Temperature and pressure factor judgment method for pore extinction of organic matters in shale

Through the comprehensive application of various experimental methods of shale, the problem of determining the temperature pressure factors of organic pore depletion in shale is solved, and the accurate analysis of the factors affecting organic pores is achieved, and the impact of thermal evolution on the reduction of organic matter carbonization pores is verified. .

CN118980619APending Publication Date: 2024-11-19NORTHEAST GASOLINEEUM UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411069294.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The prior art is difficult to accurately determine the temperature and pressure factors for the demise of organic matter pores in shale, which leads to the inability to effectively distinguish the impact of burial depth and thermal evolution on organic matter pores.

Method used

The cylinder sample drilled into the same core was adopted, and various experimental methods such as triaxial compression, open system thermal simulation, semi-enclosed system thermal simulation, two-dimensional domain microscopic statistics, three-dimensional digital core reconstruction and extracted organic matter nitrogen adsorption. , comprehensively determine the temperature and pressure factors for organic matter pore depletion.

Benefits of technology

Through the combined application of multiple experiments, the influence of sample substance differences was avoided, and the impact of temperature and pressure factors on organic matter pores was objectively analyzed, and the hypothesis that the degree of thermal evolution on the reduction of organic matter carbonized pores was verified, which improved the accuracy of judgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118980619A_ABST
    Figure CN118980619A_ABST
Patent Text Reader

Abstract

The invention discloses a temperature and pressure factor judgment method for extinction of organic matter pores in shale, and relates to the technical field of organic matter pores, and the method comprises the following steps: drilling and collecting a column sample of the same rock core, pretreating, preparing an experimental sample, and dividing the experimental sample into a plurality of parts; by drilling column samples of the same rock core, the influence of substance difference of the samples on experimental results is avoided, and then experimental methods such as triaxial compression, open system thermal simulation, closed system thermal simulation, two-dimensional plane domain microscopic statistics, three-dimensional digital rock core reconstruction and extraction and nitrogen adsorption combination are adopted. The temperature and pressure factors of organic matter pore extinction are comprehensively judged, and the experimental judgment method of the organic matter pore extinction factors is formed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of organic pores, and more particularly to a method for determining temperature and pressure factors of organic pore disappearance in shale. Background Art

[0002] Organic pores (abbreviated as organic pores) refer to the nanoscale pore throat system developed in the organic matter of fine-grained sedimentary rocks, which is one of the main components of the total pores of fine-grained sedimentary rocks. The difference in the development of shale reservoirs and organic pores is one of the main reasons. It is recognized that the development of organic pores is not a simple function of organic abundance, type and maturity, but is also restricted by multiple factors such as inorganic minerals and pore pressure, indicating that the formation and evolution of organic pores is complex and has strong heterogeneity; and the reduction of organic pores is a response result under deep burial and high degree of thermal evolution. However, it is still unclear whether it is caused by the deformation and reduction of organic pores due to excessive pressure at deep burial, or the reduction of organic carbonization pores due to high degree of thermal evolution, or the comprehensive response of temperature and pressure.

[0003] Therefore, how to provide a method for determining the temperature and pressure factors of the disappearance of organic pores in shale and determine the factors affecting the disappearance of organic matter through the combined application of multiple experiments is an urgent problem that technicians in this field need to solve. Summary of the invention

[0004] In view of this, the present invention provides a method for determining the temperature and pressure factors of the disappearance of organic pores in shale. By drilling cylindrical samples from the same core, the influence of material differences in the samples themselves on the experimental results is avoided. Then, triaxial compression, open system thermal simulation, closed system thermal simulation, two-dimensional surface microscope statistics, three-dimensional digital core reconstruction, extraction and nitrogen adsorption combined experimental methods are adopted to carry out a comprehensive determination of the temperature and pressure factors of the disappearance of organic pores, thereby forming an experimental determination method for the factors of the disappearance of organic pores.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme: a method for determining temperature and pressure factors of organic pore extinction in shale, comprising: drilling and collecting columnar samples of the same core, and pre-treating them to prepare experimental samples, and dividing the experimental samples into multiple portions;

[0006] The experimental samples were subjected to triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test respectively;

[0007] The pore development during the triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test was characterized by two-dimensional large-viewing-area imaging statistics, three-dimensional digital core reconstruction and organic matter nitrogen adsorption.

[0008] The data of the three experiments were comprehensively compared to analyze the effects of different factors on pore development.

