A method, apparatus, device, and readable storage medium for predicting core permeability.

Abstract

This invention discloses a method, apparatus, device, and readable storage medium for predicting core permeability. The method involves applying different confining pressures to the core samples of each block and measuring the corresponding permeability. Based on the permeability of the core samples under different confining pressures for each block, a curve showing the relationship between core permeability and confining pressure for each block is fitted. Using the first coefficient in the functional relationship of each block, along with the rock physical properties and rock composition parameters of that block, and combining this with a machine learning algorithm, a function corresponding to the first coefficient of the model is obtained. Using the second coefficient in the functional relationship of each block, along with the rock physical properties and rock composition parameters of that block, and combining this with a machine learning algorithm, a function corresponding to the second coefficient of the model is obtained. Substituting the functions corresponding to the first and second coefficients of the model into the core permeability model yields a relationship for predicting core permeability. This invention can improve the accuracy of core permeability prediction.

Description

Technical Field

[0001] This invention relates to the field of oil and gas field development, and specifically to a method, apparatus, equipment, and readable storage medium for predicting core permeability. Background Technology

[0002] Microfractures are widely distributed in tight sandstone gas reservoirs. Due to the low permeability of the matrix and the high permeability of the microfractures, these microfractures often serve as important seepage channels for oil and gas. Simultaneously, the presence of microfractures significantly increases the permeability of core samples within tight sandstone gas reservoir formations. Therefore, the study and prediction of permeability patterns in microfractured core samples has been a focus of scholarly attention.

[0003] Current research and prediction of permeability patterns in microfractured cores largely follow the same approach as with conventional cores, primarily considering core depth and lithology. However, prediction methods based on depth and lithology often result in low accuracy due to insufficient consideration of influencing factors and a lack of data distinctiveness. Summary of the Invention

[0004] To address the problems existing in the prior art, the present invention provides a method, apparatus, device, and readable storage medium for predicting core permeability, which can improve the accuracy of core permeability prediction.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0006] A method for predicting core permeability, comprising:

[0007] Cores were obtained from several different blocks, and different confining pressures were applied to the cores of each block and the corresponding permeability was measured.

[0008] Based on the permeability of the core samples from each block under different confining pressures, a curve relating core permeability to confining pressure for each block is fitted. The functional relationships corresponding to these curves are structurally identical for each block, each including a first coefficient and a second coefficient. Both the first and second coefficients in each functional relationship are constants related to the rock properties and composition of that block. These structurally identical functional relationships are defined as a core permeability model, which includes a first model coefficient and a second model coefficient.

[0009] Obtain the rock physical properties and rock composition parameters for each block;

[0010] Based on the first coefficient in the functional relationship between the core permeability and confining pressure curve of each block, as well as the rock physical property parameters and rock composition parameters of that block, and combined with machine learning algorithms, the function corresponding to the first coefficient of the model is obtained.

[0011] Based on the second coefficient in the functional relationship between the core permeability and confining pressure curve of each block, as well as the rock physical property parameters and rock composition parameters of that block, and combined with machine learning algorithms, the function corresponding to the second coefficient of the model is obtained.

[0012] Substituting the functions corresponding to the first coefficient and the second coefficient of the model into the core permeability model yields the relationship for predicting core permeability. Core permeability is then predicted based on this relationship.

[0013] Furthermore, the core permeability model is as follows:

[0014] Y = -aln(x) + b

[0015] Where Y is the core permeability in mD; x is the confining pressure in MPa; a is the first coefficient of the model; and b is the second coefficient of the model.

[0016] Furthermore, the rock physical properties include initial porosity, initial permeability, median pore throat radius, and maximum pore throat radius; the rock composition parameters include plagioclase content, potassium feldspar content, calcite content, cement content, and sensitive mineral content, wherein the sensitive mineral content includes chlorite content, illite content, montmorillonite content, and kaolinite content.

