Deep learning-based implicit 3D reconstruction method and system for rock multi-mineral microstructures

Abstract

The present invention provides a deep learning-based implicit three-dimensional reconstruction method and system for rock multi-mineral microscopic data. The method comprises: obtaining a fractal dimension function of a rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images obtained from the rock specimen; constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen; generating multiple two-dimensional images of the rock using the trained generative adversarial network; and reconstructing a three-dimensional rock model based on the multiple two-dimensional images of the rock specimen when the multiple two-dimensional rock images meet preset accuracy requirements. The present invention achieves three-dimensional rock reconstruction based on a small number of rock microscopic images by constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm.

Description

Technical Field

[0001] The present invention relates to the field of deep learning technology, and in particular to a method and system for deep learning-based implicit three-dimensional reconstruction of rock and multi-mineral microstructures. Background Art

[0002] The microstructural characteristics of rock materials determine the flow evolution of various fluids within the rock (such as oil, natural gas, and CO2 hydrates), the evolution of mechanical properties, and the fracture mechanism of deep rock reservoirs. Accurately characterizing the 3D (3D) microstructure of rock materials and studying their fracture processes and mechanical property evolution have great application prospects and economic value for deep reservoir resource extraction and space development.

[0003] Algorithms for 3D reconstruction of rock materials primarily include direct 3D reconstruction, theoretical 3D reconstruction, random statistical 3D reconstruction techniques, and machine learning-based 3D reconstruction. These techniques can establish 3D rock structural models, promoting research on rock physical and mechanical properties and fracture patterns. However, these existing technologies are limited by factors such as rock material size, imaging resolution, image data volume, and economic costs, making it impossible to create accurate 3D models of rock microstructures. Summary of the Invention

[0004] The present invention provides a method and system for implicit three-dimensional reconstruction of rock multi-mineral microstructures based on deep learning, which is used to solve the defects of the existing technology of rock three-dimensional reconstruction, such as redundant data and small data volume resulting in insufficient accuracy, and realize a method for three-dimensional reconstruction of rock microstructures with higher accuracy using a small amount of data.

[0005] The present invention provides a deep learning-based implicit three-dimensional reconstruction method for rock multi-mineral microstructures, comprising:

[0006] Obtaining a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images obtained based on the rock specimen;

[0007] Constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generating a plurality of two-dimensional images of the rock through the trained generative adversarial network;

[0008] In the case that the multiple two-dimensional images of the rocks meet the preset accuracy conditions, a three-dimensional model of the rock is reconstructed based on the multiple two-dimensional images of the rock samples.

[0009] According to a method for implicit three-dimensional reconstruction of rock multi-mineral microstructures based on deep learning provided by the present invention, before the step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, the method further includes:

[0010] collecting microscopic multiphase images of the rock specimen to obtain the first microscopic image sequence;

[0011] Segmenting the images in the first microscopic image sequence to obtain segmented images of each sub-phase structure of the rock specimen;

[0012] The segmented images of each type of sub-phase structure of the rock specimen are encoded, and a data set for training the generative adversarial network is constructed based on the encoded segmented images.

[0013] According to a deep learning-based implicit three-dimensional reconstruction method for multi-mineral rock microstructures provided by the present invention, the step of segmenting the images in the first microscopic image sequence to obtain segmented images of each sub-phase structure of the rock specimen specifically includes:

[0014] Inputting the images in the first microscopic image sequence into a pre-built deep learning segmentation model to obtain a segmented image of each type of sub-phase structure of the rock specimen output by the deep learning segmentation model;

[0015] Among them, the deep learning segmentation model constructs a loss function based on the rock image microstructure target loss, the real target and predicted target boundary compensation loss and the rock microstructure fractal dimension loss, and is trained using the mineral boundary difference as a low-rank fine-tuning parameter.

