Unconventional oil and gas reservoir core permeability test system and test method

Abstract

The invention discloses an unconventional oil and gas reservoir core permeability test system and test method, and the test method comprises the following steps: S1, collecting feature data and parameter data, and extracting key data; s2, constructing an evaluation model; s3, aiming at the millimeter-scale or micron-scale particle rock core, constructing a correction model; s4, collecting to-be-measured core feature data, extracting key data, and evaluating model simulation prediction; s5, judging whether the core is a millimeter-scale or micron-scale particle core; s6, adopting an evaluation model to predict a centimeter-level rock core as a test result; and S7, correcting the millimeter-scale or micron-scale rock core through the correction model to obtain a test result. By combining data driving and a physical model, accurate prediction of the permeability of rock cores with different sizes is realized, the accuracy and efficiency of testing are remarkably improved, the experiment cost is reduced, the resource waste is reduced, and powerful technical support is provided for development of unconventional oil and gas reservoirs, so that effective development and utilization of oil and gas resources are promoted.

Description

Technical Field

[0001] The invention relates to the technical field of core experimental analysis, and in particular to a core permeability testing system and a testing method for unconventional oil and gas reservoirs. Background Art

[0002] In the field of oil and gas exploration and development, the permeability of oil and gas reservoirs is an important parameter for evaluating reservoir productivity and fluid flow capacity. Permeability determines the ease with which fluids (such as oil, natural gas, and water) can pass through rock pores. Therefore, accurate measurement and prediction of core permeability is crucial for the development design and production optimization of oil and gas fields.

[0003] Traditional permeability testing methods mainly rely on laboratory experiments, such as steady-state methods, non-steady-state methods (such as pressure pulse decay methods), etc., which usually require obtaining centimeter-level core samples and testing them under specific experimental conditions. However, with the deepening of oil and gas exploration, unconventional oil and gas reservoirs (such as shale gas, tight oil, etc.) have gradually become important exploration targets. The cores of these oil and gas reservoirs are often small in size, such as millimeter-level or micron-level particles, which poses a challenge to traditional permeability testing.

[0004] For centimeter-scale cores, although traditional permeability testing methods can provide relatively accurate permeability data, the experiments are costly and time-consuming, and laboratory resources are often difficult to meet the testing needs of a large number of samples.

[0005] For millimeter- or micron-sized particle cores, due to their small size and complex pore structure, traditional permeability testing methods are difficult to apply. Not only are there difficulties in experimental technology, but their permeability is also significantly affected by the characteristics of nanoscale flow channels, such as rarefaction effect and adsorption effect. The rarefaction effect refers to the enhanced interaction between fluid molecules at the nanoscale, resulting in a significant difference in fluid flow behavior from that at the macroscale; while the adsorption effect refers to the adsorption of fluid molecules on the surface of rock pores, which further affects the permeability.

[0006] Therefore, it is necessary to improve the permeability test according to the influence of cores of different sizes on the permeability test in order to solve the above problems. Summary of the invention

[0007] The present invention overcomes the deficiencies of the prior art and provides a core permeability testing system and a testing method for unconventional oil and gas reservoirs.

[0008] To achieve the above object, the technical solution adopted by the present invention is: a method for testing the core permeability of unconventional oil and gas reservoirs, comprising the following steps:

[0009] S1. Collect characteristic data of centimeter-level cores and parameter data in permeability tests under known different permeabilities, and extract key data affecting permeability from the collected characteristic data and parameter data;

[0010] S2. Based on key data, an evaluation model for evaluating the core permeability of unconventional oil and gas reservoirs is constructed. The core characteristic data with known permeability is used to train the evaluation model and simulate and predict the permeability under different parameter data;

[0011] S3. Considering the nanoscale flow channel characteristics of millimeter- or micron-sized particle cores, the influence of rarefaction effect and adsorption effect on permeability is considered to construct a correction model;

[0012] S4, collecting characteristic data of the core to be tested, extracting key data of the core characteristic data, and inputting the key data into the evaluation model for simulation prediction of permeability;

[0013] S5, determining whether the core to be tested is a millimeter-level or micron-level particle core;

[0014] S6. The core to be tested is a centimeter-level core, and the permeability predicted by the evaluation model is used as the test result;

[0015] S7. The core to be tested is a millimeter-scale or micron-scale granular core. The permeability predicted by the evaluation model is corrected by the correction model, and the corrected permeability is used as the test result.

