Electromagnetic method model parameterization method, system, equipment and medium

Abstract

The invention relates to the field of geophysical exploration, and discloses an electromagnetic method model parameterization method, system and device and a medium. The method comprises the steps that a first single fracturing section in a horizontal well serves as a target single fracturing section, and three-dimensional coordinates of each fracturing cluster in the target single fracturing section are obtained; constructing a center coordinate set corresponding to each fracturing cluster based on each three-dimensional coordinate; the main stress direction angle of the horizontal well is obtained, and an extension direction angle set is constructed according to the main stress direction angle; based on each center coordinate set and the extension direction angle set, generating a fracturing fluid model sample set corresponding to the target single fracturing section; and taking the next single fracturing section of the target single fracturing section as a new target single fracturing section, and returning to the step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single fracturing section until the target single fracturing section is the last single fracturing section of the horizontal well. According to the scheme, the characterization degree of the three-dimensional fracturing fluid model sample set is enriched, and the model parameterization efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of geophysical exploration, and particularly relates to an electromagnetic method model parameterization method, system, device and medium. BACKGROUND

[0002] Hydraulic fracturing technology, as one of the key strategies in the field of oil and gas development, plays a core role in improving reserves and increasing production, and is widely used in the development of oil and gas resources of various burial depths, including but not limited to tight oil (shale oil), heavy oil, oil sand oil, tight gas, shale gas, coal rock gas and natural gas hydrate. Fracturing monitoring technology is considered as a key means for evaluating fracturing effect, which helps to reduce the risk and accident rate of hydraulic fracturing operation, and guides the deployment of the next stage of fracturing operation. However, traditional geophysical exploration methods, such as conventional seismic method, gravity, magnetic force and electrical method, often show the characteristics of post-evaluation when providing fracturing monitoring results, that is, the data feedback is lagging and lacks timeliness. In order to solve this problem, an artificial intelligence method is proposed to be integrated into the traditional time-frequency electromagnetic method to make up for the defects of traditional monitoring technology in timeliness. Through this integrated technology, real-time monitoring of fracturing fluid can be directly performed, and the three-dimensional distribution state and migration of the fracturing fluid in the underground space can be quickly obtained, providing more timely and accurate fracturing effect evaluation data for oil and gas development, so as to further optimize the fracturing operation strategy and improve the efficiency of oil and gas resource development.

[0003] At present, when using electromagnetic method to quickly predict the fracturing site monitoring results, no matter what artificial intelligence processing method is used, it is inevitable to generate a large number of high-precision training data sets in advance in network training. The realization of this process highly depends on an efficient electromagnetic method three-dimensional model parameterization method. In the numerical simulation process of traditional electromagnetic method, the demand for models is not large, and usually only a few models need to be constructed to meet the analysis requirements. Common three-dimensional model parameterization methods mainly use hexahedron or tetrahedron to form a cuboid or a geometric body, and parameterize by adjusting the length, width and height of the cuboid or the multiple degrees of freedom of the geometric body. However, this method is not sufficient when facing artificial intelligence networks, especially those networks that require tens of thousands of training model sample sets. Especially when the model parameterization needs to highly represent the complex model characteristics of the underground fracturing fluid, the traditional simple geometric body parameterization method cannot meet the requirements.

[0004] Therefore, it is necessary to develop a more detailed electromagnetic method model parameterization method, system, device and medium to overcome the above-mentioned defects, so as to provide technical support for the rapid and accurate three-dimensional fracturing fluid distribution prediction of artificial intelligence in the fracturing site. SUMMARY

[0005] In view of this, the present application provides an electromagnetic method model parameterization method, system, device and medium, which solves the technical problems of low efficiency and long time of previous model parameterization, improves the representation degree of the three-dimensional model sample set, and can generate a single-fracturing-cluster multi-cluster fracturing fluid model training data set with high representation degree in batches with high precision for a time-frequency electromagnetic artificial intelligence network used for fracturing monitoring technology.

[0006] Based on the above purpose, one aspect of an embodiment of the present application provides an electromagnetic method model parameterization method, which specifically includes the following steps: Taking the first single-fracturing cluster in the horizontal well as a target single-fracturing cluster, three-dimensional coordinates of each fracturing cluster in the target single-fracturing cluster are obtained; Based on the three-dimensional coordinates, a center coordinate set corresponding to each fracturing cluster is constructed; The main stress direction angle of the horizontal well is obtained, and an extension direction angle set is constructed according to the main stress direction angle; Based on the center coordinate set and the extension direction angle set, a fracturing fluid model sample set corresponding to the target single-fracturing cluster is generated; The next single-fracturing cluster of the target single-fracturing cluster is taken as a new target single-fracturing cluster, and the step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single-fracturing cluster is returned until the target single-fracturing cluster is the last single-fracturing cluster of the horizontal well.

[0007] In some embodiments, the step of generating the fracturing fluid model sample set corresponding to the target single-fracturing cluster based on the center coordinate set and the extension direction angle set includes: Based on the center coordinate set, the center point coordinate parameters of a plurality of sub-fracturing fluid models corresponding to the center coordinate set are batch-set; Based on the extension direction angle set, the extension direction angle parameters of all the sub-fracturing fluid models are batch-set, and based on the extension direction angle parameters, the directions of three axes of all the sub-fracturing fluid models are determined; Based on the three-axis radius length set, the radius length parameters of the three axes of all the sub-fracturing fluid models are batch-set; Based on all the sub-fracturing fluid models with the set center point coordinate parameters, extension direction angle parameters and radius length parameters of the three axes, the fracturing fluid model sample set corresponding to the target single-fracturing cluster is generated; The three axes include a long axis, a middle axis and a short axis.