[0016] According to a deep learning-based implicit three-dimensional reconstruction method for multi-mineral rock microstructures provided by the present invention, the steps of encoding the segmented images of each subphase structure of the rock specimen and constructing a data set for training the generative adversarial network based on the encoded segmented images specifically include:

[0017] encoding the segmented image corresponding to each image in the first microscopic image sequence with numbers and mineral names according to a preset order;

[0018] The segmented images with numbers and mineral name codes corresponding to each image in the first microscopic image sequence are merged, and the merged images are organized into a data set for training the generative adversarial network.

[0019] According to a deep learning-based implicit three-dimensional reconstruction method for rock multi-mineral microstructures provided by the present invention, the step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen specifically includes:

[0020] Constructing a generator of the generative adversarial network based on the fractal dimension function of the rock specimen;

[0021] Constructing a discriminator of the generative adversarial network based on the difference between the generated distribution and the true distribution;

[0022] A gradient penalty function of the discriminator is constructed based on the boundary similarity parameter.

[0023] According to a rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning provided by the present invention, the preset accuracy conditions include: generalization evaluation index, fractal dimension standard deviation and accuracy rate;

[0024] When the generalization evaluation index is less than a first preset threshold, the fractal dimension standard deviation is not greater than a second preset threshold, and the accuracy is not less than a third preset threshold, it is considered that the two-dimensional image of the rock sample meets the preset accuracy conditions.

[0025] The present invention also provides a rock multi-mineral microscopic implicit three-dimensional reconstruction system based on deep learning, comprising:

[0026] an acquisition module, configured to acquire a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images acquired based on the rock specimen;

[0027] A generation module is used to construct a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generate multiple two-dimensional images of the rock specimen through the trained generative adversarial network;

[0028] The reconstruction module is used to reconstruct a three-dimensional rock model based on the two-dimensional images of the multiple rock samples when the two-dimensional images of the multiple rock samples meet a preset accuracy condition.

[0029] The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for implicit three-dimensional reconstruction of multi-mineral microstructures of rocks based on deep learning as described above is implemented.

[0030] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements any of the deep learning-based implicit three-dimensional reconstruction methods for rock multi-minerals as described above.

[0031] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the deep learning-based rock multi-mineral microscopic implicit three-dimensional reconstruction methods described above.

[0032] The deep learning-based implicit three-dimensional reconstruction method and system of rock multi-mineral microstructures provided by the present invention generates a two-dimensional image of rock with a fractal dimension function similar to the microstructure image of the rock specimen by constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm, and determines the optimal network with the best generalization ability in combination with preset accuracy conditions. Finally, based on the determined generative adversarial network, multiple two-dimensional images of rocks are generated, and a three-dimensional model of the rock is rendered, so that the final three-dimensional rock model can accurately reflect the microstructure of the rock sample, facilitates the precise study of the micro-scale mechanical properties and fracture mechanism of the rock based on the generated three-dimensional rock model, and realizes the three-dimensional reconstruction of the rock based on a small number of rock microscopic images. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0034] Figure 1 This is one of the flow charts of the method for implicit three-dimensional reconstruction of rock multi-mineral microstructures based on deep learning provided by the present invention;

[0035] Figure 2 (a) is a schematic diagram of a microstructure image of a rock specimen in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0036] Figure 2 (b) is a deep learning segmentation model in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0037] Figure 2 (c) is a 0-pore segmentation image in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0038] Figure 2 (d) is a 1-feldspar segmentation image in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0039] Figure 2 (e) is a 2-quartz segmentation image in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0040] Figure 2 (f) is a 3-muscovite segmentation image in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0041] Figure 3 (a) is a schematic diagram of a microstructure image with digital and mineral name coding input into the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0042] Figure 3 (b) in the figure is a plurality of two-dimensional images of rocks generated by MGAN in the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning provided by the present invention;

[0043] Figure 3 (c) is a 3D data set obtained based on multiple two-dimensional images of rocks in the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning provided by the present invention;

