A method and apparatus for fracture prediction

Abstract

The application discloses a kind of fracture prediction method and device.The method comprises, by fracture prediction model and model parameter, obtain predicted fracture data volume from poststack seismic data volume;Judge whether predicted fracture data volume satisfies the matching condition between fracture-related data volume;If yes, the predicted fracture data volume currently obtained is determined as the final fracture data volume;If not, optimize model parameters, obtain new predicted fracture data volume from poststack seismic data volume by fracture prediction model and model parameters again.The fracture information with high resolution, large number of identification, strong contrast, good continuity, high fidelity can be identified in conventional poststack seismic data, and the fracture interpretation work is more efficient and accurate, which provides necessary basis for subsequent structure modeling, oil and gas reservoir prediction and oil and gas resource evaluation.

Description

Technical Field

[0001] This invention relates to the fields of geophysics and petroleum industry, and in particular to a method and apparatus for predicting fractures. Background Technology

[0002] Faults are fracture surfaces formed in underground rocks under geological stress. Based on the morphology of the fracture surface, they can be classified into faults of different scales and orientations. Fault interpretation is fundamental to oil and gas exploration and is widely used in structural geology, petroleum geology, engineering geology, active earthquake prediction, and other Earth science-related research and production tasks. For a long time, the seismic exploration field has been committed to improving the accuracy and efficiency of fault interpretation. The rationality and accuracy of fault interpretation results directly affect subsequent structural modeling, oil and gas reservoir prediction, and oil and gas resource evaluation. However, areas that have experienced complex tectonic movements, both domestically and internationally, commonly exhibit problems such as poor quality of post-stack seismic data, difficulty in distinguishing between real fault information and noise artifacts, a large number of faults, significant scale variations, and complex morphologies, all of which make fault identification challenging. In recent years, the industry has conducted extensive research on identification methods for multi-level and multi-occurrence faults, successively developing fault identification technologies based on seismic attributes, image analysis, and deep learning. By analyzing seismic parameters sensitive to faults, such as seismic waveforms, amplitudes, and frequencies, these technologies highlight the discontinuities in seismic reflection interfaces caused by faults, continuously improving the efficiency and accuracy of fault interpretation. Summary of the Invention

[0003] The inventors discovered that previous fault prediction techniques using post-stack seismic data have many limitations in terms of methods and applications. For example, they can only identify a limited number of faults, have low resolution, and suffer from poor continuity and fidelity, making it difficult to meet the needs of high-precision fault prediction. This significantly limits the efficiency and accuracy of structural interpretation, especially since commonly used prediction methods lack intelligent identification methods based on deep learning. Furthermore, the applicability of each method varies, and they may not be suitable for predicting data specific to the region. To at least partially address the technical problems of existing technologies, the inventors developed this invention, which, through specific embodiments, provides a fault prediction method and apparatus capable of accurately and efficiently achieving high-precision fault prediction.

[0004] In a first aspect, embodiments of the present invention provide a fracture prediction method, comprising:

[0005] The predicted fault data volume is obtained from the post-stack seismic data volume using the fault prediction model and model parameters.

[0006] Determine whether the predicted fracture data volume meets the matching conditions with the fracture-related data volume;

[0007] If so, the currently obtained predicted fracture data volume is determined as the final fracture data volume;

[0008] If not, optimize the model parameters and return to the previous step to obtain the predicted fault data volume from the post-stack seismic data volume using the fault prediction model and model parameters.

[0009] Secondly, embodiments of the present invention provide a fracture prediction device, comprising:

[0010] The fracture data volume prediction module is used to obtain the predicted fracture data volume from the post-stack seismic data volume using the fracture prediction model and model parameters.

[0011] The judgment module is used to determine whether the predicted fracture data body obtained by the fracture data body prediction module satisfies the matching condition between the fracture-related data body and the fracture-related data body.

[0012] The final fracture data body determination module is used to determine the currently obtained predicted fracture data body as the final fracture data body if the judgment module determines that it is true.

[0013] The model parameter optimization module is used to optimize the model parameters if the judgment module determines that it is not true. The fracture data volume prediction module is also used to return to the execution of obtaining the predicted fracture data volume from the post-stack seismic data volume through the fracture prediction model and model parameters.

[0014] Thirdly, embodiments of the present invention provide a computer program product with fracture prediction function, including a computer program / instruction, wherein the computer program / instruction implements the above-mentioned fracture prediction method when executed by a processor.

