An intelligent modeling method and system for tracer monitoring of wellbore-matrix-fracture

Abstract

The present invention discloses a method and system for intelligent modeling of a wellbore-matrix-fracture for tracer monitoring, which relates to the technical field of numerical simulation of tracer monitoring in oil and gas reservoirs, and solves the problem that the prior art cannot reduce the total number of grids of an actual model and improve the operation speed while ensuring or even improving the three-dimensional modeling accuracy of an oil and gas reservoir; the present invention includes obtaining reservoir grid coordinates, performing encryption operation near the wellbore to obtain a wellbore grid coordinate point data volume, performing encryption operation near the fracturing fracture to obtain a modeling matrix-fracturing fracture grid coordinate point data volume, combining the wellbore grid coordinate point data volume and the matrix-fracturing fracture grid coordinate point data volume as an overall grid coordinate point data volume, and then performing clustering processing to obtain the coupling connection relationship between the unencrypted grid and the encrypted grid therein; the present invention adopts hierarchical multi-scale encrypted grid modeling to improve the model operation speed, thereby further improving the accuracy of oil and gas well productivity analysis based on tracer monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of numerical simulation of tracer monitoring in oil and gas reservoirs, and particularly relates to an intelligent modeling method and system for tracer monitoring of wellbore-matrix-fracture. Background Art

[0002] Geological modeling of oil and gas reservoirs is a key step in characterizing the spatial distribution and heterogeneity of underground reservoirs. The interval of on-site logging data points is generally 0.125 m, while the grid size used in traditional oil and gas reservoir simulation is more than 10 m. It is necessary to coarsen the logging data with an interval of 0.125 m to more than 10 m for production capacity analysis. This greatly reduces the accuracy and utilization rate of real logging data and reduces the accuracy of subsequent production capacity analysis.

[0003] There are many related studies on modeling oil and gas reservoirs in the prior art. For example, CN105095986B discloses a method for predicting the overall production of a multi-layer oil reservoir; CN111222271B discloses a numerical simulation method and system for fractures in a matrix-fracture unsteady crossflow oil reservoir; CN105528522A discloses a method and device for calculating the resource volume of a continuous oil and gas reservoir based on spatial grids; in 2021, Volume 40, Bulletin of Geological Science and Technology, Liu Yanfeng, Zhang Wenbiao, Duan Taizhong, etc. conducted research on the progress of deep learning in oil and gas reservoir geological modeling; in 2018, Volume 3, Acta Petrolei Sinica (Petroleum Science), Zhu Zhouyuan, Li Minghui, etc. conducted research on high-order separate chemical flooding simulation based on high-order formats, and selected high-order format methods to improve the accuracy of chemical flooding simulation; in 2010, Volume 31, Acta Petrolei Sinica, Su Yunhe, Du Zhimin, etc. conducted research on dynamic local grid encryption technology for high water cut oil reservoirs. However, none of the above studies can reduce the total number of grids in the actual model while ensuring or even improving the three-dimensional modeling accuracy of the oil and gas reservoir, and further improve the accuracy of oil and gas well production capacity analysis based on tracer monitoring. Summary of the Invention

[0004] In order to solve the problems existing in the above prior art, the present invention provides an intelligent modeling method and system for tracer monitoring of wellbore-matrix-fracture, which solves the technical problem that the prior art cannot reduce the total number of grids in the actual model while ensuring or even improving the three-dimensional modeling accuracy of the oil and gas reservoir, and further improve the accuracy of oil and gas well production capacity analysis.

[0005] An intelligent modeling method for tracer monitoring of wellbore-matrix-fracture includes:

[0006] Step 1: Collect basic parameters, well trajectory data, logging interpretation data, and fracturing data;

[0007] Step 2: Process the data collected in Step 1 to determine the maximum and minimum values of the three-dimensional coordinates of the reservoir and establish a reservoir grid model to obtain reservoir grid coordinates;

[0008] Specifically, the coordinate value of the center point of each grid in the reservoir grid model is used as the grid coordinate:

[0009] x 4i = x0 + 0.5l + il

[0010] y 4i = y0 + 0.5l + jl

[0011] z 4i = z0 + 0.5l + kl

[0012] Wherein, i, j, and k are the numbers of each grid in the three-dimensional block reservoir grid model in the XYZ three directions, and (x0, y0, z0) are the coordinates of the starting point of the grid.