[0044] Figure 4 (a) is a three-dimensional rock model reconstructed by the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning provided by the present invention;

[0045] Figure 4 (b) is the 0-pore 3D model reconstructed in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0046] Figure 4 (c) is the reconstructed 1-feldspar 3D model in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0047] Figure 4 (d) is a 2-quartz three-dimensional model reconstructed in the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning provided by the present invention;

[0048] Figure 4 (e) is a 3D model of 3-muscovite reconstructed in the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning provided by the present invention;

[0049] Figure 5 Schematic diagram of the structure of the rock multi-mineral microscopic implicit three-dimensional reconstruction system based on deep learning provided by the present invention;

[0050] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0051] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0052] The following combination Figures 1 to 4 The present invention introduces a rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning, such as Figure 1 Shown, including:

[0053] Step 101: obtaining a fractal dimension function of a rock sample based on a first microscopic image sequence of the rock sample, wherein the first microscopic image sequence represents a small number of images obtained based on the rock sample;

[0054] Based on the processed rock specimen, high-precision modern imaging technology is used to perform high-resolution digital imaging of the microstructure of the rock material to obtain a first microscopic image sequence, wherein the first microscopic image sequence contains a small number of rock microscopic multiphase images. In this embodiment, one image is collected from each of the upper, middle and lower layers of the rock specimen, and the three images obtained are used as the first microscopic image sequence.

[0055] Optionally, each image in the first microscopic image sequence is segmented to obtain a microscopic image of each sub-type of material, and then based on the microscopic image of each type of sub-phase structure, the fractal dimension function of the rock specimen is obtained.

[0056] Step 102: constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generating a plurality of two-dimensional images of the rock through the trained generative adversarial network;

[0057] It can be understood that the fractal dimension function of the rock specimen characterizes the shape and distribution of the sub-phase structure of the rock specimen. Therefore, a generative adversarial network (MGAN) based on the fractal dimension feature pyramid algorithm is constructed and trained based on the fractal dimension function of the rock specimen.

[0058] That is, the pyramid algorithm is integrated into the traditional generative adversarial network (GAN). By calculating the fractal dimension function at different scales, the structural complexity of image data at various resolutions is captured, so that the images generated by the MGAN network trained based on a small number of images have fractal dimension similar to the microstructure images of rock specimens, and the trained MGAN can generate two-dimensional images of rocks with higher accuracy.

[0059] Optionally, during the training process, a GAN network with the best generalization ability is selected as the trained GAN model.

[0060] The trained generative adversarial network generates multiple two-dimensional images of rocks, so that the generated images have a fractal dimension function that is closer to the rock specimens, and can more realistically reflect the structural characteristics of the rock specimens, so as to be used for the study of the micro-scale mechanical properties and fracture mechanisms of rocks.

[0061] Step 103 : When the plurality of two-dimensional rock images meet a preset accuracy condition, a three-dimensional rock model is reconstructed based on the plurality of two-dimensional rock images.

[0062] In order to make the two-dimensional rock images generated by GAN more realistically reflect the microstructure of the rock specimen, after the GAN training is completed, its accuracy needs to be evaluated through pre-set preset accuracy conditions.

[0063] Optionally, the preset accuracy condition includes a generalization ability evaluation condition and / or a model accuracy evaluation condition. The threshold of each evaluation condition can be determined based on experience, and is usually set to be greater than 90%, such as setting the model accuracy to be greater than 90%.

[0064] When the 2D rock images generated by the GAN meet the preset accuracy requirements, the generative adversarial network is considered to be the optimal network with the best generalization ability. Therefore, based on this generative adversarial network, it can sequentially generate multiple layers of 2D rock images, which are then rendered into a 3D rock model. The 2D rock images are images of the rock's microscopic structure characteristics.

[0065] For example, 300 layers of rock 2D images are generated with an image size of 300×300. The generated 300 rock 2D images are constructed into a 3D dataset, and rendered to obtain a 300×300×300 rock 3D model.