[0015] Fourthly, embodiments of this disclosure provide a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described fracture prediction method.

[0016] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0017] The fracture prediction method provided in this invention uses fracture-related data volumes as a reference, repeatedly optimizing model parameters and iteratively predicting fracture data volumes until the predicted fracture data volumes meet the matching conditions with the fracture-related data volumes. It can identify high-resolution, numerous, high-contrast, continuous, and high-fidelity fracture information in conventional post-stack seismic data, accurately depicting the locations and combinations of multi-level and multi-attitude fractures, thus completing fracture interpretation work more efficiently and accurately. This ensures the efficient completion of three-dimensional structural interpretation work, laying the foundation for determining oil and gas traps and comprehensively evaluating favorable exploration zones.

[0018] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0019] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0021] Figure 1 This is a flowchart of the fracture prediction method in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart illustrating the specific implementation of the fracture prediction method in Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of the fracture prediction device in an embodiment of the present invention. Detailed Implementation

[0024] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0025] It should be understood that the terminology used in this invention is merely for describing particular embodiments and is not intended to limit the invention. Furthermore, with respect to numerical ranges in this invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Every smaller range between any stated value or intermediate value within a stated range, and any other stated value or intermediate value within said range, is also included in this invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0026] Unless otherwise stated, 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 invention pertains. While only preferred methods and materials have been described herein, any methods and materials similar or equivalent to those described herein may be used in the implementation or testing of this invention. All references to this specification are incorporated by way of citation to disclose and describe methods and / or materials associated with those references. In the event of any conflict with any incorporated reference, the content of this specification shall prevail.

[0027] To address the problem of inaccurate and inefficient fracture prediction in existing technologies, this invention provides a fracture prediction method and apparatus that can identify fracture information with high resolution, large number of fractures, strong contrast, good continuity, and high fidelity in conventional post-stack seismic data, thereby completing fracture interpretation work more efficiently and accurately.

[0028] Example 1

[0029] Embodiment 1 of the present invention provides a fracture prediction method, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0030] Step S11: Obtain the predicted fault data volume from the post-stack seismic data volume using the fault prediction model and model parameters.

[0031] Fracture prediction models can be pre-established in the following ways:

[0032] A massive amount of three-dimensional fracture body models are established as labeled big data. By identifying and training these models, a stable deep neural network fracture prediction model is obtained.

[0033] Model parameters may include at least one of the following parameters:

[0034] (1) Calculate the unit size.

[0035] This refers to the dimensions of the volume elements calculated during the fracture prediction process. During the prediction process, a fracture attribute value is assigned to each volume element. For example, if the calculation result is a fracture, the value is assigned as 1; if the calculation result is not a fracture, the value is assigned as 0.

[0036] For example, a minimum computational unit can be defined as 32 inlines horizontally, 32 crosslines horizontally, and 32ms vertically. Based on this, the size of the computational unit can be increased exponentially as the unit size increases. Typically, the maximum size of the computational unit should not exceed eight times the minimum size mentioned above.

[0037] (2) Whether to add speed to the calculation.

[0038] (3) Velocity body.

[0039] The velocity volume can be uniformly distributed, meaning the entire three-dimensional velocity volume is assigned a single value; or it can be non-uniformly distributed. The value of the velocity volume is typically between 1000 and 10000 m / s.

[0040] The specific values ​​of the initial model parameters can be determined based on the characteristics of the post-stack seismic data volume.

[0041] Step S12: Determine whether the predicted fracture data volume meets the matching conditions with the fracture-related data volume.

[0042] The fault-related data volume may include post-stack seismic data volume, fault-related seismic attribute data volume, and / or imaging logging data. The fault-related seismic attribute data volume is a seismic attribute data volume extracted or converted from the seismic data volume that reflects the fault distribution. Further, the fault-related data volume includes at least one of the following data volumes:

[0043] Post-stack seismic data volume, coherence data volume, variance data volume, structural curvature data volume, and imaging logging data.

[0044] To ensure the reliability of the predicted fault data volume, it is necessary to verify it using post-stack seismic data, other fault prediction attributes (coherence data volume, variance data volume, tectonic curvature data volume), and imaging logging data. If the predicted fault data volume is inconsistent with any of its data on a plane or profile, at least one parameter in the model parameters should be adjusted, and subsequent calculation steps should be repeated until the verification results are consistent.