[0017] Furthermore, the machine learning algorithm is a linear regression model, as detailed below:

[0018] y = w1x 1 +w2x 2 +w3x 3 +w4x 4 +w5x 5 +w6x 6 +w7x 7

[0019] +w8x 8 +w9x 9 +w 10 x 10 +w 11 x 11 +w 12 x 12 +m

[0020] Where y represents the first coefficient in the functional relationship between core permeability and confining pressure for each block, the second coefficient in the functional relationship between core permeability and confining pressure for each block, the first coefficient of the model, and the second coefficient of the model; x 1 Represents the initial porosity, x2 x represents the initial penetration rate. 3 x represents the median orifice throat radius. 4 x represents the maximum throat radius. 5 Represents plagioclase content, x 6 Represents potassium feldspar content, x 7 Represents calcite content, x 8 Represents the cementitious content, x 9 Represents chlorite content, x 10 Represents illite content, x 11 Represents montmorillonite content, x 12 Represents kaolinite content; w1~w 12 And m represents the parameters of the function corresponding to the first coefficient of the model, and also represents the parameters of the function corresponding to the second coefficient of the model.

[0021] Furthermore, the core includes matrix core and fracture core.

[0022] Furthermore, it also includes:

[0023] Obtain the fracture aperture of several fractured rock cores;

[0024] The permeability of each fractured core is predicted based on the formula used to predict core permeability.

[0025] Based on the fracture aperture and corresponding permeability of each fracture core, a curve relating fracture core aperture to permeability is fitted, and the fracture core aperture is predicted based on this curve.

[0026] A core permeability prediction device, comprising:

[0027] The measurement module is used to obtain core samples from several different blocks, apply different confining pressures to the core samples of each block, and measure the corresponding permeability.

[0028] The first fitting module is used to fit the permeability of the core sample in each block under different confining pressures to obtain the relationship curve between the core permeability and the confining pressure for each block. The functional relationship curves for the relationship between the core permeability and the confining pressure for each block have the same structure. Each functional relationship includes a first coefficient and a second coefficient, and the first and second coefficients in each functional relationship are constants related to the rock properties and rock composition of that block. The functional relationships with the same structure are defined as a core permeability model, which includes a first coefficient and a second coefficient.

[0029] The first acquisition module is used to acquire the rock physical property parameters and rock composition content parameters of each block;

[0030] The first calculation module is used to obtain the function corresponding to the first coefficient of the model based on the first coefficient in the function relationship curve corresponding to the core permeability and confining pressure of each block, as well as the rock physical property parameters and rock composition parameters of the block, and combined with machine learning algorithms.

[0031] The second calculation module is used to obtain the function corresponding to the second coefficient of the model based on the second coefficient in the function relationship curve corresponding to the core permeability and confining pressure of each block, as well as the rock physical property parameters and rock composition parameters of the block, and combined with machine learning algorithms.

[0032] The output module is used to substitute the functions corresponding to the first coefficient of the model and the functions corresponding to the second coefficient of the model into the core permeability model, thereby obtaining the relationship for predicting core permeability, and predicting core permeability based on the relationship for predicting core permeability.

[0033] Furthermore, it also includes:

[0034] The second acquisition module is used to acquire the fracture aperture of several fractured rock cores;

[0035] The fracture core permeability prediction module is used to predict the permeability of each fracture core according to the relationship used to predict core permeability.

[0036] The fracture core aperture prediction module is used to fit the relationship curve between fracture core aperture and permeability based on the fracture aperture and corresponding permeability of each fracture core, and to predict the fracture core aperture based on the relationship curve between fracture core aperture and permeability.

[0037] An apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for predicting core permeability.

[0038] A computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of a method for predicting core permeability.

[0039] Compared with existing technologies, the present invention has at least the following beneficial effects: The present invention provides a method for predicting core permeability, which involves obtaining rock physical property parameters and rock composition parameters for each block, obtaining core samples from several different blocks, applying different confining pressures to the core samples of each block and measuring the corresponding permeability; based on the permeability of the core samples of each block under different confining pressures, fitting a core permeability versus confining pressure relationship curve for each block; based on the first coefficient in the functional relationship formula corresponding to the core permeability versus confining pressure relationship curve for each block, as well as the rock physical property parameters and rock composition parameters of that block, and combining with a machine learning algorithm, obtaining the function corresponding to the first coefficient of the model; based on the first coefficient in the functional relationship formula corresponding to the core permeability versus confining pressure relationship curve for each block... The second coefficient, along with the rock physical properties and rock composition parameters of the block, is used in conjunction with a machine learning algorithm to obtain the function corresponding to the second coefficient of the model. Substituting the functions corresponding to the first and second coefficients of the model into the core permeability model yields the formula for predicting core permeability. This formula takes into account thirteen influencing factors affecting microfractured cores, including confining pressure, rock physical properties, and rock composition, making the core data obtained from the experiment more diverse and refined. Based on this, a linear regression model can fully explore the variation law of core permeability, thereby establishing a formula for predicting core permeability that closely matches the experimental data. Furthermore, core permeability can be predicted based on this formula, greatly improving the prediction accuracy.

