Shale reservoir pore throat structure parameter determination method, device and system and storage medium
Through micro CT scanning and image denoising network technology, the problem of poor accuracy in pore throat structure segmentation and parameter calculation of shale reservoirs is solved, and the fine characterization and parameter acquisition of shale oil microstructure is realized, which improves the oil and gas mining technology accuracy.
Patent Information
- Application Number
- CN202411256042.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-12-27
AI Technical Summary
In the prior art, the accuracy of segmentation and parameter calculation of pore throat structures in unconventional shale reservoirs is poor, resulting in a lack of understanding of the micro-movement effect of shale oil and the complexity of pore throat structure.
Micro CT scanning technology is used to obtain the two-dimensional grayscale image of the core, and perform binarization and image denoising network processing. Through threshold segmentation and digital core construction, the pore throat structure is carefully portrayed, and the characteristic parameters of the pore throat size structure are obtained.
The precise segmentation and parameter calculation of the pore throat structure of unconventional shale reservoirs has been achieved, the understanding of the micro-enrichment mechanism of shale oil has been improved, and more accurate technical guidance has been provided on oil and gas mining.
Smart Images
Figure CN119198805A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of unconventional oil and gas development, and in particular relates to a method and device, a system and a storage medium for determining pore throat structure parameters of a shale reservoir. Background Art
[0002] Unconventional shale reservoirs are mostly developed with nano-scale pore throats, which are characterized by small size, complex microstructure, and strong heterogeneity, which determines the storage and seepage of unconventional shale reservoirs and ultimately affects the production capacity of the reservoir. From the perspective of mining, due to the complex pore throat structure, large seepage resistance, and damage from external liquids, the initial production decline is fast and the difference in production after compression is large; from the perspective of resources, shale oil is an important component of unconventional oil and gas resources, and its resource potential is huge. It is an important strategic oil replacement resource in China in the future and is of great significance to ensuring national energy security.
[0003] At present, there is little information about the effect of pore throat structure on the micro-scale seepage characteristics of unconventional shale oil, and traditional numerical simulation methods are not suitable for micro-scale research. The research on unconventional shale oil should start from the actual temperature, pressure and reservoir pore throat characteristics. The micro-migration effect of oil in unconventional shale reservoirs is closely related to pore throats. Its micro-migration effect will cause the properties of shale in the microscopic pore space to differentiate. However, it is difficult to accurately characterize the reservoir due to its small pore radius and complex pore throat structure, resulting in a lack of understanding of the microscopic enrichment mechanism of unconventional shales. Summary of the invention
[0004] The technical problem to be solved by the present invention is to provide a method and device, system and storage medium for determining the pore throat structure parameters of a shale reservoir, which can solve the problem of poor accuracy in pore throat segmentation and parameter calculation of unconventional shale reservoirs in the prior art.
[0005] To achieve the above object, the present invention adopts the following technical solution:
[0006] A method for determining pore throat structure parameters of a shale reservoir, comprising:
[0007] Step S1, obtaining a core of an unconventional shale reservoir;
[0008] Step S2, using micro-CT scanning technology to slice and scan the core to obtain a two-dimensional grayscale image of the core;
[0009] Step S3, binarizing the obtained two-dimensional grayscale image to obtain a binary image of the core;
[0010] Step S4, using an image denoising network to denoise the image;
[0011] Step S5, performing threshold segmentation on the denoised image to distinguish the difference in grayscale values between the pore space and the rock skeleton;
[0012] Step S6, establishing a digital core for visually observing the spatial structure of pores inside the rock;
[0013] Step S7: pore throat segmentation can be performed based on the digital core to obtain core pore throat size structure characteristic parameters.
[0014] Preferably, step S1 comprises: cutting a core from a rock of unconventional shale and making the core into a core with a height of 15 cm and a diameter of 10 cm.