[0016] In a preferred embodiment of the present invention, the step S1 includes the following sub-steps:

[0017] S11, collecting characteristic data of centimeter-level cores at different permeability levels and parameter data in the permeability test of the cores;

[0018] S12, preprocessing the collected feature data and parameter data, including removing duplicate, incomplete or abnormal data items, and normalizing the data;

[0019] S13. From the large amount of pre-processed characteristic data and parameter data, identify the key data that have a significant impact on the permeability.

[0020] In a preferred embodiment of the present invention, in the step S13, the key data is used as a construction factor for establishing an evaluation model, and the correlation coefficient r between each characteristic data or parameter data and the core permeability is analyzed and identified: Among them, x is the preprocessed characteristic data or parameter data; y is the core permeability; x i and i are the corresponding observation values; and are the corresponding average values.

[0021] In a preferred embodiment of the present invention, the step S2 includes the following sub-steps:

[0022] S21. Using the extracted key data affecting permeability as input features and the known permeability as output targets, an evaluation model capable of evaluating core permeability is constructed;

[0023] S22. Divide the core characteristic data of known permeability into a training set and a validation set, simulate and predict the permeability of the training set and the validation set under different parameter data, use the training set data to train the evaluation model, and use the validation set data to evaluate the performance of the model to ensure that the model has good generalization ability.

[0024] In a preferred embodiment of the present invention, in the step S21, the permeability of the core is evaluated, and a machine learning algorithm is used to perform regression learning using a neural network tool;

[0025] Core permeability prediction: in, is the predicted permeability; β n are the model coefficients; x n is the key data affecting permeability; ∈ is the error term.

[0026] In a preferred embodiment of the present invention, in the step S22, in the training of the evaluation model, in order to prevent overfitting, a regularization term is added to the loss function to make the predicted value as close as possible to the actual observed value: minimize in, is the sum of all N observations; y i is the target variable for the ith observation; β 0 is the intercept term, the base level of the model prediction value; β j is the model coefficient, indicating the jth feature x j The degree of influence on the target variable; x ij is the jth eigenvalue of the ith observation; n is the number of features; α is the regularization strength parameter, which controls the strength of regularization. A larger α value will more severely penalize large absolute values ​​of coefficients, resulting in more coefficients being reduced to zero.

[0027] In a preferred embodiment of the present invention, the step S3 includes the following sub-steps:

[0028] S31. Analyze the influence mechanism of rarefaction effect and adsorption effect on permeability based on the nanoscale flow channel characteristics of millimeter- or micron-sized particle cores;

[0029] S32. Based on the analysis results, a correction model is constructed that can take into account the influence of rarefaction effect and adsorption effect on permeability;

[0030] S33. Use millimeter-scale or micrometer-scale particle core data with known permeability to verify the corrected model to ensure that the corrected model can accurately predict and correct the permeability.

[0031] In a preferred embodiment of the present invention, in step S31, the influence of the rarefaction effect on the permeability is: Where Kn is the Knudsen number; λ is the mean free path of gas molecules; R is the pore throat radius;

[0032] The influence of the adsorption effect on the permeability is calculated by the BET equation to calculate the monolayer adsorption amount: Where PV is the product of the volume V of the gas and the equilibrium adsorption gas pressure P under the equilibrium adsorption gas pressure P; P 0 is the saturated vapor pressure of the adsorbate; V m is the monolayer saturated adsorption capacity; C is the BET equation constant.

[0033] In a preferred embodiment of the present invention, in step S32, the permeability k considering the rarefaction effect is Kn : in, is the predicted permeability; Kn is the Knudsen number;

[0034] The permeability is corrected by considering the effect of the adsorption layer on the effective cross-sectional area of ​​the pores. The permeability k after correction considering the adsorption effect ads : Among them, A ads is the area of ​​the adsorption layer; A total is the total area of ​​the pores;

[0035] The rarefaction effect and the adsorption effect are combined to construct a correction model k corrected :

[0036]

[0037] The present invention provides a testing system for a core permeability testing method of an unconventional oil and gas reservoir, comprising:

[0038] Data collection module, used to collect core characteristic data and parameter data in permeability test;

[0039] A data extraction module is used to extract key data affecting permeability from the collected characteristic data and parameter data;

[0040] The evaluation model is used to simulate and predict the permeability of the core under different parameter data based on the characteristic data of the core;

[0041] The correction model is used to correct the permeability output by the evaluation model by considering the influence of rarefaction effect and adsorption effect on permeability for millimeter- or micron-sized particle cores;

[0042] The category judgment module is used to judge the centimeter-level, millimeter-level and micron-level categories of the core.