[0009] Preferably, the experimental samples are subjected to a triaxial compression test, an open system thermal simulation test, and a semi-closed system thermal simulation test, respectively, including:

[0010] The prepared experimental samples were placed in a triaxial compression experimental device, and the pressure was gradually increased to simulate the pore evolution process of shale under pressure changes, and the corresponding relationship between pressure and pore size was established;

[0011] Conduct an open system thermal simulation experiment on the experimental samples, set the experimental parameters, start the heating system, control the experimental conditions, gradually increase the temperature, and establish the corresponding relationship between temperature and pore size;

[0012] A semi-closed system thermal simulation experiment was carried out on the experimental samples. By changing the pressure and temperature, the corresponding relationship between temperature, pressure and pore size was established.

[0013] Preferably, the pore development during the triaxial compression test, the open system thermal simulation test and the semi-closed system thermal simulation test is characterized by a two-dimensional large-viewing-area imaging statistical method, including:

[0014] Use large field of view imaging technology to obtain a two-dimensional panoramic image of the sample surface;

[0015] Preprocessing the two-dimensional panoramic image;

[0016] Arranging the two-dimensional panoramic images in chronological order and automatically identifying pores using an image processing algorithm;

[0017] Calculate and compare the pore parameters and porosity under different experimental conditions.

[0018] Preferably, the pore development during the triaxial compression test, the open system thermal simulation test and the semi-closed system thermal simulation test is characterized by a three-dimensional digital core reconstruction method, including:

[0019] Obtain two-dimensional image data of the sample during the experiment by X-ray computed tomography equipment;

[0020] Preprocessing the two-dimensional image data;

[0021] Perform three-dimensional reconstruction on the preprocessed two-dimensional image data to generate a three-dimensional core model;

[0022] Analyzing and identifying pore characteristics based on the three-dimensional core model;

[0023] Calculate and compare the pore parameters and porosity under different experimental conditions.

[0024] Preferably, the pore development during the triaxial compression test, the open system thermal simulation test and the semi-closed system thermal simulation test is characterized by the organic matter extraction nitrogen adsorption method, including:

[0025] In different experimental processes, sample data are extracted separately;

[0026] Use a nitrogen adsorption instrument to place the dried sample data in the sample chamber of the adsorption instrument;

[0027] Set the temperature for the nitrogen adsorption experiment;

[0028] Gradually increase the nitrogen pressure and record the nitrogen adsorption isotherm;

[0029] The specific surface area, pore volume and pore size distribution were calculated using the BET method based on the nitrogen adsorption isotherms.

[0030] Preferably, the two-dimensional panoramic images are arranged in chronological order, and an image processing algorithm is used to automatically identify pores, including:

[0031] Perform feature detection, extraction and matching on the two-dimensional panoramic image, and then perform geometric estimation,

[0032] Cutting out the organic pores in the two-dimensional panoramic image;

[0033] Divide data into different pore size gradients;

[0034] Different pore size gradients are annotated. For each pore in the image, the smallest quadrilateral surrounding the pore is found, and the position of the quadrilateral is represented by the offset of the upper left corner, lower left corner, upper right corner, and lower right corner relative to the upper left corner. The annotated data is divided into a training set and a validation set at a ratio of 9:1.

[0035] A neural network model is constructed, wherein the neural network model includes an input layer, a feature extraction layer, and a recognition layer, and the pore size is identified based on the neural network model.

[0036] Preferably, performing three-dimensional reconstruction on the preprocessed two-dimensional image data to generate a three-dimensional core model includes:

[0037] The characteristic region of each organic pore in the two-dimensional image data is marked and segmented by an image segmentation algorithm;

[0038] The pore edge model is constructed by using different characteristic regions obtained by the image segmentation algorithm, and multiple characteristic regions are merged into multiple pore edge regions;

[0039] Acquire a two-dimensional image sequence having a plurality of pore edge regions, sequentially stack the two-dimensional image sequence, extract the position coordinates of the center points of the plurality of pore edge regions in each two-dimensional image, and obtain three-dimensional pore units of the plurality of pore edge regions;

[0040] Acquire all two-dimensional image sequences in the two-dimensional image data, and establish a triangular mesh model according to the two-dimensional image sequences;

[0041] According to the voxels of the plurality of three-dimensional pore units, positions of the three-dimensional pore units are marked in the triangular mesh model.