[0013] Step 3: Use the unsupervised machine learning algorithm to encrypt n reservoir grid points near the wellbore to obtain the wellbore grid coordinate point data volume, and use the unsupervised machine learning algorithm to encrypt m reservoir grid points near the fracture to obtain the modeling matrix-fracture grid coordinate point data volume. The encryption operation is realized through a clustering processing algorithm;

[0014] Step 4: Combine the wellbore grid coordinate point data volume and the matrix-fracture grid coordinate point data volume as the overall grid coordinate point data volume, and use the unsupervised machine learning algorithm to perform clustering processing on the overall grid coordinate point data volume to obtain the coupling connection relationship between the unencrypted grid (i.e., the coarse grid) and the encrypted grid (i.e., the fine grid). Use the overall grid coordinate point data volume and the coupling connection relationship between the coarse and fine grids as the reservoir model corresponding to the wellbore-fracture-matrix.

[0015] The unsupervised machine learning algorithm can be implemented by a clustering model, and the clustering model includes: KNN, Kmeans, density clustering, hierarchical clustering, etc.

[0016] Furthermore, specifically:

[0017] 1. Basic parameters: Coarse grid size l 粗 , fine grid size l 细 , formation temperature, original formation pressure, viscosity and density of formation oil and water, apparent molecular weight of gas, injection and production time, etc.;

[0018] 2. Well trajectory data: Drilling depth d 1i , actual vertical depth z i , east-west deviation x i , north-south deviation y i ;

[0019] 3. Log interpretation data: Logging depth d 2i , porosity Φ i , permeability ki , water saturation S wi ;

[0020] 4. Fracturing data: the depth d of the fracturing section 3i , the east-west half-length f of the fracture xi , the height f of the fracture yi , the permeability k of the main fracture fi , the permeability k of the fracturing fracture zone SRVi .

[0021] Furthermore, step 3 includes: using the wellbore coordinate data as search points within the reservoir grid coordinate range to search for the n grid points closest to all wellbore points and performing an encryption operation to obtain the wellbore grid coordinate point data volume; using the fracturing fracture data volume as search points within the reservoir grid coordinate range to search for the m grid points closest to all fracturing fractures and performing an encryption operation to obtain the matrix-fracturing fracture grid coordinate point data volume.

[0022] Furthermore, the encryption operation includes: deleting the searched reservoir grid points, calculating the starting point of the local grid and the coordinates of all encrypted grids according to the size of the searched grid points and the encryption grid parameters, and merging the reserved reservoir grid point data volume with the encrypted grid coordinate point data volume to obtain a new grid coordinate point data volume. Specifically:

[0023] 1. Digging holes. Dig out the selected reservoir grid points and delete their corresponding grid numbers and coordinate point values (x 4i , y 4i , z 4i );

[0024] 2. Filling. According to the side length of the selected grid and the grid size parameters to be encrypted (such as the encryption multiple, the side length l of the encrypted grid 细 ), calculate the starting point of the local grid and the central point coordinates of all encrypted grids;

[0025] 3. Merging. Merge the reserved reservoir grid point data volume with the fine grid coordinate point data volume (i.e., the central point coordinates of all encrypted grids) to obtain a new grid coordinate point data volume, where the wellbore grid coordinate point data volume is represented as (x 4i ', y 4i ', z 4i '), and the overall grid coordinate point data volume is represented as (x 4i ", y 4i ", z 4i ").

[0026] Furthermore, in step 3, the encryption grid parameters for encrypting the n reservoir grid points near the wellbore are different from the encryption grid parameters for encrypting the m reservoir grid points near the fracturing fracture.

[0027] Further, the calculation process of the wellbore coordinate data includes: establishing interpolation functions between the drilling depth and the actual vertical depth, the east-west deviation, and the north-south deviation respectively as the interpolation functions of the three well trajectories. Specifically, taking the fitting process of the interpolation function F 1i between the drilling depth d i and the actual vertical depth z z (d 1i ) as an example:

[0028] A. Determine the complexity of the wellbore;

[0029] B1. For a simple wellbore trajectory, divide the wellbore trajectory into multiple sections (such as vertical well section, inclined well section, horizontal section), and fit the relationship between z i and d 1i in each section, using a linear or non-linear function for fitting:

[0030] z i = F z (d 1i ) = fk(d 1i ), d 1i ∈[d 1k , d 1k+1

[0031] where k is the number of well sections;

[0032] It can also be used for complex wellbore trajectories, but manual segmentation is required.

