A method, system, device, and medium for predicting rock wettability

Abstract

The application discloses a rock wettability prediction method, system, device and medium, and relates to the technical field of oil exploration. The method comprises the following steps: acquiring well logging curve values of a target area full well section; predicting target component content of the full well section according to the well logging curve values of the full well section and a target component content prediction model, to obtain a full well section target component content prediction value; predicting a rock lipophilic index of the full well section according to the full well section target component content prediction value and a rock lipophilic index prediction model, to obtain a full well section rock lipophilic index prediction value; and the full well section rock lipophilic index prediction value is used for representing rock wettability of the full well section. The application can get rid of the limitation of sample on spontaneous imbibition test, realize prediction of the rock lipophilic index of the full well section and overall evaluation of reservoir wettability.

Description

Technical Field

[0001] This invention relates to the field of petroleum exploration technology, and in particular to a method, system, equipment and medium for predicting rock wettability. Background Technology

[0002] Wettability is a key parameter characterizing reservoir properties. Contact angle measurement and spontaneous percolation are commonly used methods for characterizing rock wettability. The contact angle method measures the wetting characteristics of the rock surface, while spontaneous percolation tests can characterize the wettability of interconnected pores in the rock. Compared to the contact angle method, the results of spontaneous percolation experiments can more accurately reflect the overall wetting characteristics of the rock. However, both contact angle measurement and spontaneous percolation methods can only characterize the wettability of the actual sampled rock. Furthermore, due to the high cost of coring, only a small number of key wells undergo coring. Therefore, due to the limitation of the sample size, traditional spontaneous percolation tests have certain limitations in characterizing wettability. Summary of the Invention

[0003] The purpose of this invention is to provide a method, system, equipment and medium for predicting rock wettability, so as to get rid of the limitation of spontaneous percolation test of samples and realize the prediction of the oleophilic index of rocks in the whole well section and the overall evaluation of reservoir wettability.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] A method for predicting rock wettability includes:

[0006] Obtain logging curve values ​​for the entire well section of the target area;

[0007] The target component content of the entire well section is predicted based on the logging curve values ​​of the entire well section and the target component content prediction model, thus obtaining the predicted value of the target component content of the entire well section. The target component content prediction model is based on neural network modeling and is determined according to the logging curve values ​​at different depths in the target area and the corresponding target component content. The target component is determined based on the correlation between the material composition information of the rock sample in the target area and the rock oleophilic index. The material composition information is determined by basic experimental analysis. The rock oleophilic index is determined by spontaneous permeation test.

[0008] The rock oleophilic index of the entire well section is predicted based on the predicted values ​​of the target component content and the oleophilic index prediction model. The predicted value of the rock oleophilic index of the entire well section is used to characterize the wettability of the rock in the entire well section. The oleophilic index prediction model is determined based on the content of the target component and the corresponding rock oleophilic index of the rock sample in the target area.

[0009] Optionally, the method for determining the target component specifically includes:

[0010] Obtain rock samples from the target area;

[0011] Basic experimental analysis was performed on the rock sample to obtain material composition information; the material composition information included: mineral composition information and organic matter content information; the mineral composition information included: siliceous mineral content, calcareous mineral content and clay mineral content; the basic experimental analysis included: X-ray diffraction analysis and total organic carbon analysis.

[0012] Spontaneous percolation tests were conducted on the rock samples, and the rock oleophilicity index was calculated based on the percolation test results.

[0013] The correlation between the material composition information and the rock oleophilic index is determined, and the components with an absolute value of correlation greater than a set value are taken as target components.

[0014] Optionally, the method for determining the lipophilic index prediction model specifically includes:

[0015] Using mathematical modeling software, an oleophilic index prediction model was established based on the content of the target components in the rock sample and the corresponding rock oleophilic index.

[0016] Optionally, the method for determining the target component content prediction model specifically includes:

[0017] Obtain well logging curve values ​​at different depths in the target area and the corresponding content of the target components;

[0018] The logging curve values ​​at different depths are normalized to obtain normalized logging curve values.

[0019] Based on neural network modeling, a target component content prediction model is established by taking the normalized logging curve value as input and the corresponding target component content as output.

