Rock pore segmentation, porosity determination, evaluation method, device and system

Abstract

The present disclosure relates to a method, device, and system for rock pore segmentation, porosity determination, and assessment, and relates to the field of geotechnical engineering technology. The pore segmentation method comprises: acquiring multiple first three-dimensional, multi-layer rock images, pore images containing rock pore markers, and second three-dimensional, multi-layer rock images of the pores to be segmented; training the parameters of a preset convolutional neural network segmentation model using the multiple first three-dimensional, multi-layer rock images and the pore images; and performing pore segmentation on the second three-dimensional, multi-layer rock images based on the trained preset convolutional neural network segmentation model. Embodiments of the present disclosure can achieve rock pore segmentation, porosity determination, and assessment.

Description

Technical Field

[0001] The present disclosure relates to the field of geotechnical engineering technology, and in particular to a method, device, and system for rock pore segmentation, porosity determination, and evaluation. Background Art

[0002] The voids in rocks are spaces formed by various pores, holes, cracks and diagenetic fractures, and are an important indicator for evaluating rocks.

[0003] Currently, rock porosity measurement primarily involves direct and indirect methods. For example, direct porosity measurement includes conventional core porosity measurements, which directly measure the volume of pores and rock from rock samples (small core cores taken from the core) in the laboratory. Alternatively, the volume of interconnected pores can be measured using the volume of fluids that cannot be absorbed by the rock surface. In contrast, indirect porosity measurement utilizes geophysical parameters and corresponding calculation formulas to determine the porosity of rocks in the formation.

[0004] In the field of geotechnical engineering, direct porosity measurement is currently the most commonly used method for measuring rock porosity. However, the conventional core porosity measurement method among the current direct porosity measurement methods requires rock sampling, which may damage the internal structure of the rock during the sampling process. At the same time, if the fluid volume measurement method is used, it must be coordinated with the corresponding fluid (such as nitrogen, helium), and the operation process is extremely complicated or cumbersome.

[0005] Therefore, the above method cannot quickly and directly obtain the pore location information of the rock, which is not conducive to subsequent evaluation and analysis of the rock. Summary of the Invention

[0006] The present disclosure proposes a rock pore segmentation, porosity determination, and evaluation method, device, and system technical solution.

[0007] According to one aspect of the present disclosure, a method for pore segmentation of rock is provided, comprising:

[0008] Acquire multiple first three-dimensional multi-layer rock images and pore images with rock pore marks, and second three-dimensional multi-layer rock images of pores to be segmented;

[0009] Training parameters of a preset convolutional neural network segmentation model using the plurality of first three-dimensional multi-layer rock images and the pore images;

[0010] Based on the trained preset convolutional neural network segmentation model, pore segmentation is performed on the second three-dimensional multi-layer rock image.

[0011] Preferably, the pore segmentation method further comprises:

[0012] Acquire skeleton images with rock skeleton marks corresponding to the plurality of first three-dimensional multi-layer rock images;

[0013] Training parameters of a preset convolutional neural network segmentation model using the plurality of first three-dimensional multi-layer rock images, the skeleton image, and the pore image;

[0014] During the process of training the parameters of the preset convolutional neural network segmentation model, a classifier is used to calculate the skeleton probability map and the pore probability map corresponding to the plurality of first three-dimensional multi-layer rock images, and the skeleton probability map and the pore probability map are simultaneously maximized, thereby completing the parameter training of the preset convolutional neural network segmentation model; and / or,

[0015] Before acquiring the plurality of first three-dimensional multi-layer rock images and the pore images with rock pore marks, the plurality of first three-dimensional multi-layer rock images and the pore images with rock pore marks are determined, and the determination method includes:

[0016] obtaining a plurality of fluorescent rocks after pores of the plurality of rocks are filled with fluorescent dyes;

[0017] Performing computer three-dimensional tomography on the plurality of fluorescent rocks and the plurality of rocks respectively to obtain corresponding plurality of first three-dimensional multi-layer rock images and plurality of first three-dimensional multi-layer fluorescent rock images;

[0018] Marking the fluorescent areas of the plurality of first three-dimensional multi-layer fluorescent rock images respectively to obtain a plurality of pore images with pore marks corresponding to the plurality of first three-dimensional multi-layer rock images; and / or,

[0019] Before acquiring skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images, determining skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images, wherein the determining method includes:

[0020] obtaining a plurality of fluorescent rocks after pores of the plurality of rocks are filled with fluorescent dyes;

[0021] Performing computer three-dimensional tomography on the plurality of fluorescent rocks and the plurality of rocks respectively to obtain corresponding plurality of first three-dimensional multi-layer rock images and plurality of first three-dimensional multi-layer fluorescent rock images;

[0022] Marking the fluorescent areas of the plurality of first three-dimensional multi-layer fluorescent rock images respectively to obtain a plurality of pore images with pore marks corresponding to the plurality of first three-dimensional multi-layer rock images;

[0023] Based on the plurality of first three-dimensional multi-layer rock images and the plurality of pore images corresponding thereto, determining a plurality of skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images; and / or,

[0024] Before obtaining a plurality of fluorescent rocks obtained by filling pores in a plurality of rocks with fluorescent dyes, the plurality of rocks are cleaned with water at a set pressure and dried at a set temperature; the plurality of rocks after the drying process are imaged with X-rays to obtain a plurality of rock projection images; based on the plurality of rock projection images, it is determined whether the rocks are cleaned; if so, the plurality of fluorescent rocks obtained by filling pores in the plurality of rocks with fluorescent dyes are obtained; otherwise, the plurality of rocks are continued to be cleaned with water at a set pressure and dried at a set temperature until the rocks are cleaned.

[0025] Preferably, the method of respectively marking the fluorescent areas of the plurality of first three-dimensional multi-layer rock images to obtain the plurality of first three-dimensional multi-layer rock images with pore markings includes:

[0026] Obtaining set grayscale interval values or set grayscale values corresponding to the fluorescent areas in the plurality of first three-dimensional multi-layer rock images;

[0027] Based on the set grayscale interval value or the set grayscale value, the fluorescent areas of the plurality of first three-dimensional multi-layer rock images are marked respectively to obtain a plurality of first three-dimensional multi-layer rock images with pore marks; and / or,

[0028] The method for determining a plurality of skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images based on the plurality of first three-dimensional multi-layer rock images and the plurality of pore images corresponding thereto includes:

[0029] respectively determining a plurality of rock contour images from the plurality of first three-dimensional multi-layer rock images;

[0030] The corresponding pore images are subtracted from the multiple rock contour images to obtain multiple skeleton images with rock skeleton marks corresponding to the multiple first three-dimensional multi-layer rock images.