[0008] In some embodiments, the electromagnetic method model parameterization method further includes: According to a first preset angle interval, a plurality of rotation angle values are selected at equal intervals in a preset rotation angle range to construct a rotation angle set; Based on the set of rotation angles, batch set the rotation angle parameters of the three axes of all the sub-fracturing fluid models; Based on all the sub-fracturing fluid models with the set rotation angle parameters, update the fracturing fluid model sample set.

[0009] In some embodiments, the step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single fracturing section comprises: Obtaining well trajectory data of the horizontal well and preset two-dimensional coordinates of each fracturing cluster in the target single fracturing section; Based on the well trajectory data and each preset two-dimensional coordinate, determining the corresponding three-dimensional coordinates of each fracturing cluster on the horizontal well.

[0010] In some embodiments, the step of constructing a set of center coordinates corresponding to each fracturing cluster based on each three-dimensional coordinate comprises: Obtaining the fracturing cluster spacing in the target single fracturing section; Taking each three-dimensional coordinate as a center point and the fracturing cluster spacing as a radius, determining the center point distribution range corresponding to each fracturing cluster; According to a preset distance interval, equally spaced selecting a plurality of coordinate points in each center point distribution range to construct a set of center coordinates corresponding to each fracturing cluster.

[0011] In some embodiments, the step of obtaining the principal stress direction angle of the horizontal well and constructing a set of extension direction angles based on the principal stress direction angle comprises: Obtaining the principal stress direction angle of the horizontal well; Based on the principal stress direction angle and a preset angle range value, determining an extension direction angle range; According to a second preset angle interval, equally spaced selecting a plurality of extension direction angles in the extension direction angle range to construct the set of extension direction angles.

[0012] In some embodiments, the electromagnetic method model parameterization method further comprises: Obtaining the grid cells respectively occupied by each fracturing fluid model in the fracturing fluid model sample set in a three-dimensional network; Setting the resistivity attribute of all the grid cells to a preset resistivity value.

[0013] Another aspect of the embodiments of the present application also provides an electromagnetic method model parameterization system, comprising: A fracturing cluster coordinate acquisition unit configured to determine a target single fracturing section and obtain three-dimensional coordinates of each fracturing cluster in the target single fracturing section; The first set construction unit is configured to construct a center coordinate set corresponding to each of the fracturing clusters based on the three-dimensional coordinates. The second set construction unit is configured to obtain a main stress direction angle of the horizontal well, and construct a propagation direction angle set according to the main stress direction angle. The generation unit is configured to generate a fracturing fluid model sample set corresponding to the target single fracturing section based on the center coordinate set and the propagation direction angle set.

[0014] In another aspect, the embodiment of the present application further provides a computer device, which comprises at least one processor and a memory storing a computer program capable of running on the processor, and the computer program is executed by the processor to realize the steps of the above method.

[0015] In another aspect, the embodiment of the present application further provides a computer readable storage medium storing a computer program capable of being executed by a processor to realize the steps of the above method.

[0016] The electromagnetic method model parameterization method has at least the following beneficial technical effects: the center coordinate set is constructed in batches according to the three-dimensional coordinates of each fracturing cluster under the single fracturing section, which helps to understand the possible distribution range of the center point of the sub-fracturing fluid model of each fracturing cluster, and the propagation direction angle set is constructed according to the main stress direction of the horizontal well formation, so as to ensure that the propagation direction of the constructed fracturing fluid model is consistent with the main stress direction of the horizontal well formation, and there is a certain degree of redundant bias range. On the basis of the above-constructed sets, the high-precision parameterized fracturing fluid model sample can be generated in batches, which not only covers the three-dimensional spatial position of each fracturing cluster, but also meets the main stress propagation direction characteristics of the formation where the fracturing cluster is located, greatly enriches the representation degree of the time-frequency electromagnetic artificial intelligence network training sample set, and improves the model parameterization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other embodiments can also be obtained from these drawings without creative labor.

[0018] Figure 1 A block diagram of an embodiment of the electromagnetic method model parameterization method provided by the present application; Figure 2 A schematic diagram of an embodiment of a three-cluster fracturing fluid model provided by the present application; Figure 3A schematic diagram of an embodiment of another three-cluster fracturing fluid model with rotation angle parameter provided by the present invention; Figure 4 A schematic diagram of an embodiment of the electromagnetic method model parameterization system provided by the present invention; Figure 5 A schematic diagram of the structure of an embodiment of the computer device provided by the present invention; Figure 6 This is a schematic diagram of an embodiment of the computer-readable storage medium provided by the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to specific examples and the accompanying drawings.

[0020] It should be noted that all uses of "first" and "second" in the embodiments of the present invention are for the purpose of distinguishing two entities or parameters with the same name but different names. It is clear that "first" and "second" are only for the convenience of expression and should not be construed as limiting the embodiments of the present invention. Subsequent embodiments will not explain this in detail.

