracture cluster is identified, and its volume is calculated. .parameter B Defined as:

[0108] in, This represents the total volume of all cracks. B The closer the value is to 1, the better the connectivity.

[0109] Permeability parameter C: The equivalent permeability can be estimated based on the geometry of the fracture network through fluid flow simulation (such as LBM) or empirical formulas (such as the cubic law).

[0110] Crack porosity D: This parameter is defined as the crack volume. Total volume of shale core Percentage:

[0111] Average crack aperture E: This parameter represents the average width of the crack. It can be calculated by deploying a distance transformation algorithm within the crack to calculate the distance from each crack center point to the nearest matrix boundary, and then taking the average of twice the distances from all center points.

[0112] Crack surface roughness F This parameter is used to quantify the roughness of the crack surface. In a preferred embodiment, the root mean square roughness is used. Characterization:

[0113] Where A is the surface area of ​​the crack. It is the height of the surface point. It is the average height.

[0114] Step 230: Calculate the adaptive comprehensive evaluation index, such as... Figure 5 As shown, the specific steps are as follows: First, based on the input "geological application scenario," a weight determination module is invoked. This module internally stores a geological knowledge base (such as a lookup table) and pre-sets different weight coefficient sets for different scenarios. For example: If the scenario is "evaluation of natural fracture reservoirs", the weight set may be: {w_B=0.4, w_C=0.3,...}. In this case, the parameter set of natural fractures is mainly used, and connectivity and permeability are highlighted.

[0115] If the scenario is "evaluation of artificial fracturing effect", the weight set may be: {w_R=0.3, w_E=0.3,...}. In this case, the parameter set of artificial hydraulic fracture is mainly used, and the orientation and aperture are highlighted.

[0116] 234: Normalization and weighted summation: Normalize the parameters calculated in step 220, and then obtain the final comprehensive evaluation index Q (i.e., comprehensive evaluation) by weighted summation according to the determined weights.

[0117] Step 240: End. Output the comprehensive evaluation index Q and various detailed parameters to provide a comprehensive and quantitative basis for reservoir evaluation.

[0118] Figure 6 This is a schematic diagram of the device for evaluating reservoir productivity based on whole-core CT images of shale, provided in an embodiment of this application. Please refer to [link / reference]. Figure 6 This application also provides a device 600 for evaluating reservoir productivity based on shale whole-core CT images, which can realize the above-mentioned method for evaluating reservoir productivity based on shale whole-core CT images. The device 600 for evaluating reservoir productivity based on shale whole-core CT images includes: Image acquisition module 601 is used to acquire a three-dimensional label map of a whole shale core in a target reservoir. The three-dimensional label map includes labels for each phase in the whole shale core. The three-dimensional label map is obtained from the CT image of the whole shale core. The parameter calculation module 602 is used to calculate multidimensional feature parameters of the fracture network of the shale whole core based on the voxels labeled as fracture phase in the three-dimensional label map, and obtain the multidimensional feature parameter set corresponding to the fracture network; the multidimensional feature parameter set includes at least two feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness. The weight determination module 603 is used to determine the target weight coefficient set according to the target geological application scenario corresponding to the target reservoir; the weight coefficient set includes the weights corresponding to each feature parameter in the multidimensional feature parameter set; The evaluation calculation module 604 is used to perform weighted summation of the feature parameters in the multidimensional feature parameter set according to the weights corresponding to each feature parameter in the target weight coefficient set, so as to obtain the productivity evaluation of the target reservoir.

[0119] The specific implementation of the device 600 for evaluating reservoir productivity based on shale whole-core CT images is basically the same as the specific implementation of the method for evaluating reservoir productivity based on shale whole-core CT images described above, and will not be repeated here.

[0120] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for evaluating reservoir productivity based on shale whole-core CT images. This electronic device can be any smart terminal, including desktop computers, tablets, mobile phones, and in-vehicle computers.

[0121] Please see Figure 7 , Figure 7 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to execute the method for evaluating reservoir productivity based on shale whole-core CT images according to the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0122] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for evaluating reservoir productivity based on shale whole-core CT images.

[0123] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0124] In addition, this application embodiment can provide a computer program product for implementation. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device implements the method for evaluating reservoir productivity based on shale whole core CT images in the above embodiment.

[0125] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0126] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0127] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0129] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0130] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0131] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0132] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0133] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0134] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0135] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for evaluating reservoir productivity based on whole-core CT images of shale, characterized in that, The method includes: A three-dimensional label map of a whole shale core in a target reservoir is obtained. The three-dimensional label map includes labels for each phase in the whole shale core. The three-dimensional label map is obtained from CT images of the whole shale core. Based on the voxels labeled as fracture facies in the three-dimensional label map, multidimensional feature parameters are calculated for the fracture network of the shale whole core to obtain the multidimensional feature parameter set corresponding to the fracture network; the multidimensional feature parameter set includes at least two of the following feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness. Based on the target geological application scenario corresponding to the target reservoir, a target weight coefficient set is determined; the weight coefficient set includes the weights corresponding to each feature parameter in the multidimensional feature parameter set; Based on the weights corresponding to each feature parameter in the target weight coefficient set, the feature parameters in the multidimensional feature parameter set are weighted and summed to obtain the productivity evaluation of the target reservoir.