[0020] Optionally, the rock sample includes two sets of parallel samples; a spontaneous percolation test is performed on the rock sample, and the rock oleophilic index is calculated based on the percolation test results, specifically including:

[0021] Aqueous phase percolation test was performed on the first group of parallel samples to obtain the normalized volume of water.

[0022] Oil phase percolation tests were conducted on the second group of parallel samples to obtain the normalized oil volume.

[0023] The rock oleophilicity index is calculated based on the normalized water volume and the normalized oil volume.

[0024] Optionally, rock samples are obtained from the target area, specifically including:

[0025] Obtain full-diameter core samples from the target area;

[0026] The full-diameter core sample was cut into cylindrical samples of a predetermined size;

[0027] The column sample is washed with oil and then dried to obtain a rock sample from the target area.

[0028] Optionally, the target components include: siliceous minerals, calcareous minerals, and clay minerals; the target component content prediction model includes: a siliceous mineral content prediction model, a calcareous mineral content prediction model, and a clay mineral content prediction model.

[0029] A system for predicting rock wettability includes:

[0030] The data acquisition module is used to acquire logging curve values ​​for the entire well section of the target area;

[0031] The content prediction module is used to predict the target component content of the entire well section based on the logging curve values ​​of the entire well section and the target component content prediction model, thereby obtaining the predicted value of the target component content of the entire well section. The target component content prediction model is based on neural network modeling and is determined according to the logging curve values ​​at different depths in the target area and the corresponding target component content. The target component is determined based on the correlation between the material composition information of the rock sample in the target area and the rock oleophilic index. The material composition information is determined by basic experimental analysis. The rock oleophilic index is determined by spontaneous permeation experiments.

[0032] The oleophilic index prediction module is used to predict the rock oleophilic index of the entire well section based on the predicted value of the target component content and the oleophilic index prediction model, and obtain the predicted value of the rock oleophilic index of the entire well section; the predicted value of the rock oleophilic index of the entire well section is used to characterize the rock wettability of the entire well section; the oleophilic index prediction model is determined based on the content of the target component and the corresponding rock oleophilic index of the rock sample in the target area.

[0033] An electronic device includes a memory and a processor, the memory storing a computer program and the processor running the computer program to enable the electronic device to perform the above-described method for predicting rock wettability.

[0034] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for predicting rock wettability.

[0035] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0036] The rock wettability prediction method provided by this invention establishes an oleophilic index prediction model based on fundamental experimental analysis and spontaneous permeation tests. This model enables the prediction of the oleophilic index through rock material composition, overcoming the limitations of spontaneous permeation tests on samples. By establishing a target component content prediction model based on neural network modeling, the mineral content of the entire well section is predicted. Combining the oleophilic index prediction model and the target component content prediction model allows for the prediction of the oleophilic index of the entire well section, thus characterizing the rock wettability of the entire well section and facilitating a comprehensive evaluation of reservoir wettability. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart of the rock wettability prediction method provided by the present invention;

[0039] Figure 2 The image shows the prediction effect of the rock oleophilicity index provided by this invention.

[0040] Figure 3 The image shows the predicted effect of silica mineral content provided by this invention.

[0041] Figure 4 The image shows the predicted effect of calcium mineral content provided by this invention.

[0042] Figure 5 The image shows the predicted effect of clay mineral content provided by this invention.

[0043] Figure 6 This is a schematic diagram of the mineral prediction results for the entire well section provided by the present invention;

[0044] Figure 7 This is a schematic diagram of the prediction results of the rock oleophilicity index for the entire well section provided by the present invention;

[0045] Figure 8 This is a block diagram of the rock wettability prediction system provided by the present invention.

[0046] Symbol explanation:

[0047] Data acquisition module—1, content prediction module—2, lipophilic index prediction module—3. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] The purpose of this invention is to provide a method, system, equipment and medium for predicting rock wettability, so as to get rid of the limitation of spontaneous percolation test of samples and realize the prediction of the oleophilic index of rocks in the whole well section and the overall evaluation of reservoir wettability.