[0066] The present invention constructs a generative adversarial network based on a fractal dimension feature pyramid algorithm to generate a two-dimensional image of a rock that is similar to the fractal dimension function of the microstructure image of the rock specimen, and determines the optimal network with the best generalization ability in combination with preset accuracy conditions. Finally, based on the determined generative adversarial network, multiple two-dimensional images of the rock are generated and rendered to obtain a three-dimensional model of the rock. The final three-dimensional rock model can accurately reflect the microstructure of the rock specimen, facilitate the precise study of the micro-scale mechanical properties and fracture mechanism of the rock based on the generated three-dimensional rock model, and realize the three-dimensional reconstruction of the rock based on a small number of rock microscopic images.

[0067] In the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning of the present invention, before the step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, the method further includes:

[0068] collecting microscopic multiphase images of the rock specimen to obtain the first microscopic image sequence;

[0069] Segmenting the images in the first microscopic image sequence to obtain segmented images of each sub-phase structure of the rock specimen;

[0070] The segmented images of each type of sub-phase structure of the rock specimen are encoded, and a data set for training the generative adversarial network is constructed based on the encoded segmented images.

[0071] Rock specimens of certain standard sizes are processed and manufactured. In this embodiment, standard sandstone thin section specimens with a length, width, and height of 20 mm, 20 mm, and 2 mm, respectively, are manufactured. High-precision modern imaging technology, such as EBSD (Electron Backscatter Diffraction, scanning electron microscope) imaging technology, is used to perform high-resolution digital imaging of the microstructure of the sandstone material. In this embodiment, the resolution of the obtained microstructure image is 5 μm, and the corresponding microscopic multiphase image is 500 pixels, with a size of 500×500.

[0072] It should be noted that, in acquiring microscopic multiphase images, this embodiment does not require the rock specimen to be divided into layers as much as possible. To acquire microscopic multiphase images of each layer of the rock specimen, only a small number of images are required to complete the three-dimensional reconstruction of the rock.

[0073] Specifically, in this embodiment, a microscopic structure image is obtained from each of the top, middle and bottom of the rock sample, and the three microscopic images are used as the first microscopic image sequence.

[0074] In other feasible implementations, the rock sample may be divided into two parts, an upper part and an lower part, and a microstructure image is obtained from each of the upper part and the lower part, and the obtained two images are used as the first microscopic image sequence.

[0075] On this basis, each microscopic multiphase image is segmented to obtain the segmented image of each type of subphase structure of the rock sample in each image, such as Figure 2 As shown. Since sandstone is selected as the rock sample in this embodiment, the subphase structure of the rock sample includes Figure 2 The pores shown in (c) Figure 2 Feldspar shown in (d) Figure 2 The quartz shown in (e) and Figure 2 Muscovite shown in (f).

[0076] That is to say, each microstructure image is segmented to obtain segmented images of these four types of sub-phase structures.

[0077] Further, if Figure 3As shown in , the segmentation structure of each sub-phase corresponding to each microstructure is encoded as the label of the image, and a dataset for training MGAN is constructed based on the encoded image, so that the image output by MGAN also contains the encoding of each sub-phase structure, as shown in Figure 3 As shown in (c) in the figure.

[0078] In the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning of the present invention, before the step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, the method further includes:

[0079] encoding the segmented image corresponding to each image in the first microscopic image sequence with numbers and mineral names according to a preset order;

[0080] The segmented images with numbers and mineral name codes corresponding to each image in the first microscopic image sequence are merged, and the merged images are organized into a data set for training the generative adversarial network.

[0081] Optionally, the segmented images are coded with numbers and mineral names in a clockwise order from top to bottom as a preset order.

[0082] For example, the code is 0-pore structure, 1-feldspar, 2-quartz, 3-muscovite.

[0083] Furthermore, for each microstructure image, all the segmented images with numbers and mineral code names are merged to obtain microstructure images coded with numbers and mineral names, and used as the dataset for training MGAN, as shown in the following example: Figure 3 As shown in (a) in .

