Method and system for analyzing shale pores changing along with buried depth

Abstract

The invention relates to the technical field of testing or analyzing materials by means of measuring chemical or physical properties of the materials, in particular to a method and a system for analyzing shale pores changing along with depth, and the method comprises the following steps: acquiring a target area shale sample characterization information set; obtaining a target area shale sample standard grayscale image set; extracting a pore image based on the standard grayscale image; performing fracture data acquisition on the pore image based on a fracture analysis model; and performing machine learning-based supervised model processing on the fracture data to obtain an analysis result. According to the invention, real-time analysis of shale pores with different depths is realized.

Description

Technical Field

[0001] This application relates to the technical field of testing or analyzing materials by measuring the chemical or physical properties of materials. In particular, it relates to a shale pore analysis method that varies with burial depth, and also to an analysis system. Background Art

[0002] The pore space structure of shale reservoirs is complex, with small pore scales, mainly nano-pores, and complex types, including organic pores, inorganic pores, and micro-fractures. The oil and gas in the organic pores of shale reservoirs exist in an adsorbed and dissolved state, while the oil and gas in inorganic pores mostly exist in a free state. Accurately and quantitatively characterizing the pore structures of different types of pores in shale is of great significance for studying the occurrence state of shale oil and gas, evaluating resource quality, and formulating reasonable development methods.

[0003] In the prior art, a Chinese invention patent application with a publication date of January 14, 2025, a publication number of CN119313932A, and a title of "Shale Pore Type Identification and Quantitative Characterization Method Based on Digital Core" discloses that for the original grayscale image of the shale sample to be identified, grayscale adjustment processing and image noise reduction processing are performed to obtain a standard grayscale image; the organic matter and transition zone images in the standard grayscale image are extracted, organic matter identification processing is performed to determine the organic matter connected body image; the pore images in the standard grayscale image are extracted, combined with the organic matter connected body image, pore identification processing is performed to determine the organic pore image and the inorganic pore image; for the inorganic pore image, micro-fracture identification processing is performed to determine the micro-fracture image and the inorganic pore image.

[0004] The foregoing technical solution can quantitatively identify organic pores, inorganic pores, and micro-fractures in shale, quantitatively characterize the pore structure of shale, and analyze the structural parameters of organic pores, inorganic pores, and micro-fractures, but it has obvious deficiencies in analyzing shale pores according to different depths. Summary of the Invention

[0005] The inventors found through research that: gas adsorption, mercury intrusion, and nuclear magnetic resonance, as the mainstream methods for quantitatively characterizing the pore structure of porous media materials, theoretically cannot accurately determine the pores and non-pores of shale. Although imaging means can be used for identification, they all require manual operation, with low efficiency and only qualitative analysis within a certain quantitative range.

[0006] The purpose of this application is to provide a shale pore analysis method and system that vary with depth. By performing crack data acquisition on the pore image based on the crack analysis model and processing the crack data based on the machine learning supervision model, it solves the technical problems that the prior art cannot provide a method for real-time and accurate shale pore analysis according to depth changes, and at the same time, it also solves the technical problem that it cannot provide a system for real-time and accurate shale pore analysis according to depth changes.

[0007] According to one aspect of the present application, a shale pore analysis method varying with depth is provided. The method is executed by a processor and includes:

[0008] Obtaining a set of characterization information of shale samples in a target area;

[0009] Obtaining a set of standard grayscale images of shale samples in the target area;

[0010] Extracting pore images based on the standard grayscale images;

[0011] Performing fracture data acquisition on the pore images based on a fracture analysis model;

[0012] Performing processing on the fracture data based on a machine learning supervision model to obtain an analysis result.

[0013] In some embodiments, the process of obtaining the set of characterization information of shale samples in the target area is as follows:

[0014] Determining the shale type according to the humidity and terrain of the target area environment;

[0015] Based on the shale type and previous research data of the shale, preliminarily estimating the current shale pore type;

[0016] Based on the estimated shale pore type, establishing a relationship model between the porosity of the shale reservoir, the shale component content, and undetermined coefficients;

[0017] Based on the relationship model, obtaining the set of characterization information of shale samples in the target area.

