Fracture reconstruction method, system and equipment for fault control carbonate rock stratum based on spectral clustering algorithm and medium

Abstract

The invention provides a fracture reconstruction method, system and equipment for a fault control carbonate rock stratum based on a spectral clustering algorithm, and a medium. The method comprises the following steps: step 1, obtaining seismic volume data of a target area; step 2, processing the obtained seismic volume data by using a spectral clustering algorithm to obtain a cluster division result; step 3, connecting each cluster point set in the cluster division result by taking a seismic exploration fracture azimuth angle in the seismic volume data as a constraint, and reconstructing to obtain the associated fracture of the strike-slip fault zone of the fault control type carbonate rock stratum; according to the method, the reconstruction precision of the associated fracture of the strike-slip fault zone of the fault control type carbonate rock stratum is improved, and the high fidelity of seismic fracture attribute extraction is ensured.

Description

Technical Field

[0001] This invention belongs to the field of oil and gas development technology, and in particular relates to a method, system, equipment and medium for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm. Background Technology

[0002] Fault-controlled carbonate reservoirs are an important component of carbonate reservoirs in the Tarim and Tahe oilfields. Unlike sandstone, fault-controlled carbonate reservoirs have limited primary storage and permeability spaces, primarily consisting of fractures and caverns, and their original porosity is relatively underdeveloped after later alteration. Previous researchers have accumulated rich and valuable experience in the exploration and development of fault-controlled carbonate oil and gas reservoirs, achieving significant breakthroughs and successes. Driven by the increasing demand for natural gas and advancements in key technologies for the exploration and development of fault-controlled carbonate gas reservoirs, the exploration and development of complex and hidden fault-controlled carbonate oil and gas reservoirs, which were previously difficult to access, have now been successfully achieved. The exploration and development of fault-controlled carbonate oil and gas reservoirs both domestically and internationally is showing a year-on-year growth trend.

[0003] The Ordovician Yingshan Formation reservoir in the Tarim Basin was formed under strike-slip fault control during multiple tectonic movements. This modified reservoir, eroded by top precipitation and bottom hydrothermal activity, is characterized by strong source connectivity. Strike-slip faults and associated fractures are the main factors controlling the formation of the reservoir; therefore, accurate characterization of strike-slip faults and associated fractures is crucial for the detailed description of fault-controlled carbonate reservoirs. Strike-slip fault zones exhibit multi-scale and complex fracture morphologies due to multiple tectonic stresses, even forming intricate fracture networks in areas of high stress, with interconnected fractures forming a network. Therefore, scientifically describing the associated fractures within strike-slip fault zones is of paramount importance.

[0004] Because the fracture morphology associated with strike-slip fault zones in fault-controlled carbonate strata is complex, current industry software fracture extraction methods produce results with poor accuracy, failing to accurately reproduce the properties and morphology of seismic fractures and exhibiting distortion. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, equipment, and medium for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithms, which solves the problem of distortion in the existing characterization of fractures associated with strike-slip fault zones in fault-controlled carbonate formations.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: This invention provides a method for reconstructing fractures in fault-controlled carbonate rock formations based on spectral clustering algorithm, comprising the following steps: Step 1: Obtain seismic body data for the target area; Step 2: Process the obtained seismic body data using a spectral clustering algorithm to obtain cluster partitioning results; Step 3: Using the azimuth angle of the seismic exploration fractures in the seismic body data as a constraint, connect each cluster point set in the cluster division results to reconstruct the associated fractures of the strike-slip fault zone in the fault-controlled carbonate strata.

[0007] Preferably, in step 2, the obtained seismic body data is processed using a spectral clustering algorithm to obtain cluster partitioning results. Specifically, the method is as follows: S21, the Laplace matrix is ​​calculated using seismic volume data of the target area; S22, construct the standardized Laplace matrix; S23, calculate the eigenvectors corresponding to the k1 smallest eigenvalues ​​in the standardized Laplacian matrix; S24. The obtained eigenvectors are combined into a matrix, and the matrix is ​​standardized by row to obtain a new matrix. S25, treat each row of the new matrix as a sample to obtain multiple samples; S26. Cluster the obtained samples to obtain the cluster division results.

[0008] Preferably, in S21, the Laplace matrix is ​​calculated using seismic volume data of the target area. The specific method is as follows: The adjacency matrix and degree matrix are constructed using seismic volume data of the target area; The Laplace matrix is ​​calculated based on the obtained adjacency matrix and degree matrix.

