Graph representation learning driven electrical imaging well logging fracture online identification method and system

Abstract

The application discloses a kind of graph representation learning driven electric imaging well logging fracture online identification method and system, it is related to geological resource exploration and exploitation field, this method includes: the real-time electric imaging well logging fracture data obtained is divided into several sequence electric imaging segment graphs;Each sequence electric imaging segment graph is carried out binaryzation processing and denoising processing, and binaryzation segment graph is obtained;According to binaryzation segment graph, determine original path graph;According to engineering-geology priori knowledge, the spatial features and morphological features of each node in original path graph are determined and the corresponding node is embedded, to obtain the reconstructed knowledge path graph, and projected to high-dimensional feature space, the high-dimensional space distance of different segments is calculated;The segments with distance lower than threshold value are connected, to obtain recombination element fracture knowledge graph;Recombination element fracture knowledge graph is input into graph representation learning driven fracture intelligent identification model, to obtain fracture class.The present application can realize the non-perfect fracture intelligent online identification based on electric imaging in field.

Description

Technical Field

[0001] The present invention relates to the technical field of geological resource exploration and mining, and in particular to a method and system for online identification of electrical imaging logging fractures driven by graph representation learning. Background Art

[0002] The exploitation of underground energy resources, including oil, natural gas, and geothermal resources, plays a vital role in global economic activity and relies heavily on the continuous development of advanced exploration technologies. Natural fractures, as crucial media for underground energy storage and seepage, can effectively describe and evaluate subsurface reservoir properties. Therefore, accurately extracting, identifying, and interpreting natural fractures in reservoirs is a key engineering challenge.

[0003] Electrical imaging logging, based on the differences in microresistance response between reservoir rock background and pores and vugs, can effectively and intuitively depict reservoir fractures and vugs, offering advantages such as wide borehole coverage and high vertical resolution. Furthermore, fracture detection, which extracts and interprets the distribution of natural fractures from discrete micro-electrical scanning data, is a key step in the quantitative description and evaluation of reservoir properties. However, unlike ideal laboratory simulations, field electrical imaging logging data inevitably suffers from incompleteness, primarily manifested in missing data due to sensor failure, strong background noise from widespread pore-vug-sedimentation, and incomplete natural fracture segments due to fragmentation and missing data. This incomplete data issue is a significant constraint on the intelligent use of electrical imaging, resulting in field exploration interpretation still relying on the expert knowledge and manual identification of field engineers. To reduce manual intervention and improve field efficiency, automating the reservoir natural fracture detection process is a critical issue that urgently needs research.

[0004] With the advent of the artificial intelligence era, a large number of algorithms based on machine learning or deep learning have been used to try to solve the problem of crack detection automation. Academia and industry have begun to try to use some intelligent models to identify natural cracks, but there are still some limitations.

[0005] 1) Traditional computer vision-driven methods are generally limited to processing well-imaged natural fractures, i.e., complete continuous sinusoidal curves. The key reason for this is that edge detection and segmentation algorithms cannot recognize the physical meaning of pixels and have difficulty processing broken fractures.

[0006] 2) Similarly, when holes and cracks intersect, it is difficult for a purely visually driven model to accurately separate the two, resulting in rough model recognition accuracy.

[0007] 3) The crack area in electrical imaging is considered as a whole, ignoring the prior knowledge contained in the correlation between pixels. This knowledge contains rich geographical and engineering information and can provide key characterization for crack detection.

[0008] Based on this, there is an urgent need for a high-precision, automated method and system for rapid identification of reservoir fractures based on electrical imaging logging to provide an intelligent solution for complex field logging exploration and interpretation tasks. Summary of the Invention

[0009] The purpose of the present invention is to provide a method and system for online identification of electrical imaging logging fractures driven by graph representation learning, which can realize intelligent online identification of incomplete fractures based on electrical imaging on site.

[0010] To achieve the above objectives, the present invention provides the following solutions.

[0011] In a first aspect, the present invention provides a graph representation learning-driven electrical imaging logging fracture identification method, the graph representation learning-driven electrical imaging logging fracture identification method comprising.

[0012] The acquired real-time electrical imaging logging fracture data is segmented into a plurality of first sequence electrical imaging segment images.

[0013] Each of the first sequence of electrical imaging fragment images is binarized to obtain a first binarized image, wherein the first binarized image is a plurality of binarized images containing only cracks and holes.