[0033] B2. For a complex wellbore trajectory, use an exponential or logarithmic function for fitting:

[0034] z i = F z (d 1i ) = a·ln(d 1i ) + b + c

[0035] or

[0036] z i = F z (d 1i ) = a·exp(b·d 1i ) + c

[0037] where a and b are fitting coefficients, and c is the spatial offset. c can be set manually (used to adjust the offset of the well trajectory in space);

[0038] B21. On the basis of the exponential or logarithmic function, the well inclination angle can be further added for correction to improve the fitting accuracy:

[0039] z​i = F z (d 1i ) = a·ln(d 1i ) + b + c·cosθ i

[0040] or

[0041] z i = F z (d 1i ) = a·exp(b·d 1i ) + c·cosθ i

[0042] Similarly, an interpolation function x between the drilling depth d 1i and the east-west deviation x i is established; i x x (d 1i ), an interpolation function y between the drilling depth d 1i and the north-south deviation y i is established; i y y (d 1i );

[0043] The complete well trajectory coordinate values in the reservoir, i.e., the wellbore coordinate data, are calculated by interpolating according to the three well trajectory interpolation functions.

[0044] Furthermore, obtaining the reservoir grid coordinates in step 2 includes:

[0045] Step 2.1: Substitute the logging depth values in the logging interpretation data into the three well trajectory interpolation functions to calculate the three-dimensional coordinates of the logging data points in the reservoir, and combine this calculated value with the logging interpretation data as a complete logging data volume;

[0046] Step 2.2: Determine the range of the three-dimensional coordinates based on the logging point coordinate values in the complete logging data volume and then calculate the three-dimensional maximum length of the reservoir;

[0047] Step 2.3: Set the side length of the reservoir grid and calculate the number of reservoir grids;

[0048] Step 2.4: Establish a reservoir grid model and calculate the center point coordinates of each grid in the reservoir grid model as the reservoir grid coordinates.

[0049] Further, substitute the fracture stage depth in the fracture data into the three well trajectory interpolation functions to calculate the three-dimensional coordinates of the fracture initiation point and termination point in the reservoir. Calculate the normal vector of the main fracture plane based on the three-dimensional coordinate values of the starting point and termination point of the well trajectory. Combine the aforementioned calculated values with the fracture data to obtain a complete fracture data volume. Specifically, set the starting point P1=(x1, y1, 1) and termination point P2=(x2, y2, 1) of the well trajectory, then the direction vector can be expressed as:

[0050]

[0051] Its length L can be calculated by the following formula:

[0052]

[0053] The final normal vector Can be expressed as the direction vector divided by the length:

[0054]

[0055] Combine the above calculation results with the fracture data to obtain a complete fracture data volume, specifically including: the coordinate values (x 3i , y 3i , z 3i ) of the fracture initiation point, the normal vector centered on the fracture initiation point The east-west half length f of the fracture xi , the fracture height f yi , the main fracture permeability k fi , the fracture breakdown zone permeability k SRVi .

[0056] The subscript i in the data indicates that there are multiple data points and they are stored in a list form in the computer.

[0057] Further, the calculation formula for the extension range of the fracture is as follows:

[0058]

[0059] Among them, (x 3i , y 3i , z 3i ) are the fracture starting point coordinate data, (x 4i , y 4i , z 4i ) are the reservoir grid coordinates, l 粗 is the reservoir grid size, f xi is the east-west half length of the fracture, f yi is the fracture height.

[0060] A tracer monitoring wellbore-matrix-fracture intelligent modeling system for implementing a tracer monitoring wellbore-matrix-fracture intelligent modeling method, including a data volume generation module, a data volume processing module, a reservoir grid model construction module, and an encryption modeling module; the data volume generation module is used to generate an original data volume according to the collected data, the data volume processing module is used to process the original data volume to obtain well trajectory coordinates, a logging data volume, and a fracturing fracture data volume respectively, the reservoir grid model construction module is used to establish a reservoir grid model according to the logging data volume, and the encryption modeling module is used to perform clustering and encryption operations on the reservoir grid model based on the logging data volume and the fracturing fracture data volume respectively to obtain a grid system corresponding to the wellbore-fracture-matrix.