[0045] (1) Post-stack seismic data volume: The predicted fault data volume and the post-stack seismic data volume are overlaid and displayed transparently. By adjusting the color scale, the non-faulted part of the predicted fault data volume is made transparent. On the vertical slice and the horizontal slice, the fault information of the predicted fault data volume is checked to see if it matches the misalignment position of the seismic phase axis in the post-stack seismic data volume.

[0046] (2) Fault-related seismic attribute data volume: The post-stack seismic data volume or the structure-guided filter data volume of the post-stack seismic data volume is used as input, and the coherence data volume, variance data volume and structure curvature data volume are obtained by calculation respectively. The fault information of the predicted fault data volume on the vertical slice and the horizontal slice is checked to see if it is consistent with the fault morphology of the above three types of data.

[0047] (3) Imaging logging data: If there is imaging logging data of a drilled well within the data range of the back-stack seismic data volume, check the fracture information passed by the well trajectory on the vertical slice of the predicted fracture data volume that passes through the well, and check whether the fracture information is consistent with the fracture information in the imaging logging data.

[0048] If step S12 is correct, proceed to step S13; if step S12 is incorrect, proceed to step S14.

[0049] Step S13: Determine the currently obtained predicted fracture data volume as the final fracture data volume.

[0050] Step S14: Optimize model parameters.

[0051] Smaller computational unit size results in higher resolution and a greater number of fractures identified in the predicted fracture data volume, but also worsens continuity. Higher speed improves the continuity of fractures in the predicted fracture data volume, but excessive continuity can lead to fracture distortion. Therefore, optimizing model parameters can specifically include:

[0052] Fractures are identified from the fracture-related data volume to obtain the identified fracture data volume; the model parameters are optimized based on the matching results of the predicted fracture data volume and the identified fracture data volume in terms of fracture number, continuity and / or resolution.

[0053] Furthermore, it may include performing at least one of the following:

[0054] If the number of fractures in the predicted fracture data body is less than the number of fractures in the identified fracture data body, reduce the size of the computing unit.

[0055] If the continuity of the predicted fracture data volume is worse than that of the identified fracture data volume, increase the size of the computational unit and / or increase the velocity volume;

[0056] If the predicted continuity of the fracture data volume is stronger than the identified continuity of the fracture data volume, reduce the size of the computational unit and / or reduce the velocity volume;

[0057] If the resolution of the predicted fracture data volume is lower than the resolution of the identified fracture data volume, reduce the size of the computational unit.

[0058] After step S14, return to step S11.

[0059] The fracture prediction method provided in Embodiment 1 of this invention uses fracture-related data volumes as a reference, repeatedly optimizes model parameters, and iteratively predicts fracture data volumes until the predicted fracture data volumes meet the matching conditions with the fracture-related data volumes. It can identify high-resolution, numerous, high-contrast, continuous, and high-fidelity fracture information in conventional post-stack seismic data, accurately characterizing the locations and combinations of multi-level and multi-attitude fractures, thus completing fracture interpretation work more efficiently and accurately. This ensures the efficient completion of three-dimensional structural interpretation work and lays the foundation for determining oil and gas traps and comprehensively evaluating favorable exploration zones.

[0060] Example 2

[0061] The inventors discovered that relying on only one or a few fault prediction methods can provide very limited effective fault information. It is necessary to use the output of one prediction method as input data for another method, gradually improve the overall quality of the prediction results, and finally verify them by combining them with other geological results.

[0062] Embodiment 2 of the present invention provides a specific implementation flow of a fracture prediction method, referring to... Figure 2 As shown, it includes the following steps:

[0063] Step S21: Calculate the dip and azimuth data volumes of the seismic reflection interface from the post-stack seismic data volume. Perform structural steering filtering on the post-stack seismic data volume using the dip and azimuth data volumes as constraints to obtain the structural steering filtered data volume.

[0064] Around the post-stack seismic data volume, a multi-window dip scan is first performed. The dip and azimuth of the seismic reflection interface are estimated using a vertical calculation window. The window with the largest similarity is selected as the dip and azimuth data volume for the analysis point, generating dip and azimuth volumes respectively. Then, during the structural steering filtering process, information from these two data volumes is used to locate the reflection interface of the post-stack seismic data volume. The structural steering filtering process mainly includes smoothing continuous reflection interfaces and amplifying waveform differences at discontinuous locations (making the reflection interface more discontinuous, facilitating fault identification). This structural steering filtering improves the signal-to-noise ratio, resolution, and fidelity of the post-stack seismic data volume, improves the continuity of seismic phase axes, and makes fault breaks more crisp and clear. In the newly generated structural steering filtered data volume, structural boundary features are clearer, and different levels of faults and horizons on the profile are easier to identify. Extracting other geometric attributes based on this will yield even better results.