[0042] Preferably, a two-dimensional image sequence having a plurality of pore edge regions is obtained, the two-dimensional image sequence is sequentially stacked, and the position coordinates of the center points of the plurality of pore edge regions are extracted in each two-dimensional image to obtain the three-dimensional pore units of the plurality of pore edge regions, specifically comprising:

[0043] Selecting a two-dimensional image sequence having a plurality of pore edge regions, and sequentially stacking the two-dimensional image sequence;

[0044] Extract the position coordinates of the center point of the pore edge region in each two-dimensional image;

[0045] The pore edge areas of all two-dimensional images are traversed by moving the window, and the eigenvectors between the window centers are calculated. A window of size A*B*C is set, where A, B, and C are the length, width, and height of the window, respectively. The window is traversed within the set window, and then all two-dimensional images are traversed by moving the window. The eigenvector L(i, j) between the window centers is calculated according to the following formula:

[0046]

[0047] Among them, w q is a window, q represents the sequence number of each position the window moves, I i is the position vector of the center point i of the pore edge region, I j is the position vector of the center point j of the pore edge region, μ q is the position vector of the window center, U q is the covariance matrix at the center of the window, ε is a constant parameter, I 3 is the position vector of the identity matrix;

[0048] Find V pore edge regions where the center points of multiple windows with the smallest eigenvectors are located, and superimpose multiple two-dimensional images to obtain three-dimensional pore units of the V pore edge regions;

[0049] V three-dimensional pore elements F 1 ...F k ...FV Combination, then the voxel I of the kth three-dimensional pore unit k It is expressed as:

[0050]

[0051] in, is the position of point i of the three-dimensional pore element k, Represents the position of point i of the three-dimensional pore element k opacity, M represents the total number of points i contained in the three-dimensional pore unit.

[0052] It can be seen from the above technical scheme that, compared with the prior art, the present invention discloses a method for determining the temperature and pressure factors of the disappearance of organic pores in shale, including: drilling and collecting column samples of the same core, and pre-processing to prepare experimental samples, and dividing the experimental samples into multiple parts; performing triaxial compression tests, open system thermal simulation experiments and semi-closed system thermal simulation experiments on the experimental samples respectively; characterizing the pore development during the triaxial compression experiment, open system thermal simulation experiment and semi-closed system thermal simulation experiment by two-dimensional large-viewing-area imaging statistics method, three-dimensional digital core reconstruction method and organic nitrogen adsorption method respectively; and comprehensively comparing the data of the three experiments to analyze the influence of different factors on pore development. 1. The present invention uses drill string samples from the same core to avoid the influence of material differences in the samples themselves on the analysis results; 2. The present invention uses different experiments on the same core drill string samples to simulate the influence of factors such as temperature and pressure on the disappearance of organic pores; 3. The present invention uses two-dimensional and three-dimensional microscopic statistics and organic matter adsorption after extraction methods to objectively analyze the development of organic pores under the influence of difference factors from multiple experimental statistics; 4. The present invention verifies the hypothesis of organic matter disappearance "the degree of thermal evolution is too high, and the carbonization pores of organic matter are reduced" through the combined application of multiple experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] 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 will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0054] Figure 1 A schematic flow chart of a method for determining temperature and pressure factors for the disappearance of organic pores in shale provided by the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] The embodiment of the present invention specifically discloses a method for determining the temperature and pressure factors of organic pore disappearance in shale, such as Figure 1 As shown, it includes: drilling and collecting a column sample of the same core, and pre-processing it to prepare an experimental sample, and dividing the experimental sample into multiple parts;

[0057] The experimental samples were subjected to triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test respectively;

[0058] The pore development during the triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test was characterized by two-dimensional large-viewing-area imaging statistics, three-dimensional digital core reconstruction and organic matter nitrogen adsorption.

[0059] The data of the three experiments were comprehensively compared to analyze the effects of different factors on pore development, and the differences in pore development under different experimental conditions were statistically analyzed.

[0060] Specifically, the experimental samples are subjected to a triaxial compression test, an open system thermal simulation test, and a semi-closed system thermal simulation test, respectively, including:

[0061] The prepared experimental samples are placed in a triaxial compression experimental device, and the pressure is gradually increased to simulate the pore evolution process of shale under pressure changes, and the corresponding relationship between pressure and pore size is established; the change law of the pore structure of organic matter in shale under different pressure conditions is obtained; and the influence of pressure factors on pore development is measured through triaxial compression experiments.

[0062] An open system thermal simulation experiment was conducted on the experimental samples. The experimental parameters were set, the heating system was turned on, the experimental conditions were controlled, the temperature was gradually increased, and the corresponding relationship between temperature and pore size was established. The change law of the pore structure of organic matter in shale under different temperature conditions was obtained; the influence of temperature factors on pore development was measured through an open system thermal simulation experiment.

[0063] A semi-closed system thermal simulation experiment was conducted on the experimental samples. By changing the pressure and temperature, the corresponding relationship between temperature, pressure and pore size was established. The change law of the pore structure of organic matter in shale under different temperature and pressure conditions was obtained. The influence of temperature and pressure factors on pore development was measured through a semi-closed system thermal simulation experiment to simulate the pore evolution process in a real formation environment.