[0040] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the specific embodiments of the present invention, the drawings used in the description of the specific embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 Permeability of core under different confining pressures;

[0043] Figure 2 In the matrix core, Ⅰ represents the deviation between the predicted and experimental values ​​of the first coefficient of the model; Ⅱ represents the deviation between the predicted and experimental values ​​of the second coefficient of the model; Ⅲ represents the deviation between the predicted and experimental values ​​of the first coefficient of the model in the fracture core; and Ⅳ represents the deviation between the predicted and experimental values ​​of the second coefficient of the model in the fracture core.

[0044] Figure 3 A comparison of the theoretical and actual curves showing the relationship between permeability and crack aperture;

[0045] Figure 4 The values ​​represent the core permeability under different confining pressures. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] As a specific embodiment of the present invention, a method for predicting core permeability specifically includes the following steps:

[0048] S1. Obtain core samples from several different blocks, apply different confining pressures to the core samples from each block, and measure the corresponding permeability.

[0049] In other words, by applying different confining pressures to the core samples obtained from each block and measuring the permeability of the core samples under each confining pressure, several sets of confining pressure and permeability data can be obtained for the core samples from each block.

[0050] S2. Based on the permeability of the core samples from each block under different confining pressures, a curve relating the core permeability to the confining pressure for each block is fitted. The functional relationships corresponding to the core permeability to confining pressure curves for each block have the same structure. Each functional relationship includes a first coefficient and a second coefficient, and the first and second coefficients in each functional relationship are constants related to the rock properties and rock composition of that block. The functional relationships with the same structure are defined as a core permeability model, which includes a first coefficient and a second coefficient.

[0051] In other words, this step yields the core permeability versus confining pressure curves for each block, resulting in several such curves. It is observed that each curve shares a functional relationship with the same structure. While the functional relationship for each curve is fixed, the first coefficient is generally different across all curves. Similarly, the second coefficient is also generally different. Both the first and second coefficients are influenced by the rock properties and composition of the respective block. Therefore, these functional relationships with the same structure can be defined as a core permeability model. By determining the functional relationships between the first and second coefficients of the model and their influence on rock properties and composition, the relationship used to predict core permeability can be established.

[0052] Specifically, the core permeability model is as follows:

[0053] Y = -aln(x) + b

[0054] Where Y is the core permeability in mD; x is the confining pressure in MPa; a is the first coefficient of the model; and b is the second coefficient of the model.

[0055] In this model, 'a' and 'b' correspond to the first and second coefficients in the functional relationship between core permeability and confining pressure for each curve. However, in the functional relationship between core permeability and confining pressure for each curve, the first and second coefficients are fixed constants.

[0056] S3. Obtain the rock physical property parameters and rock composition parameters for each block.

[0057] Specifically, rock physical properties include initial porosity, initial permeability, median pore throat radius, and maximum pore throat radius;

[0058] The rock composition parameters include plagioclase content, potassium feldspar content, calcite content, cement content, and sensitive mineral content, wherein the sensitive mineral content includes chlorite content, illite content, montmorillonite content, and kaolinite content.

[0059] S4. Based on the first coefficient in the function expression corresponding to the core permeability versus confining pressure curve of each block, as well as the rock physical property parameters and rock composition parameters of that block, and combined with machine learning algorithms, obtain the function corresponding to the first coefficient of the model.

[0060] S5. Based on the second coefficient in the function formula corresponding to the core permeability versus confining pressure curve of each block, as well as the rock physical property parameters and rock composition parameters of that block, and combined with machine learning algorithms, obtain the function corresponding to the second coefficient of the model.