[0084] In the rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning of the present invention, the step of segmenting the images in the first microscopic image sequence to obtain the segmented images of each sub-phase structure of the rock specimen specifically includes:

[0085] Inputting the images in the first microscopic image sequence into a pre-built deep learning segmentation model to obtain a segmented image of each type of sub-phase structure of the rock specimen output by the deep learning segmentation model;

[0086] Among them, the deep learning segmentation model constructs a loss function based on the rock image microstructure target loss, the real target and predicted target boundary compensation loss and the rock microstructure fractal dimension loss, and is trained using the mineral boundary difference as a low-rank fine-tuning parameter.

[0087] In order to achieve accurate recognition and segmentation of each type of sub-phase structure, a deep learning segmentation model (MFD-UNet) based on multi-phase feature loss function and low-rank fine-tuning parameters is pre-constructed in this embodiment.

[0088] Specifically, the multiphase feature loss function is composed of a weighted average of the rock image microstructure target loss, the boundary compensation loss between the real target and the predicted target, and the rock microstructure fractal dimension loss:

[0089] ;

[0090] Where, is the total loss function, is the target loss function of the rock image microstructure, Compensate the loss function for the boundary between the real target and the predicted target, is the fractal dimension loss function of rock microstructure; 、 and are the weight values ​​of the three types of loss functions respectively.

[0091] To predict the microstructure prototype coefficient, is the true microstructure prototype coefficient, To predict the microstructure boundary prototype coefficient, is the prototype coefficient of the real microstructure boundary.

[0092] In order to further improve the segmentation accuracy, the mineral boundary difference is used as a low-rank fine-tuning parameter to fine-tune the parameters of MFD-UNet:

[0093] ;

[0094] Where, represents the low-rank fine-tuning parameter, N represents the image dimension, represents the prediction boundary, Indicates the true boundary.

[0095] In the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning of the present invention, the step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen specifically includes:

[0096] Constructing a generator of the generative adversarial network based on the fractal dimension function of the rock specimen;

[0097] Constructing a discriminator of the generative adversarial network based on the difference between the generated distribution and the true distribution;

[0098] A gradient penalty function of the discriminator is constructed based on the boundary similarity parameter.

[0099] In order to generate a more accurate two-dimensional rock image based on a small amount of rock microstructure images, in this embodiment, a generative adversarial network based on a fractal dimension feature pyramid algorithm is constructed.

[0100] Specifically, the generator of the generative adversarial network is constructed based on the fractal dimension function of the rock specimen. , construct a discriminator based on the difference between the generated distribution and the true distribution , construct a gradient penalty function based on boundary similarity parameters :

[0101] ;

[0102] Where, PDF is the conditional probability density, MP fd represents the fractal dimension function, N s represents the number of similar objects, S represents the scaling factor, E For expectations, K is the gradient penalty function, P gdata Generate a distribution for the rock microstructure, P tdata is the true distribution, λ is the gradient penalty function, is the discriminator gradient, is the L2 norm, represents the generating function based on the fractal dimension function.

[0103] Through the above method, a generalized adversarial deep learning network (MGAN) for multi-layer image generation based on the fractal dimension function feature pyramid algorithm (FPN) can be constructed. A dataset with numbers and mineral name codes is used as input parameters, and hyperparameters such as the batch size, learning rate, and number of iterations of the MGAN model are adjusted to train the MGAN.

[0104] In the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning of the present invention, the preset accuracy conditions include: generalization evaluation index, fractal dimension standard deviation and accuracy rate;

[0105] When the generalization evaluation index is less than a first preset threshold, the fractal dimension standard deviation is not greater than a second preset threshold, and the accuracy is not less than a third preset threshold, it is considered that the two-dimensional image of the rock sample meets the preset accuracy conditions.