[0064] Specifically, the pore development during the triaxial compression test, the open system thermal simulation test and the semi-closed system thermal simulation test is characterized by the two-dimensional large-viewing-area imaging statistical method, including:

[0065] A two-dimensional panoramic image of the sample surface is obtained by using a large field of view imaging technology; the two-dimensional panoramic image includes a first two-dimensional panoramic image, a second two-dimensional panoramic image and a third two-dimensional panoramic image; ensuring that the entire sample surface can be covered;

[0066] The sample is placed in a triaxial compression testing machine, a two-dimensional panoramic imaging device is installed, axial and lateral pressures are gradually applied, the applied stress and strain states are recorded, and a first two-dimensional panoramic image is acquired; the two-dimensional panoramic imaging device may be a camera, a high-resolution industrial camera or a scanner;

[0067] The sample is placed in an open system thermal simulation box, and a suitable temperature and pressure environment is set. During the heating process of the sample, a second two-dimensional panoramic image of the sample is regularly collected;

[0068] The sample is placed in a thermal simulation box of a semi-enclosed system, and the third and second dimensional panoramic images of the sample are collected regularly by changing the temperature and pressure data;

[0069] The porosity changes of the samples were recorded.

[0070] The two-dimensional panoramic image is preprocessed; the preprocessing includes denoising, contrast enhancement, etc., to improve the accuracy of subsequent analysis.

[0071] Arranging the two-dimensional panoramic images in chronological order and automatically identifying pores using an image processing algorithm;

[0072] Calculate and compare the pore parameters and porosity under different experimental conditions. (The porosity is the ratio of the pore area to the total area); The pore parameters include the number, area and shape parameters (such as roundness, aspect ratio, etc.) of pores.

[0073] The analysis results are presented in graphical form to facilitate comparison and discussion.

[0074] The pore development results in triaxial compression, open and semi-closed systems are compared horizontally, and their differences and commonalities are summarized.

[0075] Specifically, the pore development during the triaxial compression test, the open system thermal simulation test, and the semi-closed system thermal simulation test is characterized by the three-dimensional digital core reconstruction method, including:

[0076] Acquire two-dimensional image data of the sample during the experiment by means of an X-ray computer tomography device; the two-dimensional image data includes first two-dimensional image data, second two-dimensional image data and third two-dimensional image data; ensure that the imaging resolution can meet the analysis of pore characteristics;

[0077] The sample is placed in a triaxial compression testing machine, an X-ray computed tomography device is installed, and during the process of gradually applying axial and lateral pressure, the applied stress and strain state is recorded, and first two-dimensional image data is collected;

[0078] The sample is placed in an open system thermal simulation box, and a suitable temperature and pressure environment is set. During the heating process of the sample, the second two-dimensional image data of the sample is collected regularly;

[0079] The sample is placed in a thermal simulation box of a semi-closed system, and the third and second dimensional image data of the sample are regularly collected by changing the temperature and pressure data;

[0080] The porosity changes of the samples were recorded.

[0081] Preprocessing the two-dimensional image data includes noise removal: applying an image processing algorithm to remove noise in the scanned image; contrast enhancement: improving the contrast of the image to make the pores more obvious;

[0082] Perform three-dimensional reconstruction on the preprocessed two-dimensional image data to generate a three-dimensional core model;

[0083] Analyzing and identifying pore characteristics based on the three-dimensional core model;

[0084] Calculate and compare the pore parameters and porosity under different experimental conditions.

[0085] The analysis and identification of pore characteristics include: calculating the number, spatial distribution, pore size and shape characteristics (such as aspect ratio and circularity) of pores.

[0086] The porosity of the samples was counted and the porosity changes under different experimental conditions were analyzed.

[0087] Use visualization tools to display the 3D pore model and its distribution characteristics under different experimental conditions.

[0088] Specifically, the organic matter nitrogen adsorption method is used to characterize the pore development during the triaxial compression test, the open system thermal simulation test and the semi-closed system thermal simulation test, including:

[0089] In different experimental processes, sample data are extracted respectively, wherein the sample data includes first sample data, second sample data and third sample data;

[0090] Before the experiment begins, the sample needs to be dried to constant weight to ensure that the moisture content has minimal effect on the nitrogen adsorption results. Oven drying or vacuum drying can be used.

[0091] In the triaxial compression experiment, axial and lateral pressures were gradually applied, and the strain conditions under each stress state were recorded; at different strain stages, the first sample data in the triaxial compression experiment was extracted for subsequent nitrogen adsorption analysis.

[0092] In the open system thermal simulation experiment, the sample is heated under controlled conditions, and second sample data in the open system thermal simulation experiment is extracted at different temperature nodes for subsequent nitrogen adsorption analysis.

[0093] In the semi-closed system thermal simulation experiment, the temperature and pressure changes were recorded, and the third sample data in the semi-closed system thermal simulation experiment was extracted at different time nodes for subsequent nitrogen adsorption analysis.