[0061] The beneficial effects of the present invention include:

[0062] 1. It is constructed based on block grids, with a fast and efficient algorithm and strong adaptability to complex wellbore trajectories - fracture extensions;

[0063] 2. Hierarchical grids are used to construct encrypted grids for the wellbore-fracture-matrix, which can make more full use of logging data points to perform hierarchical fine modeling on the reservoir around the wellbore, providing basic data for the accuracy of production capacity simulation analysis;

[0064] 3. It is first proposed to use an unsupervised machine learning algorithm to perform local grid encryption processing and establish a coarse-fine grid coupling relationship after spatial coordinate point registration of on-site data such as well trajectory data, logging interpretation data, and fracturing data;

[0065] 4. This method can not only be used for multi-scale modeling at two levels of coarse-fine grids, but also for multi-scale modeling at three or more levels of coarse-medium-fine grids. Among them, fine grids can be used for encrypted modeling near the wellbore, medium-scale grids can be used for encrypted modeling of the matrix in the fracturing fracture and its nearby areas, and the rest are coarse-scale grids. To achieve this hierarchical encrypted modeling, only the size of the encrypted grid in the "filling" step needs to be adjusted according to the selected grid;

[0066] 5. Using hierarchical multi-scale encrypted grid modeling can greatly reduce the total number of grids in the actual model while ensuring or even improving the modeling accuracy, further improving the accuracy of oil and gas well production capacity analysis based on tracer monitoring. Description of the Drawings

[0067] Figure 1 It is a schematic diagram of a coarse grid and its coupling connection relationship.

[0068] Figure 2 It is a schematic diagram of the coarse grid and the fine grid after encryption operation.

[0069] Figure 3Schematic diagram of the coupling connection relationship between the coarse and fine grids.

[0070] Figure 4 3D effect diagram of the multi-scale modeling of the coarse-fine grids of the actual reservoir model.

[0071] Figure 5 Planar effect diagram of the multi-scale modeling of the coarse-fine grids of the actual reservoir model.

[0072] Figure 6 Schematic diagram of the multi-scale of the wellbore-matrix-fracture of the coarse-fine grids of the actual reservoir model. Specific implementation manners

[0073] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Therefore, the detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0074] The adaptive modeling method for the wellbore-matrix-fracture of the fractured directional well, as Figures 1-3 shown, includes:

[0075] Step 1: Collect basic parameters, well trajectory data, logging interpretation data and fracturing data; specifically:

[0076] 1. Basic parameters: Coarse grid size l 粗 , fine grid size l 细 , formation temperature, original formation pressure, viscosities and densities of formation oil and water, apparent molecular weight of gas, injection and production time, etc.;

[0077] 2. Well trajectory data: Drilling depth d 1i , actual vertical depth z i , east-west deviation x i , north-south deviation y i ;

[0078] 3. Logging interpretation data: Logging depth d 2i , porosity Φ i , permeability k i , water saturation S wi ;

[0079] 4. Fracturing data: Fracturing section depth d 3i , east-west half length of the fracture f xi, fracture height f yi , main fracture permeability k fi , permeability k of the fracturing fracture zone SRVi .

[0080] In the data, the subscript i indicates that there are multiple data points and they are stored in a list form in the computer.

[0081] Step 2: Process the data collected in Step 1 to determine the maximum and minimum values of the reservoir three-dimensional coordinates and establish a reservoir grid model to obtain the reservoir grid coordinates;

[0082] Step 3: Use an unsupervised machine learning algorithm to encrypt n reservoir grid points near the wellbore to obtain a wellbore grid coordinate point data volume, and use an unsupervised machine learning algorithm to encrypt m reservoir grid points near the fracturing fracture to obtain a modeling matrix - fracturing fracture grid coordinate point data volume. The encryption operation is implemented through a clustering processing algorithm;

[0083] Step 4: Combine the wellbore grid coordinate point data volume and the matrix - fracturing fracture grid coordinate point data volume as an overall grid coordinate point data volume, and use an unsupervised machine learning algorithm to perform clustering processing on the overall grid coordinate point data volume to obtain the coupling connection relationship between the unencrypted grid (i.e., the coarse grid) and the encrypted grid (i.e., the fine grid) therein. Use the overall grid coordinate point data volume and the coupling connection relationship of the coarse - fine grid as the reservoir model corresponding to the wellbore - fracture - matrix.

[0084] The unsupervised machine learning algorithm can be implemented using a clustering model, and the clustering model includes: KNN, Kmeans, density clustering, hierarchical clustering, etc.