[0061] Specifically, in S4 and S5, the machine learning algorithm can be decision tree, linear regression, or logistic regression, etc. In this embodiment, a linear regression model is used, as detailed below:

[0062] y = w1x 1 +w2x 2 +w3x 3 +w4x 4 +w5x 5 +w6x 6 +w7x 7

[0063] +w8x 8 +w9x 9 +w 10 x 10 +w 11 x 11 +w 12 x 12 +m

[0064] Where y represents the first coefficient in the functional relationship between core permeability and confining pressure for each block, the second coefficient in the functional relationship between core permeability and confining pressure for each block, the first coefficient of the model, and the second coefficient of the model; x 1 Represents the initial porosity, x 2 x represents the initial penetration rate. 3 x represents the median orifice throat radius. 4 x represents the maximum throat radius. 5 Represents plagioclase content, x 6 Represents potassium feldspar content, x 7 Represents calcite content, x 8 Represents the cementitious content, x 9 Represents chlorite content, x 10 Represents illite content, x 11 Represents montmorillonite content, x 12 Represents kaolinite content; w1~w 12 And m represents the parameters of the function corresponding to the first coefficient of the model, and also represents the parameters of the function corresponding to the second coefficient of the model.

[0065] In other words, the functions corresponding to the first coefficient of the model and the functions corresponding to the second coefficient of the model have the same structural form. Both the functions corresponding to the first coefficient and the functions corresponding to the second coefficient of the model contain w1 to w1.12 In addition to the 13 unknown coefficients, including m, by using the first coefficient in the functional relationship between core permeability and confining pressure corresponding to at least 13 different blocks, as well as the rock physical property parameters and rock composition parameters, at least 13 equations can be obtained. Solving these equations simultaneously will yield w1 to w 12 And by determining the specific value of m, we ultimately obtain the functions corresponding to the first coefficient of the model and the functions corresponding to the second coefficient of the model.

[0066] Of course, when using machine learning algorithms, the first coefficient in the functional relationship between core permeability and confining pressure curves corresponding to hundreds of different blocks, as well as rock physical property parameters and rock composition parameters, are used to ensure the accuracy of the calculation results.

[0067] S6. Substitute the functions corresponding to the first coefficient of the model and the functions corresponding to the second coefficient of the model into the core permeability model to obtain the relationship for predicting core permeability. Predict core permeability based on the relationship for predicting core permeability.

[0068] In this invention, the core includes matrix core and fracture core, and the permeability prediction formulas for both matrix core and fracture core are realized by the methods S1 to S6.

[0069] In a more preferred embodiment of the present invention, the fracture core permeability can also be predicted using the above-obtained relationship for predicting core permeability. Furthermore, by combining this with the measured fracture core permeability, the relationship curve between fracture core aperture and permeability can be conveniently and quickly obtained, as detailed below:

[0070] S7. Obtain the fracture aperture of several fractured rock cores;

[0071] S8. Predict the permeability of each fractured core according to the formula used to predict core permeability;

[0072] S9. Based on the fracture aperture and corresponding permeability of each fracture core, a curve relating fracture core aperture to permeability is fitted, and the fracture core aperture is predicted based on the curve relating fracture core aperture to permeability.

[0073] Example 1

[0074] A method for predicting core permeability, the specific implementation of which is as follows:

[0075] (1) Collect rock physical properties and rock composition factors of the Bozi Block in the Tarim Basin. Rock physical properties include initial porosity, initial permeability, median pore throat radius, and maximum pore throat radius. Rock composition includes plagioclase content, potassium feldspar content, calcite content, cement content, and sensitive mineral content. Among them, sensitive mineral content includes chlorite content, illite content, montmorillonite content, and kaolinite content. The data are collected in EXCEL tables, as shown in Tables 1 and 2. The sum of the total percentages of the above rock composition contents is 100%.