[0094] The sample data after extraction should be dried again to remove the influence of the extractant and ensure the accuracy of the measured porosity.

[0095] Use a nitrogen adsorption instrument to confirm that the instrument functions properly and calibrate it. Place the dried sample data in the sample chamber of the adsorption instrument; ensure that the sample is sealed.

[0096] Set the temperature for nitrogen adsorption experiments; (usually -196 °C) to reduce gas mobility and facilitate accurate adsorption measurements.

[0097] Gradually increase the nitrogen pressure and record the nitrogen adsorption isotherm;

[0098] The specific surface area, pore volume, and pore size distribution were calculated using the Brunauer–Emmett–Teller (BET) method based on the nitrogen adsorption isotherms.

[0099] The BJH (Barrett–Joyner–Halenda) method was used to analyze the characteristics of the pore size.

[0100] The pore size distribution, porosity and other characteristics are compared with the sample data under different experimental conditions to analyze the pattern of pore development.

[0101] The changes in pore characteristics under different experimental conditions are shown through visual charts.

[0102] Specifically, the two-dimensional panoramic images are arranged in chronological order, and the pores are automatically identified using an image processing algorithm, including:

[0103] Performing feature detection, extraction and matching on the two-dimensional panoramic image, and then performing geometric estimation;

[0104] In feature detection and extraction, it is necessary to find the edges of organic pores or points with pore features. After that, the extracted features need to be matched. Since the most significant feature points are located in the overlapping area, matching the features with the reference image will display the adjusted image as the reference image. The purpose of this step is to compare the most significant features of the image with another image. If there is a match between the features of the input images, the matched feature locations will be identified as a matching pair.

[0105] In order to improve the operation speed of a large number of collected images, the SURF feature detector is used. The SURF algorithm is based on Haar wavelet and Hessian matrix, which can quickly detect key points in the image to accelerate the detection process and reduce the computational complexity. The operation process is as follows: First, the scale space pyramid of the image is calculated by applying a Gaussian filter, and then the Hessian matrix is ​​used to detect the extreme points in the scale space. These extreme points correspond to the corners, edges and spots in the image. The gradient direction of the pixels around each key point is calculated and the gradient direction histogram is constructed to select stable key points. The area near the key point is divided into sub-regions, and the gradient direction histogram in each sub-region is calculated. The gradient direction histograms of all sub-regions are connected to form a feature descriptor. For each feature descriptor, the best matching feature is found among all other feature descriptors, and the best matching feature point is selected according to the similarity threshold.

[0106] Specifically, the feature matching includes: matching the features with the reference pore image, displaying the adjusted two-dimensional panoramic image as the reference pore image, comparing the most prominent features of the two-dimensional panoramic image with the reference pore image, and if there is a match between the features of the input image, the matched feature positions are identified as a matching pair;

[0107] The geometric transformation between each matching pair is calculated. The estimated geometric transformation is applied to align each image. The projected coordinates u of a point on the rotated image are expressed as:

[0108] u=[K][Rt]X;

[0109] Where K is the calibration matrix, R is the rotation matrix, t is the translation vector, and X is the world coordinate;

[0110] Matching pair coordinates (u 1 ,u 2 ) is written in the following form:

[0111] u 1 =K 1 t 1 X,u 2 =K 2 t 2 X;

[0112] Among them, K 1 and K 2 are the two components of K, t 1 and t 2 are the two components of t, X 1 and X 2 are the two components of X;

[0113] The coordinate transformation formula is:

[0114] u 2 =Tu 1 ;

[0115] Where T is the coordinate transformation matrix,

[0116] Applying the formula for projection coordinates to all feature points yields the pixel conversion equation between images:

[0117]

[0118] in, represents the coordinates of the i-th pixel point in the n-th image after coordinate transformation, T i represents the coordinate transformation matrix of pixel i, Represents the pixel coordinates of the n-1th coordinate transformation in the nth picture;

[0119] The geometric transformation equations are calculated by looping over all matching pairs.

[0120] Cutting out the organic pores in the two-dimensional panoramic image;

[0121] Divide data into different pore size gradients;

[0122] Different pore size gradients are annotated. For each pore in the image, the smallest quadrilateral surrounding the pore is found, and the position of the quadrilateral is represented by the offset of the upper left corner, lower left corner, upper right corner, and lower right corner relative to the upper left corner. The annotated data is divided into a training set and a validation set at a ratio of 9:1.

[0123] A neural network model is constructed, wherein the neural network model includes an input layer, a feature extraction layer, and a recognition layer, and the pore size is identified based on the neural network model.