[0085] In another embodiment, the calculation process of the wellbore coordinate data includes: respectively establishing interpolation functions between the drilling depth and the actual vertical depth, east - west deviation, and north - south deviation as the interpolation functions of the three well trajectories. Specifically, taking the fitting process of establishing the interpolation function F 1i between the drilling depth d i and the actual vertical depth z z (d 1i ) as an example:

[0086] A. Determine the complexity of the wellbore trajectory;

[0087] B1. For a simple wellbore trajectory, divide the wellbore trajectory into multiple sections (such as vertical well section, inclined well section, horizontal section), and respectively fit the relationship between z i and d 1i in each section, and use a linear or non - linear function for fitting:

[0088] z i = F z (d 1i) = fk(d 1i ), d 1i ∈ [d 1k , d 1k+1

[0089] where k is the number of well sections;

[0090] It can also be used for complex wellbore trajectories, but manual segmentation is required.

[0091] B2. For complex wellbore trajectories, use exponential or logarithmic functions for fitting:

[0092] z i = F z (d 1i ) = a·ln(d 1i ) + b + c

[0093] or

[0094] z i = F z (d 1i ) = a·exp(b·d 1i ) + c

[0095] where a and b are fitting coefficients, and c is the spatial offset. c can be set manually (used to adjust the offset of the well trajectory in space);

[0096] B21. Based on the exponential or logarithmic function, the well inclination angle can be further added for correction to improve the fitting accuracy:

[0097] z i = F z (d 1i ) = a·ln(d 1i ) + b + c·cosθ i

[0098] or

[0099] z i = F z (d 1i ) = a·exp(b·d 1i ) + c·cosθ i

[0100] Similarly, establish the interpolation function x 1i between the drilling depth d i and the east - west deviation x i = F x (d 1i ), establish the interpolation function y 1i between the drilling depth d i and the north - south deviation y i = F​y (d 1i );

[0101] Interpolate and calculate the complete well trajectory coordinate values in the reservoir, i.e., the wellbore coordinate data, according to three well trajectory interpolation functions.

[0102] In another embodiment, the obtaining of the reservoir grid coordinates includes: collecting logging interpretation data to calculate a complete logging data volume, determining the range of three-dimensional coordinates based on the logging point coordinate values in the complete logging data volume, and then calculating the three-dimensional maximum length of the reservoir. Then, set the side length of the reservoir grid to calculate the number of reservoir grids, and finally establish a reservoir grid model and calculate the center point coordinates of each grid in the reservoir grid model as the reservoir grid coordinates. Specifically as follows:

[0103] Take the logging depth value d 2i in the logging interpretation data, and substitute this value into the three well trajectory interpolation functions to calculate the three-dimensional (x 2i , y 2i , z 2i ) coordinates of the logging data point in the reservoir. At this time, it is necessary to substitute the logging depth value d 2i , that is

[0104] x 2i = F x (d 2i )

[0105] y 2i = F y (d 2i )

[0106] z 2i = F z (d 2i )

[0107] Merge the above calculation results with the logging interpretation data to obtain a complete logging data volume for subsequent modeling: the coordinate values (x 2i , y 2i , z 2i ) of the logging points, porosity Φ i , permeability k i , water saturation S wi .

[0108] According to the logging point coordinate values (x 2i , y 2i , z 2i ) in the logging data volume, respectively determine the maximum and minimum values of the XYZ three-dimensional coordinates, and the three-dimensional XYZ maximum length (L x , L y , L z ) of the reservoir can be calculated:

[0109] L x = max(x i ) - min(x i )

[0110] L y = max(y i ) - min(y i )

[0111] L z = max(z i ) - min(z i )

[0112] Set the side length of the coarse grid as l 粗 , then the number of XYZ grids (n x , n y , n z ) is:

[0113] n x = L x / l 粗

[0114] n y = L y / l 粗

[0115] n z = L z / l 粗

[0116] Based on the above data, a reservoir grid model can be established, and at the same time, the center point coordinate values of each grid in the reservoir grid model are calculated as grid coordinates:

[0117] x 4i = x0 + 0.5l + il

[0118] y 4i = y0 + 0.5l + jl

[0119] z 4i = z0 + 0.5l + kl

[0120] Among them, i, j, k are the numbers of each grid in the three-dimensional block reservoir grid model in the XYZ three directions, and (x0, y0, z0) is the coordinate of the starting point of the grid.