[0009] Preferably, the adjacency matrix and degree matrix are constructed using seismic volume data of the target area, specifically by: Import the obtained seismic volume data of the target area into PETREL software to construct a seismic interpretation model diagram; The seismic interpretation model diagram was converted using the NetworkX library to obtain a converted data sample. The transformed data samples are combined with the fully connected method to construct the adjacency matrix; The degree matrix is ​​constructed using the transformed data samples.

[0010] Preferably, the kernel function of the fully connected method is a polynomial kernel function, a Gaussian kernel function, or a sigmoid kernel function.

[0011] Preferably, in step 3, the azimuth angle of the seismic exploration fractures in the seismic body data is used as a constraint to connect each cluster point set in the cluster division results, and the associated fractures of the strike-slip fault zone in the fault-controlled carbonate strata are reconstructed. The specific method is as follows: S31, calculate the angle between the line connecting a point in each cluster of points and the nearest point and the due north direction; S32, determine whether the dip angle meets the range set by the seismic crack azimuth angle. If it does, connect the point to the nearest point and proceed to S33; otherwise, exclude the point and proceed to S34. S33, select any point among the remaining points, calculate the angle between the line connecting this point and the nearest point and the due north direction, and proceed to S32; S34. Select the point closest to the given point from the remaining points, calculate the angle between the line connecting the two points and the due north direction, and proceed to S32.

[0012] A fracture reconstruction system for fault-controlled carbonate formations based on spectral clustering algorithm, comprising: Seismic body data acquisition unit, used to acquire seismic body data of the target area; The data clustering unit is used to process the obtained seismic body data using the spectral clustering algorithm to obtain cluster partitioning results; The fracture reconstruction unit is used to connect each cluster point set in the cluster division result with the seismic exploration fracture azimuth angle in the seismic body data as a constraint, and reconstruct the associated fractures of the strike-slip fault zone of the fault-controlled carbonate strata.

[0013] A computer device, comprising: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program that, when executed by the processor, performs the method.

[0014] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described.

[0015] A computer program product comprising a computer program that, when executed by a processor, implements the method.

[0016] The beneficial effects of this invention are: This invention provides a method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithms. Using spectral clustering, the method organizes and analyzes seismic attribute data of fault-controlled carbonate formations. During fracture extraction and reconstruction, the method clusters and connects the three-dimensional point sets corresponding to the seismic data, reconstructing fractures associated with strike-slip fault zones in fault-controlled carbonate formations. This improves the accuracy of fracture reconstruction and ensures high fidelity in seismic fracture attribute extraction. The fracture extraction results can be used as input for numerical simulation of embedded discrete fractured reservoirs, laying the foundation for subsequent numerical simulation work. It is also compatible with subsequent numerical simulations of embedded discrete fractured reservoirs, demonstrating good practical application results. Attached Figure Description

[0017] Figure 1 This is a flowchart of a method according to an embodiment of the present invention; Figure 2 The seismic fracture properties of the strike-slip fault zone in a specific embodiment; Figure 3 This is a model diagram of the cracks before reconstruction in a specific embodiment; Figure 4 This is a model diagram of the crack reconstruction in a specific embodiment; Figure 5 The results show a comparison of simulation accuracy before and after crack reconstruction. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0019] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0020] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0021] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0022] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0024] Example 1 This embodiment provides a method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithms, comprising the following steps: S1: Determine the algorithm input and output. Input: Based on the seismic body data collected on-site, organize it into a point set sample D = ( x 1, x 2, x 3, …, x n The method for generating the adjacency matrix, and the dimensions after dimensionality reduction. k 1. Clustering methods, dimensions after clustering k 2. Output: Cluster partitioning C ( c 1, c 2, … c k2 ).

[0025] S2: Construct the adjacency matrix W and the degree matrix D according to the adjacency matrix generation method; S3: Calculate the Laplace matrix L.

[0026] S4: Construct the standardized Laplace matrix D 1 / 2 LD -1 / 2 .

[0027] S5: Calculate the standardized Laplacian matrix D 1 / 2 LD -1 / 2 Let f be the eigenvectors corresponding to the k1 smallest eigenvalues.

[0028] S6: Form a matrix from all the eigenvectors f, normalize the resulting matrix by row, and finally form an n×k1 dimensional matrix F.

[0029] S7: Treat each row of the n×k1 dimensional matrix F as a k1-dimensional sample, for a total of n samples. Perform clustering using the input clustering method, with a clustering dimension of k2, to obtain the cluster partition. C (c 1, c 2, … c k2 ).

[0030] S8: Using the azimuth angle of the seismic exploration fracture as a constraint, and combining the cluster division results, connect the point sets of each cluster.