[0021] Based on the above objectives, a first aspect of the present invention proposes an embodiment of an electromagnetic method model parameterization method. For example... Figure 1 As shown, it includes the following steps: Step S100: Take the first single fracturing section in the horizontal well as the target single fracturing section, and obtain the three-dimensional coordinates of each fracturing cluster in the target single fracturing section; Step S200: Based on each three-dimensional coordinate, construct the set of center coordinates corresponding to each fracturing cluster; Step S300: Obtain the principal stress direction angle of the horizontal well, and construct an extension direction angle set based on the principal stress direction angle. Step S400: Based on the set of center coordinates and the set of extension direction angles, generate a fracturing fluid model sample set corresponding to the target single fracturing segment; Step S500: Take the next single fracturing segment of the target single fracturing segment as the new target single fracturing segment, and return to the step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment, until the target single fracturing segment is the last single fracturing segment of the horizontal well.

[0022] In some embodiments, a single fracturing section refers to an independent unit of fracturing treatment of subterranean rock in a horizontal well. In the fracturing operation of a horizontal well, the entire wellbore is divided into several sections, and each section is treated as an independent unit for fracturing. In a single fracturing section, there are multiple fracturing cluster perforations at certain intervals, and these perforations are the key channels for the fracturing fluid to enter the formation. After the fracturing fluid is injected into the formation through these perforations, it migrates and expands the fractures in the formation, thereby improving the permeability and recovery of the oil and gas reservoir. Therefore, the fracturing fluid model is closely related to the three-dimensional spatial position of the fracturing cluster. After calculating the three-dimensional coordinates of each fracturing cluster in the target single fracturing section based on the actual well trajectory data, the possible distribution range of the center point of each sub-fracturing cluster model corresponding to each fracturing cluster is calculated with the three-dimensional coordinates of each fracturing cluster as a reference. This facilitates the batch acquisition of all possible center point coordinates and the construction of a center coordinate set based on the distribution range of the center point. Before the fracturing of a horizontal well, it is crucial to understand the underground stress parameters and geological information to determine the principal stress direction and angle of the horizontal well. These information are usually obtained through geological exploration, well logging data, seismic interpretation, and rock mechanics testing. Principal stress is an important concept in mechanics, especially in rock mechanics, soil mechanics, and engineering mechanics. The principal stress of a horizontal well refers to the three stresses of the maximum, intermediate, and minimum in any direction at a certain point in the formation of the horizontal well. The principal stress direction angle includes the maximum principal stress direction angle, the intermediate principal stress direction angle, and the minimum principal stress direction angle. Generally, the maximum principal stress direction is perpendicular to the tectonic compression direction. With the principal stress direction angle as a reference, the possible extension direction angle range of the sub-fracturing cluster model is calculated, which facilitates the batch acquisition of all possible extension direction angle values and the construction of an extension direction angle set based on the extension direction angle range. Based on the center coordinate set and the extension direction angle set, the center point coordinate parameters and the extension direction angle parameters of multiple sub-fracturing fluid models are batch set, and on this basis, the three-axis radius length parameters of multiple sub-fracturing fluid models are batch set, thereby realizing the batch generation of high-precision parameterized fracturing fluid model samples. The fracturing fluid model sample is obtained by combining the sub-fracturing fluid models of all fracturing clusters in each single fracturing section. For example, if there are three fracturing clusters in the first single fracturing section, the fracturing fluid model sample of the first single fracturing section is a three-cluster fracturing fluid model sample obtained by combining three sub-fracturing fluid models. Each single fracturing section in a horizontal well corresponds to a fracturing fluid model sample set. Through the above method, all possible fracturing fluid model samples can be batch generated for different single fracturing sections in a horizontal well, and the corresponding fracturing fluid model sample set can be constructed.

[0023] This invention provides an electromagnetic model parameterization method that constructs a set of center coordinates in batches based on the three-dimensional coordinates of each fracturing cluster under a single fracturing section. This helps to understand all possible distribution ranges of the center points of the sub-fracturing fluid models of each fracturing cluster. Furthermore, it constructs a set of extension direction angles based on the principal stress direction of the formation in the horizontal well, ensuring that the extension direction of the constructed fracturing fluid model is consistent with the principal stress direction of the formation in the horizontal well section, and that there is a certain degree of redundant offset range. Based on the above-constructed sets, it is possible to generate high-precision parameterized fracturing fluid model samples in batches. These samples not only cover the spatial location of each fracturing cluster but also conform to the characteristics of the extension direction of the principal stress of the formation where the fracturing cluster is located. This greatly enriches the representativeness of the training sample set of the time-frequency electromagnetic artificial intelligence network and improves the efficiency of model parameterization.

[0024] In some implementations, the step of generating a fracturing fluid model sample set corresponding to the target single fracturing segment based on each set of center coordinates and extension direction angles includes: setting the center point coordinate parameters of several sub-fracturing fluid models of the fracturing cluster corresponding to each set of center coordinates in batches; setting the extension direction angle parameters of all sub-fracturing fluid models in batches based on the extension direction angle set, and determining the orientation of the three axes of all sub-fracturing fluid models based on the extension direction angle parameters; setting the radius length parameters of the three axes of all sub-fracturing fluid models in batches based on a preset set of three-axis radius lengths; and generating a fracturing fluid model sample set corresponding to the target single fracturing segment based on all sub-fracturing fluid models with set center coordinate parameters, extension direction angle parameters, and three-axis radius length parameters; wherein the three axes include the major axis, the middle axis, and the minor axis.

[0025] In some implementations, each fracturing cluster has multiple possible sub-fracturing fluid models. The number of these sub-fracturing fluid models is determined based on the number of parameters in its corresponding center coordinate set and the number of parameters in its extension direction angle set. For example, if the extension direction angle set contains N extension direction angle values, and the center coordinate set corresponding to a certain fracturing cluster contains M center point coordinate parameters, then that fracturing cluster has... There are N possible sub-fracturing fluid models, that is, there are N sub-fracturing fluid models with different extension directions on the same center point coordinate parameters.