[0121] In another embodiment, fracture data is collected, and the depth of the fractured section is substituted into three well trajectory interpolation functions to calculate the three-dimensional coordinates of the fracture initiation point in the reservoir. The normal vector of the main fracture plane is calculated based on the three-dimensional coordinate values of the starting point and the ending point of the well trajectory, as follows: Set the starting point P1=(x1, y1, 1) and the ending point P2=(x2, y2, 1) of the well trajectory, then the direction vector can be expressed as:

[0122]

[0123] Its length L can be calculated by the following formula:

[0124]

[0125] The final normal vector can be expressed as the direction vector divided by the length:

[0126]

[0127] Combining the above calculation results with the fracture data, a complete fracture data volume can be obtained, specifically including: the coordinate values (x 3i , y 3i , z 3i ) of the fracture initiation point, the normal vector centered on the fracture initiation point the east-west half-length f of the fracture xi , the fracture height f yi , the main fracture permeability k fi , the permeability k of the fracture rupture zone SRVi .

[0128] In another embodiment, step 3 includes: using the wellbore coordinate data as search points within the reservoir grid coordinate range to search for the n grid points closest to all wellbore points and performing encryption operations to obtain the wellbore grid coordinate point data volume; using the fracture data volume as search points within the reservoir grid coordinate range to search for the m grid points closest to all fractures and performing encryption operations to obtain the matrix-fracture grid coordinate point data volume.

[0129] In this embodiment, the clustering model adopts the KNN model, and the specific process is as follows:

[0130] Import the reservoir grid coordinate (x 4i , y 4i , z 4i ) data points into the KNN model, with the wellbore (well trajectory) coordinate data (x 1i , y 1i , z 1i) is the search point. The K value range can be set from 10 to 50, and the search result is the coordinate numbers of 10 to 50 grid points that are the closest to all wellbore points including the wellbore point.

[0131] Import the reservoir grid coordinate (x 4i , y 4i , z 4i ) data points into the KNN model. Take the non-zero data points obtained by multiplying the Bool i (the extension range of the fracturing fracture) × (x 4i , y 4i , z 4i ) data volume as the search point. The K value range can be set from 10 to 50, and the search result is the coordinate numbers of 10 to 50 grid points that are the closest to all fracturing fractures including the fracturing fracture and the matrix SRV area.

[0132] Among them, the calculation formula for the Bool i fracture extension range is as follows:

[0133]

[0134] Among them, (x 3i , y 3i , z 3i ) is the fracturing starting point coordinate, (x 4i , y 4i , z 4i ) is the reservoir grid coordinate, l 粗 is the reservoir grid size, f xi is the east-west half length of the fracture, f yi is the fracture height.

[0135] In another embodiment, the encryption operation includes: deleting the searched reservoir grid points, calculating the starting point of the local grid and the coordinates of all encrypted grids according to the size of the searched grid points and the encryption grid parameters, and merging the data volume of the reserved reservoir grid points with the data volume of the encrypted grid coordinate points to obtain a new data volume of grid coordinate points. Specifically:

[0136] 1. Dig holes. Dig out the selected reservoir grid points and delete their corresponding grid numbers and coordinate point values (x 4i , y 4i , z 4i );

[0137] 2. Fill. According to the side length of the selected grid and the grid size parameters to be encrypted (such as the encryption multiple, the side length of the encrypted grid l 细 ), calculate the starting point of the local grid and the center point coordinates of all encrypted grids;

[0138] 3. Merge. Merge the undeleted reservoir grid point data volume with the fine grid coordinate point data volume (i.e., the center point coordinates of all encrypted grids) to obtain a new grid coordinate point data volume, where the wellbore grid coordinate point data volume is represented by (x 4i ',y 4i ', z 4i '), the overall grid coordinate point data volume is represented by (x 4i ”,y 4i ”, z 4i ”).

[0139] In this embodiment, the encrypted grid parameters when the encryption operation is performed on the n reservoir grid points near the wellbore are the same as the encrypted grid parameters when the encryption operation is performed on the m reservoir grid points near the fracturing cracks. At this time, the generated reservoir model includes multi-scale modeling of two levels of coarse-fine grids.

[0140] In another embodiment, in step 3, the encrypted grid parameters when performing the encryption operation on the n reservoir grid points near the wellbore are different from the encrypted grid parameters when performing the encryption operation on the m reservoir grid points near the hydraulic fracture. The reservoir model generated at this time includes multi-scale modeling of three levels or multiple levels of coarse-medium-fine grids. Among them, fine grids can be used for encrypted modeling near the wellbore, medium-scale grids can be used for encrypted modeling of the matrix of the hydraulic fracture and its surrounding areas, and the rest are coarse-scale grids. To achieve this hierarchical encrypted modeling, it is only necessary to adjust the size of the encrypted grid in the "filling" step according to the selected grid.