2. The method according to claim 1, characterized in that, The three-dimensional labeled map of the whole shale core in the target reservoir includes: Obtain a three-dimensional grayscale image of the whole shale core from the target reservoir; The gray values ​​in the three-dimensional grayscale image are calculated to obtain the gray value distribution histogram of the three-dimensional grayscale image; The three-dimensional grayscale image is segmented based on the grayscale distribution histogram to obtain the three-dimensional label image.

3. The method according to claim 2, characterized in that, The step of segmenting the three-dimensional grayscale image based on the grayscale distribution histogram to obtain the three-dimensional label image includes: The phases in the three-dimensional grayscale image are determined based on the peaks in the grayscale distribution histogram; the phases are used to characterize the components in the three-dimensional grayscale image. The number of phases is used as the number of clusters, and the gray value corresponding to the peak is used as the initial cluster center. The three-dimensional grayscale image is clustered and segmented to obtain the three-dimensional label map. Each voxel in the three-dimensional label map is assigned a label corresponding to the phase of the voxel.

4. The method according to claim 1, characterized in that, The crack orientation parameters are calculated through the following steps: For each crack voxel in the 3D label image, obtain the normal vector of each crack voxel; the crack voxel is the voxel labeled as the crack phase in the 3D label image. The fracture orientation parameters are determined based on the angle between the normal vector of each fracture voxel and the preset coordinate axis; the fracture orientation parameters are used to characterize the concentration of fracture development direction.

5. The method according to claim 1, characterized in that, The crack connectivity parameter is calculated through the following steps: Three-dimensional connectivity analysis was performed on all the crack voxels in the three-dimensional label map to identify multiple connected crack clusters; the crack voxels in the connected crack clusters were interconnected. The largest connected fracture cluster among the plurality of connected fracture clusters is identified as the target connected fracture cluster; The ratio of the volume of the connected fracture cluster to the total volume of all fractures in the three-dimensional label map is determined as the fracture connectivity parameter; the fracture connectivity parameter is used to characterize the ability of the fracture network to form effective seepage channels.

6. The method according to claim 1, characterized in that, The surface roughness of the crack is calculated through the following steps: Obtain the height of each point on the crack surface in the 3D label image; The average height of the crack surface is determined based on the height of each point on the crack surface. The surface roughness of the crack is determined based on the difference between the height of each point on the crack surface and the average height of the crack surface; the surface roughness of the crack is used to characterize the degree of unevenness of the crack surface.

7. The method according to claim 1, characterized in that, The step of determining the target weight coefficient set based on the target geological application scenario corresponding to the target reservoir includes: Based on the target geological application scenario, the target weight coefficient set is obtained by matching from a preset geological knowledge base; The geological knowledge base stores multiple geological application scenarios and a set of weight coefficients corresponding to each geological application scenario. The weight of the target parameter in the set of weight coefficients corresponding to each geological application scenario is higher than the weight of the target parameter in the set of weight coefficients corresponding to other geological application scenarios. The target parameter corresponding to each geological application scenario is a parameter in the set of weight coefficients that matches the geological application scenario.

8. A device for evaluating reservoir productivity based on whole-core CT images of shale, characterized in that, The device includes: The image acquisition module is used to acquire a three-dimensional label map of a whole shale core in the target reservoir. The three-dimensional label map includes labels for each phase in the whole shale core. The three-dimensional label map is obtained from the CT image of the whole shale core. The parameter calculation module is used to calculate the multidimensional feature parameters of the fracture network of the shale whole core based on the voxels labeled as fracture phase in the three-dimensional label map, and obtain the multidimensional feature parameter set corresponding to the fracture network. The multidimensional feature parameter set includes at least two of the following feature parameters: fracture orientation parameter, fracture connectivity parameter, permeability parameter, fracture porosity, average fracture aperture, and fracture surface roughness. The weight determination module is used to determine the target weight coefficient set based on the target geological application scenario corresponding to the target reservoir; the weight coefficient set includes the weights corresponding to each feature parameter in the multidimensional feature parameter set; The evaluation calculation module is used to perform weighted summation of the feature parameters in the multidimensional feature parameter set according to the weights corresponding to each feature parameter in the target weight coefficient set, so as to obtain the productivity evaluation of the target reservoir.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the method for evaluating reservoir productivity based on shale whole-core CT images as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for evaluating reservoir productivity based on shale whole-core CT images as described in any one of claims 1 to 7.

Images