[0050] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] Example 1

[0052] This invention provides a method for predicting rock wettability. For example... Figure 1 As shown, the method for predicting rock wettability includes:

[0053] Step S1: Obtain logging curve values ​​for the entire well section of the target area. The logging curve values ​​include: natural gamma ray logging (GR) values, caliper logging (CAL) values, resistivity logging (RT) values, sonic logging (DT) values, neutron logging (CNL) values, and density logging (DEN) values.

[0054] Step S2: Predict the target component content of the entire well section based on the logging curve values ​​of the entire well section and the target component content prediction model to obtain the predicted value of the target component content of the entire well section; the target component content prediction model is based on neural network modeling and is determined according to the logging curve values ​​of different depths in the target area and the corresponding target component content; the target component is determined based on the correlation between the material composition information of the rock sample in the target area and the rock oleophilic index; the material composition information is determined by basic experimental analysis; the rock oleophilic index is determined by spontaneous permeation test.

[0055] Step S3: Predict the rock oleophilic index of the entire well section based on the predicted value of the target component content and the oleophilic index prediction model, and obtain the predicted value of the rock oleophilic index of the entire well section; the predicted value of the rock oleophilic index of the entire well section is used to characterize the rock wettability of the entire well section; the oleophilic index prediction model is determined based on the content of the target component and the corresponding rock oleophilic index of the rock sample in the target area.

[0056] The method for determining the target component specifically includes:

[0057] Step S001: Obtain rock samples from the target area.

[0058] Step S001 specifically includes: obtaining a full-diameter core sample from the target area; cutting the full-diameter core sample into a column of a set size; washing the column with oil and drying the washed column to obtain a rock sample from the target area.

[0059] As a specific implementation method, full-diameter core samples from the target stratum in the study area are selected. The full-diameter samples are cut into cylindrical samples with a diameter of 2.5 cm and a length of 2-3 cm using a wire cutting machine. Two parallel samples are cut from each full-diameter sample. The cut samples are washed with oil to remove the adsorbed gum and bitumen in the rock pores. The washed samples are then placed in a drying oven for later use.

[0060] Step S002: Perform basic experimental analysis on the rock sample to obtain material composition information; the material composition information includes: mineral composition information and organic matter content information; the mineral composition information includes: siliceous mineral content, calcareous mineral content and clay mineral content; the basic experimental analysis includes: X-ray diffraction analysis and total organic carbon analysis.

[0061] As a specific implementation method, basic experimental analysis was performed on the washed oil sample, including X-ray diffraction (XRD) analysis and total organic carbon (TOC) analysis, to obtain the mineral composition information and organic matter content information of the sample, as shown in Table 1.

[0062] Table 1. Mineral composition and total organic matter (TOC) content information of the samples (%)

[0063] Sample number quartz Potassium feldspar plagioclase Iron white dolomite calcite Total clay TOC 1 23.9 6.4 38.6 16.2 / 14.9 0.35 2 10.9 1.5 19.1 67.2 1.3 / 2.70 3 18.8 1.4 13.0 22.2 36.3 8.4 6.36 4 15.0 1.8 19.1 37.6 23.1 3.5 6.19 5 22.5 1.1 24.4 37.1 7.6 7.4 8.53 6 16.2 2.2 16.4 3.4 57.0 4.2 5.47 7 19.3 2.3 18.3 20.1 29.1 10.9 5.15

[0064] After obtaining the mineral composition information of the samples, the samples were further classified into siliceous minerals (quartz + potassium feldspar + plagioclase), calcareous minerals (ferroic dolomite + calcite), and clay minerals. The sample composition information and total organic matter (TOC) content information after further classification are shown in Table 2.

[0065] Table 2. Mineral composition and total organic matter (TOC) content information (%) of the divided samples.

[0066]

[0067]

[0068] Step S003: Conduct a spontaneous percolation test on the rock sample and calculate the rock's oleophilic index based on the percolation test results. The rock sample includes two parallel sets of samples.

[0069] Step S003 specifically includes: conducting an aqueous phase percolation test on the first group of parallel samples to obtain the water normalized volume; conducting an oil phase percolation test on the second group of parallel samples to obtain the oil normalized volume; and calculating the rock oleophilic index based on the water normalized volume and the oil normalized volume.