[0124] The embodiment of the present invention can provide a clear distribution of pore sizes. Through the neural network recognition technology, the embodiment of the present invention has higher accuracy and generalization ability in identifying and classifying pore sizes. The entire processing process is highly automated, which improves the analysis speed and accuracy.

[0125] Specifically, the neural network model includes: the input layer uses 32 3×3 convolution kernels, uses 0 to pad the image, and adjusts the image size to 416×416×32, then uses 64 3×3 convolution kernels, uses 0 to pad the image, and sets the step size to 2 to adjust the image size to 208×208×64;

[0126] The feature extraction layer further extracts feature information at different scales of the image and consists of five residual layers;

[0127] In the five residual layers, the first layer first uses 32 1×1 convolution kernels to adjust the number of image channels to 32, then uses 64 3×3 convolution kernels to extract feature information and calculate the residual value, and finally uses 256 3×3 convolution kernels with a step size of 2 to downsample the image to half of the original size, and the image size is adjusted to 104×104×128;

[0128] The second layer is composed of two identical residual units. The residual unit first uses 64 1×1 convolution kernels to adjust the number of image channels to 64, then uses 128 3×3 convolution kernels to convolve the image and calculate the residual value, and then uses 256 3×3 convolution kernels with a step size of 2 to convolve the image, downsampling the image to half of the original size, and adjusting the image size to 52×52×256;

[0129] The third layer is first composed of eight identical residual units. The residual unit first uses 128 1×1 convolution kernels to adjust the number of image channels to 128, then uses 256 3×3 convolution kernels to convolve the image and calculate the residual value, and then uses 512 3×3 convolution kernels with a step size of 2 to convolve the image, downsampling the image to half of the original size, and the image size is adjusted to 26×26×512. The output of the third layer before downsampling is saved as F1, and its size is 52×52×256;

[0130] The fourth layer is first composed of eight identical residual units, which first use 256 1×1 convolution kernels to adjust the number of image channels to 256, then use 512 3×3 convolution kernels to convolve the image and calculate the residual value, and then use 1024 3×3 convolution kernels with a step size of 2 to convolve the image, downsample the image to half of the original, and adjust the image size to 13×13×1024. The output of the fourth layer before downsampling is saved as F2, with a size of 26×26×512;

[0131] The fifth layer consists of four identical residual units, which first use 512 1×1 convolution kernels to adjust the number of image channels to 512, and then use 1024 3×3 convolution kernels to convolve the image and calculate the residual value;

[0132] The recognition layer consists of three progressive prediction structures. First, the data output by the feature extraction layer is saved as I1. Then I1 is upsampled to 26×26. Then, 512 1×1 convolution kernels are used to adjust its channel so that it is superimposed with F2 and saved as I2. Then, I2 is upsampled to 52×52. Then, 256 1×1 convolution kernels are used to adjust its channel so that it is superimposed with F1 and saved as I3.

[0133] 1024, 512, and 256 3×3 convolution kernels are used to convolve I1, I2, and I3 respectively, and then a 1×1 convolution kernel equal to the total number of classifications is used to adjust the number of image channels to the number of divided pore size gradients, which is the recognition result of the pore size.

[0134] Different pore size gradient data are divided, including:

[0135] Smaller pores, as the first gradient;

[0136] general pores, as a second gradient;

[0137] larger pores, acting as a third gradient;

[0138] How to divide the pores into smaller, normal or larger ones can be adjusted according to the actual size.

[0139] Specifically, the preprocessed two-dimensional image data is subjected to three-dimensional reconstruction to generate a three-dimensional core model, including:

[0140] The characteristic region of each organic pore in the two-dimensional image data is marked and segmented by an image segmentation algorithm;

[0141] The pore edge model is constructed by using different characteristic regions obtained by the image segmentation algorithm, and multiple characteristic regions are merged into multiple pore edge regions;

[0142] Specifically, the pore edge model consists of two parts: the pore edge c 1 、c 2 The pore edge model E is expressed by the following formula:

[0143]

[0144] Where C is the pore edge area, |C| is the pore edge curve, and (x, y) is the pixel I 0 The coordinate position of 1 ,γ 2 They represent the area parameters of the inner area in the pore edge and the outer area out of the pore edge, μ is the weight parameter, in(C'), in(C 0) represent the starting point and end point of the integration of the region within the pore edge, out(C'), out(C 0 ) represent the starting point and end point of the integration outside the pore edge, respectively;

[0145] Acquire a two-dimensional image sequence having a plurality of pore edge regions, sequentially stack the two-dimensional image sequence, extract the position coordinates of the center points of the plurality of pore edge regions in each two-dimensional image, and obtain three-dimensional pore units of the plurality of pore edge regions;

[0146] Acquire all two-dimensional image sequences in the two-dimensional image data, and establish a triangular mesh model according to the two-dimensional image sequences;

[0147] According to the voxels of the plurality of three-dimensional pore units, positions of the three-dimensional pore units are marked in the triangular mesh model.