[0076] Table 1 Physical properties of rocks in the Bozi Block

[0077] Initial porosity / % <![CDATA[Initial permeability / 10 -3 μm 2 > Median pore throat radius / μm Maximum pore throat radius / μm 7.89 0.093 0.439 2.2 6.38 0.088 0.28 2.6 8.21 51.22 9.14 11.85 2.35 0.005 21 2.4 2.64 4.3 0.144 00 4.47 4.6 … … … …

[0078] Table 2. Rock composition percentages in the Bozi Block (all figures are %)

[0079] quartz Potassium feldspar calcite Montmorillonite plagioclase illite Kaolinite chlorite cement 44.52 0.28 0.39 0.85 0.67 37.07 4.54 11.54 0.13 41.04 0.21 0.07 0.66 0.47 38.77 5.96 12.67 0.13 32.97 8.94 0.08 0.54 3.55 22.77 3.79 6.75 20.61 48.97 0.82 0.28 0.85 0.35 34.88 4.81 9.02 0.01 51.58 0.95 0.20 0.72 0.45 34.12 4.45 7.42 0.11 … … … … … … … … …

[0080] (2) The permeability of matrix core and fracture core under different confining pressures was measured and collected in an EXCEL table.

[0081] (3) Fitting the relationship curve between core permeability and confining pressure, in this embodiment, the functional relationship between core permeability and confining pressure is found to be Y=-aln(x)+b, as follows: Figure 1 As shown, the functional relationship is defined as a core permeability model, where Y is the core permeability in mD; x is the confining pressure in MPa; a is the first coefficient of the model; and b is the second coefficient of the model. Both a and b are related to the rock properties and rock composition.

[0082] (4) The first coefficient in the functional relationship between core permeability and confining pressure for each block, along with the rock physical properties and rock composition parameters of that block, are combined with multiple coefficients predicted by a linear regression model to obtain the function corresponding to the first coefficient of the model. The first coefficient in the functional relationship between core permeability and confining pressure for each block, along with the rock physical properties and rock composition parameters of that block, are combined with multiple coefficients predicted by a linear regression model to obtain the function corresponding to the first coefficient of the model. The experimental data of matrix cores and fracture cores are considered separately; specific data are shown in Table 3, and the formula is:

[0083] y = w1x 1 +w2x 2 +w3x 3 +w4x 4 +w5x 5 +w6x 6 +w7x 7

[0084] +w8x 8+w9x 9 +w 10 x 10 +w 11 x 11 +w 12 x 12 +m

[0085] Table 3

[0086]

[0087] In the list of experimental data, the IF function was used to identify and remove outliers in values ​​a and b. In this modeling exercise, data points greater than three times the average were removed; however, no outliers were found in this data set, so further removal was unnecessary.

[0088] (5) In this embodiment, the accuracy of the first and second coefficients of the model is tested using the root mean square error (RMSE). An evaluation model for predicting the values ​​of the first and second coefficients is established in a Python environment. This model uses RMSE to measure the deviation between the actual and predicted values, and also plots graphs (e.g., ...). Figure 2 Compare them. From Figure 2 As can be seen, the predicted values ​​of both the first and second model coefficients remain relatively close to the actual experimental values, regardless of whether the core sample is in matrix or fractured core. Therefore, the prediction of core permeability under different confining pressures can maintain high accuracy. The formula for calculating the root mean square is as follows:

[0089]

[0090] As shown in Table 4, the root mean square error obtained by fitting the model is within an acceptable range.

[0091] Table 4 shows the root mean square error of the predicted values ​​of the first and second model coefficients.

[0092]

[0093] (6) Inferring fracture core aperture based on permeability data. The relationship between fracture aperture and permeability was established, and fracture aperture was inferred from permeability data. By fitting permeability and fracture aperture data for the target area, the project found that the fracture aperture and permeability in this area basically conform to a functional relationship:

[0094] H = 0.0097k 0.3585

[0095] In the formula, H is the fracture aperture (mm); k is the fracture core permeability (10⁻³ μm²). The predicted and actual fracture aperture values ​​are shown in Table 5, and the comparison between the predicted and actual curves is shown below. Figure 3As shown in the curve, the prediction model has high accuracy in low-permeability core samples.

[0096] Table 5. Predicted and Actual Values ​​of Crack Aperture

[0097]

[0098] Example 2

[0099] (1) Collect rock physical properties and rock composition factors of the Dabeidong Block in the Tarim Basin. Rock physical properties include initial porosity, initial permeability, median pore throat radius, and maximum pore throat radius. Rock composition includes plagioclase content, potassium feldspar content, calcite content, cement content, and sensitive mineral content. Among them, sensitive mineral content includes chlorite content, illite content, montmorillonite content, and kaolinite content. The data are collected in EXCEL tables, as shown in Tables 6 and 7. The sum of the total percentages of the above rock composition contents is 100%.