[0065] Step S22: Obtain the predicted fracture data volume by constructing the guided filter data volume using the fracture prediction model and model parameters.

[0066] By using the structurally guided filter data volume as input, a deep learning-based intelligent fracture identification method is performed. This method accurately describes the complex nonlinear fracture characteristics in seismic data (structurally guided filter data volume). After inputting the structurally guided filter data volume, the corresponding predicted fracture data volume is directly generated.

[0067] Using the optimized computational unit size, whether to include velocity in the calculation, and velocity volume parameters, an AI fault data volume covering the seismic data range is generated, i.e., a predicted fault data volume. The identified faults have the advantages of high resolution, large number of identified faults, strong contrast, good continuity, and high fidelity.

[0068] Step S23: Perform fracture enhancement calculation and fracture skeletonization calculation on the predicted fracture data volume in sequence to obtain the fracture skeletonization data volume.

[0069] The predicted fracture data volume is typically a binary data volume, where 1 represents a fracture and 0 represents no fracture. Fracture enhancement operations are performed on the predicted fracture data volume, which increases the difference between the values ​​representing fractures and those representing no fractures. This can be done by changing the values ​​representing fractures, decreasing the values ​​representing no fractures, or both simultaneously. Fracture enhancement operations can further improve the resolution and contrast of fracture information. Fracture skeletonization operations integrate fracture data from the same fracture surface into a single surface.

[0070] To further improve the continuity of fracture information and reduce invalid non-fracture information, the predicted fracture data volume is used as input. The fracture information in the predicted fracture data volume is sharpened (fracture enhancement operation) to enhance the local fracture information of the data volume, and the output is a fracture enhancement data volume, a fracture azimuth data volume, and a fracture dip data volume. Then, based on the fracture azimuth data volume and the fracture dip data volume, a "fracture skeletonization" operation is performed on the fracture enhancement data volume. The range is traced along the fracture extension direction, and lower outliers in the analysis window are removed, while the strongest parts of the fracture information are retained, making the fracture information more detailed.

[0071] Step S24: Perform broken ant body calculation on the broken skeletonized data volume to obtain the broken ant data volume.

[0072] To further improve the continuity of fracture information and reduce invalid non-fracture information, fracture skeletonized data volume is used as input to perform fracture ant body operation (merging closely spaced fractures into one). The newly generated fracture ant body can effectively identify the true range of continuous fractures and improve the fidelity of the original data volume.

[0073] Step S25: Determine whether the broken ant data body meets the matching conditions with the broken related data body.

[0074] If yes, proceed to step S27; otherwise, proceed to step S26.

[0075] Step S26: Optimize model parameters.

[0076] After step S26, return to step S22.

[0077] Step S27: Merge the fractured ant data body with the fracture-related data body to obtain the fused data body.

[0078] The fracture data volume (fracture ant data volume) and the fracture-related data volume are normalized separately; the normalized fracture data volume and the fracture-related data volume are added together according to their respective weight coefficients to obtain the fused data volume.

[0079] Furthermore, the ant data volume, coherent data volume, variance data volume, and constructed curvature data volume are fused together to supplement each other's fracture information and form a fracture fusion data volume, making the fracture identification results richer and more accurate.

[0080] The coherence data volume calculates the correlation between the structurally guided filtered data within a given time window and the seismic data within a local time window of an adjacent trace, using the magnitude of the correlation value to reflect the lateral continuity of the reflection interface. The variance data volume uses variance to characterize the waveform differences of the structurally guided filtered data near the fault, calculating the average of the squares of the differences between each data point and the mean within a given time window, thus reflecting the dispersion and variability of the data waveforms. The structural curvature data volume automatically identifies the horizon of the dip volume obtained from multi-window dip scanning, then uses the relationship between curvature and dip angle to calculate the structural curvature volume, reflecting the changes in the seismic phase axis waveform caused by linear fault information.

[0081] Step S28: Identify fault lines from the fused data volume and generate a fault file based on the picked fault lines.

[0082] Automatically detect the part with the strongest attribute energy, pick up the fault line, and generate a fault file.