[0014] The first binarized image is subjected to denoising to obtain a first binarized segment image; the first binarized segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects.

[0015] A first original path graph is determined based on the first binarized segment graph; the first original path graph is an image obtained by connecting first nodes according to open interval path connectivity; the first nodes are bright pixels in the first binarized segment graph.

[0016] Based on engineering-geological prior knowledge, the spatial characteristics and morphological characteristics of each first node in the first original path diagram are determined; the spatial characteristics are the horizontal and vertical coordinates of all first nodes in the two-dimensional spatial coordinate system; the morphological characteristics are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio and inclination of each first node and each first node's neighboring nodes within the circular verification threshold.

[0017] The spatial features and morphological features of each first node are embedded into the corresponding first node to obtain a first reconstructed knowledge path graph.

[0018] The first reconstructed knowledge path graph is projected into a high-dimensional feature space, and the high-dimensional space distances of the knowledge path graphs corresponding to different fragments are calculated.

[0019] The segments of the knowledge path graph whose high-dimensional space distance is lower than a first preset threshold are connected to obtain a first recombinant meta-crack knowledge graph.

[0020] The first recombinant meta-fracture knowledge graph is input into a graph representation learning-driven fracture intelligent identification model to obtain fracture types; the graph representation learning-driven fracture intelligent identification model is a model established based on a graph convolutional neural network.

[0021] In a second aspect, the present invention provides a graph representation learning-driven electrical imaging logging fracture identification system, and the graph representation learning-driven electrical imaging logging fracture identification system includes.

[0022] The segmentation module is used to segment the acquired real-time electrical imaging logging fracture data into a plurality of first sequence electrical imaging segment images.

[0023] The binarization processing module is used to perform binarization processing on each of the first sequence of electrical imaging fragment images to obtain a first binarized image, wherein the first binarized image is a plurality of binarized images containing only cracks and holes.

[0024] The denoising processing module is used to perform denoising on the image after the first binarization processing to obtain a first binarization segment image; the first binarization segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects.

[0025] The first original path graph determination module is used to determine a first original path graph based on the first binarized segment graph; the first original path graph is an image obtained by connecting the first nodes according to the open interval path connectivity; the first nodes are bright pixels in the first binarized segment graph.

[0026] The spatial feature and morphological feature determination module is used to determine the spatial features and morphological features of each first node in the first original path diagram based on engineering-geological prior knowledge; the spatial features are the horizontal and vertical coordinates of all first nodes in the two-dimensional spatial coordinate system; the morphological features are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio and inclination of each first node and each first node's neighboring nodes within the circular verification threshold.

[0027] The embedding module is used to embed the spatial features and morphological features of each first node into the corresponding first node to obtain a first reconstructed knowledge path graph.

[0028] A projection module is used to project the first reconstructed knowledge path graph into a high-dimensional feature space and calculate the high-dimensional space distance between the knowledge path graphs corresponding to different fragments.

[0029] The fragment connection module is used to connect the fragments of the knowledge path graph whose high-dimensional space distance is lower than a first preset threshold to obtain a first recombinant meta-crack knowledge graph.

[0030] The crack identification module is used to input the first recombined meta-crack knowledge graph into a crack intelligent identification model driven by graph representation learning to obtain crack types; the crack intelligent identification model driven by graph representation learning is a model established based on a graph convolutional neural network.

[0031] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] The present invention provides a method and system for online identification of electrical imaging logging fractures driven by graph representation learning. First, the acquired real-time electrical imaging logging fracture data is divided into a plurality of first-sequence electrical imaging segment graphs; each of the first-sequence electrical imaging segment graphs is binarized to obtain a first binarized image, which is a plurality of binarized images containing only fractures-holes; the first binarized image is denoised to obtain a first binarized segment graph; the first binarized segment graph is a plurality of images containing only natural fractures and broken natural fracture segments as research objects; secondly, a first original path graph is determined based on the first binarized segment graph; the first original path graph is an image obtained by connecting the first nodes according to the path connectivity between open intervals; the first node is a bright pixel in the first binarized segment graph; further, based on engineering-geology prior knowledge, the first original path graph is determined. The spatial and morphological features of each first node are as follows: the spatial features are the horizontal and vertical coordinates of all first nodes in a two-dimensional spatial coordinate system; the morphological features are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio, and inclination of each first node and its neighboring nodes within a circular verification threshold; the spatial and morphological features of each first node are embedded into the corresponding first node to obtain a first reconstructed knowledge path graph; then, the first reconstructed knowledge path graph is projected into a high-dimensional feature space, and the high-dimensional spatial distances of the knowledge path graphs corresponding to different segments are calculated; segments of the knowledge path graph whose high-dimensional spatial distances are less than a first preset threshold are connected to obtain a first reconstructed meta-fracture knowledge graph; finally, the first reconstructed meta-fracture knowledge graph is input into a graph representation learning-driven intelligent fracture identification model to obtain fracture types; the graph representation learning-driven intelligent fracture identification model is a model established based on a graph convolutional neural network. The present invention uses a graph representation learning method to empower the geological reservoir exploration process, embedding prior knowledge in the geological field to construct a graph, and can achieve efficient identification of oil and gas reservoir fractures without relying on on-site manual labor. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only 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 A flowchart of a method for identifying fractures in electrical imaging logging driven by graph representation learning is provided in one embodiment of the present invention.