[0106] In this implementation, in order to obtain the optimal MGAN model with the best generalization ability, the generalization evaluation index, fractal dimension standard deviation, and accuracy are used as preset accuracy conditions to evaluate the generation accuracy of the MGAN model obtained by preliminary training:

[0107] ;

[0108] Where, F precision is the generalization evaluation index (the closer it is to 0, the better the generalization performance), STD fd is the standard deviation of the fractal dimension, is the accuracy, TP, TN, FP and FN are true positive, true negative, false positive and false negative, respectively.

[0109] The rock microstructure dataset with numbers and mineral name codes (such as 0-pore structure, 1-feldspar, 2-quartz, 3-muscovite) was divided into training set (30%), test set and validation set (70%) according to the division ratio. The MGAN model was trained by adjusting the hyperparameters such as batch size (2), learning rate (0.98) and number of iterations (100). When it is close to 0, that is, less than the first preset threshold determined by experience, it is considered that the MGAN generalization ability is optimal. is not greater than a second preset threshold, which is 0.1 in this embodiment, and When the value is not less than a third preset threshold value, which is 0.95 in this embodiment, the model accuracy is considered to be the highest.

[0110] On this basis, the final MGAN model is used to generate a two-dimensional microstructural feature image of sequential multi-layer rocks, and a three-dimensional model of the rock is rendered, such as Figure 4 shown.

[0111] It should be noted that the MGAN trained on the rock microstructure dataset with numbers and mineral name codes also outputs two-dimensional images with numbers and mineral name codes, such as Figure 3 As shown in (c), on this basis, the three-dimensional model obtained by rendering based on the output two-dimensional image is as follows: Figure 4 (a) in the figure can also be used to obtain the three-dimensional model of each sub-phase structure by extracting the code, such as Figure 4 As shown in (b), (c), (d) and (e).

[0112] The rock multi-mineral microscopic implicit three-dimensional reconstruction system based on deep learning provided by the present invention is described below. The rock multi-mineral microscopic implicit three-dimensional reconstruction system based on deep learning described below and the rock multi-mineral microscopic implicit three-dimensional reconstruction method based on deep learning described above can be referenced to each other.

[0113] like Figure 5 As shown, the rock multi-mineral microscopic implicit 3D reconstruction system based on deep learning includes an acquisition module 501, a generation module 502 and a reconstruction module 503:

[0114] An acquisition module 501 is configured to acquire a fractal dimension function of a rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images acquired based on the rock specimen;

[0115] Based on the processed rock specimen, high-precision modern imaging technology is used to perform high-resolution digital imaging of the microstructure of the rock material to obtain a first microscopic image sequence, wherein the first microscopic image sequence contains a small number of rock microscopic multiphase images. In this embodiment, one image is collected from each of the upper, middle and lower layers of the rock specimen, and the three images obtained are used as the first microscopic image sequence.

[0116] Optionally, each image in the first microscopic image sequence is segmented to obtain a microscopic image of each sub-type of material, and then based on the microscopic image of each type of sub-phase structure, the fractal dimension function of the rock specimen is obtained.

[0117] A generation module 502 is configured to construct a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generate a plurality of two-dimensional images of the rock specimen through the trained generative adversarial network;

[0118] It can be understood that the fractal dimension function of the rock specimen characterizes the shape and distribution of the sub-phase structure of the rock specimen. Therefore, a generative adversarial network (MGAN) based on the fractal dimension feature pyramid algorithm is constructed and trained based on the fractal dimension function of the rock specimen.

[0119] That is, the pyramid algorithm is integrated into the traditional generative adversarial network (GAN). By calculating the fractal dimension function at different scales, the structural complexity of image data at various resolutions is captured, so that the images generated by the MGAN network trained based on a small number of images have fractal dimension similar to the microstructure images of rock specimens, and the trained MGAN can generate two-dimensional images of rocks with higher accuracy.

[0120] Optionally, during the training process, a GAN network with the best generalization ability is selected as the trained GAN model.