[0015] Preferably, the image denoising network includes: an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure; wherein the image denoising network structure is used to decompose the binary data into the original data of the image to obtain the high-frequency and low-frequency information in the image; the image transformation structure is used to decompose the original image Y into a combination of a low-frequency sub-band (L1), a horizontal high-frequency sub-band (L2), a vertical high-frequency sub-band (L3), and a diagonal high-frequency sub-band (L4); the image feature enhancement structure is used to enhance the global and local high- and low-frequency key feature information; the image decomposition structure is used to enhance the texture in the image and reduce the noise after denoising; the image feature reconstruction structure is used to reconstruct the decomposed high-frequency and low-frequency information.
[0016] Preferably, step S6 includes: stacking the two-dimensional grayscale images after threshold segmentation from bottom to top to reconstruct the digital core for observing the real three-dimensional image of pores inside the rock.
[0017] The present invention also provides a device for determining pore throat structure parameters of a shale reservoir, comprising:
[0018] an acquisition module for acquiring cores from unconventional shale reservoirs;
[0019] A scanning module is used to slice and scan the core using micro-CT scanning technology to obtain a two-dimensional grayscale image of the core;
[0020] A binarization processing module is used to perform binarization processing on the obtained two-dimensional grayscale image to obtain a binary image of the core;
[0021] A denoising module, used to denoise the image using an image denoising network;
[0022] The segmentation module is used to perform threshold segmentation on the denoised image to distinguish the difference in grayscale values between the pore space and the rock skeleton;
[0023] Building module, creating digital cores for visually observing the spatial structure of pores inside rocks;
[0024] The determination module is used to segment the pore throat according to the digital core and obtain the core pore throat size and structural characteristic parameters.
[0025] Preferably, the acquisition module cuts the core from the unconventional shale rock and makes it into a core with a height of 15 cm and a diameter of 10 cm.
[0026] Preferably, the image denoising network includes: an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure; wherein the image denoising network structure is used to decompose the binary data into the original data of the image to obtain the high-frequency and low-frequency information in the image; the image transformation structure is used to decompose the original image Y into a combination of a low-frequency sub-band (L1), a horizontal high-frequency sub-band (L2), a vertical high-frequency sub-band (L3), and a diagonal high-frequency sub-band (L4); the image feature enhancement structure is used to enhance the global and local high- and low-frequency key feature information; the image decomposition structure is used to enhance the texture in the image and reduce the noise after denoising; the image feature reconstruction structure is used to reconstruct the decomposed high-frequency and low-frequency information.
[0027] Preferably, the construction module superimposes the two-dimensional grayscale images after threshold segmentation from bottom to top to reconstruct the digital core for observing the real three-dimensional image of pores inside the rock.
[0028] The present invention also provides a shale reservoir pore throat structure parameter determination system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a shale reservoir pore throat structure parameter determination method when executed by the processor.
[0029] The present invention also provides a storage medium, on which a computer program is stored, and when the computer program is run, the method for determining the pore throat structure parameters of a shale reservoir is executed.
[0030] The present invention obtains a binary image of the rock, and processes the binary image using an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure of an image denoising network to obtain a denoised image, and then uses digital core technology to segment the pores and throats more intuitively, accurately, and conveniently. The present invention avoids using logging data, drilling data, and production dynamic data as the core for pore and throat segmentation and calculation evaluation of shale digital core technology, fully considers the current geological conditions of the reservoir, and determines accurate judgments on pore and throat segmentation and calculation of shale reservoir digital core technology, thereby providing technical guidance for oil and gas production technology. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] 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.
[0032] Figure 1 It is a schematic diagram of a flow chart of a method for determining pore throat structure parameters of a shale reservoir according to an embodiment of the present invention;
[0033] Figure 2 This is a schematic diagram of the neural network structure of an embodiment of the present invention;
[0034] Figure 3 This is a schematic diagram of the image denoising network structure according to an embodiment of the present invention;
[0035] Figure 4 Schematic diagram of image transformation structure according to an embodiment of the present invention;
[0036] Figure 5 This is a schematic diagram of an image feature enhancement structure according to an embodiment of the present invention;
[0037] Figure 6 This is a schematic diagram of an image decomposition structure according to an embodiment of the present invention;
[0038] Figure 7 Schematic diagram of the image feature reconstruction structure according to an embodiment of the present invention. DETAILED DESCRIPTION
[0039] 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.