[0026] In some implementations, when generating fracturing fluid model samples corresponding to a target single fracturing segment in batches, continuing with the above example, if there are 3 fracturing clusters in the target single fracturing segment, and each fracturing cluster has There are 10 possible sub-fracturing fluid models, and the number of batches of fracturing fluid model samples generated in this batch is 10. For each generation batch, a center coordinate parameter is randomly selected from the center coordinate sets corresponding to the three fracturing clusters and set as the center point coordinate parameter of its corresponding sub-fracturing fluid model, with the spacing between the three center point coordinate parameters consistent with the spacing of the fracturing clusters. Further, based on the above-determined center point coordinate parameters, for each generation batch, an extension direction angle value is randomly selected from the extension direction angle set and set as the extension direction angle parameter for all sub-fracturing fluid models within that generation batch. Further, based on the above-determined center point coordinate parameters and extension direction angle parameters, the triaxial radius length parameters are randomly sampled from a preset triaxial radius length set according to the total number of all sub-fracturing fluid models and allocated to each sub-fracturing fluid model to complete the batch setting of the triaxial radius length parameters for all sub-fracturing fluid models. Finally, based on the above-determined center point coordinate parameters, extension direction angle parameters, and triaxial radius length parameters, a fracturing fluid model sample corresponding to a target single fracturing segment is obtained by combining the three sub-fracturing fluid models from the same batch. The extension direction angles include the maximum extension direction angle, the intermediate extension direction angle, and the minimum extension direction angle. Each extension direction angle in the set of extension direction angles is calculated based on the principal stress direction angles (including the maximum, intermediate, and minimum principal stresses) and with a certain degree of redundant offset.

[0027] In some implementations, the major axis of the sub-fracturing fluid model represents the primary propagation path of the fracture in three-dimensional space after the fracturing fluid is injected into the formation through fracturing clusters. The direction of the major axis corresponds to the direction of maximum propagation. The minor axis can be considered as the propagation path of the fracture perpendicular to the primary propagation direction (i.e., the direction of the major axis), meaning the direction of the minor axis corresponds to the direction of minimum propagation. The minor axis is typically much shorter than the major axis. The intermediate axis can be considered as the propagation path perpendicular to the major axis and with a length between the major and minor axes. The direction of the intermediate axis corresponds to the intermediate propagation direction. A preset set of triaxial radius lengths is used to approximate the spatial extension boundary of the fracturing fluid model. This preset set of triaxial radius lengths includes a major axis radius length parameter, a intermediate axis radius length parameter, and a minor axis radius length parameter, with the radius length parameters ranging from 0 meters to 500 meters.

[0028] The electromagnetic model parameterization method of this invention, based on the determination of the center point coordinate parameters, uses triaxial parameters (including the direction and radius of the three axes) to approximately characterize the spatial extension boundary of the fracturing fluid model, so that the fracturing fluid model can cover the position of all fracturing clusters in the target single fracturing segment in three-dimensional space, while conforming to the characteristics of the principal stress extension direction of the formation where the fracturing clusters are located.

[0029] In some embodiments, the electromagnetic model parameterization method of the present invention further includes: selecting a number of rotation angle values ​​at equal intervals within a preset rotation angle range according to a first preset angle interval to construct a rotation angle set; setting the rotation angle parameters of the three axes of all sub-fracturing fluid models in batches based on the rotation angle set; and updating the fracturing fluid model sample set based on all sub-fracturing fluid models with the rotation angle parameters set.

[0030] In some implementations, the preset rotation angle range can be Degree to The preset rotation angle range is 1 degree or 2 degrees. The preset rotation angle range and the first preset angle interval can be set according to actual application requirements. Batch selection of rotation angle values ​​is performed according to the first preset angle interval. That is, when the first preset angle interval is 2 degrees, the batch selection of rotation angle values ​​includes... , , , … , , A set of 31 rotation angle values ​​was constructed. Based on this set, the rotation angle parameters of the three axes of all sub-fracturing fluid models were calculated and set in batches, and the spatial coordinates of all sub-fracturing fluid models in the 3D network were updated based on these rotation angle parameters. Specifically, for each sub-fracturing fluid model, its center point was used as the origin, its major axis, median axis, and minor axis were used as rotation axes, and the extension direction angles of its three axes were used as the starting point. Based on the extension direction angle parameters, the three-axis rotation angle parameters were added in batches. Then, all the updated sub-fracturing fluid models were stored in the fracturing fluid model sample set to update the fracturing fluid model sample set. In one example, the rotation angle set includes the aforementioned 31 rotation angle values, with the center point of a certain sub-fracturing fluid model as the origin, and the angle between its major axis and the XOY plane being... The axis is parallel to the YOZ plane, and its minor axis is parallel to the XOY plane and perpendicular to the YOZ plane. The minor axis is parallel to the YOZ plane and makes a 60-degree angle with the XOY plane. Three rotation angle values ​​are randomly sampled from the set of rotation angles and assigned to the three axes to set the corresponding rotation angle parameters. For example, if the sampled rotation angle value is... And assign it to the major axis, where the rotation angle parameter corresponding to the major axis is... The degree is extracted, the rotation angle value is 0, and it is assigned to the minor axis. At this time, the rotation angle parameter corresponding to the minor axis is 0 degrees, and the extracted rotation angle value is... And assign it to the central axis, at which point the rotation angle parameter corresponding to the central axis is... Based on the rotation angle parameters and extension direction angle parameters of the three axes mentioned above, the spatial position coordinates of the sub-fracturing fluid model in the three-dimensional network are updated. For example, the angle between the major axis and the XOY plane is updated to... The angle between the central axis and the YOZ has been updated to [degrees]. Spend.