[0035] Figure 2A schematic flow chart of an online intelligent identification method for reservoir electrical imaging logging fractures embedded with a priori knowledge graph representation provided by one embodiment of the present invention.

[0036] Figure 3 A schematic diagram of a micro-electrical scanning imaging logging system provided in one embodiment of the present invention.

[0037] Figure 4 This is a schematic diagram of a segmented on-site microresistance scanning imaging logging image provided by one embodiment of the present invention.

[0038] Figure 5 A schematic diagram of graph structure data provided by an embodiment of the present invention.

[0039] Figure 6 A schematic diagram of converting electrical imaging data into a crack path diagram according to an embodiment of the present invention.

[0040] Figure 7 A schematic diagram of the construction and training process of a crack recognition model based on a graph convolutional neural network provided in one embodiment of the present invention.

[0041] Figure 8 A schematic diagram of the storage fracture identification results of electrical imaging logging provided by one embodiment of the present invention.

[0042] Figure 9 Schematic diagram of comparative test results of multiple methods and models in data set (a) provided by one embodiment of the present invention.

[0043] Figure 10 Schematic diagram of comparative test results of multiple methods and models in data set (b) provided by one embodiment of the present invention.

[0044] Figure 11 Schematic diagram of comparative test results for setting the hole length noise reduction threshold L provided in one embodiment of the present invention.

[0045] Figure 12 A schematic diagram of the functional modules of a graph representation learning-driven electrical imaging logging fracture identification system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] The purpose of the present invention is to solve the problems in the prior art of poor accuracy of incomplete fracture identification caused by reliance on manual experience annotation for electrical imaging logging interpretation and lack of prior knowledge guidance for the model.

[0049] To achieve the above objectives, the present invention provides a method and system for online fracture identification using electrical imaging logging driven by graph representation learning. This method uses graph representation learning to empower geological reservoir exploration, embedding prior geological knowledge into the graph to efficiently identify fractures in oil and gas reservoirs without relying on on-site manual work. Furthermore, by calculating the spatial and morphological characteristics of fractures, it accurately identifies and matches natural fracture segments, enabling intelligent online identification of incomplete fractures using electrical imaging. This method is simple in structure, easy to operate, and has low implementation costs.

[0050] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a graph representation learning-driven electrical imaging logging fracture identification method is provided, and the graph representation learning-driven electrical imaging logging fracture identification method includes.

[0051] S1: Segmenting the acquired real-time electrical imaging logging fracture data into a plurality of first sequence electrical imaging segment images.

[0052] S2: performing binarization processing on each of the first sequence of electrical imaging fragment images to obtain a first binarized image, wherein the first binarized image is a plurality of binarized images containing only cracks and holes.

[0053] S3: Denoising the image after the first binarization process to obtain a first binarization segment image; the first binarization segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects.

[0054] S4: Determine a first original path graph based on the first binarized segment graph; the first original path graph is an image obtained by connecting the first nodes according to open interval path connectivity; the first nodes are bright pixels in the first binarized segment graph.

[0055] S5: Based on engineering-geological prior knowledge, determine the spatial characteristics and morphological characteristics of each first node in the first original path diagram; the spatial characteristics are the horizontal and vertical coordinates of all first nodes in the two-dimensional space coordinate system; the morphological characteristics are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio and inclination of each first node and each first node's neighboring nodes within the circular verification threshold.