[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0041] Embodiment 1:
[0042] like Figure 1 As shown, an embodiment of the present invention provides a method for determining pore throat structure parameters of a shale reservoir, comprising the following steps:
[0043] Step 1: Obtain the core of the unconventional shale reservoir and cut it into cores with a height of 15 cm and a diameter of 10 cm.
[0044] Step 2: Use micro-CT scanning technology to slice and scan the core to obtain a two-dimensional grayscale image of the core, and binarize the obtained two-dimensional grayscale image to obtain a binary image of the core.
[0045] Step 3: Use the obtained binary image of the core to perform image denoising on the image using the image denoising network.
[0046] Step 4: Use the denoised image to perform threshold segmentation to distinguish the difference in grayscale values between the pore space and the rock skeleton.
[0047] Step 5: Create a digital core to visually observe the spatial structure of the pores inside the rock.
[0048] Step 6: Pore throat segmentation: divide the pore structure into some units with different functions to obtain important structural characteristic parameters such as core pore throat size.
[0049] like Figure 2 As shown, in the embodiment provided by the present invention, the image denoising network of step three includes an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure.
[0050] In the embodiment provided by the present invention, in step three, the core is first sliced and scanned using micro-CT scanning technology to obtain a two-dimensional grayscale image of the core; the obtained two-dimensional grayscale image is binarized to obtain a binary image of the core, and finally image denoising is performed.
[0051] In the embodiment provided by the present invention, the image denoising network combines the strong learning ability of CNN, and the structure of this network adopts encoder-subnetwork-decoder.
[0052] like Figure 3 As shown in the figure, the image denoising network structure is used to restore the original data of the noisy image to obtain the high frequency (CD) and low frequency (CA) information in the image. In this network, the Haar wavelet is used as the wavelet basis to first process the row direction, and the data of each row is divided into low frequency and high frequency, and then the column direction is processed. In the column direction processing, Haar is also used as the wavelet basis to divide the data of each column into low frequency and high frequency. After decomposition according to the data, the low frequency and high frequency are extracted from the information obtained after decomposition.
[0053] like Figure 4 As shown in the figure, the image transformation structure in the image denoising network is used to decompose the original image Y into a combination of low-frequency sub-bands (L1), horizontal high-frequency sub-bands (L2), vertical high-frequency sub-bands (L3) and diagonal high-frequency sub-bands (L4) to avoid information loss and retain image details and texture information. In this network, the high-frequency and low-frequency undecomposed information obtained by the image denoising network structure is decomposed.
[0054] like Figure 5 As shown in the figure, the image feature enhancement structure aims to solve the problem of poor denoising effect caused by directly mixing high- and low-frequency information. An image feature enhancement structure is added to enhance global and local high- and low-frequency key feature information and suppress the influence of noise. This network is similar to a four-layer residual dense block. Each layer above and below can output to the next layer. In this module, convolution kernels are used to obtain more detailed information and have a good protection effect on information.
[0055] like Figure 6 As shown in the figure, in order to prevent the introduction of noise into the image during image reconstruction, the image decomposition structure uses haar as the wavelet basis, and the high-frequency (CD) and low-frequency (CA) information obtained after decomposition are used to enhance the detailed texture part of the image and reduce the noise part after denoising. This network inserts the low-frequency and high-frequency information after decomposition into the wavelet network to construct low-frequency and high-frequency low-frequency subband components (L1′), horizontal high-frequency subband components (L2′), vertical high-frequency subband components (L3′) and diagonal high-frequency subband components (L4′). The last four components reconstruct new feature information.
[0056] like Figure 7 As shown, the image feature reconstruction stage is to reconstruct the decomposed high-frequency and low-frequency information again. The purpose is to enhance the image detail texture and reduce the noise part after denoising before reconstruction, so that a clear image can be better obtained at this stage. In this network, the low-frequency and high-frequency information decomposed from the image are first obtained to obtain low-frequency subband components (L1′), horizontal high-frequency subband components (L2′), vertical high-frequency subband components (L3′) and diagonal high-frequency subband components (L4′), and then new components are constructed from them. The different features of the new components are reconstructed to obtain an image with enhanced image detail texture and reduced denoising.