[0043] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0044] (1) The present invention provides a core permeability testing system and method for unconventional oil and gas reservoirs. By combining data-driven and physical models, it not only targets the characteristics of centimeter-level cores, but also considers the nanoscale flow channel characteristics of millimeter-level and micron-level particle cores. By constructing a correction model, it effectively solves the problem of the influence of rarefaction effect and adsorption effect on permeability, and achieves accurate prediction of the permeability of cores of different sizes, thereby significantly improving the accuracy and efficiency of the test, reducing experimental costs, and reducing resource waste, providing strong technical support for the development of unconventional oil and gas reservoirs, thereby promoting the effective development and utilization of oil and gas resources.

[0045] (2) In the present invention, permeability simulation tests can be performed on cores of different sizes, such as centimeters, millimeters, and micrometers, breaking the limitations of traditional testing methods on core size. By constructing an evaluation model and a correction model, the data-driven prediction capability and the accuracy of the physical model are combined, and the permeability influencing mechanism of nanoscale flow channel characteristics is considered, which helps to optimize the development plan and improve resource utilization.

[0046] (3) In the present invention, by constructing an evaluation model and a correction model to predict permeability, the demand for a large number of experimental samples is reduced, and the experimental cost is reduced. This not only improves the accuracy of the permeability test, but also can significantly reduce the time and cost required for the experimental test, thereby improving the test efficiency. Accurate permeability testing helps to optimize the development and design of oil and gas fields, reduce unnecessary resource investment, and thus improve resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a flow chart of a method for testing the core permeability of unconventional oil and gas reservoirs of the present invention;

[0049] Figure 2 It is a structural diagram of an unconventional oil and gas reservoir core permeability testing system of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0052] like Figure 1 As shown, a method for testing the core permeability of unconventional oil and gas reservoirs comprises the following steps:

[0053] S1. Collect characteristic data of centimeter-level cores and parameter data in permeability tests under known different permeabilities, and extract key data affecting permeability from the collected characteristic data and parameter data;

[0054] S2. Based on key data, an evaluation model for evaluating the core permeability of unconventional oil and gas reservoirs is constructed. The core characteristic data with known permeability is used to train the evaluation model and simulate and predict the permeability under different parameter data;

[0055] S3. Considering the nanoscale flow channel characteristics of millimeter- or micron-sized particle cores, the influence of rarefaction effect and adsorption effect on permeability is considered to construct a correction model;

[0056] S4, collecting characteristic data of the core to be tested, extracting key data of the core characteristic data, and inputting the key data into the evaluation model for simulation prediction of permeability;

[0057] S5, determining whether the core to be tested is a millimeter-level or micron-level particle core;

[0058] S6. The core to be tested is a centimeter-level core, and the permeability predicted by the evaluation model is used as the test result;

[0059] S7. The core to be tested is a millimeter-scale or micron-scale granular core. The permeability predicted by the evaluation model is corrected by the correction model, and the corrected permeability is used as the test result.

[0060] It should be noted that by combining data-driven and physical models, not only the characteristics of centimeter-scale cores are targeted, but also the nanoscale flow channel characteristics of millimeter-scale and micron-scale particle cores are considered. By constructing a corrected model, the problem of the influence of rarefaction effect and adsorption effect on permeability is effectively solved, and the permeability of cores of different sizes can be accurately predicted, thereby significantly improving the accuracy and efficiency of the test, reducing experimental costs, and reducing resource waste, providing strong technical support for the development of unconventional oil and gas reservoirs, thereby promoting the effective development and utilization of oil and gas resources.

[0061] In some specific embodiments, the step S1 includes the following sub-steps:

[0062] S11, collecting characteristic data of centimeter-level cores at different permeability levels and parameter data in the permeability test of the cores;

[0063] S12, preprocessing the collected feature data and parameter data, including removing duplicate, incomplete or abnormal data items, and normalizing the data;

[0064] S13. From the large amount of pre-processed characteristic data and parameter data, identify the key data that have a significant impact on the permeability.