[0018] In some embodiments, the process of obtaining the set of standard grayscale images of shale samples in the target area is as follows:

[0019] Obtaining three-dimensional original grayscale images of shale samples in the target area according to computerized tomography;

[0020] According to the set of three-dimensional original grayscale images of shale samples in the target area, and performing gray level adjustment on the set of original grayscale images;

[0021] Performing noise reduction processing based on the gray level adjustment result images to obtain a set of standard grayscale images.

[0022] In some embodiments, the process of performing gray level adjustment on the set of original grayscale images is as follows:

[0023] Obtaining the image to be processed in the set of three-dimensional original grayscale images of shale samples in the target area;

[0024] Performing weighted average on the image to be processed to obtain a gray level value;

[0025] Performing gray level value adjustment based on a linear function to obtain a grayscale image.

[0026] In some embodiments, the process of extracting the pore image based on the standard grayscale image is as follows:

[0027] Perform a global threshold on the standard grayscale image set to obtain a pore and non-pore image set;

[0028] Perform morphology on the non-pore image set to obtain the missing pores between adjacent non-pores;

[0029] Perform feature extraction on the missing pores and merge them with the pores to obtain the pore image.

[0030] In some embodiments, the process of obtaining fracture data for the pore image based on the fracture analysis model is as follows:

[0031] Clean the data of the pore image to obtain an interference-free pore image;

[0032] Input the interference-free pore image into the statistical model for analysis to obtain the statistical characteristics of the pores;

[0033] Input the statistical characteristics into the geometric model for spatial morphology reshaping to obtain the fracture data.

[0034] In some embodiments, the process of processing the fracture data based on the machine learning supervised model to obtain the analysis result is as follows:

[0035] Clean the data of the fracture data to obtain interference-free fracture data;

[0036] Upload the interference-free fracture data to the support vector machine model for screening;

[0037] According to the screening result and in combination with the Cartesian coordinate system, obtain the correlation analysis result of the pores and the burial depth.

[0038] According to another aspect of the present application, there is provided a shale pore analysis system that varies with depth. The system includes a processor and further includes:

[0039] A first acquisition unit, where the acquisition unit is used to acquire a set of shale sample characterization information of the target area;

[0040] A second acquisition unit, where the second acquisition unit is used to acquire a set of standard grayscale images of the shale samples in the target area;

[0041] An extraction unit, where the extraction unit is used to extract the pore image based on the standard grayscale image;

[0042] A third acquisition unit, where the third acquisition unit is used to obtain fracture data for the pore image based on the fracture analysis model;

[0043] An analysis unit, where the analysis unit is used to process the fracture data based on the machine learning supervised model to obtain the analysis result.

[0044] In some embodiments, the processor data is connected to a first acquisition unit, a second acquisition unit, an extraction unit, a third acquisition unit, and an analysis unit.

[0045] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0046] The present application realizes the reasonable determination of the accuracy of the initial stage data by obtaining the shale sample characterization information set of the target area and the standard gray-scale image set of the shale sample of the target area, effectively distinguishing the acquisition of the data surface of a single layer in the prior art; then, the present application extracts the pore image based on the standard gray-scale image, and performs fracture data acquisition on the pore image based on the fracture analysis model, realizing a more comprehensive and detailed understanding of the pore image situation, distinguishing the singleness and limitation of the data in the prior art; finally, the present application performs processing on the fracture data based on the machine learning supervision model to obtain an analysis result, ensuring the accuracy of the shale pore analysis at different depths, so as to ensure the acquisition of a correlation analysis result of pores and burial depth with practical value and significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 is the flowchart of the analysis method of the present application;

[0049] Figure 2 is the schematic structural diagram of the analysis system of the present application;

[0050] Figure 3 is the usage scenario diagram of the analysis system of the present application;

[0051] Figure 4 is the partial correlation analysis point-line diagram corresponding to the analysis method of the present application; where the abscissa is the pore specific surface area and the ordinate is the depth. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] The following will combine the drawings in the embodiments of the present application Figures 1-4 to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments.