[0148] The embodiments of the present invention can display three-dimensional pore units in a three-dimensional structure in a more realistic manner, thereby improving the accuracy of marking three-dimensional pores in a three-dimensional model.

[0149] Specifically, a two-dimensional image sequence having a plurality of pore edge regions is obtained, the two-dimensional image sequence is sequentially stacked, and the position coordinates of the center points of the plurality of pore edge regions are extracted in each two-dimensional image to obtain the three-dimensional pore units of the plurality of pore edge regions, specifically including:

[0150] Selecting a two-dimensional image sequence having a plurality of pore edge regions, and sequentially stacking the two-dimensional image sequence;

[0151] Extract the position coordinates of the center point of the pore edge region in each two-dimensional image;

[0152] The pore edge areas of all two-dimensional images are traversed by moving the window, and the eigenvectors between the window centers are calculated. A window of size A*B*C is set, where A, B, and C are the length, width, and height of the window, respectively. The window is traversed within the set window, and then all two-dimensional images are traversed by moving the window. The eigenvector L(i, j) between the window centers is calculated according to the following formula:

[0153]

[0154] Among them, w q is a window, q represents the sequence number of each position the window moves, I i is the position vector of the center point i of the pore edge region, I j is the position vector of the center point j of the pore edge region, μ q is the position vector of the window center, U q is the covariance matrix at the center of the window, ε is a constant parameter, I 3is the position vector of the identity matrix;

[0155] Find V pore edge regions where the center points of multiple windows with the smallest eigenvectors are located, and superimpose multiple two-dimensional images to obtain three-dimensional pore units of the V pore edge regions;

[0156] V three-dimensional pore elements F 1 ...F k ...F V Combination, then the voxel I of the kth three-dimensional pore unit k It is expressed as:

[0157]

[0158] in, is the position of point i of the three-dimensional pore element k, Represents the position of point i of the three-dimensional pore element k opacity, M represents the total number of points i contained in the three-dimensional pore unit.

[0159] Specifically, all two-dimensional image sequences in the two-dimensional image data are obtained, and a triangular mesh model is established according to the two-dimensional image sequences, including:

[0160] Obtain all 2D image sequences, determine the position of each 2D image, and generate a grid-aligned 3D array;

[0161] Performing data processing on the obtained three-dimensional array to obtain a binary three-dimensional array, performing three-dimensional mesh modeling based on the obtained binary three-dimensional array and saving the model as a triangular mesh model file;

[0162] Load the triangular mesh model file into the 3D drawing software to visualize the triangular mesh model of all 2D image sequences.

[0163] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0164] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0165] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining the temperature and pressure factors of organic pore disappearance in shale, characterized in that: include: Drilling and collecting a column sample from the same core, pre-processing it, preparing an experimental sample, and dividing the experimental sample into multiple portions; The experimental samples were subjected to triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test respectively; The pore development during the triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test was characterized by two-dimensional large-viewing-area imaging statistics, three-dimensional digital core reconstruction and organic matter nitrogen adsorption. The data of the three experiments were comprehensively compared to analyze the effects of different factors on pore development.

2. The method for determining temperature and pressure factors of organic pore disappearance in shale according to claim 1, characterized in that: The experimental samples are subjected to a triaxial compression test, an open system thermal simulation test, and a semi-closed system thermal simulation test, respectively, including: The prepared experimental samples were placed in a triaxial compression experimental device, and the pressure was gradually increased to simulate the pore evolution process of shale under pressure changes, and the corresponding relationship between pressure and pore size was established; Conduct an open system thermal simulation experiment on the experimental samples, set the experimental parameters, start the heating system, control the experimental conditions, gradually increase the temperature, and establish the corresponding relationship between temperature and pore size; A semi-closed system thermal simulation experiment was carried out on the experimental samples. By changing the pressure and temperature, the corresponding relationship between temperature, pressure and pore size was established.

3. The method for determining the temperature and pressure factors of organic pore disappearance in shale according to claim 2, characterized in that: The pore development during the triaxial compression test, the open system thermal simulation test and the semi-closed system thermal simulation test is characterized by the two-dimensional large-viewing-area imaging statistical method, including: Use large field of view imaging technology to obtain a two-dimensional panoramic image of the sample surface; Preprocessing the two-dimensional panoramic image; Arranging the two-dimensional panoramic images in chronological order and automatically identifying pores using an image processing algorithm; Calculate and compare the pore parameters and porosity under different experimental conditions.