[0065] In this embodiment, in step S11, the characteristic data include lithology, porosity, mineral composition and fluid properties, and the parameter data include pressure gradient, fluid flow rate and temperature.

[0066] In this embodiment, in step S12, duplicate data is removed from the collected feature data and parameter data, and abnormal values ​​are identified and processed: abnormal values ​​may be caused by data entry errors or special circumstances of patients, and need to be processed according to actual conditions, such as replacing them with mean values, medians, or deletions; normalization processing is specifically to scale the data so that it falls into a small specific interval, such as [0, 1] or [-1, 1], which helps to eliminate the impact of the dimension on the results. The calculation formula is: Among them, X is the original data; X′ is the normalized data.

[0067] In this embodiment, in step S13, the key data is used as a construction factor for establishing an evaluation model, and the correlation coefficient r between each characteristic data or parameter data and the core permeability is analyzed and identified: Among them, x is the preprocessed characteristic data or parameter data; y is the core permeability; x i and i are the corresponding observation values; and are the corresponding average values;

[0068] When the correlation coefficient r=1, it means that the preprocessed characteristic data or parameter data and the core permeability are completely positively correlated, that is, the increase of one variable is always accompanied by the increase of another variable; when r=-1, it means that the preprocessed characteristic data or parameter data and the core permeability are completely negatively correlated, that is, the increase of one variable is always accompanied by the decrease of another variable; when r=0, it means that there is no linear correlation between the characteristic data or parameter data and the core permeability; that is, the closer the absolute value of r is to 1, the stronger the linear relationship between the characteristic data or parameter data and the core permeability, and the closer it is to 0, the weaker the linear relationship.

[0069] In some specific embodiments, the step S2 includes the following sub-steps:

[0070] S21. Using the extracted key data affecting permeability as input features and the known permeability as output targets, an evaluation model capable of evaluating core permeability is constructed;

[0071] S22. Divide the core characteristic data of known permeability into a training set and a validation set, simulate and predict the permeability of the training set and the validation set under different parameter data, use the training set data to train the evaluation model, and use the validation set data to evaluate the performance of the model to ensure that the model has good generalization ability.

[0072] In this embodiment, in step S21, the permeability of the core is evaluated, and a machine learning algorithm is used to enable it to automatically learn and discover laws and patterns from the data, and then use these laws and patterns to perform prediction, classification, clustering, and dimensionality reduction tasks. Preferably, a deep learning model is used, combined with modeling and simulation performed by an artificial intelligence algorithm, and a neural network tool is used for regression learning;

[0073] Core permeability prediction (linear regression): in, is the predicted permeability; β n are the model coefficients; x n is the key data affecting permeability; ∈ is the error term.

[0074] In this implementation, in step S22, during the training of the evaluation model, in order to prevent overfitting, a regularization term is added to the loss function to make the predicted value as close to the actual observed value as possible:

[0075] minimize in, is the sum of all N observations; y i is the target variable for the ith observation (e.g., the actual measured value of the core permeability); β 0 is the intercept term, the base level of the model prediction value; β j is the model coefficient, indicating the jth feature xj The degree of influence on the target variable; x ij is the jth eigenvalue of the ith observation; n is the number of features; α is the regularization strength parameter, which controls the strength of regularization. A larger α value will more severely penalize large absolute values ​​of coefficients, resulting in more coefficients being reduced to zero.

[0076] In some specific implementations, the step S3 includes the following sub-steps:

[0077] S31. Analyze the influence mechanism of rarefaction effect and adsorption effect on permeability based on the nanoscale flow channel characteristics of millimeter- or micron-sized particle cores;

[0078] S32. Based on the analysis results, a correction model is constructed that can take into account the influence of rarefaction effect and adsorption effect on permeability;

[0079] S33. Use millimeter-scale or micrometer-scale particle core data with known permeability to verify the corrected model to ensure that the corrected model can accurately predict and correct the permeability.

[0080] In this embodiment, in step S31, the influence of rarefaction effect on permeability is: Where Kn is the Knudsen number (which describes the relative importance of molecular diffusion and molecular momentum transfer. The larger the Knudsen number, the more significant the rarefaction effect); λ is the mean free path of gas molecules; R is the pore throat radius;

[0081] The influence of adsorption effect on permeability was calculated by BET equation: Where PV is the product of the volume V of the gas and the equilibrium adsorption gas pressure P under the equilibrium adsorption gas pressure P; P 0 is the saturated vapor pressure of the adsorbate; V m is the monolayer saturated adsorption capacity; C is the BET equation constant.