[0083] Fault files can be in the form of text files, for example, containing multiple columns, one column for the line number, one column for the trace number (or there may be no line number or trace number, one column for the X coordinate of the geodetic coordinates, one column for the Y coordinate of the geodetic coordinates), one column for time depth (or depth), one column for the fault sequence number, and each of the other columns for a fault attribute (such as whether it is a normal or reverse fault, strike, dip, and dip angle, etc.).

[0084] Step S29: Display the fracture fusion data volume and fault lines in the three-dimensional visualization space.

[0085] Fault lines can be manually edited as needed to analyze the spatial distribution and combination characteristics of multi-level and multi-occurrence faults, providing an intuitive and accurate basis for analyzing the deformation characteristics of geological structures.

[0086] Based on the inventive concept of this invention, embodiments of this invention also provide a fracture prediction device, the structure of which is as follows: Figure 3 As shown, it includes:

[0087] The fracture data volume prediction module 31 is used to obtain the predicted fracture data volume from the post-stack seismic data volume through the fracture prediction model and model parameters.

[0088] The judgment module 32 is used to judge whether the predicted fracture data body obtained by the fracture data body prediction module 31 meets the matching conditions with the fracture-related data body.

[0089] The final fracture data body determination module 33 is used to determine the currently obtained predicted fracture data body as the final fracture data body if the judgment module 32 determines that it is true.

[0090] The model parameter optimization module 34 is used to optimize the model parameters if the judgment module 33 determines no. The fracture data volume prediction module 31 is also used to return to the execution of obtaining the predicted fracture data volume from the post-stack seismic data volume through the fracture prediction model and model parameters.

[0091] In some embodiments, the model parameter optimization module 34, specifically for optimizing model parameters, is used to:

[0092] Fractures are identified from the fracture-related data volume to obtain the identified fracture data volume; the model parameters are optimized based on the matching results of the predicted fracture data volume and the identified fracture data volume in terms of fracture number, continuity and / or resolution.

[0093] In some embodiments, the model parameter optimization module 34 optimizes the model parameters based on the matching results of the number of fractures, continuity, and / or resolution between the predicted fracture data body and the identified fracture data body, specifically by performing at least one of the following:

[0094] If the number of fractures in the predicted fracture data volume is less than the number of fractures in the identified fracture data volume, reduce the computational unit size; if the continuity of the predicted fracture data volume is worse than that of the identified fracture data volume, increase the computational unit size and / or increase the velocity volume; if the continuity of the predicted fracture data volume is stronger than that of the identified fracture data volume, reduce the computational unit size and / or reduce the velocity volume; if the resolution of the predicted fracture data volume is lower than that of the identified fracture data volume, reduce the computational unit size.

[0095] In some embodiments, the above-described apparatus further includes a construction-guided filtering processing module 35 for preprocessing the post-stack seismic data volume in the following manner:

[0096] The dip and azimuth data volumes of the seismic reflection interface are calculated from the post-stack seismic data volume; the post-stack seismic data volume is then subjected to structurally guided filtering processing using the dip and azimuth data volumes as constraints.

[0097] In some embodiments, the above-described apparatus further includes a fracture skeletonization calculation module 36, used for:

[0098] Before determining whether the predicted fracture data body meets the matching conditions with the fracture-related data body, the judgment module 32 performs fracture enhancement calculation and fracture skeletonization calculation on the predicted fracture data body in sequence.

[0099] In some embodiments, the above-described apparatus further includes a fractured ant body calculation module 37, used for:

[0100] The fracture skeletonization calculation module 36 performs fracture enhancement calculation and fracture skeletonization calculation on the predicted fracture data volume in sequence, and then performs fracture ant body calculation on the calculated predicted fracture data volume.

[0101] In some embodiments, the above-described apparatus further includes a fusion module 38 and a broken file generation module 39;

[0102] The final fracture data body determination module 33 determines the currently obtained predicted fracture data body as the final fracture data body. The fusion module 38 is used to fuse the fracture data body with the fracture-related data body to obtain a fused data body. The fracture file generation module 39 is used to identify fault lines from the fused data body and generate a fault file based on the identified fault lines.

[0103] In some embodiments, the fusion module 38 fuses the fracture data body with the fracture-related data body to obtain a fused data body, specifically used for:

[0104] The fracture data volume and the fracture-related data volume are normalized respectively; the normalized fracture data volume and the fracture-related data volume are added together according to their respective weight coefficients to obtain the fused data volume.