[0121] The trained generative adversarial network generates multiple two-dimensional images of rocks, so that the generated images have a fractal dimension function that is closer to the rock specimens, and can more realistically reflect the structural characteristics of the rock specimens, so as to be used for the study of the micro-scale mechanical properties and fracture mechanisms of rocks.

[0122] The reconstruction module 503 is configured to reconstruct a three-dimensional rock model based on the two-dimensional images of the multiple rock samples when the two-dimensional images of the multiple rock samples meet a preset accuracy condition.

[0123] In order to make the two-dimensional rock images generated by GAN more realistically reflect the microstructure of the rock specimen, after the GAN training is completed, its accuracy needs to be evaluated through pre-set preset accuracy conditions.

[0124] Optionally, the preset accuracy condition includes a generalization ability evaluation condition and / or a model accuracy evaluation condition. The threshold of each evaluation condition can be determined based on experience, and is usually set to be greater than 90%, such as setting the model accuracy to be greater than 90%.

[0125] When the 2D rock images generated by the GAN meet the preset accuracy requirements, the generative adversarial network is considered to be the optimal network with the best generalization ability. Therefore, based on this generative adversarial network, it can sequentially generate multiple layers of 2D rock images, which are then rendered into a 3D rock model. The 2D rock images are images of the rock's microscopic structure characteristics.

[0126] Figure 6 An example of a physical structure diagram of an electronic device is shown below. Figure 6 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 communicate with each other via the communications bus 640. The processor 610 may call logic instructions in the memory 630 to execute a deep learning-based implicit three-dimensional reconstruction method for multi-mineral microscopic rocks. The method includes: obtaining a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images obtained based on the rock specimen; constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen; generating multiple two-dimensional images of the rock using the trained generative adversarial network; and reconstructing a three-dimensional rock model based on the multiple two-dimensional images of the rock specimen when the multiple two-dimensional images of the rock meet a preset accuracy condition.

[0127] Furthermore, the logic instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0128] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the deep learning-based rock multi-mineral microscopic implicit three-dimensional reconstruction method provided by the above-mentioned methods. The method includes: obtaining a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images obtained based on the rock specimen; constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generating multiple two-dimensional images of rocks through the trained generative adversarial network; when the two-dimensional images of the multiple rocks meet the preset accuracy conditions, reconstructing a three-dimensional rock model based on the two-dimensional images of the multiple rock samples.

[0129] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the deep learning-based rock multi-mineral microscopic implicit three-dimensional reconstruction method provided by the above-mentioned methods, the method comprising: obtaining a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images obtained based on the rock specimen; constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generating multiple two-dimensional images of rocks through the trained generative adversarial network; when the two-dimensional images of the multiple rocks meet the preset accuracy conditions, reconstructing a three-dimensional rock model based on the two-dimensional images of the multiple rock samples.

[0130] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0131] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A deep learning-based implicit 3D reconstruction method for rock multi-mineral microstructures, characterized by: include: Obtaining a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images obtained based on the rock specimen; Constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generating a plurality of two-dimensional images of the rock through the trained generative adversarial network; When the two-dimensional images of the plurality of rocks meet a preset accuracy condition, reconstructing a three-dimensional rock model based on the two-dimensional images of the plurality of rock samples; The generative adversarial network is constructed in the following way: Constructing a generator for generative adversarial networks based on the fractal dimension function of rock specimens , construct a discriminator based on the difference between the generated distribution and the true distribution , construct a gradient penalty function based on boundary similarity parameters : ； Where, PDF is the conditional probability density, MP fd represents the fractal dimension function, N s represents the number of similar objects, S represents the scaling factor, E For expectations, K is the gradient penalty function, P gdata Generate a distribution for rock microstructure, P tdata is the true distribution, λ is the gradient penalty function, is the discriminator gradient, is the L2 norm, represents the generating function based on the fractal dimension function.