[0056] S6: Embed the spatial features and morphological features of each first node into the corresponding first node to obtain a first reconstructed knowledge path graph.

[0057] S7: Project the first reconstructed knowledge path graph into a high-dimensional feature space, and calculate the high-dimensional space distance between the knowledge path graphs corresponding to different segments.

[0058] S8: Connect the segments of the knowledge path graph whose high-dimensional space distance is lower than a first preset threshold to obtain a first recombinant meta-crack knowledge graph.

[0059] S9: Inputting the first recombinant meta-fracture knowledge graph into a graph representation learning-driven fracture intelligent identification model to obtain fracture types; the graph representation learning-driven fracture intelligent identification model is a model established based on a graph convolutional neural network.

[0060] By implementing the above steps S1 to S9, the present invention uses a graph representation learning method to empower the geological reservoir exploration process, embeds prior knowledge composition in the geological field, and can achieve efficient identification of oil and gas reservoir fractures without relying on on-site manual work.

[0061] As an optional implementation, in step S1, based on the instrument model and on-site geological characteristics, a rectangular sliding window of a certain specification is used to segment the acquired continuous long-segment real-time electrical imaging logging data into a plurality of first-sequence electrical imaging segment images.

[0062] As an optional implementation, in step S2, the original image is binarized based on the microresistivity response differences of the on-site rock formations and holes, and the fracture-hole objects to be studied are extracted from the formation background.

[0063] Specifically, such as Figure 3 As shown, the electrical imaging logging fracture data used in this embodiment is collected by field logging using a microresistance scanning imaging system. The microresistance scanning imaging system comprises two components: a microelectrical scanning logging device and a logging interpretation system. The microelectrical scanning logging device is used to continuously advance through the formation and record the microcurrent values ​​flowing in the rock formation and fractures. The logging interpretation system converts the measured discrete values ​​into interpretable electrical imaging data based on the current-resistance formula and the wellbore response. The instrument used is the MCI6575 microresistivity imager, and its key parameters are shown in Table 1 below.

[0064] Table 1 Key parameters of microresistivity imager MCI6575

[0065]

[0066] In this example, the electrical imaging logging data at depths of 3066 to 3723 meters were selected as the main analysis object, and data from two other wells with similar depths and geological conditions were added to test the generalization ability of the proposed method. Furthermore, a sliding window of 360*360 pixels was used to segment the original long electrical imaging logging image into multiple sequentially spliced ​​sub-images. By interleaving and rotating the image, 2112 field images were obtained for experimental verification. The obtained electrical imaging logging segmentation sub-images are shown in Figure 2. Figure 4 shown.

[0067] Specifically, relying on prior knowledge of formation microresistance logging, combined with laboratory experimental principles and field engineering experience, a binarization threshold is determined that accurately distinguishes the formation background from the fracture-pore research objects based on the different resistivity responses caused by differences in formation-pore water content. Regions with resistivity below this threshold are converted to white pixel blocks, and those with resistivity below this threshold are converted to black pixel blocks, resulting in a binary image containing only fractures and pores. This example uses a binarization algorithm encapsulated in the Python-Opencv module, sets the image light sensitivity coefficient to 25, and separates the fractures from the background rock layer to obtain a binary logging image containing only fractures and pores.

[0068] As an optional implementation, in step S3, it specifically includes.

[0069] S31: Calculate all connected domains of open intervals in the first binarized image using an edge detection algorithm to obtain first labeled candidate individual objects; the first labeled candidate individual objects are a number of labeled candidate crack-hole-silt open interval individual objects.

[0070] S32: Calculating basic morphological features of the first marked candidate individual object; the basic morphological features include: length, longitudinal width, transverse width, longitudinal aspect ratio, and transverse aspect ratio.

[0071] S33: According to prior geological knowledge, on-site logging conditions, and the basic morphological characteristics, a first length threshold is set to remove hole-sediment noise to obtain a first binarized segment image.

[0072] In step S3, an edge detection algorithm is used to calculate all the connected domains between open intervals in the fragment graph to obtain the marked candidate fracture-pore-sediment individual objects; further, the length threshold L is used to filter and reduce noise to remove holes and sediment in the fragment graph to obtain a binary fragment graph containing only research objects such as natural fractures and broken natural fracture segments.