[0031] According to one aspect of the present disclosure, a method for determining rock porosity is provided, which applies or includes the above-mentioned pore segmentation method to obtain multiple pore images corresponding to a second three-dimensional multi-layer rock image of pores to be segmented; and

[0032] Acquire multiple rock contour images corresponding to the second three-dimensional multi-layer rock image;

[0033] Based on the multiple pore images and the multiple rock contour images, the porosity corresponding to the porous rock to be segmented is determined.

[0034] According to one aspect of the present disclosure, there is provided a rock evaluation method, which applies or includes the porosity determination method as described above; and

[0035] Obtaining the porosity of the porous rock to be segmented corresponding to multiple moments;

[0036] Using a preset registration algorithm, the porosities of the rocks to be segmented corresponding to the multiple moments are registered to obtain the porosities of the pores at the corresponding positions;

[0037] Based on the porosity of the pores at the corresponding positions, the strength of the porous rock to be segmented is evaluated.

[0038] Preferably, the method for evaluating the strength of the porous rock to be segmented based on the porosity of the pores at the corresponding positions includes:

[0039] respectively calculating a plurality of differences between the total porosities at adjacent moments at positions corresponding to the plurality of moments;

[0040] Extracting a corresponding maximum difference value from the plurality of difference values, and configuring a time period corresponding to the maximum difference value as a time period with the maximum intensity attenuation; and / or,

[0041] determining the pore connectivity of the positions corresponding to the multiple moments respectively;

[0042] Determine, based on the pore connectivity at the positions corresponding to the multiple moments, the pores corresponding to the maximum pore connectivity at the positions corresponding to the multiple moments, and respectively calculate the connected pore volumes corresponding to the maximum pore connectivity at the multiple moments of the porous rock to be segmented; or, based on the pore connectivity at the positions corresponding to the multiple moments, respectively calculate the connected pore volumes at the positions corresponding to the multiple moments of the porous rock to be segmented;

[0043] Evaluating the strength of the porous rock to be segmented based on the connected pore volumes at the corresponding positions at the multiple moments and the total volume of the porous rock to be segmented; and / or,

[0044] The method for evaluating the strength of the porous rock to be segmented based on the connected pore volumes at the corresponding positions at the multiple moments and the total volume of the porous rock to be segmented includes:

[0045] If a first ratio of the connected pore volume at the positions corresponding to the multiple moments to the total volume at a certain moment is greater than a first set ratio, the strength of the porous rock to be segmented is poor; otherwise, the strength of the porous rock to be segmented is good; and / or,

[0046] If a first ratio of the connected pore volumes at the positions corresponding to the multiple moments to the total volume is less than or equal to a first set ratio, determining a pore connection position map corresponding to the multiple moments based on the pore connectivity at the positions corresponding to the multiple moments, and evaluating the strength of the porous rock to be segmented based on the pore connection position map corresponding to the multiple moments; and / or,

[0047] The method for evaluating the strength of the porous rock to be segmented based on the pore connectivity position maps corresponding to the multiple moments includes:

[0048] Determining a plurality of pores and gaps greater than a set length and a set width in the pore communication position map corresponding to the plurality of moments, and calculating a plurality of shortest distances between the plurality of adjacent pores and gaps;

[0049] If the multiple shortest distances corresponding to the multiple moments gradually decrease and are less than the set distance, the strength of the porous rock to be segmented deteriorates; otherwise, the strength of the porous rock to be segmented does not deteriorate; and / or,

[0050] The method for evaluating the strength of the porous rock to be segmented based on the pore connectivity position maps corresponding to the multiple moments further includes:

[0051] If the total porosity at adjacent moments of the positions corresponding to the multiple moments is greater than or equal to the preset porosity, then a plurality of differences between the total porosity at adjacent moments of the positions corresponding to the multiple moments are calculated respectively;

[0052] If the multiple differences are greater than or equal to the second set ratio, and the multiple shortest distances are less than the set distance, the strength of the porous rock to be divided deteriorates; otherwise, the strength of the porous rock to be divided does not deteriorate.

[0053] According to one aspect of the present disclosure, there is provided a rock pore segmentation device, comprising:

[0054] A first acquisition unit is configured to acquire a plurality of first three-dimensional multi-layer rock images and pore images thereof with rock pore marks, and a second three-dimensional multi-layer rock image of pores to be segmented;

[0055] A training unit, configured to train parameters of a preset convolutional neural network segmentation model using the plurality of first three-dimensional multi-layer rock images and the pore image;

[0056] A segmentation unit is used to perform pore segmentation on the second three-dimensional multi-layer rock image based on the trained preset convolutional neural network segmentation model.

[0057] According to one aspect of the present disclosure, there is provided a rock porosity determination device, which applies to or includes the pore segmentation device as described above; and

[0058] a second acquiring unit, configured to acquire a plurality of rock contour images corresponding to the second three-dimensional multi-layer rock image;

[0059] A determination unit is used to determine the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images.

[0060] According to one aspect of the present disclosure, there is provided a rock evaluation device, which applies or includes the porosity determination device as described above; and

[0061] The third acquisition unit is used to obtain the porosity corresponding to the porous rock to be segmented at multiple moments;

[0062] A registration unit, configured to register the porosities of the pore rocks to be segmented corresponding to the plurality of moments using a preset registration algorithm, to obtain the porosities of the pores at the corresponding positions;

[0063] An evaluation unit is used to perform strength evaluation on the porous rock to be segmented based on the porosity of the pores at the corresponding positions.

[0064] According to one aspect of the present disclosure, there is provided a rock analysis system, comprising: an electronic device configured with a processor;

[0065] a memory for storing processor-executable instructions;

[0066] Wherein, the processor is configured to call the instructions stored in the memory to execute the pore segmentation method as described above; and / or, the porosity determination method as described above; and / or, the evaluation method as described above.

[0067] Or, comprising: a computer-readable storage medium having computer program instructions stored thereon, characterized in that when the computer program instructions are executed by a processor, the pore segmentation method as described above is implemented; and / or the porosity determination method as described above is implemented; and / or the evaluation method as described above is implemented.