[0070] As a specific implementation method, a percolation test was conducted on the washed oil-treated sample. One parallel sample was used to percolate deionized water, and the other was used to percolate n-dodecane. After the test, the rock oleophilic index WI was calculated. o The calculation formula is as follows:

[0071]

[0072] In the formula, WI o I represents the rock's oleophilicity index. o Normalized volume of oil absorbed into the column sample, %; I w The normalized volume of water absorbed into the column sample, % I w (or I) o The absorption volume is calculated by dividing the total absorbed volume of water (or oil) by the pore volume of the sample. The absorbed volume is obtained by dividing the mass of absorbed water (or oil) by the density of water (or oil).

[0073] In this embodiment, the calculated rock oleophilicity index of the rock sample is shown in Table 3.

[0074] Table 3. Rock oleophilicity index of rock samples

[0075] Sample number <![CDATA[I o / %]]> <![CDATA[I w / %]]> <![CDATA[WI o ]]> J1 0.91 0.92 0.50 J2 0.69 0.12 0.85 J3 0.81 0.50 0.62 J4 0.43 0.69 0.38 J5 0.51 1.26 0.29 J6 0.73 0.47 0.61 J7 0.73 0.96 0.43

[0076] Step S004: Determine the correlation between the material composition information and the rock oleophilic index, and take the components whose absolute value of the correlation is greater than a set value as target components.

[0077] The rock oleophilicity index is calculated based on the volume of n-dodecane and deionized water spontaneously infiltrating the pores, reflecting the differences in the affinity of the rock's pores for n-dodecane and deionized water. Rock pores are composed of inorganic minerals and organic matter, and different inorganic minerals and organic matter have different affinities for n-dodecane and deionized water. Therefore, the rock oleophilicity index can be predicted based on the rock's mineral composition and organic matter content.

[0078] Specifically, the correlation between the lipophilic index and the contents of different mineral components and organic matter was analyzed in SPSS software, as shown in Table 4.

[0079] Table 4. Correlation between the oleophilic index of rock samples and different components

[0080] Siliceous mineral content / % Calcium mineral content / % Clay mineral content / % TOC / % Oil affinity index -0.398 0.430 -0.456 -0.084

[0081] Table 4 shows that the oleophilic index correlates well with siliceous minerals, calcareous minerals, and clay minerals, but poorly with TOC, which is consistent with the underdeveloped organic matter pores in the study area. Therefore, the target components include siliceous minerals, calcareous minerals, and clay minerals.

[0082] The method for determining the lipophilic index prediction model specifically includes:

[0083] Step S005: Using mathematical modeling software, establish an oleophilic index prediction model based on the content of the target component of the rock sample and the corresponding rock oleophilic index.

[0084] As a specific implementation method, siliceous minerals, calcareous minerals, and clay minerals with good correlation to the lipophilic index are selected, and the lipophilic index is modeled using SPSS Modeler software. In this embodiment, the prediction effect of the established lipophilic index prediction model is as follows: Figure 2 As shown.

[0085] The method for determining the target component content prediction model specifically includes:

[0086] Step S006: Obtain well logging curve values ​​at different depths in the target area and the corresponding target component contents; normalize the well logging curve values ​​at different depths to obtain normalized well logging curve values; based on neural network modeling, using the normalized well logging curve values ​​as input and the corresponding target component contents as output, establish a target component content prediction model. The target component content prediction model includes: a silica mineral content prediction model, a calcareous mineral content prediction model, and a clay mineral content prediction model.

[0087] Well logging information features high vertical resolution, and minerals and organic matter in the formation exhibit unique response characteristics in the logging curves. Based on step S004, after identifying the material components with a good correlation to the oleophilic index, the material components with a good correlation to the oleophilic index throughout the well section are predicted, namely siliceous minerals, calcareous minerals, and clay minerals. The specific method is as follows:

[0088] 1. Obtain information on the mineral composition of rocks through basic experimental analysis.

[0089] 2. The main logging curves—natural gamma ray logging (GR), caliper logging (CAL), resistivity logging (RT), sonic logging (DT), neutron logging (CNL), and density logging (DEN)—were selected for neural network modeling of siliceous minerals, calcareous minerals, and clay minerals. Predictive models for these minerals were established. Modeling was performed using SPSS Modeler software. Before modeling, the logging data needed to be normalized. The normalization methods are shown in equations (2) and (3).