[0073] Specifically, five parameters were calculated for each candidate fracture-void-sediment interval: length, longitudinal width, transverse width, longitudinal aspect ratio, and transverse aspect ratio. These parameters are used to describe the basic morphological characteristics of each candidate fracture-void-sediment interval. The maximum path length traversing all nodes in the interval is taken as the maximum value; the transverse width of the interval is calculated by traversing all nodes and taking the average of the transverse path lengths; and the longitudinal width of the interval is calculated by traversing all nodes and taking the average of the longitudinal path lengths. Furthermore, the ratio of the length to the transverse width is recorded as the transverse aspect ratio, and the ratio of the length to the longitudinal width is recorded as the longitudinal aspect ratio. Finally, based on prior geological knowledge and field logging data, a threshold value L = 70 was set for each interval parameter to remove vug-sediment noise.

[0074] In an exemplary embodiment, step S4 specifically includes:

[0075] S41: Projecting the first binarized segment image into a two-dimensional space coordinate system of the same size to obtain the spatial coordinates of each first pixel point.

[0076] S42: Determine a first original path map according to the spatial coordinates of each of the first pixel points.

[0077] Specifically, the first binary fragment graph is projected into a two-dimensional spatial coordinate system of the same size to obtain the spatial coordinates of each pixel point; then, according to the graph representation learning theory, the bright pixels in the fragment graph are regarded as nodes, and the nodes are connected according to the open interval path connectivity to form a first original path graph, that is, a graph structure representation form of the natural crack segment; and edge connections are created between the nodes based on the spatial correlation degree calculated by Euclidean distance, and the open intervals of the alternative crack segment path are converted into a path graph matching the original form.

[0078] The process of determining the neighboring nodes of a node is shown in the following formula.

[0079]

[0080] Among them, D(v i ,v j ) represents node v i and node v j The Euclidean distance in the rectangular coordinate system, ψ(V p ) represents node v p The set of k minimum distance neighbor nodes of Indicates v p A neighboring node of dist-k Indicates a set of k minimum distance values, (x i ,y i ) is the node v i The coordinates of (x j ,y j) is the node v j 's coordinates.

[0081] Furthermore, the spatial and morphological characteristics of the nodes are calculated based on prior engineering-geological knowledge. The graph structure data conversion form is as follows: Figure 5 As shown in the figure, the pixel graph structure conversion process of the open interval of the connected domain is as follows: Figure 6 shown.

[0082] Specifically, the binary fragment graph is projected onto a two-dimensional spatial coordinate system of the same size to obtain the spatial coordinates of each pixel. Furthermore, based on graph representation learning theory, the pixels are treated as nodes, and edges are created between the nodes based on the degree of spatial association calculated by Euclidean distance. The corresponding intervals of the candidate crack fragment paths are converted into a path graph that matches the original morphology. The process of determining the neighboring nodes of a node is shown in the following formula:

[0083] Furthermore, edge connections are created between adjacent nodes. The calculation and storage of edge connections between nodes can be expressed as follows:

[0084]

[0085] Among them, e(v i ,v j ) represents node v i and node v j There are edge connections between them, matrix A adj It is the adjacency matrix of graph structure data, which is used to record the edge connection relationship between nodes and participate in graph convolution calculation.

[0086] In step S5, the horizontal and vertical coordinates of all nodes in the graph in the two-dimensional space coordinate system are traversed and recorded as the graph space feature set; the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio and inclination angle of all nodes in the graph and their neighboring nodes within the circular verification threshold are traversed as node morphological features. The calculation method is the same as that described in step S3 and will not be repeated here.

[0087] In another exemplary embodiment of the present invention, in step S6, the spatial features and morphological features calculated based on the prior knowledge are embedded into the nodes to obtain a first reconstructed knowledge path graph;

[0088] Furthermore, in step S7, the similarity of each knowledge path graph in the fragment graph in the high-dimensional feature space is calculated, and in step S8, a first preset threshold is set to match the similarity graph to combine the natural fracture segments to obtain a first recombined meta-fracture knowledge graph.

[0089] Specifically, the distance between each node and its neighboring nodes in the verification domain is calculated, and the morphological and spatial features determined by prior knowledge and calculated together are embedded as node features to obtain a knowledge embedding path graph that contains the spatial and morphological knowledge of the neighboring nodes. Specifically, the knowledge path graph containing spatial and morphological features is projected into a high-dimensional feature space, and the high-dimensional spatial distance between the knowledge path graphs corresponding to different segments is calculated. The high-dimensional spatial distance of the knowledge path graph is measured by the Mahalanobis distance function, as shown in the following formula:

[0090]

[0091] Among them, Dist M (G i ,G j ) is the high-dimensional space distance between the knowledge path graphs of the readout vector of graph i and the readout vector of graph j, G i is the readout vector of graph i, G j is the readout vector of image i, ∑ -1 is the covariance matrix of the overall data distribution in the high-dimensional data space.