[0031] The electromagnetic model parameterization method of this invention uniformly selects the three-axis rotation angle values ​​of the sub-fracturing fluid model according to a certain rule, calculates and updates the spatial position coordinates of the sub-fracturing fluid model in the three-dimensional network, and can increase the degree of freedom and control parameters of the three-axis rotation of the sub-fracturing fluid model by means of the rotation angle set, thereby increasing the diversity of fracturing fluid model features.

[0032] In some implementations, the step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment includes: obtaining well trajectory data of the horizontal well and preset two-dimensional coordinates of each fracturing cluster in the target single fracturing segment; and determining the three-dimensional coordinates of each fracturing cluster on the horizontal well based on the well trajectory data and each preset two-dimensional coordinate.

[0033] In some implementations, during horizontal well fracturing operations, we typically have complete three-dimensional trajectory data of the horizontal well (i.e., well trajectory data), obtained through measurements during the drilling process. However, when designing fracturing sections and clusters, since fracturing operations primarily focus on fracture propagation in the horizontal direction, the pre-designed coordinates of the fracturing cluster may only include (x, y) coordinates (i.e., two-dimensional coordinates). It is necessary to calculate the z-coordinate corresponding to the fracturing cluster based on the actual well trajectory data to determine the three-dimensional coordinates of the fracturing cluster. That is, by collecting well trajectory data (x...y ... well , y well , z well ) and the design coordinates (x) of each fracturing cluster in a single fracturing segment cluster , y cluster The unknown coordinates z of each fracturing cluster were calculated using a three-dimensional linear interpolation method. cluster This allows us to obtain the three-dimensional coordinates (x, y) of each fracturing cluster in a single fracturing section on a horizontal well. cluster , y cluster ,z cluster ).

[0034] The electromagnetic model parameterization method of this invention uses a three-dimensional linear interpolation calculation method to obtain the accurate position of each fracturing cluster on the actual trajectory of a horizontal well under a single fracturing section, which plays a key role in subsequent model parameterization.

[0035] In some implementations, the step of constructing a set of center coordinates corresponding to each fracturing cluster based on each three-dimensional coordinate includes: obtaining the spacing between fracturing clusters in the target single fracturing segment; determining the distribution range of center points corresponding to each fracturing cluster with each three-dimensional coordinate as the center point and the spacing between fracturing clusters as the radius; and selecting several coordinate points at equal intervals in each center point distribution range according to a preset distance interval to construct a set of center coordinates corresponding to each fracturing cluster.

[0036] In some implementations, the distribution range of the center point of each fracturing cluster is calculated with reference to the three-dimensional coordinates of the multiple clusters, that is, with reference to the three-dimensional spatial coordinates (x, y, z) of each fracturing cluster. cluster , y cluster , z cluster Using (400, 0, ...) as the center point and the distance between fracturing clusters within each fracturing segment as the radius, the three-dimensional center point distribution range corresponding to each fracturing cluster is calculated. The distance between fracturing clusters varies within different fracturing segments. The preset distance interval is typically between 1 meter and 5 meters, designed according to actual application requirements. For example, with a preset distance interval of 5 meters, samples are taken at 5-meter intervals within the center point distribution range, and all sampled coordinate values ​​are used as the data for the center coordinate set. In one example, assume the target fracturing segment includes three-dimensional coordinates (400, 0, ...). The fracturing cluster A has three-dimensional coordinates of (500, 0, ...). The fracturing cluster B and its three-dimensional coordinates are (600, 0, ...). Fracturing cluster C has a spacing of 100 meters between clusters. Taking fracturing cluster A as an example, its corresponding three-dimensional center point distribution range is (600, 0, ...). A sphere with a radius of 100 meters, its x-coordinate ranges from 300 meters to 500 meters, and its y-coordinate ranges from... The z-coordinate ranges from 1 meter to 100 meters. Rice to Meters. Sampling is performed at 5-meter intervals, so the sampling points for the x-coordinate are 300, 305, 310, ..., 490, 495, 500, and the sampling points for the y-coordinate are... , , The sampling points for the z-coordinate are 90, ..., 90, 95, 100. , , … , , Multiple coordinate points are obtained by randomly combining sampling points of the x, y, and z coordinates. After removing duplicates from all coordinate points, these points are stored and used to construct the central coordinate set corresponding to fracturing cluster A. The central coordinate sets corresponding to fracturing clusters B and C are constructed in the same way.

[0037] The electromagnetic model parameterization method of this invention creates a set of center coordinates by using the three-dimensional coordinates of each fracturing cluster under a single fracturing section. This facilitates the batch acquisition of all possible center point coordinate parameters of the sub-fracturing fluid model of each fracturing cluster, preparing for the subsequent addition of model parameters with other ranges of variation based on the center point coordinate parameters.

[0038] In some embodiments, the step of obtaining the principal stress direction angle of the horizontal well and constructing an extension direction angle set based on the principal stress direction angle includes: obtaining the principal stress direction angle of the horizontal well; determining the extension direction angle range based on the principal stress direction angle and a preset angle range value; and selecting several extension direction angles at equal intervals within the extension direction angle range according to a second preset angle interval to construct an extension direction angle set.