[0100] Table 6 Physical properties of rocks in the Dabei Block

[0101] initial porosity <![CDATA[Initial permeability / 10 -3 μm 2 > Median pore throat radius / μm Maximum pore throat radius / μm 2.67 0.009 08 2.8 2.87 4.02 0.093 30 4.1 4.15 3.29 0.140 00 3.3 3.34 3.15 0.007 34 3.2 3.68 2.62 0.004 95 2.7 2.77 … … … …

[0102] Table 7. Rock composition percentages in the Dabeidong Block (all figures are %)

[0103] quartz Potassium feldspar calcite Montmorillonite plagioclase illite Kaolinite chlorite cement 51.22 0.75 0.21 0.71 0.33 32.28 4.61 9.88 0.01 49.93 0.89 0.32 0.38 0.41 33.19 4.74 10.08 0.05 47.81 0.76 0.32 0.39 0.37 37.85 4.57 7.83 0.10 46.08 0.69 0.38 0.57 0.35 38.52 4.28 9.10 0.04 47.28 0.66 0.13 0.39 0.24 39.30 4.79 7.19 0.00 … … … … … … … … …

[0104] (2) The permeability of matrix core and fracture core under different confining pressures was measured and collected in an EXCEL table.

[0105] (3) Fitting the relationship curve between core permeability and confining pressure, in this embodiment, the functional relationship between core permeability and confining pressure is found to be Y=-aln(x)+b, as follows: Figure 4 As shown, the functional relationship is defined as a core permeability model, where Y is the core permeability in mD; x is the confining pressure in MPa; a is the first coefficient of the model; and b is the second coefficient of the model. Both a and b are related to the rock properties and rock composition.

[0106] (4) The first coefficient in the functional relationship between core permeability and confining pressure for each block, along with the rock physical properties and rock composition parameters of that block, are combined with multiple coefficients predicted by a linear regression model to obtain the function corresponding to the first coefficient of the model. The first coefficient in the functional relationship between core permeability and confining pressure for each block, along with the rock physical properties and rock composition parameters of that block, are combined with multiple coefficients predicted by a linear regression model to obtain the function corresponding to the first coefficient of the model. The experimental data of matrix cores and fractured cores are considered separately; specific data are shown in Table 8, and the formula is:

[0107] y = w1x 1 +w2x 2 +w3x 3 +w4x 4 +w5x 5 +w6x 6 +w7x 7

[0108] +w8x 8 +w9x 9 +w 10 x 10 +w 11 x 11 +w 12 x 12 +m

[0109] Table 8

[0110]

[0111] In the list of experimental data, the IF function was used to identify and remove outliers in values ​​a and b. This modeling process removed experimental data points greater than three times the average. The outlier a = 107.1150 in the crack was found and removed.

[0112] (5) In this embodiment, the accuracy of the first and second model coefficients is tested using the root mean square error (RMSE). An evaluation system for the first and second model coefficients is established in a Python environment. This model uses RMSE to measure the deviation between the actual and predicted values ​​in the training set, and also plots graphs (e.g., ...). Figure 2 Compare them. From Figure 2 As can be seen, the predicted values ​​of both the first and second model coefficients remain relatively close to the actual experimental values, regardless of whether the core sample is in matrix or fractured core. Therefore, the prediction of core permeability under different confining pressures can maintain high accuracy. The formula for calculating the root mean square is as follows:

[0113]

[0114] As shown in Table 9, the root mean square error obtained from fitting the model is within an acceptable range.

[0115] Table 9 shows the root mean square error of the predicted values ​​of the first and second model coefficients.