[0092] Furthermore, in step S9, segments with similar distances are connected to obtain a first recombined meta-crack knowledge graph corresponding to the complete original crack.

[0093] In another exemplary embodiment of the present invention, in step S9, a graph representation learning-driven fracture intelligent identification model based on a graph convolutional neural network is constructed, and a meta-fracture knowledge graph training model converted from historical electrical imaging logging fracture data collected at the exploration site is used to obtain a trained graph representation learning-driven fracture intelligent identification model.

[0094] The determination process of the graph representation learning-driven crack intelligent identification model is as follows.

[0095] S91: Segment the acquired historical electrical imaging logging fracture data into a plurality of second sequence electrical imaging segment images.

[0096] S92: performing binarization processing on each of the second series of electrical imaging fragment images to obtain a second binarized image, wherein the second binarized image is a plurality of binarized images containing only cracks and holes.

[0097] S93: performing denoising on the second binarized image to obtain a second binarized segment image; the second binarized segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects.

[0098] S94: Determine a second original path graph based on the second binarized segment graph; the second original path graph is an image obtained by connecting the second nodes according to open interval path connectivity; the second nodes are bright pixels in the second binarized segment graph.

[0099] S95: Based on engineering-geological prior knowledge, determine the spatial characteristics and morphological characteristics of each second node in the second original path diagram; the spatial characteristics are the horizontal and vertical coordinates of all second nodes in the two-dimensional space coordinate system; the morphological characteristics are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio and inclination of each second node and each second node's neighboring nodes within the circular verification threshold.

[0100] S96: Embed the spatial features and morphological features of each second node into the corresponding second node to obtain a second reconstructed knowledge path graph.

[0101] S97: Project the second reconstructed knowledge path graph into a high-dimensional feature space, and calculate the high-dimensional space distance between the knowledge path graphs corresponding to different segments.

[0102] S98: Connecting the segments of the knowledge path graph whose high-dimensional space distance is lower than a second preset threshold to obtain a second recombinant meta-crack knowledge graph.

[0103] S99: Using the second reorganized meta-fracture knowledge graph as input and the crack type corresponding to the second reorganized meta-fracture knowledge graph as output, the graph convolutional neural network is trained to obtain a graph representation learning-driven crack intelligent recognition model.

[0104] Specifically, the graph convolutional neural network model is composed of three layers of Chebyshev graph convolutional neural network (GCN) and two layers of fully connected layers (FC_Layer) stacked in sequence; the model uses leaky rectifier units (LeakyRelu) as the activation function between the networks and uses the cross entropy loss (CE_Loss) loss function as the model training function. The model receives graph structure data and activates the dropout mechanism to suppress possible overfitting trends. Among them, the Chebyshev graph convolution operation is expressed as:

[0105]

[0106] L=In-D -1 / 2 WD -1 / 2 (7).

[0107]

[0108] Among them, D i,i is a degree matrix containing only diagonal elements, A i,jis the adjacency matrix of the graph, L is the Laplace matrix, In is the identity matrix, W is the computable weight matrix, F∈R n×m is a graph signal, representing the input of the Chebyshev convolution operation, Represents the output of the Chebyshev convolution operation, U is the eigenvector matrix of the characteristic quantity in L, K represents the highest order of the Chebyshev polynomial, k represents the order of the Chebyshev polynomial, represents the feature matrix, represents the K-order Chebyshev polynomial, Represents the Chebyshev coefficient vector. At this time, the output Y∈R of the ChebGCN convolutional layer n×s Expressed as:

[0109]

[0110] Where W∈R m×s Represents the weight matrix learned by the ChebGCN convolutional layer.