[0068] In the embodiments disclosed herein, a method, device, and system technical solution for pore segmentation, porosity determination, and evaluation of rocks are proposed to address the problems that the current method may destroy the internal structure of the rock during sampling or the operation process is complicated or tedious, and the pore position information of the rock cannot be obtained quickly and directly, which is not conducive to subsequent evaluation and analysis of the rock.

[0069] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0070] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0072] Figure 1 A flow chart showing a method for pore segmentation of rock according to an embodiment of the present disclosure;

[0073] Figure 2 A block diagram showing a rock pore segmentation device according to an embodiment of the present disclosure;

[0074] Figure 3 is a block diagram of an electronic device 800 according to an exemplary embodiment;

[0075] Figure 4 is a block diagram of an electronic device 1900 according to an exemplary embodiment. Implementation Method

[0076] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0077] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0078] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent the existence of three situations: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0079] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0080] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, the present disclosure will not elaborate on them.

[0081] In addition, the present disclosure also provides pore segmentation, porosity determination, and evaluation processing devices, systems, electronic devices, computer-readable storage media, and programs, all of which can be used to implement any pore segmentation, porosity determination, and evaluation method provided by the present disclosure. The corresponding technical solutions and descriptions are referred to the corresponding records in the method section and will not be repeated here.

[0082] Figure 1 FIG. 1 is a flow chart showing a method for pore segmentation of rock according to an embodiment of the present disclosure. Figure 1 As shown, the rock pore segmentation method includes: step S101: obtaining multiple first 3D multi-layer rock images, pore images with rock pore labels, and second 3D multi-layer rock images of the pores to be segmented; step S102: training parameters of a preset convolutional neural network segmentation model using the multiple first 3D multi-layer rock images and the pore images; and step S103: performing pore segmentation on the second 3D multi-layer rock image based on the trained preset convolutional neural network segmentation model. This method addresses the problems of current methods, such as the potential damage to the rock's internal structure during sampling, the complexity or tediousness of the sampling process, the inability to quickly and directly obtain rock pores, and the resulting hindrance to subsequent rock evaluation and analysis.

[0083] Step S101: obtaining a plurality of first three-dimensional multi-layer rock images and pore images with rock pore labels, and second three-dimensional multi-layer rock images of pores to be segmented.

[0084] In an embodiment of the present disclosure, before obtaining the plurality of first three-dimensional multi-layer rock images and the pore images with rock pore markers, the plurality of first three-dimensional multi-layer rock images and the pore images with rock pore markers are determined, and the determination method includes: obtaining a plurality of fluorescent rocks after pores of the plurality of rocks are filled with fluorescent dyes; performing computer three-dimensional tomography on the plurality of fluorescent rocks and the plurality of rocks respectively to obtain a corresponding plurality of first three-dimensional multi-layer rock images and a plurality of first three-dimensional multi-layer fluorescent rock images; and marking the fluorescent areas of the plurality of first three-dimensional multi-layer fluorescent rock images respectively to obtain a plurality of pore images with pore markers corresponding to the plurality of first three-dimensional multi-layer rock images.

[0085] In an embodiment of the present disclosure, before obtaining a plurality of fluorescent rocks after pore filling of a plurality of rocks with a fluorescent dye, the plurality of rocks are cleaned with water at a set pressure and dried at a set temperature; the plurality of rocks after drying are imaged with X-rays to obtain a plurality of rock projection images; based on the plurality of rock projection images, it is determined whether the rocks are cleaned; if so, the plurality of fluorescent rocks after pore filling of the plurality of rocks with a fluorescent dye are obtained; otherwise, the plurality of rocks are continued to be cleaned with water at a set pressure and dried at a set temperature until the rocks are cleaned. Those skilled in the art may configure the values corresponding to the set pressure and the set temperature according to actual needs.

[0086] In the embodiments of the present disclosure and other possible embodiments, the method for determining whether the rock is cleaned based on the multiple rock projection images includes: drawing a grayscale histogram corresponding to the multiple rock projection images; based on the grayscale histogram, using the set grayscale range corresponding to the rock skeleton, determining whether the rock is cleaned.

[0087] In the embodiments of the present disclosure and other possible embodiments, the method for determining whether the rock is cleaned based on the grayscale histogram and using the set grayscale range corresponding to the rock skeleton includes: if the amplitude corresponding to the grayscale histogram is concentrated within the set grayscale range, then determining that the rock is cleaned; otherwise, determining that the rock is not cleaned.

[0088] In the embodiment of the present disclosure and other possible embodiments, if the amplitudes corresponding to the grayscale histogram are concentrated within the set grayscale range, then the rock is determined to be clean; otherwise, the method for determining that the rock is not clean includes: obtaining a first amplitude and a second amplitude corresponding to within the set grayscale range and outside the set grayscale range; if the difference between the first amplitude and the second amplitude is greater than or equal to the set difference, then the rock is determined to be clean; otherwise, the method for determining that the rock is not clean. Those skilled in the art may configure the value corresponding to the set difference according to actual needs.

[0089] In the embodiment of the present disclosure and other possible embodiments, the method for cleaning the plurality of rocks using water at a set pressure includes: obtaining the positions of nozzles; detecting the contours of the rocks; adjusting the positions of the plurality of nozzles based on the contours, controlling the nozzles to traverse the contours of the rocks along a set trajectory until a set number of traversals are achieved, and then the nozzles spray water at the set pressure to clean the plurality of rocks. The numerical value corresponding to the set number of traversals may be configured by those skilled in the art according to actual needs.

[0090] In the embodiments of the present disclosure and other possible embodiments, the method for detecting the contour of the rock includes: obtaining multiple first three-dimensional multi-layer rock images and their corresponding contour-marked images, and three-dimensional multi-layer rock images to be contour-segmented; using the multiple first three-dimensional multi-layer rock images and their corresponding contour-marked images, training the parameters of a preset convolutional neural network contour segmentation model; and based on the trained preset convolutional neural network contour segmentation model, performing contour segmentation on the three-dimensional multi-layer rock image to obtain the contour of the rock.

[0091] In the embodiments of the present disclosure and other possible embodiments, the preset convolutional neural network contour segmentation model and the preset convolutional neural network segmentation model can be configured as a U-net convolutional neural network or other improved convolutional neural networks, such as ResU-net (residual U-net) convolutional neural network, U-net++ convolutional neural network, nnU-net convolutional neural network, or other convolutional neural networks for segmentation.