[0141] Specific modeling effects such as Figures 4-6 As shown in the figure, the block grid is used as the basis for construction. The algorithm is fast and efficient and has strong adaptability to complex wellbore trajectory-fracture extension. The hierarchical grid is used to encrypt the wellbore-fracture-matrix grid structure, which can make more full use of logging data and well trajectory data to perform hierarchical and detailed modeling of the reservoir around the wellbore. The hierarchical multi-scale encrypted grid modeling can greatly reduce the total number of grids in the actual model while ensuring or even improving the modeling accuracy, further improving the accuracy of subsequent oil and gas well productivity analysis.

[0142] In another embodiment, a tracer monitoring wellbore-matrix-fracture intelligent modeling system is involved, which is used to implement the adaptive modeling method of the wellbore-matrix-fracture of a fracturing directional well, including a data volume generation module, a data volume processing module, a reservoir grid model construction module, and an encryption modeling module; the data volume generation module is used to generate an original data volume according to the collected data, the data volume processing module is used to process the original data volume to respectively obtain well trajectory coordinates, a logging data volume, and a fracturing fracture data volume, the reservoir grid model construction module is used to establish a reservoir grid model according to the logging data volume, and the encryption modeling module is used to perform clustering and encryption operations on the reservoir grid model based on the logging data volume and the fracturing fracture data volume respectively to obtain a grid system corresponding to the wellbore-fracture-matrix.

[0143] The above embodiments only represent the specific implementation manners of the present application, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation on the protection scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the technical solution of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application.

Claims

1. A smart modeling method for tracer monitoring of wellbore-matrix-fracture, characterized in that, Including: Step 1: Collect basic parameters, well trajectory data, logging interpretation data, and fracturing data; Step 2: Process the data collected in Step 1 to determine the maximum and minimum values of the reservoir's three-dimensional coordinates, and establish a reservoir grid model to obtain reservoir grid coordinates; Step 3: Use an unsupervised machine learning algorithm to encrypt n reservoir grid points near the wellbore to obtain a wellbore grid coordinate point data volume, and use an unsupervised machine learning algorithm to encrypt m reservoir grid points near the fracturing cracks to obtain a modeling matrix-fracturing crack grid coordinate point data volume. The encryption operation is implemented through a clustering processing algorithm; Step 4: Combine the wellbore grid coordinate point data volume with the matrix-fracturing crack grid coordinate point data volume as an overall grid coordinate point data volume, and use an unsupervised machine learning algorithm to perform clustering processing on the overall grid coordinate point data volume to obtain the coupling connection relationship between the unencrypted grids (i.e., coarse grids) and the encrypted grids (i.e., fine grids) therein. Use the overall grid coordinate point data volume and the coupling connection relationship of the coarse-fine grids as the reservoir model corresponding to the wellbore-fracture-matrix; The said Step 3 includes: Using the wellbore coordinate data as search points within the reservoir grid coordinate range to search for the n grid points closest to all wellbore points and perform encryption operations to obtain a wellbore grid coordinate point data volume; Using the fracturing crack data volume as search points within the reservoir grid coordinate range to search for the m grid points closest to all fracturing cracks and perform encryption operations to obtain a matrix-fracturing crack grid coordinate point data volume; The calculation process of the wellbore coordinate data includes: respectively establishing interpolation functions between the drilling depth and the actual vertical depth, the east-west deviation, and the north-south deviation as the interpolation functions of the three well trajectories. Among them, the drilling depth is d 1i and the actual vertical depth is z i The fitting process of the interpolation function F z (d 1i ) is as follows: A. Determine the complexity of the wellbore; B1. If it is a simple wellbore trajectory, divide the wellbore trajectory into multiple sections including vertical well sections, deviated well sections, and horizontal sections, and use linear or nonlinear functions to fit respectively within each section: z i = F z (d 1i ) = fk(d 1i ), d 1i ∈ [d 1k , d 1k+1 ​ where k is the number of well sections; B2. If it is a complex wellbore trajectory, use exponential or logarithmic functions for fitting: z i = F z (d 1i ) = a·ln(d 1i ) + b + c or z i = F z (d 1i ) = a·exp(b·d 1i ) + c where a and b are fitting coefficients, and c is the spatial offset; B21. Further correct by adding the well inclination angle on the basis of the exponential or logarithmic function: z i = F z (d 1i ) = a·ln(d 1i ) + b + c·cosθ i or z i = F z (d 1i ) = a·exp(b·d 1i ) + c·cosθ i where θ i is the well deviation angle; Similarly, an interpolation function x between the drilling depth d 1i and the east-west deviation x i is established as x i = F x (d 1i ), and an interpolation function y between the drilling depth d 1i and the north-south deviation y i is established as y i = F y (d 1i ); Interpolate and calculate the complete wellbore trajectory coordinate values in the reservoir, i.e., wellbore coordinate data, according to the three well trajectory interpolation functions.