4. The method for determining temperature and pressure factors of organic pore disappearance in shale according to claim 2, characterized in that: The pore development during triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test is characterized by three-dimensional digital core reconstruction method, including: Obtain two-dimensional image data of the sample during the experiment by X-ray computed tomography equipment; Preprocessing the two-dimensional image data; Perform three-dimensional reconstruction on the preprocessed two-dimensional image data to generate a three-dimensional core model; Analyzing and identifying pore characteristics based on the three-dimensional core model; Calculate and compare the pore parameters and porosity under different experimental conditions.

5. The method for determining the temperature and pressure factors of organic pore disappearance in shale according to claim 2, characterized in that: The pore development during the triaxial compression test, open system thermal simulation test and semi-closed system thermal simulation test was characterized by the organic matter extraction nitrogen adsorption method, including: In different experimental processes, sample data are extracted separately; Use a nitrogen adsorption instrument to place the dried sample data in the sample chamber of the adsorption instrument; Set the temperature for the nitrogen adsorption experiment; Gradually increase the nitrogen pressure and record the nitrogen adsorption isotherm; The specific surface area, pore volume and pore size distribution were calculated using the BET method based on the nitrogen adsorption isotherms.

6. The method for determining temperature and pressure factors of organic pore disappearance in shale according to claim 3, characterized in that: The two-dimensional panoramic images are arranged in chronological order, and an image processing algorithm is used to automatically identify pores, including: Perform feature detection, extraction and matching on the two-dimensional panoramic image, and then perform geometric estimation, Cutting out the organic pores in the two-dimensional panoramic image; Divide data into different pore size gradients; Different pore size gradients are annotated. For each pore in the image, the smallest quadrilateral surrounding the pore is found, and the position of the quadrilateral is represented by the offset of the upper left corner, lower left corner, upper right corner, and lower right corner relative to the upper left corner. The annotated data is divided into a training set and a validation set at a ratio of 9:

1. A neural network model is constructed, wherein the neural network model includes an input layer, a feature extraction layer, and a recognition layer, and the pore size is identified based on the neural network model.

7. The method for determining temperature and pressure factors of organic pore disappearance in shale according to claim 4, characterized in that: The pre-processed two-dimensional image data is reconstructed into three dimensions to generate a three-dimensional core model, including: The characteristic region of each organic pore in the two-dimensional image data is marked and segmented by an image segmentation algorithm; The pore edge model is constructed by using different characteristic regions obtained by the image segmentation algorithm, and multiple characteristic regions are merged into multiple pore edge regions; Acquire a two-dimensional image sequence having a plurality of pore edge regions, sequentially stack the two-dimensional image sequence, extract the position coordinates of the center points of the plurality of pore edge regions in each two-dimensional image, and obtain three-dimensional pore units of the plurality of pore edge regions; Acquire all two-dimensional image sequences in the two-dimensional image data, and establish a triangular mesh model according to the two-dimensional image sequences; According to the voxels of the plurality of three-dimensional pore units, positions of the three-dimensional pore units are marked in the triangular mesh model.

8. The method for determining temperature and pressure factors of organic pore disappearance in shale according to claim 7, characterized in that: Acquiring a two-dimensional image sequence having a plurality of pore edge regions, sequentially stacking the two-dimensional image sequence, extracting position coordinates of center points of the plurality of pore edge regions in each two-dimensional image, and obtaining three-dimensional pore units of the plurality of pore edge regions, specifically includes: Selecting a two-dimensional image sequence having a plurality of pore edge regions, and sequentially stacking the two-dimensional image sequence; Extract the position coordinates of the center point of the pore edge region in each two-dimensional image; The pore edge areas of all two-dimensional images are traversed by moving the window, and the eigenvectors between the window centers are calculated. A window of size A*B*C is set, where A, B, and C are the length, width, and height of the window, respectively. The window is traversed within the set window, and then all two-dimensional images are traversed by moving the window. The eigenvector L(i, j) between the window centers is calculated according to the following formula: Among them, w q is a window, q represents the sequence number of each position the window moves, I i is the position vector of the center point i of the pore edge region, I j is the position vector of the center point j of the pore edge region, μ q is the position vector of the window center, U q is the covariance matrix of the window center, ε is a constant parameter, and I3 is the position vector of the identity matrix; Find V pore edge regions where the center points of multiple windows with the smallest eigenvectors are located, and superimpose multiple two-dimensional images to obtain three-dimensional pore units of the V pore edge regions; V three-dimensional pore elements F1...F k ...F V Combination, then the voxel I of the kth three-dimensional pore unit k It is expressed as: Among them, F i k is the position of point i of the three-dimensional pore element k, The position F of point i in the three-dimensional pore element k is represented by i k opacity, M represents the total number of points i contained in the three-dimensional pore unit.