[0092] In the embodiment of the present disclosure and other possible embodiments, three-dimensional computer tomography (CT) imaging is performed on multiple rocks and multiple three-dimensional multi-layer rock images to obtain multiple first three-dimensional multi-layer rock images and multiple three-dimensional multi-layer rock images. Simultaneously, edge detection is performed on each of the multiple first three-dimensional multi-layer rock images using an edge detection algorithm to obtain contour-marked images corresponding to the multiple first three-dimensional multi-layer rock images.

[0093] In the embodiments of the present disclosure and other possible embodiments, the method of using an edge detection algorithm to perform edge detection on the multiple first three-dimensional multi-layer rock images respectively to obtain contour marking images corresponding to the multiple first three-dimensional multi-layer rock images includes: using an edge detection algorithm to perform edge detection on the multiple first three-dimensional multi-layer rock images respectively to obtain multiple edge images corresponding to the multiple first three-dimensional multi-layer rock images; and extracting the outermost edge lines from the multiple edge images respectively to obtain contour marking images corresponding to the multiple first three-dimensional multi-layer rock images.

[0094] In the embodiments of the present disclosure and other possible embodiments, the edge detection algorithm can be configured as one or more of a Canny edge detection operator, a second-order edge detection operator, a Laplacian operator, a Marr-Hildreth operator, a LoG (Laplacian of Gaussian) operator, a DoG operator, a SUSAN operator, or a Trajkovic operator, or as one or more of a Moravec detector or a Harris detector.

[0095] In the embodiments of the present disclosure and other possible embodiments, before obtaining skeleton images with rock skeleton labels corresponding to the multiple first three-dimensional multi-layer rock images, the skeleton images with rock skeleton labels corresponding to the multiple first three-dimensional multi-layer rock images are determined, and the determination method includes: obtaining multiple fluorescent rocks after pores of multiple rocks are filled with fluorescent dyes; performing computer three-dimensional tomography on the multiple fluorescent rocks and multiple rocks respectively to obtain corresponding multiple first three-dimensional multi-layer rock images and multiple first three-dimensional multi-layer fluorescent rock images; marking the fluorescent areas of the multiple first three-dimensional multi-layer fluorescent rock images respectively to obtain multiple pore images with pore labels corresponding to the multiple first three-dimensional multi-layer rock images; and determining the multiple skeleton images with rock skeleton labels corresponding to the multiple first three-dimensional multi-layer rock images based on the multiple first three-dimensional multi-layer rock images and the corresponding multiple pore images.

[0096] In the embodiment of the present disclosure and other possible embodiments, before obtaining skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images, a method for determining the skeleton image with rock skeleton markers includes: obtaining rock contour images and pore images with rock pore markers corresponding to the plurality of first three-dimensional multi-layer rock images; and determining the skeleton image with rock skeleton markers based on the plurality of rock contour images and the plurality of pore images. The skeleton image with rock skeleton markers is determined by subtracting the corresponding plurality of pore images from the plurality of rock contour images.

[0097] In an embodiment of the present disclosure, the method for separately marking the fluorescent regions of the plurality of first three-dimensional multi-layer rock images to obtain the plurality of first three-dimensional multi-layer rock images with pore markings includes: obtaining set grayscale interval values or set grayscale values corresponding to the fluorescent regions in the plurality of first three-dimensional multi-layer rock images; and separately marking the fluorescent regions in the plurality of first three-dimensional multi-layer rock images based on the set grayscale interval values or set grayscale values to obtain the plurality of first three-dimensional multi-layer rock images with pore markings. Those skilled in the art may configure the numerical values corresponding to the set grayscale interval values or set grayscale values according to actual needs.

[0098] In an embodiment of the present disclosure, the method for determining a plurality of skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images based on the plurality of first three-dimensional multi-layer rock images and the plurality of pore images corresponding thereto includes: separately determining a plurality of rock contour images in the plurality of first three-dimensional multi-layer rock images; and subtracting the corresponding pore images from the plurality of rock contour images to obtain a plurality of skeleton images with rock skeleton markers corresponding to the plurality of first three-dimensional multi-layer rock images.

[0099] Step S102: Utilizing the plurality of first three-dimensional multi-layer rock images and the pore images, parameters of a preset convolutional neural network segmentation model are trained.

[0100] In an embodiment of the present disclosure, the pore segmentation method further includes: obtaining skeleton images with rock skeleton labels corresponding to multiple first three-dimensional multi-layer rock images; using the multiple first three-dimensional multi-layer rock images, the skeleton images and the pore images to train the parameters of a preset convolutional neural network segmentation model; in the process of training the parameters of the preset convolutional neural network segmentation model, using a classifier to calculate the skeleton probability map and the pore probability map corresponding to the multiple first three-dimensional multi-layer rock images, and simultaneously maximizing the skeleton probability map and the pore probability map to complete the parameter training of the preset convolutional neural network segmentation model.

[0101] In the embodiments of the present disclosure and other possible embodiments, the classifier may be configured as one or more of the classification layers corresponding to the GoogleNet convolutional neural network, the DenseNet convolutional neural network, or other convolutional neural networks for classification. Similarly, the classifier may be configured as one or more of the support vector machine, decision tree, random forest, K-nearest neighbor, logistic regression, adaptive boosting, linear discriminant analysis, and multilayer perceptron.

[0102] For example, the Random Forest (RF) algorithm constructs multiple decision trees and comprehensively evaluates the predictions from these trees to arrive at a final result. The RF model is an extension of the bagging algorithm, combining the advantages of both bagging and decision trees.

[0103] Specifically, the RF model uses bootstrap resampling technology to repeatedly extract n samples from the dataset with replacement to form new training samples to train a decision tree. Then, the n decision trees are used to form m random forests. The final prediction value is determined based on the voting or mean structure of the m random forests. When the number of decision trees is large enough, the generalization ability of the random forest is between the following formula (1).

[0104] (1)

[0105] in, R Indicates that the generalization error of the random forest upper bound converges to the lower bound, represents the average correlation coefficient between decision trees, s It is a measure of the strength of the decision tree.

[0106] Usually the strength of a model represents its average performance, and the performance can be expressed by the model's margin M, as shown in Equation (2).