[0039] In some implementations, the principal stress direction angle of the horizontal well is obtained through underground stress parameters and geological information. Using this principal stress direction angle as the median, a preset angle range is added to the formation plane to obtain the extended direction angle range. The preset angle range value can be... to Any value can be set according to actual application requirements. For example, the angle between the maximum principal stress and the XOY plane is... The preset angle range is 10 degrees, meaning that an angle of 10 degrees is added to the formation plane relative to the principal stress direction. Degree to If the maximum extension direction is within a certain range, then the angle between the maximum extension direction and the XOY plane is within the range of... Degree to degrees, that is, the maximum extension direction angle range is Degree to The second preset angle interval can be 1 degree or 2 degrees. For example, taking a second preset angle interval of 2 degrees as an example, sampling is performed at 2-degree intervals in all extension direction angle ranges to determine the extension direction angle values ​​in batches, and all extension direction angle values ​​are stored in the extension direction angle set.

[0040] The electromagnetic model parameterization method of this invention determines all possible extension direction angle values ​​of the sub-fracturing fluid models of each fracturing cluster in batches within the extension direction angle range. This ensures that the final fracturing fluid model is consistent with the principal stress direction of the horizontal well formation, while also having a certain degree of redundancy bias range, thus guaranteeing the characterization capability of the fracturing fluid model.

[0041] In some embodiments, the electromagnetic model parameterization method of the present invention further includes: obtaining the grid cells occupied by each fracturing fluid model in the three-dimensional network in the fracturing fluid model sample set; and setting the resistivity attribute of all grid cells to a preset resistivity value.

[0042] In some implementations, the discrete values ​​of the fracturing fluid model in the three-dimensional network space are calculated using the center point coordinates, extension direction angle, and triaxial radius parameters of the fracturing fluid model. This determines the coordinate positions of all grid cells occupied by the fracturing fluid model in the entire three-dimensional network space. Once the discrete coordinate values ​​of all fracturing fluid models in the three-dimensional network space are calculated in batches and obtained, the spatial position of each small grid cell occupied by the fracturing fluid model is determined. Resistivity values ​​are then assigned to these small grid cells, i.e., the resistivity attribute of all grid cells is set to a preset resistivity value, which is the measured resistivity value of the fracturing fluid. Each grid cell can be a cube with a side length of 1 meter.

[0043] The electromagnetic model parameterization method of this invention can accurately and quickly calculate all discrete coordinate values ​​of the grid cells occupied by the fracturing fluid model in the entire three-dimensional network. By filling and marking the grid cells occupied by the fracturing fluid model with attributes, it can indicate that there is fracturing fluid at the location in the three-dimensional space.

[0044] In some implementations, it is assumed that the target single fracturing section is the first single fracturing section in a horizontal well, and that the first single fracturing section is designed with three fracturing clusters, combined with... Figure 2 and Figure 3 The implementation process of the electromagnetic method model parameterization method of the present invention is described below: Step 1: Calculate the three-dimensional coordinates of the three fracturing clusters below the first single fracturing section using well trajectory data. In the well trajectory data, the start and end coordinates of the vertical segment of the horizontal well are (0, 0, 0) and (0, 0, 0), respectively. The vertical section is 1000 meters deep, and the starting and ending coordinates of the horizontal section of the horizontal well are (0, 0, ...). (1000, 0, The horizontal section is 1000 meters long. The design coordinates of the three fracturing clusters in the first single fracturing section are (400, 0), (500, 0), and (600, 0). Using a three-dimensional linear interpolation method, the three-dimensional coordinates of the three fracturing clusters in the first single fracturing section are obtained as (400, 0, 0). (500, 0, (600, 0, ).

[0045] Step 2: Calculate the distribution range of the center points corresponding to the three fracturing clusters, using their three-dimensional coordinates as a reference. The three-dimensional coordinates of the three fracturing clusters (400, 0, ...) are used as the reference. (500, 0, (600, 0, Using a fracturing cluster as the center and a radius of 100 meters between clusters, calculate the range of all possible center points for the three fracturing clusters. Then, select coordinate values ​​by sampling at 5-meter intervals within the distribution range of each of the three center points, and construct the center coordinate set of the three fracturing clusters using these selected coordinate values.

[0046] Step 3: Calculate the extension direction range of the sub-fracturing fluid models for the three fracturing clusters. The angle between the formation principal stress direction of the horizontal well and the XOY plane of the 3D network containing the horizontal well is obtained as +30 degrees. Using this angle as the median, the extension direction angle range of all sub-fracturing fluid models is calculated to be +20 degrees to +40 degrees.

[0047] Step 4: Spatial Discretization of Extension Direction Angles. Using the extension direction angle range calculated in Step 3, angle values ​​are selected in batches by sampling at 2-degree intervals. This batch obtains all possible extension direction angle values ​​of the three fracturing clusters under the first single fracturing segment on the three-dimensional network, and constructs an extension direction angle set.

[0048] Step 5: Calculate the triaxial radius range of the sub-fracturing fluid models for each fracturing cluster. Based on the center coordinate set and extension direction angle set obtained in Steps 2 and 4, add a triaxial radius length set. The triaxial radius length range is set to 0 meters to 300 meters. Triaxial parameters are sampled according to the number of parameterized samples of the batch-generated sub-fracturing fluid models mentioned above, and freely allocated to each sub-fracturing fluid model. Finally, three clusters of fracturing fluid models with defined triaxial radius parameters are obtained, and a fracturing fluid model sample set is constructed.