[0031] The specific connection method is as follows: S81, calculate the angle between the line connecting a point in each cluster of points and the nearest point and the due north direction; S82, determine whether the dip angle meets the range set by the seismic crack azimuth angle. If it does, connect the point to the nearest point and proceed to S83; otherwise, exclude the point and proceed to S84. S83, select any point among the remaining points, calculate the angle between the line connecting this point and the nearest point and the due north direction, and proceed to S82; S84: Select the point closest to the given point from the remaining points, calculate the angle between the line connecting the two points and the due north direction, and proceed to S82.

[0032] Example 2 Based on Example 1, this example provides a method for reconstructing fractures in fault-controlled carbonate strata based on spectral clustering algorithm, which preprocesses seismic data and includes the following steps: A: Import the seismic data collected on-site into PETREL software to construct a seismic interpretation model diagram; B: Export the seismic interpretation model diagram, and use the NetworkX library provided by Python to convert the format of the seismic model diagram to obtain the converted data sample.

[0033] Example 3 Based on Example 1, this example provides a method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm, constructing an adjacency matrix W and a degree matrix D, including the following steps: A: Construct the adjacency matrix W using the fully connected method.

[0034] The fully connected method can choose different kernel functions to define edge weights. Commonly used kernel functions include the polynomial kernel function, the Gaussian kernel function, and the sigmoid kernel function. In this case, the Gaussian kernel function is used to define the adjacency matrix W, and its corresponding formula is as follows:

[0035] B: Construct the degree matrix D. The seismic model diagram is an undirected graph. For such graphs, the diagonal elements d of the degree matrix D... iiThe degree of node i is represented by d, which is calculated as the sum of the rows (or columns) containing that node. ii =ΣW ij , where j is the node adjacent to node i. Elements at other positions d ij = 0 (for i ≠ j).

[0036] Example 4 Based on Example 1, this example provides a method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm. The calculated Laplace matrix L satisfies the following properties: A: Since D and W are both symmetric matrices, L is also a symmetric matrix; B: All of its eigenvalues ​​are real numbers; C: For any vector, the following relationship holds:

[0037] D: Since the Laplace matrix is ​​positive semi-definite, all of its n eigenvalues ​​are greater than or equal to 0.

[0038] Example 5 Based on the specific data provided on-site, taking a fault-controlled carbonate reservoir block in a strike-slip fault zone in the Tarim Basin as an example, the specific implementation scheme provided by this invention is described.

[0039] Collect and organize seismic fracture attribute data of carbonate reservoirs in a strike-slip fault zone in the Tarim Basin. Figure 2 The seismic interpretation model was constructed by importing the data into the PETREL software. The NetworkX library provided by Python was used to convert the seismic model diagram format into an adjacency matrix format, generating the adjacency matrix W1 and the degree matrix D1. The Laplace matrix L1 was calculated, and the standardized Laplace matrix D1 was constructed. 1 / 2 LD1 -1 / 2 Calculate D1 1 / 2 LD1 -1 / 2 The eigenvectors f corresponding to the k1 smallest eigenvalues ​​are then standardized to form an n×k1 dimensional matrix F1. Each row of F1 is treated as a k1-dimensional sample, resulting in a total of n samples. These samples are then clustered using the input clustering method, with a clustering dimension of k2, resulting in a cluster partition C1 (c1, c2, …c…). k2 The azimuth range of the cracks in the block is obtained by constructing the seismic interpretation model. Using this as a constraint, the dip angle of the line connecting a point in each cluster of points in C1 to the nearest point and due north is calculated. If this dip angle is within ±5° of the crack azimuth, the two points are connected. Otherwise, the point is excluded and the judgment is continued. This process is repeated until all points in the cluster are judged and connected, resulting in a high-precision crack reconstruction result. Figure 3 The crack model before reconstruction. Figure 4 Comparing the reconstructed crack model, we found that: Figure 3 Extracting cracks from these cracks cannot accurately reconstruct the crack network morphology of earthquake cracks. Figure 4 The method achieves high fissure accuracy in reconstructing seismic fracture attributes and accurately describes the fracture network connectivity. Numerical simulations were conducted using fracture models before and after reconstruction, and comparative analysis was performed using historical production data from actual fault-controlled carbonate reservoirs. The simulation results, obtained using the method described in this invention, accurately depicted the water breakthrough time and production rate of fractured water in the reservoir. The calculated production curve showed minimal error compared to the actual production curve. This demonstrates that the fracture reconstruction method for fault-controlled carbonate formations based on spectral clustering algorithms can significantly improve fracture description accuracy in practical applications, accurately characterizing the mechanism of water breakthrough along fractures in fault-controlled carbonate reservoirs.