[0107] (2)

[0108] in, According to the random vector The predicted classification result of the constructed decision tree for attribute x, y and z In general, the larger the margin, the more accurately the model predicts the attribute value of the unknown data instance. x Therefore, as the ensemble of decision trees increases, the relevance of the random forest tree increases, the generalization ability increases, and the classification error decreases.

[0109] Step S103: performing pore segmentation on the second three-dimensional multi-layer rock image based on the trained preset convolutional neural network segmentation model.

[0110] In addition, the present disclosure also proposes a method for determining the porosity of rock, which applies or includes the above-mentioned pore segmentation method to obtain multiple pore images corresponding to the second three-dimensional multi-layer rock image of the pores to be segmented; obtain multiple rock contour images corresponding to the second three-dimensional multi-layer rock image; and determine the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images.

[0111] In the embodiments of the present disclosure and other possible embodiments, the method for determining the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images includes: respectively calculating the void volume and rock contour volume corresponding to the multiple pore images and the multiple rock contour images; dividing the void volume by the rock contour volume to obtain the porosity corresponding to the porous rock to be segmented.

[0112] In the embodiment of the present disclosure and other possible embodiments, the method for respectively calculating the void volume and rock contour volume corresponding to the multiple pore images and the multiple rock contour images includes: obtaining first unit pixel values and second unit pixel values corresponding to the multiple pore images and the multiple rock contour images, respectively; performing three-dimensional reconstruction on the multiple pore images and the multiple rock contour images to obtain pore reconstructed images and contour reconstructed images, respectively; calculating the first number of pixels and the second number of pixels corresponding to the pore reconstructed images and the contour reconstructed images, respectively; obtaining the void volume based on the first pixel value and the first number of pixels; and obtaining the rock contour volume based on the second pixel value and the second number of pixels. The first pixel value and the second pixel value are respectively configured as corresponding unit pixel area values.

[0113] In the embodiment of the present disclosure and other possible embodiments, the method for obtaining the void volume based on the first pixel value and the first number of pixel points includes: multiplying the first pixel value by the first number of pixel points to obtain the void volume.

[0114] In the embodiment of the present disclosure and other possible embodiments, the method for obtaining the rock contour volume based on the second pixel value and the second number of pixel points includes: multiplying the second pixel value by the second number of pixel points to obtain the rock contour volume.

[0115] In addition, the present disclosure also proposes a rock evaluation method, which applies or includes the porosity determination method as described above to obtain the porosity corresponding to the porous rock to be segmented at multiple moments; uses a preset alignment algorithm to align the porosity corresponding to the porous rock to be segmented at the multiple moments to obtain the porosity of the pores at the corresponding positions; and based on the porosity of the pores at the corresponding positions, performs strength evaluation on the porous rock to be segmented.

[0116] In the embodiment of the present disclosure and other possible embodiments, the preset registration algorithm can be configured as one or more of the Kabsch registration algorithm (point cloud registration algorithm), KAZE registration algorithm, SIFT registration algorithm, SURF registration algorithm, etc.

[0117] In the embodiment of the present disclosure and other possible embodiments, the multiple moments may be configured as 1 month, and those skilled in the art may configure the values corresponding to the multiple moments according to actual needs.

[0118] In the embodiments of the present disclosure and other possible embodiments, the method for evaluating the strength of the porous rock to be divided based on the porosity of the pores at the corresponding positions includes: obtaining a fitting curve corresponding to a preset porosity and strength; based on the fitting curve, using the porosity of the pores at the corresponding positions, evaluating or predicting the strength of the porous rock to be divided.

[0119] In the embodiments of the present disclosure and other possible embodiments, before obtaining the fitting curve corresponding to the preset porosity and strength, the method of constructing the fitting curve corresponding to the preset porosity and strength includes: obtaining rock strength experimental data corresponding to multiple different porosities; performing curve fitting on the rock strength experimental data corresponding to the multiple different porosities, and constructing the fitting curve corresponding to the preset porosity and strength.

[0120] In an embodiment of the present disclosure, the method for performing strength evaluation on the porous rock to be segmented based on the porosity of the pores at the corresponding positions includes: respectively calculating multiple differences between the total porosities at adjacent moments of the corresponding positions at the multiple moments; extracting the corresponding maximum difference among the multiple differences, and configuring the time period corresponding to the maximum difference as the time period with the largest strength attenuation.

[0121] For example, multiple differences S1, S2, S3, ..., Sn-1 between the total porosities at adjacent moments corresponding to the multiple moments T1, T2, T3, ..., Tn-1, Tn are calculated respectively, the corresponding maximum difference S3 among the multiple differences is extracted, and the time period T3-T4 corresponding to the maximum difference S3 is configured as the time period with the largest intensity attenuation.

[0122] In an embodiment of the present disclosure, the method for evaluating the strength of the porous rock to be segmented based on the porosity of the pores at the corresponding positions further includes: determining the pore connectivity of the corresponding positions at the multiple moments respectively;

[0123] According to the pore connectivity at the positions corresponding to the multiple moments, the pores corresponding to the maximum pore connectivity at the positions corresponding to the multiple moments are determined, and the connected pore volumes corresponding to the maximum pore connectivity at the multiple moments of the porous rock to be divided are calculated respectively; or, according to the pore connectivity at the positions corresponding to the multiple moments, the connected pore volumes at the positions corresponding to the multiple moments of the porous rock to be divided are calculated respectively; based on the connected pore volumes at the positions corresponding to the multiple moments and the total volume of the porous rock to be divided, the strength of the porous rock to be divided is evaluated.

[0124] In the embodiments of the present disclosure and other possible embodiments, the method of respectively determining the pore connectivity of the positions corresponding to the multiple moments includes: performing expansion and corrosion operations on the pores at the positions corresponding to the multiple moments respectively to determine the pore connectivity of the positions corresponding to the multiple moments.

[0125] In an embodiment of the present disclosure, the method for evaluating the strength of the porous rock to be segmented based on the interconnected pore volumes at the locations corresponding to the multiple moments and the total volume of the porous rock to be segmented includes: if a first ratio of the interconnected pore volumes at the locations corresponding to the multiple moments to the total volume at a certain moment is greater than a first set ratio, then the strength of the porous rock to be segmented is poor; otherwise, the strength of the porous rock to be segmented is good. Those skilled in the art may configure the value corresponding to the first set ratio according to actual needs.