[0116]

[0117] (6) Inferring fracture core aperture based on permeability data. The relationship between fracture aperture and permeability was established, and fracture aperture was inferred from permeability data. By fitting permeability and fracture aperture data for the target area, the project found that the fracture aperture and permeability in this area basically conform to a functional relationship:

[0118] H = 0.0097k 0.3585

[0119] In the formula, H is the fracture width in mm, and k is the core permeability in 10⁻³ μm². The predicted and actual fracture widths are shown in Table 10, and the comparison between the predicted and actual curves is shown below. Figure 3 As shown in the curve, the prediction model has high accuracy in low-permeability core samples.

[0120] Table 10 Predicted and Actual Values ​​of Crack Aperture

[0121]

[0122] This invention provides a device for predicting core permeability, comprising:

[0123] The measurement module is used to obtain core samples from several different blocks, apply different confining pressures to the core samples of each block, and measure the corresponding permeability.

[0124] The first fitting module is used to fit the permeability of the core sample in each block under different confining pressures to obtain the relationship curve between the core permeability and the confining pressure for each block. The functional relationship curves for the relationship between the core permeability and the confining pressure for each block have the same structure. Each functional relationship includes a first coefficient and a second coefficient, and the first and second coefficients in each functional relationship are constants related to the rock properties and rock composition of that block. The functional relationships with the same structure are defined as a core permeability model, which includes a first coefficient and a second coefficient.

[0125] The first acquisition module is used to acquire the rock physical property parameters and rock composition content parameters of each block;

[0126] The first calculation module is used to obtain the function corresponding to the first coefficient of the model based on the first coefficient in the function relationship curve corresponding to the core permeability and confining pressure of each block, as well as the rock physical property parameters and rock composition parameters of the block, and combined with machine learning algorithms.

[0127] The second calculation module is used to obtain the function corresponding to the second coefficient of the model based on the second coefficient in the function relationship curve corresponding to the core permeability and confining pressure of each block, as well as the rock physical property parameters and rock composition parameters of the block, and combined with machine learning algorithms.

[0128] The output module is used to substitute the functions corresponding to the first coefficient of the model and the functions corresponding to the second coefficient of the model into the core permeability model, thereby obtaining the relationship for predicting core permeability, and predicting core permeability based on the relationship for predicting core permeability.

[0129] In a preferred embodiment, a core permeability prediction device further includes:

[0130] The second acquisition module is used to acquire the fracture aperture of several fractured rock cores;

[0131] The fracture core permeability prediction module is used to predict the permeability of each fracture core according to the relationship used to predict core permeability.

[0132] The fracture core aperture prediction module is used to fit the relationship curve between fracture core aperture and permeability based on the fracture aperture and corresponding permeability of each fracture core, and to predict the fracture core aperture based on the relationship curve between fracture core aperture and permeability.

[0133] In one embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used in the operation of a core permeability prediction method.

[0134] In one embodiment of the present invention, a method for predicting core permeability, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data.

[0135] The computer storage medium can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs)), optical storage (e.g., CDs, DVDs, BDs, HVDs), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0136] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0137] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0138] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0139] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0140] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for predicting core permeability, characterized in that, include: Cores were obtained from several different blocks, and different confining pressures were applied to the cores of each block and the corresponding permeability was measured. Based on the permeability of the core samples from each block under different confining pressures, a curve relating core permeability to confining pressure for each block is fitted. The functional relationships corresponding to these curves for each block have the same structure, each including a first coefficient and a second coefficient. Both the first and second coefficients in each functional relationship are constants related to the rock properties and composition of that block. These structurally identical functional relationships are defined as a core permeability model, which includes a first model coefficient and a second model coefficient. Obtain the rock physical properties and rock composition parameters for each block; Based on the first coefficient in the functional relationship between the core permeability and confining pressure curve of each block, as well as the rock physical property parameters and rock composition parameters of that block, and combined with machine learning algorithms, the function corresponding to the first coefficient of the model is obtained. Based on the second coefficient in the functional relationship between the core permeability and confining pressure curve of each block, as well as the rock physical property parameters and rock composition parameters of that block, and combined with machine learning algorithms, the function corresponding to the second coefficient of the model is obtained. Substituting the functions corresponding to the first coefficient and the second coefficient of the model into the core permeability model yields the relationship for predicting core permeability. Core permeability is then predicted based on this relationship.

2. The method for predicting core permeability according to claim 1, characterized in that, The core permeability model is as follows: Y = -aln(x) + b Where Y is the core permeability in mD; x is the confining pressure in MPa; a is the first coefficient of the model; and b is the second coefficient of the model.