[0057] In the designed image denoising network, the main task is to denoise the image and protect the edge texture information and detail features of the image, so as to improve the accuracy of subsequent quantitative analysis and better observe the information of core pores and microcracks as well as the details of the microscopic pore structure of shale oil reservoirs.
[0058] Threshold segmentation can distinguish the pore space from the rock skeleton based on the difference in grayscale values between the two. By continuously adjusting the threshold, when the selected threshold just covers the black area, the part below the threshold is considered to be the pore space, and the area above the threshold is considered to be the rock skeleton.
[0059] When establishing the digital core, the images after threshold segmentation are superimposed from bottom to top to construct the digital core and reconstruct the real three-dimensional image of the pores inside the core. This allows for intuitive observation of the spatial structure of the pores inside the core, and provides a good understanding of the porosity and heterogeneity of unconventional shale oil reservoirs at the micron scale, as well as a clear understanding of the pore space performance, connectivity, and residual intergranular pores in some areas.
[0060] Pore throat segmentation first divides the pore structure into some units with different functions. The throat represents the narrow and long pore space, and the pore body represents the relatively large pore space at the junction of the throat. The pore body and throat are set to some ideal geometric shapes, and the central axis algorithm and the maximum sphere algorithm are used to perform quantitative analysis of the geometric parameters, and finally the important structural characteristic parameters such as the core pore throat size are obtained.
[0061] Embodiment 2:
[0062] The embodiment of the present invention further provides a device for determining pore throat structure parameters of a shale reservoir, comprising:
[0063] an acquisition module for acquiring cores from unconventional shale reservoirs;
[0064] A scanning module is used to slice and scan the core using micro-CT scanning technology to obtain a two-dimensional grayscale image of the core;
[0065] A binarization processing module is used to perform binarization processing on the obtained two-dimensional grayscale image to obtain a binary image of the core;
[0066] A denoising module, used to denoise the image using an image denoising network;
[0067] The segmentation module is used to perform threshold segmentation on the denoised image to distinguish the difference in grayscale values between the pore space and the rock skeleton;
[0068] Building module, creating digital cores for visually observing the spatial structure of pores inside rocks;
[0069] The determination module is used to segment the pore throat according to the digital core and obtain the core pore throat size and structural characteristic parameters.
[0070] As an implementation method of the embodiment of the present invention, the acquisition module cuts the core from the unconventional shale rock and makes it into a core with a height of 15 cm and a diameter of 10 cm.
[0071] As an implementation mode of an embodiment of the present invention, an image denoising network includes: an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure; wherein the image denoising network structure is used to decompose the binary data into the original data of the image to obtain the high-frequency and low-frequency information in the image; the image transformation structure is used to decompose the original image Y into a combination of a low-frequency sub-band (L1), a horizontal high-frequency sub-band (L2), a vertical high-frequency sub-band (L3) and a diagonal high-frequency sub-band (L4); the image feature enhancement structure is used to enhance the global and local high- and low-frequency key feature information; the image decomposition structure is used to enhance the texture in the image and reduce the noise after denoising; the image feature reconstruction structure is used to reconstruct the decomposed high-frequency and low-frequency information.
[0072] As an implementation method of the embodiment of the present invention, the construction module superimposes the two-dimensional grayscale images after threshold segmentation from bottom to top to reconstruct the digital core for observing the real three-dimensional image of pores inside the rock.
[0073] Embodiment 3:
[0074] An embodiment of the present invention also provides a shale reservoir pore throat structure parameter determination system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a shale reservoir pore throat structure parameter determination method when executed by the processor.
[0075] Embodiment 4:
[0076] The embodiment of the present invention further provides a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is run, the method for determining the pore throat structure parameters of a shale reservoir is executed.
[0077] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.