2. The rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning according to claim 1 is characterized in that: Before the step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, the method further includes: collecting microscopic multiphase images of the rock specimen to obtain the first microscopic image sequence; Segmenting the images in the first microscopic image sequence to obtain segmented images of each sub-phase structure of the rock specimen; The segmented images of each type of sub-phase structure of the rock specimen are encoded, and a data set for training the generative adversarial network is constructed based on the encoded segmented images.

3. The rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning according to claim 2 is characterized in that: The step of segmenting the images in the first microscopic image sequence to obtain segmented images of each sub-phase structure of the rock specimen specifically includes: Inputting the images in the first microscopic image sequence into a pre-built deep learning segmentation model to obtain a segmented image of each type of sub-phase structure of the rock specimen output by the deep learning segmentation model; Among them, the deep learning segmentation model constructs a loss function based on the rock image microstructure target loss, the real target and predicted target boundary compensation loss and the rock microstructure fractal dimension loss, and is trained using the mineral boundary difference as a low-rank fine-tuning parameter.

4. The rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning according to claim 2 is characterized in that: The step of encoding the segmented image of each type of sub-phase structure of the rock specimen and constructing a data set for training the generative adversarial network based on the encoded segmented image specifically includes: encoding the segmented image corresponding to each image in the first microscopic image sequence with numbers and mineral names according to a preset order; The segmented images with numbers and mineral name codes corresponding to each image in the first microscopic image sequence are merged, and the merged images are organized into a data set for training the generative adversarial network.

5. The rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning according to any one of claims 1 to 4, characterized in that: The step of constructing a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen specifically includes: Constructing a generator of the generative adversarial network based on the fractal dimension function of the rock specimen; Constructing a discriminator of the generative adversarial network based on the difference between the generated distribution and the true distribution; A gradient penalty function of the discriminator is constructed based on the boundary similarity parameter.

6. The rock multi-mineral microscopic implicit 3D reconstruction method based on deep learning according to any one of claims 1 to 4, characterized in that: The preset accuracy conditions include: generalization evaluation index, fractal dimension standard deviation and accuracy; When the generalization evaluation index is less than a first preset threshold, the fractal dimension standard deviation is not greater than a second preset threshold, and the accuracy is not less than a third preset threshold, it is considered that the two-dimensional image of the rock sample meets the preset accuracy conditions.

7. A rock multi-mineral microscopic implicit 3D reconstruction system, characterized by: include: an acquisition module, configured to acquire a fractal dimension function of the rock specimen based on a first microscopic image sequence of the rock specimen, wherein the first microscopic image sequence represents a small number of images acquired based on the rock specimen; A generation module is used to construct a generative adversarial network based on a fractal dimension feature pyramid algorithm based on the fractal dimension function of the rock specimen, and generate multiple two-dimensional images of the rock specimen through the trained generative adversarial network; a reconstruction module, configured to reconstruct a three-dimensional rock model based on the two-dimensional images of the plurality of rock samples when the two-dimensional images of the plurality of rock samples meet a preset accuracy condition; The generative adversarial network is constructed in the following way: Constructing a generator for generative adversarial networks based on the fractal dimension function of rock specimens , construct a discriminator based on the difference between the generated distribution and the true distribution , construct a gradient penalty function based on boundary similarity parameters : ； Where, PDF is the conditional probability density, MP fd represents the fractal dimension function, N s represents the number of similar objects, S represents the scaling factor, E For expectations, K is the gradient penalty function, P gdata Generate a distribution for the rock microstructure, P tdata is the true distribution, λ is the gradient penalty function, is the discriminator gradient, is the L2 norm, represents the generating function based on the fractal dimension function.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the rock multi-mineral microscopic implicit three-dimensional reconstruction method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the rock multi-mineral microscopic implicit three-dimensional reconstruction method as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the rock multi-mineral microscopic implicit three-dimensional reconstruction method as claimed in any one of claims 1 to 6 is implemented.

Images