[0090]

[0091]

[0092] In the formula, X i These are the normalized logging curve values; The original logging curve value; X * max and These are the maximum and minimum logging curve values ​​of the target formation in the study area, respectively. In this embodiment, the maximum and minimum logging curve values ​​of the top and bottom boundaries of the target formation in the study area are taken.

[0093] The prediction results of the established models for predicting silica, calcareous, and clay mineral content are shown in the graphs below. Figure 3 , Figure 4 and Figure 5 .from Figures 3 to 5 It can be seen that applying neural network modeling can effectively predict mineral content.

[0094] The established mineral prediction model was used to predict the mineral content of the entire well section. The prediction results are as follows: Figure 6 As shown, from Figure 6 It can be observed that the prediction results of the mineral prediction model have good consistency with the measured mineral content results, and the prediction model can effectively predict the longitudinal mineral content changes in the study area.

[0095] Finally, by substituting the above mineral prediction results, i.e., the predicted values ​​of the target component content for the entire well section, into the established oleophilic index prediction model, the predicted value of the rock oleophilic index for the entire well section can be obtained, thus realizing the prediction of the rock oleophilic index for the entire well section. The prediction results are as follows: Figure 7 As shown.

[0096] Example 2

[0097] To implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a rock wettability prediction system is provided below. For example... Figure 8As shown, the rock wettability prediction system includes:

[0098] Data acquisition module 1 is used to acquire logging curve values ​​for the entire well section of the target area.

[0099] The content prediction module 2 is used to predict the target component content of the entire well section based on the logging curve values ​​of the entire well section and the target component content prediction model, and obtain the predicted value of the target component content of the entire well section. The target component content prediction model is based on neural network modeling and is determined according to the logging curve values ​​of different depths in the target area and the corresponding target component content. The target component is determined based on the correlation between the material composition information of the rock sample in the target area and the rock oleophilic index. The material composition information is determined by basic experimental analysis. The rock oleophilic index is determined by spontaneous permeation test.

[0100] The oleophilic index prediction module 3 is used to predict the rock oleophilic index of the entire well section based on the predicted value of the target component content and the oleophilic index prediction model, and obtain the predicted value of the rock oleophilic index of the entire well section; the predicted value of the rock oleophilic index of the entire well section is used to characterize the rock wettability of the entire well section; the oleophilic index prediction model is determined based on the content of the target component and the corresponding rock oleophilic index of the rock sample in the target area.

[0101] Example 3

[0102] This invention also provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the rock wettability prediction method of Embodiment 1. The electronic device may be a server.

[0103] In addition, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the rock wettability prediction method in Embodiment 1.

[0104] The rock wettability prediction method, system, equipment, and medium provided by this invention establish an oleophilic index prediction model based on fundamental experimental analysis and spontaneous permeation tests. This enables the prediction of the oleophilic index through rock material composition, overcoming the limitations of spontaneous permeation tests on samples. By establishing a neural network prediction model for inorganic minerals, the mineral content of the entire well section can be predicted. By combining the oleophilic index prediction model and the inorganic mineral prediction model, the oleophilic index prediction of the entire well section can be achieved, which is beneficial for the overall evaluation of reservoir wettability.

[0105] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0106] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting rock wettability, characterized in that, include: Obtain logging curve values ​​for the entire well section of the target area; The logging curve values ​​include: natural gamma logging value, caliber logging value, resistivity logging value, sonic logging value, neutron logging value, and density logging value; The target component content of the entire well section is predicted based on the logging curve values ​​of the entire well section and the target component content prediction model, thus obtaining the predicted value of the target component content of the entire well section. The target component content prediction model is based on neural network modeling and is determined according to the logging curve values ​​at different depths in the target area and the corresponding target component content. The target component is determined based on the correlation between the material composition information of the rock sample in the target area and the rock oleophilic index. The material composition information is determined by basic experimental analysis. The rock oleophilic index is determined by spontaneous permeation test. The rock oleophilic index of the entire well section is predicted based on the predicted values ​​of the target component content and the oleophilic index prediction model. The predicted value of the rock oleophilic index of the entire well section is used to characterize the rock wettability of the entire well section. The oleophilic index prediction model is determined based on the content of the target component and the corresponding rock oleophilic index of the rock sample in the target area. The method for determining the target component content prediction model specifically includes: Obtain well logging curve values ​​at different depths in the target area and the corresponding content of the target components; The logging curve values ​​at different depths are normalized to obtain normalized logging curve values. Based on neural network modeling, a target component content prediction model is established with the normalized logging curve value as input and the corresponding target component content as output. The method for determining the lipophilic index prediction model specifically includes: Using mathematical modeling software, an oleophilic index prediction model was established based on the content of the target components in the rock sample and the corresponding rock oleophilic index.