[0040] Example 6 This embodiment provides a fracture reconstruction system for fault-controlled carbonate formations based on spectral clustering algorithm, including: Seismic body data acquisition unit, used to acquire seismic body data of the target area; Data clustering units are used to process the obtained seismic body data using spectral clustering algorithms to obtain cluster partitioning results. The specific method is as follows: S2: Construct the adjacency matrix W and the degree matrix D based on the seismic body data; S3: Calculate the Laplace matrix L.

[0041] S4: Construct the standardized Laplace matrix D 1 / 2 LD -1 / 2 .

[0042] S5: Calculate the standardized Laplacian matrix D 1 / 2 LD -1 / 2 Let f be the eigenvectors corresponding to the k1 smallest eigenvalues.

[0043] S6: Form a matrix from all the eigenvectors f, normalize the resulting matrix by row, and finally form an n×k1 dimensional matrix F.

[0044] S7: Treat each row of the n×k1 dimensional matrix F as a k1-dimensional sample, for a total of n samples. Perform clustering using the input clustering method, with a clustering dimension of k2, to obtain the cluster partition. C ( c 1, c 2, … c k2 ).

[0045] The fracture reconstruction unit is used to connect each cluster point set in the cluster division results, constrained by the azimuth angle of the seismic exploration fractures in the seismic body data, to reconstruct the fractures associated with the strike-slip fault zone of the fault-controlled carbonate strata. The specific method is as follows: S1, calculate the angle between the line connecting a point in each cluster of points and the nearest point and the due north direction; S2, determine whether the dip angle meets the range set by the seismic crack azimuth angle. If it does, connect the point to the nearest point and proceed to S3; otherwise, exclude the point and proceed to S4. S3, select any point among the remaining points, calculate the angle between the line connecting this point and the nearest point and the due north direction, and then proceed to S2; S4. Select the point closest to the given point from the remaining points, calculate the angle between the line connecting the two points and the due north direction, and proceed to S2.

[0046] Example 7 This embodiment 7 provides a computer device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of a computer method.

[0047] When the processor executes the computer program, it implements the steps of the above-described computer method. For example: A method for reconstructing fractures in fault-controlled carbonate strata based on spectral clustering algorithm includes the following steps: Step 1: Obtain seismic body data for the target area; Step 2: Process the obtained seismic body data using a spectral clustering algorithm to obtain cluster partitioning results; Step 3: Using the azimuth angle of seismic exploration fractures in the seismic data as a constraint, connect each cluster point set in the cluster division results to reconstruct the fractures associated with the strike-slip fault zone in the fault-controlled carbonate strata. A method for reconstructing fractures in fault-controlled carbonate strata based on spectral clustering algorithm includes the following steps: Step 1: Obtain seismic body data for the target area; Step 2: Process the obtained seismic body data using a spectral clustering algorithm to obtain cluster partitioning results; Step 3: Using the azimuth of seismic exploration fractures in the seismic body data as constraints, connect each cluster point set in the cluster division results to reconstruct the fractures associated with the strike-slip fault zone in the fault-controlled carbonate strata. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above system, such as including: Seismic body data acquisition unit, used to acquire seismic body data of the target area; The data clustering unit is used to process the obtained seismic body data using the spectral clustering algorithm to obtain cluster partitioning results; The fracture reconstruction unit is used to connect each cluster point set in the cluster division result with the seismic exploration fracture azimuth angle in the seismic body data as a constraint, and reconstruct the associated fractures of the strike-slip fault zone of the fault-controlled carbonate strata.

[0048] The computer device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above are examples of computer devices and do not constitute a limitation on the computer device; it may include more components than described above, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.

[0049] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or any conventional processor, etc. The processor is the control center of the computer device, connecting various parts of the computer device through various interfaces and lines.

[0050] The memory can be used to store the computer program and / or module, and the processor implements various functions of the computer device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory.

[0051] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.); the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMediaCards (SMC), Secure Digital (SD) cards, FlashCards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0052] Example 8 This embodiment 8 also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described.

[0053] For example, a method for reconstructing fractures in fault-controlled carbonate strata based on spectral clustering algorithm includes the following steps: Step 1: Obtain seismic body data for the target area; Step 2: Process the obtained seismic body data using a spectral clustering algorithm to obtain cluster partitioning results; Step 3: Using the azimuth angle of the seismic exploration fractures in the seismic body data as a constraint, connect each cluster point set in the cluster division results to reconstruct the associated fractures of the strike-slip fault zone in the fault-controlled carbonate strata.