[0126] In the embodiment of the present disclosure and other possible embodiments, the method for respectively calculating the connected pore volume at the corresponding positions at the multiple moments and the total volume of the porous rock to be segmented includes: respectively obtaining third unit pixel values and fourth unit pixel values corresponding to the multiple connected pore images and the multiple rock contour images; respectively performing three-dimensional reconstruction on the multiple connected pore images and the multiple rock contour images to obtain a connected pore reconstructed image and a contour reconstructed image; respectively calculating the number of third pixels and the number of fourth pixels corresponding to the connected pore reconstructed image and the contour reconstructed image; obtaining the connected pore volume based on the third pixel value and the third pixel number; and obtaining the total volume of the rock contour based on the fourth pixel value and the fourth pixel number. The third pixel value and the fourth pixel value are respectively configured as corresponding unit pixel area values.

[0127] In the embodiment of the present disclosure and other possible embodiments, the method for obtaining the volume of the interconnected void based on the third pixel value and the third number of pixels includes: multiplying the first pixel value by the first number of pixels to obtain the volume of the interconnected void. Simultaneously, in the embodiment of the present disclosure and other possible embodiments, the method for obtaining the total volume based on the fourth pixel value and the fourth number of pixels includes: multiplying the fourth pixel value by the fourth number of pixels to obtain the total volume.

[0128] In an embodiment of the present disclosure, if a first ratio of the connected pore volume at the positions corresponding to the multiple moments to the total volume is less than or equal to a first set ratio, the pore connectivity position map corresponding to the multiple moments is determined based on the pore connectivity at the positions corresponding to the multiple moments, and the strength of the porous rock to be divided is evaluated based on the pore connectivity position map corresponding to the multiple moments.

[0129] In an embodiment of the present disclosure, the method for evaluating the strength of the porous rock to be segmented based on the pore connectivity position diagrams corresponding to the multiple moments includes: determining multiple pore fractures corresponding to a set length and a set width in the pore connectivity position diagrams corresponding to the multiple moments, and calculating multiple shortest distances between multiple adjacent pore fractures; if the multiple shortest distances corresponding to the multiple moments gradually decrease and are less than the set distances, the strength of the porous rock to be segmented deteriorates; otherwise, the strength of the porous rock to be segmented does not deteriorate. Those skilled in the art can configure the values corresponding to the set distances, set lengths, and set widths according to actual needs.

[0130] In the embodiment of the present disclosure and other possible embodiments, if two pore slits have an intersection, they are regarded as one pore slit; at the same time, if the slit width of a certain section of the pore slit is greater than the set width, it is considered that the width condition is met.

[0131] In the embodiments of the present disclosure and other possible embodiments, the method for calculating multiple shortest distances between multiple adjacent pore slits includes: extracting multiple coordinate values on each pore slit respectively; calculating multiple distances between each of the multiple coordinate values on each pore slit and each of the multiple coordinate values on other adjacent pore slits respectively; and taking the minimum value of the multiple distances to obtain the multiple shortest distances between the multiple adjacent pore slits.

[0132] In an embodiment of the present disclosure, the method for evaluating the strength of the porous rock to be segmented based on the pore connectivity position diagram corresponding to the multiple moments further includes: if the total porosity at adjacent moments of the positions corresponding to the multiple moments is greater than or equal to the preset porosity, then calculating multiple differences between the total porosities at adjacent moments of the positions corresponding to the multiple moments; if the multiple differences are greater than or equal to a second set ratio, and the multiple shortest distances are less than the set distance, then the strength of the porous rock to be segmented has deteriorated; otherwise, the strength of the porous rock to be segmented has not deteriorated. Those skilled in the art can configure the values corresponding to the preset porosity, the second set ratio, and the set distance according to actual needs.

[0133] The pore segmentation, porosity determination, and assessment methods may be executed by a pore segmentation, porosity determination, and assessment apparatus. For example, the pore segmentation, porosity determination, and assessment methods may be executed by a terminal device, a server, or other processing device, wherein the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, etc. In some possible implementations, the pore segmentation, porosity determination, and assessment methods may be implemented by a processor invoking computer-readable instructions stored in a memory.

[0134] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0135] Figure 2 FIG. 1 is a block diagram of a rock pore segmentation device according to an embodiment of the present disclosure. Figure 2As shown, the rock pore segmentation device includes: a first acquisition unit 101 for acquiring multiple first three-dimensional multi-layer rock images, pore images with rock pore labels, and second three-dimensional multi-layer rock images of pores to be segmented; a training unit 102 for training parameters of a preset convolutional neural network segmentation model using the multiple first three-dimensional multi-layer rock images and the pore images; and a segmentation unit 103 for performing pore segmentation on the second three-dimensional multi-layer rock image based on the trained preset convolutional neural network segmentation model. This addresses the problem that current methods, such as the potential damage to the rock's internal structure during sampling or the complex or cumbersome operation process, cannot quickly and directly obtain rock pores, hindering subsequent rock evaluation and analysis.

[0136] In addition, the present disclosure also proposes a rock porosity determination device, which applies or includes the pore segmentation device as described above; and a second acquisition unit for acquiring multiple rock contour images corresponding to the second three-dimensional multi-layer rock image; and a determination unit for determining the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images.

[0137] In addition, the present disclosure also proposes a rock evaluation device, which applies or includes the porosity determination device as described above; and a third acquisition unit, which is used to obtain the porosity corresponding to the porous rock to be segmented at multiple moments; a registration unit, which is used to use a preset registration algorithm to align the porosity corresponding to the porous rock to be segmented at the multiple moments to obtain the porosity of the pores at the corresponding positions; and an evaluation unit, which is used to perform strength evaluation on the porous rock to be segmented based on the porosity of the pores at the corresponding positions.

[0138] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0139] An embodiment of the present disclosure also proposes a rock analysis system, comprising: an electronic device, the electronic device being configured with a processor, and a memory for storing instructions executable by the processor; wherein the processor is configured to call the instructions stored in the memory to execute the above-mentioned pore segmentation, porosity determination, and evaluation methods; or, comprising: a computer-readable storage medium, on which computer program instructions are stored, characterized in that the computer program instructions implement the above-mentioned pore segmentation, porosity determination, and evaluation methods when executed by the processor.

[0140] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the above-mentioned pore segmentation, porosity determination, and evaluation methods. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

[0141] The present disclosure also provides an electronic device comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the aforementioned pore segmentation, porosity determination, and assessment methods. The electronic device may be provided as a terminal, server, or other device.