2. The intelligent modeling method for tracer monitoring wellbore-matrix-fracture according to claim 1, wherein The said encryption operation includes: Delete the searched reservoir grid points, calculate the starting point of the local grid and the coordinates of all encrypted grids according to the size of the searched grid points and the encryption grid parameters, and combine the reserved reservoir grid point data volume with the encrypted grid coordinate point data volume to obtain a new grid coordinate point data volume.

3. The intelligent modeling method for tracing and monitoring wellbore-matrix-fracture according to claim 2, wherein, In the said Step 3, the encryption grid parameters when encrypting the n reservoir grid points near the wellbore are different from the encryption grid parameters when encrypting the m reservoir grid points near the fracturing cracks.

4. A method for intelligent modeling of tracer monitoring wellbore-matrix-fracture, according to claim 1, characterized in that The obtaining of reservoir grid coordinates in the said Step 2 includes: Step 2.1: Substitute the logging depth values in the logging interpretation data into the three well trajectory interpolation functions to calculate the three-dimensional coordinates of the logging data points in the reservoir, and combine this calculated value with the logging interpretation data as a complete logging data volume; Step 2.2: Determine the range of the three-dimensional coordinates based on the logging point coordinate values in the complete logging data volume, and then calculate the three-dimensional maximum length of the reservoir; Step 2.3: Set the side length of the reservoir grid to calculate the number of reservoir grids; Step 2.4: Establish a reservoir grid model and calculate the central point coordinates of each grid in the reservoir grid model as the reservoir grid coordinates.

5. The intelligent modeling method for tracing and monitoring wellbore-matrix-fracture according to claim 1, wherein, Substitute the fracture section depth in the fracture data into the three well trajectory interpolation functions to calculate the three-dimensional coordinates of the fracture initiation point and termination point in the reservoir. Calculate the normal vector of the main fracture surface according to the three-dimensional coordinate values of the starting point and ending point of the well trajectory. Combine the aforementioned calculated values with the fracture data to obtain a complete fracture data volume.

6. The intelligent modeling method for tracing and monitoring wellbore-matrix-fracture according to claim 5, wherein, The calculation formula for the extension range of the fracture is as follows: Among them, is the normal vector centered on the crack initiation point, (x 3i , y 3i , z 3i ) is the coordinate data of the fracturing starting point, (x 4i , y 4i , z 4i ) is the reservoir grid coordinate, l 粗 is the reservoir grid size, f xi is the east-west half length of the crack, f yi is the crack height.

7. A tracer monitoring wellbore-matrix-fracture intelligent modeling method according to claim 1, wherein The basic parameters include: the coarse grid size l 粗 , the fine grid size l 细 , formation temperature, original formation pressure, viscosities and densities of formation oil and water, apparent molecular weight of gas, injection and production time; The well trajectory data includes: drilling depth d 1i , actual vertical depth z i , east-west deviation x i , north-south deviation y i ; The well logging interpretation data includes: well logging depth d 2i , porosity Φ i , permeability k i , water saturation S wi ; The fracturing data includes: the depth d of the fracturing stage 3i , the east-west half length f of the fracture xi , the fracture height f yi , the permeability k of the main fracture fi , the permeability k of the fracturing fracture zone SRVi .

8. A tracer monitoring wellbore-matrix-fracture intelligent modeling system, characterized in that, A device for implementing the tracer monitoring wellbore-matrix-fracture intelligent modeling method according to any one of claims 1-7, comprising a data volume generation module, a data volume processing module, a reservoir grid model construction module, and an encryption modeling module; the data volume generation module is used to generate an original data volume according to the collected data, the data volume processing module is used to process the original data volume to obtain well trajectory coordinates, a logging data volume, and a fracture data volume respectively, the reservoir grid model construction module is used to establish a reservoir grid model according to the logging data volume, and the encryption modeling module is used to perform clustering and encryption operations on the reservoir grid model based on the logging data volume and the fracture data volume respectively to obtain a grid system corresponding to the wellbore-fracture-matrix.

Images