[0053] Embodiment 1

[0054] Figure 1The figure is a flowchart of the shale pore analysis method that varies with burial depth provided in this embodiment, and this method is executed by a processor. The so-called processor may be a Central Processing Unit (CPU), or it may also be 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. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0055] The method includes:

[0056] Obtain the characterization information set of the shale sample in the target area. In the prior art, shale samples are usually collected at the same depth, or only multi-region shale at the same depth is collected, and the pore derivation analysis is performed to determine possible pores, so as to provide guidance for subsequent drilling and other work. In this embodiment, it is considered that as the burial depth increases, the pressure of the overlying rock formation increases, which will cause the porosity of the mud shale to decrease, the rock to become denser, and thus the drillability to become worse. Therefore, dynamic samples at different depths are obtained.

[0057] In some possible implementation manners, the shale type can be determined according to the humidity and the terrain of the target area environment. It can be understood that an increase in humidity will cause the water content of the shale to rise, resulting in an increase in the bulk density of the shale, because the density of water is relatively large, and the overall weight will increase after entering the shale pores. With the change of humidity, the porosity and permeability of the shale will also be affected. When the humidity is relatively high, the pores are filled with water, the effective porosity may decrease, and the penetration difficulty of gas or liquid in the shale increases, and the permeability decreases; while when the humidity is relatively low, the moisture in the pores decreases, and the porosity and permeability may increase to a certain extent, but excessive drying may cause microcracks in the shale, which will also change its pore structure and permeability to a certain extent; under different terrain conditions, the formation pressure borne by the shale is different.

[0058] In areas with lower terrain such as the center of deeply buried basins, the overlying formation pressure on the shale is relatively large, which will increase the compaction degree of the shale, reduce the porosity, and make the rock denser. In areas with higher terrain, such as the top of an anticline structure, the formation pressure on the shale is relatively small, and the compaction degree of the rock is relatively low, and more pores and fractures may be retained, which is beneficial to later oil and gas exploitation and other activities. Based on the foregoing, in this embodiment, considering the foregoing factors, the possible shale types under corresponding factors, and past research data, the pore types of the current shale are preliminarily estimated. It can be understood that the estimation of pore types here is also a preliminary judgment of possible pore types, such as intergranular pores, intragranular pores, organic matter pores, microfractures, and nano-scale organic clay composite pores, etc. Then, based on the estimated shale pore types, a relationship model between the porosity of the shale reservoir and the shale component content and undetermined coefficients is established. It should be noted that the process of establishing the relationship model here is to construct a linear model based on the porosity of the shale reservoir, and use the least squares method or the gradient descent method to solve the undetermined coefficients in the model, and then use cross-validation to perform model verification to obtain the relationship model, where the linear model is:

[0059]

[0060] where, a0, a1....., a m are undetermined coefficients, and ε i is the error term, which follows a normal distribution with a mean of 0.

[0061] Finally, based on the relationship model, a set of shale sample characterization information for the target area is obtained. This information set includes at least shale characterization and preliminary pore images.

[0062] A set of standard grayscale images of shale samples in the target area is obtained. Obtaining the grayscale image set according to the images in the shale sample characterization information set can reduce storage costs, reduce computational complexity, improve processing speed, avoid interference that may be caused by color information, and at the same time, grayscale images can meet the visual perception requirements of the human eye for images to a certain extent.