[0111] On this basis, the constructed graph convolution model is as follows:

[0112]

[0113] Among them, W( 1 )∈R m×l is the trainable weight matrix of the first graph convolutional layer, W (2) ∈R l×v is the trainable weight matrix of the second convolutional layer, W( 3 )∈R v×g is the trainable weight matrix of the third graph convolution layer, Cheb(·) is the Chebyshev graph convolution function, m is the scale of the input vector, l is the first scale of the output vector, v is the second scale of the output vector, g is the third scale of the output vector, Y( 1 )∈R n×l Represents the output of the first convolutional layer, Y (2) ∈R n×v Represents the output of the second convolutional layer, Y( 3 )∈R n×g represents the output of the third convolutional layer, σ represents the leaky rectifier unit (LeakyRelu) activation function; the model structure and parameter details are shown in Table 2.

[0114] Table 2 Structure and parameter details of the crack recognition model based on graph convolutional neural network

[0115]

[0116] Specifically, the mathematical expression of the activation function LeakyReLU described in this embodiment is shown in formula (11), and the mathematical expression of the CE_Loss loss function is shown in formula (12).

[0117]

[0118] Where LeakyReLU(x) is the activation function, x is the input, α is a constant, CE_Loss(p,q) is the loss function, C is the total number of categories, in this embodiment C = 4, p i is the true value of the sample, q i The predicted value output by the model.

[0119] As an optional implementation, in step S93, it specifically includes.

[0120] S931: Calculate all connected domains of open intervals in the second binarized image using an edge detection algorithm to obtain second labeled candidate individual objects; the second labeled candidate individual objects are a number of labeled candidate crack-hole-silt open interval individual objects.

[0121] S932: Calculate basic morphological features of the second marked candidate individual object; the basic morphological features include: length, longitudinal width, transverse width, longitudinal aspect ratio, and transverse aspect ratio.

[0122] S933: According to prior geological knowledge, on-site logging conditions, and the basic morphological characteristics, a second length threshold is set to remove hole-sediment noise to obtain a second binarized segment image.

[0123] As an optional implementation, in step S94, it specifically includes.

[0124] S941: Project the second binarized segment image into a two-dimensional space coordinate system of the same size to obtain the spatial coordinates of each second pixel point.

[0125] S942: Determine a second original path map according to the spatial coordinates of each of the second pixel points.

[0126] In an exemplary embodiment, the real-time electrical imaging data collected by the micro-resistance logging instrument is converted into corresponding meta-fracture knowledge graphs according to the above steps. These graphs are sequentially fed into the trained graph representation learning-driven fracture intelligent identification model for fracture classification and identification, thereby achieving online fracture intelligent identification as the instrument advances. The graph representation learning-driven model training process is as follows: Figure 7 shown.

[0127] Specifically, the electrical imaging data measured by multiple wells on site are collected for model training to obtain a trained fracture recognition model based on graph convolutional neural network. Furthermore, a sliding time window is used to collect and cut the online measurement electrical imaging data, which is converted into a knowledge graph structure according to the above steps. These graphs are sequentially fed into the trained fracture intelligent recognition model for fracture classification and recognition, thus realizing online fracture intelligent recognition as the instrument advances. The fracture recognition results are shown in Figure 2. Figure 8 shown.

[0128] Specifically, to verify the performance of the fracture identification method provided in this example, we selected several advanced similar methods for comparative experiments using electrical imaging data collected from two wells. These included an edge detection method (EDM), a path morphology method (PMM), an artificial neural network (ANN), and a mask regional convolutional neural network (M-RCNN). The average of ten results was used as the final performance of each method for comparison. Model performance was evaluated using metrics including detection rate, accuracy, F1 score, and time consumption. The formulas for these metrics are shown below.

[0129]

[0130] Among them, TP is the positive sample predicted to be positive, TN is the negative sample predicted to be positive, FP is the positive sample predicted to be negative, FN is the negative sample predicted to be negative, P is the precision (Precision, P), R is the recall (Recall, R), and the F1 score is the comprehensive performance indicator.

[0131] Figure 9 and Figure 10The results show that in the field logging data set (a), all models have good identification results, while in the data set (b) affected by low-quality images, the effects of all models participating in the evaluation have decreased to different degrees. This phenomenon shows that the traditional machine learning and deep learning driven fracture identification model can generalize the heterogeneous logging data, but is directly affected by the quality of the original data. Among them, the EDM based on computer vision is most affected because the feature extraction without prior knowledge cannot distinguish fractures from noise. To solve this problem, the present application reduces the impact of data migration to the maximum by capturing more detailed spatial features, because the node feature embedding based on prior knowledge is suitable for representing various natural fractures at any location. However, in addition to the morphological method which needs to use multiple operator calculations for all open interval connected domains of each node in the fracture path, the model of the present application consumes the most time. It can be said that graph representation learning is to mine additional features inside the object by consuming additional computing resources, thereby improving the task accuracy without relying on more input information.