[0049] Step 6: Spatial Discretization of Triaxial Radius Parameters. Using the center point coordinates of the three fracturing fluid models obtained in steps 1 to 5 as the origin, and the extension direction angle and triaxial radius length as morphological parameters, calculate the discrete values ​​of each sub-fracturing fluid model within a 1000m*1000m*1000m three-dimensional network. This determines the accurate node coordinates of the grid cells occupied by the three fracturing fluid models in the entire grid space. One of the generated three fracturing fluid models is shown below. Figure 2 As shown.

[0050] Step 7: Calculate the triaxial rotation angle range of the three-cluster fracturing fluid model. Using the center of each sub-fracturing fluid model within the three-cluster fracturing fluid model as the origin, and the major axis, minor axis, and median axis as the rotation axes, and the model extension direction angle from Step 3 as the starting angle, proceed according to... Degree to The rotation angle range varies.

[0051] Step 8: Spatial Discretization of Triaxial Rotation Angle Parameters. Within the rotation angle range of Step 7, angle values ​​are selected by equal-interval sampling at 2-degree intervals to obtain a rotation angle set. Triaxial rotation angle values ​​are randomly selected from this set and assigned to each sub-fracturing fluid model in the three-cluster fracturing fluid model dataset as its triaxial rotation angle parameter. The spatial coordinates of all sub-fracturing fluid models with rotation angle parameters in the 3D network are calculated and updated in batches. One of the generated three-cluster fracturing fluid models with rotation angle parameters is shown below. Figure 3 As shown.

[0052] Step 9: Assign attribute values ​​to the mesh cells containing the three-cluster fracturing fluid model of the first single fracturing stage. Through steps 1 to 8, batch calculate and obtain the discrete coordinate values ​​of all three-cluster fracturing fluid models in the 3D network within the fracturing fluid model sample set, determining the spatial node coordinate values ​​of each mesh cell occupied by the model. The measured fracturing fluid resistivity (1 ohm-meter) is then batch-assigned to all mesh cells containing the three-cluster fracturing fluid models, thus filling the fracturing fluid model attributes in the 3D network.

[0053] Step 10: Repeat steps 1 to 9 multiple times to complete the parameterization of the sub-fracturing fluid models of each fracturing cluster under all other single fracturing sections, and obtain multiple fracturing fluid model sample sets corresponding to any single fracturing section.

[0054] Through the above steps, a fracturing fluid model sample set that conforms to the characteristics of fracturing clusters under each fracturing stage can be obtained, and the multiple features of the fracturing fluid models in the sample set are independent of each other. The electromagnetic model parameterization method of this invention effectively avoids the problems of overfitting and poor generalization ability in the trained network due to the uniformity of the training dataset, solving the technical difficulties of complex, inefficient, and time-consuming model parameterization processes in the past. It can gradually realize the efficient and batch generation of sub-fracturing fluid models for all fracturing clusters under each single fracturing stage, and the fracturing fluid model sample set has a stronger characterization ability for different single fracturing stages. It provides support for targeted training model datasets for artificial intelligence networks in electromagnetic fracturing monitoring.

[0055] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 4 As shown, embodiments of the present invention also provide an electromagnetic method model parameterization system, which includes: The fracturing cluster coordinate acquisition unit 110 is configured to determine the target single fracturing segment and acquire the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment; The first set construction unit 120 is configured to construct the set of center coordinates corresponding to each fracturing cluster based on each three-dimensional coordinate. The second set construction unit 130 is configured to obtain the principal stress direction angle of the horizontal well and construct the extended direction angle set based on the principal stress direction angle. The generation unit 140 is configured to generate a fracturing fluid model sample set corresponding to the target single fracturing segment based on the set of center coordinates and the set of extension direction angles.

[0056] This invention's electromagnetic model parameterization system constructs a set of center coordinates in batches based on the three-dimensional coordinates of each fracturing cluster under a single fracturing section. This helps to understand all possible distribution ranges of the center points of the sub-fracturing fluid models of each fracturing cluster. Furthermore, it constructs a set of extension direction angles based on the principal stress direction of the formation in the horizontal well, ensuring that the extension direction of the constructed fracturing fluid model is consistent with the principal stress direction of the formation in the horizontal well section, and that there is a certain degree of redundant offset range. Based on the aforementioned constructed sets, it can achieve batch generation of high-precision parameterized fracturing fluid model samples. These samples not only cover the spatial location of each fracturing cluster but also conform to the characteristics of the principal stress extension direction of the formation where the fracturing cluster is located. This greatly enriches the representativeness of the training sample set of the time-frequency electromagnetic artificial intelligence network and improves the efficiency of model parameterization.

[0057] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 5 As shown, an embodiment of the present invention also provides a computer device 30, which includes a processor 310 and a memory 320. The memory 320 stores a computer program 321 that can be run on the processor. When the processor 310 executes the program, it performs the steps of the method described above.

[0058] Based on the same inventive concept, according to another aspect of the present invention, such as Figure 6 As shown, embodiments of the present invention also provide a computer-readable storage medium 40, which stores a computer program 410 that, when executed by a processor, performs the methods described above.

[0059] Finally, 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. The storage medium for the program can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The above computer program embodiments can achieve the same or similar effects as any of the corresponding foregoing method embodiments.