[0105] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0106] Based on the inventive concept of the present invention, embodiments of the present invention also provide a computer program product with fracture recognition function, including a computer program / instruction, wherein the computer program / instruction implements the above-mentioned fracture prediction method when executed by a processor.

[0107] Based on the inventive concept of this invention, this embodiment of the invention also provides a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described fracture prediction method.

[0108] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0109] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0110] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.

[0111] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0112] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0113] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0114] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. A fracture prediction method, characterized in that, include: The predicted fault data volume is obtained from the post-stack seismic data volume using the fault prediction model and model parameters. Determine whether the predicted fracture data volume meets the matching conditions with the fracture-related data volume; If so, the currently obtained predicted fracture data volume is determined as the final fracture data volume; If not, optimize the model parameters and return to the execution of the fault prediction model and model parameters to obtain the predicted fault data volume from the post-stack seismic data volume; The optimized model parameters specifically include: identifying fractures from fracture-related data volumes to obtain identified fracture data volumes; and performing at least one of the following optimized model parameters based on the matching results of the number, continuity, and / or resolution of fractures between the predicted fracture data volumes and the identified fracture data volumes: If the number of fractures in the predicted fracture data body is less than the number of fractures in the identified fracture data body, reduce the size of the computing unit. If the continuity of the predicted fracture data volume is worse than that of the identified fracture data volume, increase the size of the computational unit and / or increase the velocity volume; If the predicted continuity of the fracture data volume is stronger than the identified continuity of the fracture data volume, reduce the size of the computational unit and / or reduce the velocity volume; If the resolution of the predicted fracture data volume is lower than the resolution of the identified fracture data volume, reduce the size of the computational unit.

2. The method as described in claim 1, characterized in that, The model parameters include at least one of the following parameters: Calculate the unit size, whether to include velocity in the calculation, and the velocity volume.

3. The method as described in claim 1 or 2, characterized in that, The fracture-related data body includes at least one of the following data bodies: The data includes post-stack seismic data, fault-related seismic attribute data, and imaging logging data.

4. The method as described in claim 1, characterized in that, This also includes preprocessing the post-stack seismic data volume in the following manner: The dip and azimuth data volumes of the seismic reflection interface are calculated from the post-stack seismic data volume; The post-stack seismic data volume is subjected to structurally guided filtering processing using the dip angle data volume and azimuth angle data volume as constraints.

5. The method as described in claim 1, characterized in that, Before determining whether the predicted fracture data volume meets the matching conditions with the fracture-related data volume, the method further includes: The predicted fracture data volume is subjected to fracture enhancement calculation and fracture skeletonization calculation in sequence.

6. The method as described in claim 5, characterized in that, After sequentially performing fracture enhancement calculations and fracture skeletonization calculations on the predicted fracture data volume, the process further includes: Perform fracture ant body calculation on the calculated predicted fracture data volume.

7. The method as described in claim 1, characterized in that, After determining the currently obtained predicted fracture data volume as the final fracture data volume, the process further includes: The fracture data volume is fused with the fracture-related data volume to obtain a fused data volume; Fault lines are identified from the fused data volume, and fault files are generated based on the identified fault lines.

8. The method as described in claim 7, characterized in that, The process of fusing the fracture data volume with the fracture-related data volume to obtain a fused data volume specifically includes: The fracture data volume and the fracture-related data volume are respectively normalized. The normalized fracture data volume and the fracture-related data volume are added together according to their respective weight coefficients to obtain the fused data volume.

9. A fracture prediction device, characterized in that, The apparatus is used to perform the method of claim 1, the apparatus comprising: The fracture data volume prediction module is used to obtain the predicted fracture data volume from the post-stack seismic data volume using the fracture prediction model and model parameters. The judgment module is used to determine whether the predicted fracture data body obtained by the fracture data body prediction module satisfies the matching condition between the fracture-related data body and the fracture-related data body. The final fracture data body determination module is used to determine the currently obtained predicted fracture data body as the final fracture data body if the judgment module determines that it is true. The model parameter optimization module is used to optimize the model parameters if the judgment module determines that it is not true. The fracture data volume prediction module is also used to return to the execution of obtaining the predicted fracture data volume from the post-stack seismic data volume through the fracture prediction model and model parameters.

10. A computer program product with fracture detection function, comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the fracture prediction method according to any one of claims 1 to 8.

11. A server, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the fracture prediction method according to any one of claims 1 to 8.

Images