[0054] If the modules / units integrated in the computer system are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0055] Based on this understanding, all or part of the processes in the above-described method can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described computer method. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.

[0056] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0057] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0058] Example 9 This embodiment 9 provides a computer product, which includes a computer program stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium and executes the computer program, enabling the computer device to perform the method in embodiment 1, such as: a method for reconstructing fractures in fault-controlled carbonate rock formations based on a spectral clustering algorithm, comprising the following steps: Step 1: Obtain seismic body data for the target area; Step 2: Process the obtained seismic body data using a spectral clustering algorithm to obtain cluster partitioning results; Step 3: Using the azimuth angle of the seismic exploration fractures in the seismic body data as a constraint, connect each cluster point set in the cluster division results to reconstruct the associated fractures of the strike-slip fault zone in the fault-controlled carbonate strata.

[0059] It should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods.

[0060] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention, and no reference numerals in the claims should be construed as limiting the scope of the claims.

[0061] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm, characterized in that, Includes the following steps: Step 1: Obtain seismic body data for the target area; Step 2: Process the obtained seismic body data using a spectral clustering algorithm to obtain cluster partitioning results; Step 3: Using the azimuth angle of the seismic exploration fractures in the seismic body data as a constraint, connect each cluster point set in the cluster division results to reconstruct the associated fractures of the strike-slip fault zone in the fault-controlled carbonate strata.

2. The method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm according to claim 1, characterized in that, In step 2, the obtained seismic body data is processed using a spectral clustering algorithm to obtain cluster partitioning results. The specific method is as follows: S21, the Laplace matrix is ​​calculated using seismic volume data of the target area; S22, construct the standardized Laplace matrix; S23, calculate the eigenvectors corresponding to the k1 smallest eigenvalues ​​in the standardized Laplacian matrix; S24. The obtained eigenvectors are combined into a matrix, and the matrix is ​​standardized by row to obtain a new matrix. S25, treat each row of the new matrix as a sample to obtain multiple samples; S26. Cluster the obtained samples to obtain the cluster division results.

3. The method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm according to claim 2, characterized in that, In S21, the Laplacian matrix is ​​calculated using seismic volume data of the target area. The specific method is as follows: The adjacency matrix and degree matrix are constructed using seismic volume data of the target area; The Laplace matrix is ​​calculated based on the obtained adjacency matrix and degree matrix.

4. The method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm according to claim 3, characterized in that, The adjacency matrix and degree matrix are constructed using seismic volume data of the target area, specifically as follows: Import the obtained seismic volume data of the target area into PETREL software to construct a seismic interpretation model diagram; The seismic interpretation model diagram was converted using the NetworkX library to obtain a converted data sample. The transformed data samples are combined with the fully connected method to construct the adjacency matrix; The degree matrix is ​​constructed using the transformed data samples.

5. The method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm according to claim 4, characterized in that, The kernel function of the fully connected method is a polynomial kernel function, a Gaussian kernel function, or a sigmoid kernel function.

6. The method for reconstructing fractures in fault-controlled carbonate formations based on spectral clustering algorithm according to claim 1, characterized in that, In step 3, using the azimuth of seismic exploration fractures in the seismic body data as constraints, each cluster point set in the cluster division results is connected to reconstruct the fractures associated with the strike-slip fault zone in the fault-controlled carbonate strata. The specific method is as follows: S31, calculate the angle between the line connecting a point in each cluster of points and the nearest point and the due north direction; S32, determine whether the dip angle meets the range set by the seismic crack azimuth angle. If it does, connect the point to the nearest point and proceed to S33; otherwise, exclude the point and proceed to S34. S33, select any point among the remaining points, calculate the angle between the line connecting this point and the nearest point and the due north direction, and proceed to S32; S34. Select the point closest to the given point from the remaining points, calculate the angle between the line connecting the two points and the due north direction, and proceed to S32.

7. A fracture reconstruction system for fault-controlled carbonate formations based on spectral clustering algorithm, characterized in that, include: Seismic body data acquisition unit, used to acquire seismic body data of the target area; The data clustering unit is used to process the obtained seismic body data using the spectral clustering algorithm to obtain cluster partitioning results; The fracture reconstruction unit is used to connect each cluster point set in the cluster division result with the seismic exploration fracture azimuth angle in the seismic body data as a constraint, and reconstruct the associated fractures of the strike-slip fault zone of the fault-controlled carbonate strata.

8. A computer device, characterized in that, include: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program that, when executed by the processor, performs the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images