[0082] In this embodiment, in step S32, the permeability k considering the rarefaction effect is Kn : in, is the predicted permeability; Kn is the Knudsen number;

[0083] The permeability is corrected by considering the effect of the adsorption layer on the effective cross-sectional area of ​​the pores. The permeability k after correction considering the adsorption effect ads : Among them, A ads is the area of ​​the adsorption layer; A total is the total area of ​​the pores;

[0084] Combining the rarefaction effect and adsorption effect to construct the modified model k corrected :

[0085]

[0086] In some specific embodiments, the step S4 includes the following sub-steps:

[0087] S41, collecting characteristic data of the core to be tested, and extracting key data related to permeability from the characteristic data of the core to be tested;

[0088] S42. Input the extracted key data into the evaluation model, and simulate and output the permeability under different parameter data.

[0089] In this embodiment, in step S41, the key data extraction from the core characteristic data to be measured is the same as step S13.

[0090] In some specific embodiments, in step S5, the category of the core to be tested is determined based on physical dimensions and structural characteristics; the physical dimensions include the diameter and length involved, and the structural characteristics include the lithology, mineral composition, structural components and pore fractures involved.

[0091] In some specific implementations, the step S7 includes the following sub-steps:

[0092] S71. When the type of the core to be tested is determined to be a millimeter-scale or micron-scale particle core, the permeability predicted by the evaluation model is input into the correction model, and the adjusted permeability is simulated by considering the rarefaction effect and the adsorption effect;

[0093] S72. Use the permeability output by the modified model as the test result.

[0094] It should be noted that the present invention can perform permeability simulation tests on cores of different sizes, such as centimeters, millimeters and micrometers, breaking the limitations of traditional testing methods for core size. By constructing an evaluation model and a correction model, it combines the data-driven prediction capability and the accuracy of the physical model, and considers the permeability influencing mechanism of nanoscale flow channel characteristics, thereby helping to optimize development plans and improve resource utilization.

[0095] like Figure 2 As shown, a testing system for a core permeability testing method of an unconventional oil and gas reservoir comprises:

[0096] Data collection module, used to collect core characteristic data and parameter data in permeability test;

[0097] A data extraction module is used to extract key data affecting permeability from the collected characteristic data and parameter data;

[0098] The evaluation model is used to simulate and predict the permeability of the core under different parameter data based on the characteristic data of the core;

[0099] The correction model is used to correct the permeability output by the evaluation model by considering the influence of rarefaction effect and adsorption effect on permeability for millimeter- or micron-sized particle cores;

[0100] The category judgment module is used to judge the centimeter-level, millimeter-level and micron-level categories of the core.

[0101] It should be noted that the unconventional oil and gas reservoir core permeability testing system can implement the steps in the unconventional oil and gas reservoir core permeability testing method in the above embodiment, and can achieve the same technical effects. Please refer to the description in the above embodiment and no detailed description will be given here.

[0102] The above is based on the ideal embodiment of the present invention. Through the above description, it is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the attached claims rather than the above description, and it is intended to include all changes within the meaning and scope of the equivalent elements of the claims. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0103] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for testing the core permeability of unconventional oil and gas reservoirs, characterized in that: The following steps are involved: S1. Collect characteristic data of centimeter-level cores and parameter data in permeability tests under known different permeabilities, and extract key data affecting permeability from the collected characteristic data and parameter data; S2. Based on key data, an evaluation model for evaluating the core permeability of unconventional oil and gas reservoirs is constructed. The core characteristic data with known permeability is used to train the evaluation model and simulate and predict the permeability under different parameter data; S3. Considering the nanoscale flow channel characteristics of millimeter- or micron-sized particle cores, the influence of rarefaction effect and adsorption effect on permeability is considered to construct a correction model; S4, collecting characteristic data of the core to be tested, extracting key data of the core characteristic data, and inputting the key data into the evaluation model for simulation prediction of permeability; S5, determining whether the core to be tested is a millimeter-level or micron-level particle core; S6. The core to be tested is a centimeter-level core, and the permeability predicted by the evaluation model is used as the test result; S7. The core to be tested is a millimeter-scale or micron-scale granular core. The permeability predicted by the evaluation model is corrected by the correction model, and the corrected permeability is used as the test result.

2. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 1, characterized in that: The step S1 includes the following sub-steps: S11, collecting characteristic data of centimeter-level cores at different permeability levels and parameter data in the permeability test of the cores; S12, preprocessing the collected feature data and parameter data, including removing duplicate, incomplete or abnormal data items, and normalizing the data; S13. From the large amount of pre-processed characteristic data and parameter data, identify the key data that have a significant impact on the permeability.

3. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 2, characterized in that: In the step S13, the key data is used as a construction factor for establishing an evaluation model, and the correlation coefficient r between each characteristic data or parameter data and the core permeability is analyzed and identified: Among them, x is the preprocessed characteristic data or parameter data; y is the core permeability; x i and i are the corresponding observation values; and are the corresponding average values.

4. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 1, characterized in that: The step S2 includes the following sub-steps: S21. Using the extracted key data affecting permeability as input features and the known permeability as output targets, an evaluation model capable of evaluating core permeability is constructed; S22. Divide the core characteristic data of known permeability into a training set and a validation set, simulate and predict the permeability of the training set and the validation set under different parameter data, use the training set data to train the evaluation model, and use the validation set data to evaluate the performance of the model to ensure that the model has good generalization ability.

5. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 4, characterized in that: In the step S21, the permeability of the core is evaluated, and a machine learning algorithm is used to perform regression learning using a neural network tool; Core permeability prediction: in, is the predicted permeability; β n are the model coefficients; x n is the key data affecting permeability; ∈ is the error term.

6. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 4, characterized in that: In the step S22, in the training of the evaluation model, in order to prevent overfitting, a regularization term is added to the loss function to make the predicted value as close to the actual observed value as possible: minimize in, is the sum of all N observations; y i is the target variable of the ith observation; β0 is the intercept term, the base level of the model prediction value; β j is the model coefficient, indicating the jth feature x j The degree of influence on the target variable; x ij is the jth eigenvalue of the ith observation; n is the number of features; α is the regularization strength parameter, which controls the strength of regularization. A larger α value will more severely penalize large absolute values ​​of coefficients, resulting in more coefficients being reduced to zero.

7. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 1, characterized in that: The S3 step includes the following sub-steps: S31. Analyze the influence mechanism of rarefaction effect and adsorption effect on permeability based on the nanoscale flow channel characteristics of millimeter- or micron-sized particle cores; S32. Based on the analysis results, a correction model is constructed that can take into account the influence of rarefaction effect and adsorption effect on permeability; S33. Use millimeter-scale or micrometer-scale particle core data with known permeability to verify the corrected model to ensure that the corrected model can accurately predict and correct the permeability.

8. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 7, characterized in that: In the step S31, the influence of the rarefaction effect on the permeability is: Where Kn is the Knudsen number; λ is the mean free path of gas molecules; R is the pore throat radius; The influence of the adsorption effect on the permeability is calculated by the BET equation to calculate the monolayer adsorption amount: Where PV is the product of the volume V of the gas and the equilibrium adsorption gas pressure P under the equilibrium adsorption gas pressure P; P0 is the saturated vapor pressure of the adsorbate; V m is the monolayer saturated adsorption capacity; C is the BET equation constant.

9. The method for testing the core permeability of unconventional oil and gas reservoirs according to claim 7, characterized in that: In the step S32, the permeability k considering the rarefaction effect is Kn : in, is the predicted permeability; Kn is the Knudsen number; The permeability is corrected by considering the effect of the adsorption layer on the effective cross-sectional area of ​​the pores. The permeability k after correction considering the adsorption effect ads : Among them, A ads is the area of ​​the adsorption layer; A total is the total area of ​​the pores; The rarefaction effect and the adsorption effect are combined to construct a correction model k corrected :

10. A testing system for the core permeability testing method of unconventional oil and gas reservoirs based on any one of claims 1 to 9, characterized in that: include: Data collection module, used to collect core characteristic data and parameter data in permeability test; A data extraction module is used to extract key data affecting permeability from the collected characteristic data and parameter data; The evaluation model is used to simulate and predict the permeability of the core under different parameter data based on the characteristic data of the core; The correction model is used to correct the permeability output by the evaluation model by considering the influence of rarefaction effect and adsorption effect on permeability for millimeter- or micron-sized particle cores; The category judgment module is used to judge the centimeter-level, millimeter-level and micron-level categories of the core.

Images