[0060] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the functionality of various illustrative components, blocks, modules, circuits, and steps has been generally described. Whether this functionality is implemented as software or as hardware depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art can implement the functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the embodiments disclosed herein.

[0061] The above are exemplary embodiments disclosed in this invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments of this invention as defined by the claims. The functions, steps, and / or actions of the methods according to the disclosed embodiments described herein do not need to be performed in any particular order. The sequence numbers of the disclosed embodiments of this invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. Furthermore, although the elements disclosed in the embodiments of this invention may be described or claimed individually, they may be understood as multiple unless explicitly limited to a singular number.

[0062] It should be understood that, as used herein, the singular form “a” is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, “and / or” refers to any and all possible combinations of one or more of the associated listed items.

[0063] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A parameterization method for an electromagnetic method model, characterized in that, include: The first single fracturing segment in the horizontal well is taken as the target single fracturing segment, and the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment are obtained; Based on the three-dimensional coordinates, construct a set of center coordinates corresponding to each fracturing cluster; Obtain the principal stress direction angle of the horizontal well, and construct an extension direction angle set based on the principal stress direction angle. Based on the set of center coordinates and the set of extension direction angles, a fracturing fluid model sample set corresponding to the target single fracturing segment is generated. The next single fracturing segment of the target single fracturing segment is taken as the new target single fracturing segment, and the step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment is returned until the target single fracturing segment is the last single fracturing segment of the horizontal well.

2. The electromagnetic method model parameterization method according to claim 1, characterized in that, The step of generating a fracturing fluid model sample set corresponding to the target single fracturing segment based on each of the center coordinate sets and the extension direction angle sets includes: Based on each of the aforementioned center coordinate sets, the center point coordinate parameters of several sub-fracturing fluid models of the fracturing cluster corresponding to each of the aforementioned center coordinate sets are set in batches. Based on the set of extension direction angles, the extension direction angle parameters of all the sub-fracturing fluid models are set in batches, and based on the extension direction angle parameters, the directions of the three axes of all the sub-fracturing fluid models are determined; Based on a preset set of triaxial radius lengths, the radius length parameters of the three axes of all the sub-fracturing fluid models are set in batches; Based on all the sub-fracturing fluid models with the center point coordinate parameters, extension direction angle parameters, and the radius length parameters of the three axes set, a fracturing fluid model sample set corresponding to the target single fracturing segment is generated; The three axes mentioned above include the major axis, the middle axis, and the minor axis.

3. The electromagnetic method model parameterization method according to claim 2, characterized in that, Also includes: According to the first preset angle interval, several rotation angle values ​​are selected at equal intervals within the preset rotation angle range to construct a rotation angle set; Based on the set of rotation angles, set the rotation angle parameters of the three axes for all the sub-fracturing fluid models in batches; The fracturing fluid model sample set is updated based on all the sub-fracturing fluid models with the rotation angle parameter set.

4. The electromagnetic method model parameterization method according to claim 1, characterized in that, The step of obtaining the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment includes: Acquire the well trajectory data of the horizontal well and the preset two-dimensional coordinates of each fracturing cluster in the target single fracturing segment; Based on the well trajectory data and the preset two-dimensional coordinates, the three-dimensional coordinates corresponding to each fracturing cluster on the horizontal well are determined.

5. The electromagnetic method model parameterization method according to claim 1, characterized in that, The step of constructing the set of center coordinates corresponding to each fracturing cluster based on each of the three-dimensional coordinates includes: Obtain the spacing between fracturing clusters in the target single fracturing segment; Using each of the three-dimensional coordinates as the center point and the spacing between the fracturing clusters as the radius, the distribution range of the center point corresponding to each fracturing cluster is determined; According to the second preset distance interval, several coordinate points are selected at equal intervals within the distribution range of each center point to construct the center coordinate set corresponding to each fracturing cluster.

6. The electromagnetic method model parameterization method according to claim 1, characterized in that, The step of obtaining the principal stress direction angle of the horizontal well and constructing an extension direction angle set based on the principal stress direction angle includes: Obtain the principal stress direction angle of the horizontal well; Based on the principal stress direction angle and the preset angle range value, the extension direction angle range is determined; According to a preset angle interval, several extension direction angles are selected at equal intervals within the range of extension direction angles to construct the set of extension direction angles.

7. The electromagnetic method model parameterization method according to claim 1, characterized in that, Also includes: Obtain the mesh cells occupied by each fracturing fluid model in the three-dimensional network from the fracturing fluid model sample set; Set the resistivity property of all the grid cells to a preset resistivity value.

8. A parameterization system for an electromagnetic method model, characterized in that, include: The fracturing cluster coordinate acquisition unit is configured to determine the target single fracturing segment and acquire the three-dimensional coordinates of each fracturing cluster in the target single fracturing segment; The first set construction unit is configured to construct a set of center coordinates corresponding to each fracturing cluster based on each of the three-dimensional coordinates. The second set construction unit is configured to obtain the principal stress direction angle of the horizontal well and construct an extension direction angle set based on the principal stress direction angle. The generation unit is configured to generate a fracturing fluid model sample set corresponding to the target single fracturing segment based on each of the center coordinate sets and the extension direction angle sets.

9. A computer device, comprising: At least one processor; as well as A memory storing a computer program executable on the processor, characterized in that the processor executes the program by performing the steps of the method 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 a processor, it performs the steps of the method as described in any one of claims 1 to 7.

Images