[0142] Figure 3 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0143] Reference Figure 3 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0144] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0145] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0146] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0147] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensors can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide action. In some embodiments, the multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the electronic device 800 is in an operating mode, such as a capture mode or a video mode, the front-facing camera and / or the rear-facing camera can receive external multimedia data. Each front-facing camera and the rear-facing camera can have a fixed optical lens system or have focal length and optical zoom capabilities.

[0148] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0149] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to, a home button, volume buttons, a start button, and a lock button.

[0150] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor assembly 814 can also detect changes in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and temperature changes of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0151] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0152] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0153] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions. The computer program instructions can be executed by the processor 820 of the electronic device 800 to perform the above method.

[0154] Figure 4 1 is a block diagram of an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Figure 4The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute the instructions to perform the above-described method.

[0155] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0156] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0157] The present disclosure may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0158] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or raised-in-groove structure on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0159] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0160] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, the state information of the computer-readable program instructions is used to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), so that the electronic circuit can execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0161] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0162] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0163] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0164] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the prescribed logical function. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the prescribed function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0165] While various embodiments of the present disclosure have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technical improvements to existing technologies, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for pore segmentation of rock, characterized in that: include: Acquire multiple first three-dimensional multi-layer rock images and pore images with rock pore markers, and second three-dimensional multi-layer rock images of pores to be segmented; wherein, before acquiring the multiple first three-dimensional multi-layer rock images and pore images with rock pore markers, determine the multiple first three-dimensional multi-layer rock images and pore images with rock pore markers, including: acquiring multiple fluorescent rocks after pores of multiple rocks are filled with fluorescent dyes; performing computer three-dimensional tomography on the multiple fluorescent rocks and multiple rocks to obtain corresponding multiple first three-dimensional multi-layer rock images and multiple first three-dimensional multi-layer fluorescent rock images; and marking the fluorescent areas of the multiple first three-dimensional multi-layer fluorescent rock images to obtain multiple pore images with pore markers corresponding to the multiple first three-dimensional multi-layer rock images; The parameters of a preset convolutional neural network segmentation model are trained using the multiple first three-dimensional multi-layer rock images and the pore images, including: respectively determining multiple rock contour images from the multiple first three-dimensional multi-layer rock images; subtracting the corresponding pore images from the multiple rock contour images to obtain multiple skeleton images with rock skeleton labels corresponding to the multiple first three-dimensional multi-layer rock images; using the multiple first three-dimensional multi-layer rock images, the multiple skeleton images and the multiple pore images to train the parameters of the preset convolutional neural network segmentation model; in the process of training the parameters of the preset convolutional neural network segmentation model, using a classifier to calculate the skeleton probability map and the pore probability map corresponding to the multiple first three-dimensional multi-layer rock images, and simultaneously maximizing the probabilities corresponding to the skeleton probability map and the pore probability map, thereby completing the parameter training of the preset convolutional neural network segmentation model; Based on the trained preset convolutional neural network segmentation model, pore segmentation is performed on the second three-dimensional multi-layer rock image.

2. The pore segmentation method according to claim 1, characterized in that: Before obtaining the plurality of fluorescent rocks obtained by filling the pores of the plurality of rocks with fluorescent dyes, the plurality of rocks are washed with water at a set pressure, and the washed plurality of rocks are dried at a set temperature; The plurality of rocks after drying are imaged using X-rays to obtain a plurality of rock projection images; determining whether the rocks are clean based on the plurality of rock projection images; if so, filling the pores of the plurality of rocks with fluorescent dye to obtain a plurality of fluorescent rocks; otherwise, continuing to clean the plurality of rocks with water at a set pressure and drying the cleaned rocks at a set temperature; Until the rock is clean.

3. The pore segmentation method according to any one of claims 1 to 2, characterized in that: The step of respectively marking the fluorescent areas of the plurality of first three-dimensional multi-layer rock images to obtain the plurality of first three-dimensional multi-layer rock images with pore marks includes: Obtaining set grayscale interval values or set grayscale values corresponding to the fluorescent areas in the plurality of first three-dimensional multi-layer rock images; Based on the set grayscale interval value or the set grayscale value, the fluorescent areas of the multiple first three-dimensional multi-layer rock images are marked respectively to obtain multiple first three-dimensional multi-layer rock images with pore marks.

4. A method for determining rock porosity, applying or including the pore segmentation method according to any one of claims 1 to 3, to obtain multiple pore images corresponding to a second three-dimensional multi-layer rock image of pores to be segmented, characterized in that: Acquire multiple rock contour images corresponding to the second three-dimensional multi-layer rock image; Based on the multiple pore images and the multiple rock contour images, the porosity corresponding to the porous rock to be segmented is determined; wherein, the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images is determined, including: respectively calculating the void volume and rock contour volume corresponding to the multiple pore images and the multiple rock contour images; the void volume is divided by the rock contour volume to obtain the porosity corresponding to the porous rock to be segmented.

5. A rock evaluation method, applying or including the porosity determination method according to claim 4, characterized in that: Obtaining the porosity of the porous rock to be segmented corresponding to multiple moments; Using a preset registration algorithm, the porosities of the rocks to be segmented corresponding to the multiple moments are registered to obtain the porosities of the pores at the corresponding positions; Based on the porosity of the pores at the corresponding positions, the strength of the porous rock to be segmented is evaluated.

6. The evaluation method according to claim 5, characterized in that The strength evaluation of the porous rock to be segmented based on the porosity of the pores at the corresponding positions includes: respectively calculating a plurality of differences between the total porosities at adjacent moments at positions corresponding to the plurality of moments; A maximum difference value corresponding to the multiple differences is extracted, and a time period corresponding to the maximum difference value is configured as a time period with the maximum intensity attenuation.

7. The evaluation method according to any one of claims 5 or 6, characterized in that: determining the pore connectivity of the positions corresponding to the multiple moments respectively; Determine, based on the pore connectivity at the positions corresponding to the multiple moments, the pores corresponding to the maximum pore connectivity at the positions corresponding to the multiple moments, and respectively calculate the connected pore volumes corresponding to the maximum pore connectivity at the multiple moments of the porous rock to be segmented; or, based on the pore connectivity at the positions corresponding to the multiple moments, respectively calculate the connected pore volumes at the positions corresponding to the multiple moments of the porous rock to be segmented; The strength of the porous rock to be divided is evaluated based on the connected pore volumes at the corresponding positions at the multiple moments and the total volume of the porous rock to be divided.