3. The method for predicting core permeability according to claim 2, characterized in that, The rock physical properties include initial porosity, initial permeability, median pore throat radius, and maximum pore throat radius; the rock composition parameters include plagioclase content, potassium feldspar content, calcite content, cement content, and sensitive mineral content, wherein the sensitive mineral content includes chlorite content, illite content, montmorillonite content, and kaolinite content.

4. The method for predicting core permeability according to claim 3, characterized in that, The machine learning algorithm is a linear regression model, as detailed below: y=w1x 1 +w2x 2 +w3x 3 +w4x 4 +w5x 5 +w6x 6 +w7x 7 +w8x 8 +w9x 9 +w 10 x 10 +w 11 x 11 +w 12 x 12 +m Where y represents the first coefficient in the functional relationship between core permeability and confining pressure for each block, the second coefficient in the functional relationship between core permeability and confining pressure for each block, the first coefficient of the model, and the second coefficient of the model; x 1 Represents the initial porosity, x 2 x represents the initial penetration rate. 3 x represents the median orifice throat radius. 4 x represents the maximum throat radius. 5 Represents plagioclase content, x 6 Represents potassium feldspar content, x 7 Represents calcite content, x 8 Represents the cementitious content, x 9 Represents chlorite content, x 10 Represents illite content, x 11 Represents montmorillonite content, x 12 Represents kaolinite content; w1~w 12 And m represents the parameters of the function corresponding to the first coefficient of the model, and also represents the parameters of the function corresponding to the second coefficient of the model.

5. The method for predicting core permeability according to claim 1, characterized in that, The core samples include matrix cores and fracture cores.

6. The method for predicting core permeability according to claim 5, characterized in that, Also includes: Obtain the fracture aperture of several fractured rock cores; The permeability of each fractured core is predicted based on the formula used to predict core permeability. Based on the fracture aperture and corresponding permeability of each fracture core, a curve relating fracture core aperture to permeability is fitted, and the fracture core aperture is predicted based on this curve.

7. A device for predicting core permeability, characterized in that, include: The measurement module is used to obtain core samples from several different blocks, apply different confining pressures to the core samples of each block, and measure the corresponding permeability. The first fitting module is used to fit the permeability of the core sample in each block under different confining pressures to obtain the relationship curve between the core permeability and the confining pressure for each block. The functional relationship curves for the relationship between the core permeability and the confining pressure for each block have the same structure. Each functional relationship includes a first coefficient and a second coefficient, and the first and second coefficients in each functional relationship are constants related to the rock properties and rock composition of that block. The functional relationships with the same structure are defined as a core permeability model, which includes a first coefficient and a second coefficient. The first acquisition module is used to acquire the rock physical property parameters and rock composition content parameters of each block; The first calculation module is used to obtain the function corresponding to the first coefficient of the model based on the first coefficient in the function relationship curve corresponding to the core permeability and confining pressure of each block, as well as the rock physical property parameters and rock composition parameters of the block, and combined with machine learning algorithms. The second calculation module is used to obtain the function corresponding to the second coefficient of the model based on the second coefficient in the function relationship curve corresponding to the core permeability and confining pressure of each block, as well as the rock physical property parameters and rock composition parameters of the block, and combined with machine learning algorithms. The output module is used to substitute the functions corresponding to the first coefficient of the model and the functions corresponding to the second coefficient of the model into the core permeability model, thereby obtaining the relationship for predicting core permeability, and predicting core permeability based on the relationship for predicting core permeability.

8. The core permeability prediction device according to claim 7, characterized in that, Also includes: The second acquisition module is used to acquire the fracture aperture of several fractured rock cores; The fracture core permeability prediction module is used to predict the permeability of each fracture core according to the relationship used to predict core permeability. The fracture core aperture prediction module is used to fit the relationship curve between fracture core aperture and permeability based on the fracture aperture and corresponding permeability of each fracture core, and to predict the fracture core aperture based on the relationship curve between fracture core aperture and permeability.

9. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the core permeability prediction method as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of a core permeability prediction method as claimed in any one of claims 1 to 6.

Images