Claims
1. A method for determining pore throat structure parameters of a shale reservoir, characterized in that: include: Step S1, obtaining a core of an unconventional shale reservoir; Step S2, using micro-CT scanning technology to slice and scan the core to obtain a two-dimensional grayscale image of the core; Step S3, binarizing the obtained two-dimensional grayscale image to obtain a binary image of the core; Step S4, using an image denoising network to denoise the image; Step S5, performing threshold segmentation on the denoised image to distinguish the difference in grayscale values between the pore space and the rock skeleton; Step S6, establishing a digital core for visually observing the spatial structure of pores inside the rock; Step S7: pore throat segmentation can be performed based on the digital core to obtain core pore throat size structure characteristic parameters.
2. The method for determining pore throat structure parameters of a shale reservoir according to claim 1, characterized in that: Step S1 includes: cutting a core from a rock of unconventional shale and making it into a core with a height of 15 cm and a diameter of 10 cm.
3. The method for determining pore throat structure parameters of a shale reservoir according to claim 2, characterized in that: It is characterized in that The image denoising network includes: an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure; wherein the image denoising network structure is used to decompose the binary data into the original data of the image, so as to obtain the high-frequency and low-frequency information in the image; the image transformation structure is used to decompose the original image Y into a combination of a low-frequency sub-band (L1), a horizontal high-frequency sub-band (L2), a vertical high-frequency sub-band (L3), and a diagonal high-frequency sub-band (L4); the image feature enhancement structure is used to enhance the global and local high- and low-frequency key feature information; the image decomposition structure is used to enhance the texture in the image and reduce the noise after denoising; the image feature reconstruction structure is used to reconstruct the decomposed high-frequency and low-frequency information.
4. The method for determining pore throat structure parameters of a shale reservoir according to claim 3, characterized in that: Step S6 includes: stacking the two-dimensional grayscale images after threshold segmentation from bottom to top to reconstruct the digital core for observing the real three-dimensional image of pores inside the rock.
5. A device for determining pore throat structure parameters of a shale reservoir, characterized in that: include: an acquisition module for acquiring cores from unconventional shale reservoirs; A scanning module is used to slice and scan the core using micro-CT scanning technology to obtain a two-dimensional grayscale image of the core; A binarization processing module is used to perform binarization processing on the obtained two-dimensional grayscale image to obtain a binary image of the core; A denoising module, used to denoise the image using an image denoising network; The segmentation module is used to perform threshold segmentation on the denoised image to distinguish the difference in grayscale values between the pore space and the rock skeleton; Building module, creating digital cores for visually observing the spatial structure of pores inside rocks; The determination module is used to segment the pore throat according to the digital core and obtain the core pore throat size and structural characteristic parameters.
6. The device for determining pore throat structure parameters of a shale reservoir according to claim 5, characterized in that: The acquisition module cuts the core from the unconventional shale rock and makes it into a core with a height of 15 cm and a diameter of 10 cm.
7. The device for determining pore throat structure parameters of a shale reservoir according to claim 6, characterized in that: It is characterized in that The image denoising network includes: an image denoising network structure, an image transformation structure, an image feature enhancement structure, an image decomposition structure, and an image feature reconstruction structure; wherein the image denoising network structure is used to decompose the binary data into the original data of the image, so as to obtain the high-frequency and low-frequency information in the image; the image transformation structure is used to decompose the original image Y into a combination of a low-frequency sub-band (L1), a horizontal high-frequency sub-band (L2), a vertical high-frequency sub-band (L3), and a diagonal high-frequency sub-band (L4); the image feature enhancement structure is used to enhance the global and local high- and low-frequency key feature information; the image decomposition structure is used to enhance the texture in the image and reduce the noise after denoising; the image feature reconstruction structure is used to reconstruct the decomposed high-frequency and low-frequency information.
8. The device for determining pore throat structure parameters of a shale reservoir according to claim 7, characterized in that: The construction module superimposes the two-dimensional grayscale images after threshold segmentation from bottom to top to reconstruct the digital core, which is used to observe the real three-dimensional image of the pores inside the rock.
9. A system for determining pore throat structure parameters of shale reservoirs, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the method for determining the pore throat structure parameters of a shale reservoir as described in any one of claims 1 to 4 is executed.
10. A storage medium, characterized in that: The storage medium stores a computer program, which, when running, executes the method for determining pore-throat structure parameters of a shale reservoir as claimed in any one of claims 1 to 4.