8. The evaluation method according to claim 7, characterized in that The evaluating the strength of the porous rock to be segmented based on the connected pore volumes at the corresponding positions at the multiple moments and the total volume of the porous rock to be segmented includes: If a first ratio of the connected pore volume at the corresponding positions at the multiple moments to the total volume at a certain moment is greater than a first set ratio, the strength of the porous rock to be divided is poor; otherwise, the strength of the porous rock to be divided is good.

9. The evaluation method according to claim 7, wherein: The evaluating the strength of the porous rock to be segmented based on the connected pore volumes at the corresponding positions at the multiple moments and the total volume of the porous rock to be segmented includes: If a first ratio of the connected pore volume at the positions corresponding to the multiple moments to the total volume is less than or equal to a first set ratio, the pore connectivity position map corresponding to the multiple moments is determined based on the pore connectivity at the positions corresponding to the multiple moments, and the strength of the porous rock to be divided is evaluated based on the pore connectivity position map corresponding to the multiple moments.

10. The evaluation method according to claim 9, characterized in that: The evaluating the strength of the porous rock to be segmented according to the pore connectivity position maps corresponding to the multiple moments includes: Determining a plurality of pores and gaps greater than a set length and a set width in the pore communication position map corresponding to the plurality of moments, and calculating a plurality of shortest distances between the plurality of adjacent pores and gaps; If the multiple shortest distances corresponding to the multiple moments gradually become smaller and the multiple shortest distances are less than the set distance, the strength of the porous rock to be divided deteriorates; otherwise, the strength of the porous rock to be divided does not deteriorate.

11. The evaluation method according to claim 10, characterized in that: The step of evaluating the strength of the porous rock to be segmented based on the pore connectivity position maps corresponding to the multiple moments further includes: If the total porosity at adjacent moments of the positions corresponding to the multiple moments is greater than or equal to the preset porosity, then a plurality of differences between the total porosity at adjacent moments of the positions corresponding to the multiple moments are calculated respectively; If the multiple differences are greater than or equal to the second set ratio, and the multiple shortest distances are less than the set distance, the strength of the porous rock to be divided deteriorates; otherwise, the strength of the porous rock to be divided does not deteriorate.

12. A rock pore segmentation device, characterized in that: include: A first acquisition unit is configured to acquire a plurality of first three-dimensional multi-layer rock images and pore images with rock pore markers, and a second three-dimensional multi-layer rock image of pores to be segmented; wherein, before acquiring the plurality of first three-dimensional multi-layer rock images and pore images with rock pore markers, determining the plurality of first three-dimensional multi-layer rock images and pore images with rock pore markers comprises: acquiring a plurality of fluorescent rocks after pores of a plurality of rocks are filled with fluorescent dyes; performing computer three-dimensional tomography on the plurality of fluorescent rocks and the plurality of rocks to obtain corresponding plurality of first three-dimensional multi-layer rock images and plurality of first three-dimensional multi-layer fluorescent rock images; and marking the fluorescent areas of the plurality of first three-dimensional multi-layer fluorescent rock images to obtain a plurality of pore images with pore markers corresponding to the plurality of first three-dimensional multi-layer rock images; A training unit is used to train the parameters of a preset convolutional neural network segmentation model using the multiple first three-dimensional multi-layer rock images and the pore images, including: respectively determining multiple rock contour images from the multiple first three-dimensional multi-layer rock images; subtracting the corresponding pore images from the multiple rock contour images to obtain multiple skeleton images with rock skeleton labels corresponding to the multiple first three-dimensional multi-layer rock images; using the multiple first three-dimensional multi-layer rock images, the multiple skeleton images and the multiple pore images to train the parameters of the preset convolutional neural network segmentation model; in the process of training the parameters of the preset convolutional neural network segmentation model, using a classifier to calculate the skeleton probability map and the pore probability map corresponding to the multiple first three-dimensional multi-layer rock images, and simultaneously maximizing the probabilities corresponding to the skeleton probability map and the pore probability map to complete the parameter training of the preset convolutional neural network segmentation model; a segmentation unit is used to perform pore segmentation on the second three-dimensional multi-layer rock image based on the trained preset convolutional neural network segmentation model.

13. A rock porosity determination device, applying or including the pore segmentation device according to claim 12, characterized in that: Also includes: a second acquiring unit, configured to acquire a plurality of rock contour images corresponding to the second three-dimensional multi-layer rock image; A determination unit is used to determine the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images; wherein, determining the porosity corresponding to the porous rock to be segmented based on the multiple pore images and the multiple rock contour images includes: respectively calculating the void volume and rock contour volume corresponding to the multiple pore images and the multiple rock contour images; and dividing the void volume by the rock contour volume to obtain the porosity corresponding to the porous rock to be segmented.

14. A rock evaluation device, applying or including the porosity determination device according to claim 13, characterized in that: Also includes: The third acquisition unit is used to obtain the porosity corresponding to the porous rock to be segmented at multiple moments; A registration unit, configured to register the porosities of the pore rocks to be segmented corresponding to the plurality of moments using a preset registration algorithm, to obtain the porosities of the pores at the corresponding positions; An evaluation unit is used to perform strength evaluation on the porous rock to be segmented based on the porosity of the pores at the corresponding positions.

15. A rock analysis system, characterized in that: include: An electronic device, the electronic device being configured with a processor and a memory for storing instructions executable by the processor; The processor is configured to call the instructions stored in the memory to execute the pore segmentation method according to any one of claims 1 to 3.

16. A rock analysis system, characterized in that: include: An electronic device, the electronic device being configured with a processor and a memory for storing instructions executable by the processor; The processor is configured to call the instructions stored in the memory to execute the porosity determination method according to claim 4.

17. A rock analysis system, characterized in that: include: An electronic device, the electronic device being configured with a processor and a memory for storing instructions executable by the processor; The processor is configured to call the instructions stored in the memory to execute the evaluation method according to any one of claims 5 to 11.

18. A rock analysis system, characterized in that: include: A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the pore segmentation method according to any one of claims 1 to 3.

19. A rock analysis system, characterized in that: include: A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the porosity determination method according to claim 4 when executed by a processor.

20. A rock analysis system, characterized in that: include: A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the evaluation method according to any one of claims 5 to 11.

Images