[0063] In some possible embodiments, a three-dimensional original grayscale image of a shale sample in the target area is obtained according to computed tomography. Based on the set of three-dimensional original grayscale images of the shale sample in the target area, the original grayscale image set is subjected to grayscale adjustment. Then, based on the grayscale adjustment result image, noise reduction processing is performed to obtain a standard grayscale image set. Among them, the process of grayscale adjustment for the original grayscale image set is as follows: the image to be processed in the three-dimensional original grayscale image set of the shale sample in the target area is obtained; the weighted average is performed on the image to be processed to obtain a grayscale value; based on the execution of grayscale value adjustment, a grayscale image is obtained. It should be noted that the linear function in this embodiment is a linear grayscale transformation function, specifically: G' = a*G + b, where G is the original grayscale value, G' is the transformed grayscale value, and a and b are constants. Among them, a is used to control the contrast, the contrast is enhanced when a > 1, and the contrast is reduced when 0 < a < 1; b is used to control the brightness, the brightness increases when b > 0, and the brightness decreases when b < 0.

[0064] The pore image is extracted based on the standard grayscale image. The extraction can be achieved quickly and accurately according to the standard grayscale image. Among them, in some possible embodiments, a global threshold is performed on the standard grayscale image set. In this embodiment, the Otsu algorithm is used. The Otsu algorithm is based on the histogram of the image, and the image is segmented by calculating the threshold that maximizes the between-class variance to obtain a set of pore and non-pore images. Then, morphology is performed on the non-pore image set to obtain the missing pores between adjacent non-pores. It can be understood that the morphological operation on the segmented image can be erosion or dilation. Among them, the erosion operation can remove small burrs and isolated pixel points at the pore edge, and the dilation operation can connect adjacent pores to make the shape of the pores more complete. In this embodiment, the dilation operation is preferably used to connect the missing pores between adjacent non-pores. Then, feature extraction is performed on the connected missing pores and merged with the pores to obtain a pore image. Among them, the feature extraction includes at least the pore area, perimeter, and shape factor, etc.

[0065] The fracture data is obtained based on the fracture analysis model for the pore image.

[0066] In some possible embodiments, the pore image is subjected to data cleaning to obtain an interference-free pore image; the interference-free pore image is input into a statistical model for analysis to obtain the statistical characteristics of the pores; the statistical characteristics are input into a geometric model for spatial morphology reshaping to obtain fracture data.

[0067] Perform processing on the fracture data based on a machine learning supervised model to obtain an analysis result. Based on the processing of the machine learning supervised model, fracture data can be effectively acquired and analyzed, providing important basic information for research and engineering applications in related fields. Among them, in some possible implementation manners, perform data cleaning on the fracture data to obtain interference-free fracture data; upload the interference-free fracture data to a support vector machine model for screening; according to the screening result and in combination with the Cartesian coordinate system, obtain the correlation analysis result of the pore and the burial depth. It can be understood that the presentation manner of the analysis result is at least a combined graph of coordinate axes and points and lines, such as Figure 4 shown.

[0068] Example Two

[0069] Figure 2 The following is a structural diagram of a shale pore analysis system that changes with the burial depth provided in this embodiment. Exemplarily, the method can be divided into one or more modules. One or more modules are stored in the memory and executed by a processor to complete this application. One or more modules can be a series of computer program instruction segments that can complete specific functions, and these instruction segments are used to describe the execution process of the computer program. For example, the computer program can be divided into a first acquisition unit, a second acquisition unit, an extraction unit, a third acquisition unit, and an analysis unit. The specific functions of each module are as follows: The first acquisition unit is used to acquire a set of characterization information of shale samples in the target area; the second acquisition unit is used to acquire a set of standard grayscale images of shale samples in the target area; the extraction unit is used to extract pore images based on the standard grayscale images; the third acquisition unit is used to perform fracture data acquisition on the pore images based on a fracture analysis model; the analysis unit is used to perform processing on the fracture data based on a machine learning supervised model to obtain an analysis result.

[0070] In some possible implementation manners, the processor is data-connected to the first acquisition unit, the second acquisition unit, the extraction unit, the third acquisition unit, and the analysis unit.