2. The method for predicting rock wettability according to claim 1, characterized in that, The method for determining the target component specifically includes: Obtain rock samples from the target area; Basic experimental analysis was performed on the rock sample to obtain material composition information; the material composition information included: mineral composition information and organic matter content information; the mineral composition information included: siliceous mineral content, calcareous mineral content and clay mineral content; the basic experimental analysis included: X-ray diffraction analysis and total organic carbon analysis. Spontaneous percolation tests were conducted on the rock samples, and the rock oleophilicity index was calculated based on the percolation test results. The correlation between the material composition information and the rock oleophilic index is determined, and the components with an absolute value of correlation greater than a set value are taken as target components.

3. The method for predicting rock wettability according to claim 2, characterized in that, The rock samples comprise two parallel sets of samples; spontaneous percolation tests are performed on the rock samples, and the rock oleophilic index is calculated based on the percolation test results, specifically including: Aqueous phase percolation test was performed on the first group of parallel samples to obtain the normalized volume of water. Oil phase percolation tests were conducted on the second group of parallel samples to obtain the normalized oil volume. The rock oleophilicity index is calculated based on the normalized water volume and the normalized oil volume.

4. The method for predicting rock wettability according to claim 2, characterized in that, Obtaining rock samples from the target area, specifically including: Obtain full-diameter core samples from the target area; The full-diameter core sample was cut into cylindrical samples of a predetermined size; The column sample is washed with oil and then dried to obtain a rock sample from the target area.

5. The method for predicting rock wettability according to claim 2, characterized in that, The target components include: siliceous minerals, calcareous minerals, and clay minerals; the target component content prediction models include: siliceous mineral content prediction model, calcareous mineral content prediction model, and clay mineral content prediction model.

6. A system for predicting rock wettability, characterized in that, include: The data acquisition module is used to acquire logging curve values ​​for the entire well section of the target area; The logging curve values ​​include: natural gamma logging value, caliber logging value, resistivity logging value, sonic logging value, neutron logging value, and density logging value; The content prediction module is used to predict the target component content of the entire well section based on the logging curve values ​​of the entire well section and the target component content prediction model, thereby obtaining the predicted value of the target component content of the entire well section. The target component content prediction model is based on neural network modeling and is determined according to the logging curve values ​​at different depths in the target area and the corresponding target component content. The target component is determined based on the correlation between the material composition information of the rock sample in the target area and the rock oleophilic index. The material composition information is determined by basic experimental analysis. The rock oleophilic index is determined by spontaneous permeation experiments. The oleophilic index prediction module is used to predict the rock oleophilic index of the entire well section based on the predicted values ​​of the target component content and the oleophilic index prediction model, thereby obtaining the predicted value of the rock oleophilic index of the entire well section. The predicted value of the rock oleophilic index of the entire well section is used to characterize the wettability of the rock in the entire well section. The oleophilic index prediction model is determined based on the content of the target component and the corresponding rock oleophilic index of the rock sample in the target area. The method for determining the target component content prediction model specifically includes: Obtain well logging curve values ​​at different depths in the target area and the corresponding content of the target components; The logging curve values ​​at different depths are normalized to obtain normalized logging curve values. Based on neural network modeling, a target component content prediction model is established with the normalized logging curve value as input and the corresponding target component content as output. The method for determining the lipophilic index prediction model specifically includes: Using mathematical modeling software, an oleophilic index prediction model was established based on the content of the target components in the rock sample and the corresponding rock oleophilic index.

7. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the rock wettability prediction method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method for predicting rock wettability as described in any one of claims 1 to 5.

Images