[0071] The specific examples of the shale pore analysis method that changes with depth in the foregoing Example One are equally applicable to the shale pore analysis system that changes with depth in this embodiment. Through the foregoing detailed description of the shale pore analysis method that changes with depth, those skilled in the art can clearly know the shale pore analysis system that changes with depth in this embodiment. Therefore, for the sake of brevity of the specification, it will not be elaborated herein.

[0072] The above has shown and described the basic principles, main features and advantages of the present application. For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic features of the present application. Note that although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments only. Without departing from the inventive concept of the present invention, more other equivalent embodiments can be included, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for shale pore analysis varying with burial depth, which is executed by a processor, characterized in that Including: Obtain the characterization information set of the shale sample in the target area; Obtain the standard gray-scale image set of the shale sample in the target area; Extract the pore image based on the standard gray-scale image; Execute fracture data acquisition on the pore image based on the fracture analysis model; Execute processing on the fracture data based on the machine learning supervised model to obtain the analysis result.

2. The method according to claim 1, wherein The process of obtaining the characterization information set of the shale sample in the target area is as follows: Determine the shale type according to the humidity and terrain of the target area environment; Based on the shale type and previous research data of the shale, preliminarily estimate the current shale pore type; Based on the estimated shale pore type, establish a relationship model between the porosity of the shale reservoir, the shale component content, and the undetermined coefficient; Based on the relationship model, obtain the characterization information set of the shale sample in the target area.

3. The method according to claim 2, wherein The process of obtaining the standard gray-scale image set of the shale sample in the target area is as follows: Obtain the three-dimensional original gray-scale image of the shale sample in the target area according to computer tomography; Based on the three-dimensional original gray-scale image set of the shale sample in the target area, and perform gray-scale adjustment on the original gray-scale image set; Based on the gray-scale adjustment result image, perform noise reduction processing to obtain the standard gray-scale image set.

4. The method according to claim 3, wherein The process of performing gray-scale adjustment on the original gray-scale image set is as follows: Obtain the image to be processed in the three-dimensional original gray-scale image set of the shale sample in the target area; Perform weighted average on the image to be processed to obtain the gray-scale value; Based on the linear function, perform gray-scale value adjustment to obtain the gray-scale image.

5. The method according to claim 3, wherein The process of extracting the pore image based on the standard gray-scale image is as follows: Perform global thresholding on the standard gray-scale image set to obtain the pore and non-pore image set; Perform morphology on the non-pore image set to obtain the missing pores between adjacent non-pores; Perform feature extraction on the missing pores and merge them with the pores to obtain the pore image.

6. The method according to claim 5, characterized in that The process of performing fracture data acquisition on the pore image based on the fracture analysis model is as follows: Clean the data of the pore image to obtain the interference-free pore image; Input the interference-free pore image into the statistical model for analysis to obtain the statistical characteristics of the pores; Input the statistical characteristics into the geometric model to perform spatial morphology reshaping to obtain the fracture data.

7. The method according to claim 6, characterized in that, The process of performing processing on the fracture data based on the machine learning supervised model to obtain the analysis result is as follows: Clean the data of the fracture data to obtain the interference-free fracture data; Upload the interference-free fracture data to the support vector machine model for screening; According to the screening result and combined with the Cartesian coordinate system, obtain the correlation analysis result between the pores and the burial depth.

8. A shale pore analysis system that varies with burial depth, the system includes a processor, characterized in that, It also includes: The first acquisition unit, which is used to obtain the characterization information set of the shale sample in the target area; The second acquisition unit, which is used to obtain the standard gray-scale image set of the shale sample in the target area; The extraction unit, which is used to extract the pore image based on the standard gray-scale image; The third acquisition unit, which is used to perform fracture data acquisition on the pore image based on the fracture analysis model; The analysis unit, which is used to perform processing on the fracture data based on the machine learning supervised model to obtain the analysis result.

9. The system according to claim 8, wherein The processor is data-connected to the first acquisition unit, the second acquisition unit, the extraction unit, the third acquisition unit, and the analysis unit.

Images