[0132] The hyperparameters are verified as follows.

[0133] In an exemplary embodiment, the hole length denoising threshold L is set as follows: Figure 11 As shown in the figure, the performance curve of the method of the present application shows a trend of first rising and then falling, and the best performance is shown at L = 70, that is, an accuracy of 96.37% and all 2451 edges. This shows that a small length L is difficult to remove larger noise holes, and a larger length L will mistakenly remove smaller fracture fragments. It is worth noting that Figure 11 The edge number curve has a larger slope at the initial stage of threshold growth (less than 70), and the slope gradually slows down in the later stage. This shows that small L values in the early stage quickly identify and delete a large number of small holes, and large L values in the later stage delete a small number of large holes and small holes.

[0134] Chebyshev graph convolution kernel K order setting: for the Chebyshev graph convolutional neural network model, the selection of Chebyshev polynomial K is particularly important, which represents the convolution network that aggregates information from K-hop neighbor nodes of the node. A small K value will limit the network's ability to mine information from graph structure data, and a large K value will multiply the consumption of computing resources and introduce unnecessary graph calculation noise. In order to fully exploit the potential of the model, a comparative experiment is designed to determine the optimal K value, and the experimental results are shown in Table 3.

[0135] Table 3 Comparative experimental results under different graph convolution parameters K order

[0136]

[0137] As shown in Table 3, the fitting accuracy of the model constructed by the present invention is ideal at K values ​​of different orders, and the fitting accuracy is the lowest when K=2. At the same time, when K=3 and 4, the model is close to the best experimental results in both indicators (accuracy is 96.37%~95.04%, and F1 score is 94.25%~95.04). Subsequently, further increase in the K value will lead to loss of accuracy and increased consumption of computing resources. This is because aggregating related nodes for learning can enhance the model effect. On the contrary, too much node aggregation will bring a large amount of noise information, reduce the accuracy, and increase the consumption of computing resources. Furthermore, since most of the valid node information has been aggregated, continuing to increase the K value will cause irrelevant nodes to be incorrectly aggregated, thereby reducing the accuracy of the model. Therefore, the present invention selects K=4 as the optimal hyperparameter of the network layer.

[0138] Based on the same inventive concept, embodiments of the present invention also provide a graph representation learning-driven electrical imaging logging fracture identification system for implementing the aforementioned graph representation learning-driven electrical imaging logging fracture identification method. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following embodiments of the graph representation learning-driven electrical imaging logging fracture identification system can be found in the above-mentioned limitations of the graph representation learning-driven electrical imaging logging fracture identification method and will not be further elaborated here.

[0139] In an exemplary embodiment, Figure 12 As shown, a graph representation learning-driven electrical imaging logging fracture identification system is provided, and the graph representation learning-driven electrical imaging logging fracture identification system includes.

[0140] The segmentation module M1 is used to segment the acquired real-time electrical imaging logging fracture data into a plurality of first sequence electrical imaging segment images.

[0141] The binarization processing module M2 is used to perform binarization processing on each of the first sequence of electrical imaging fragment images to obtain a first binarized image, wherein the first binarized image is a plurality of binarized images containing only cracks and holes.

[0142] The denoising module M3 is used to perform denoising on the image after the first binarization process to obtain a first binarized segment image; the first binarized segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects.

[0143] The first original path graph determination module M4 is used to determine the first original path graph based on the first binarized segment graph; the first original path graph is an image obtained by connecting the first nodes according to the open interval path connectivity; the first nodes are bright pixels in the first binarized segment graph.

[0144] The spatial feature and morphological feature determination module M5 is used to determine the spatial features and morphological features of each first node in the first original path diagram based on engineering-geological prior knowledge; the spatial features are the horizontal and vertical coordinates of all first nodes in the two-dimensional spatial coordinate system; the morphological features are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio and inclination of each first node and each first node's neighboring nodes within the circular verification threshold.

[0145] The embedding module M6 is used to embed the spatial features and morphological features of each first node into the corresponding first node to obtain a first reconstructed knowledge path graph.

[0146] The projection module M7 is used to project the first reconstructed knowledge path graph into a high-dimensional feature space and calculate the high-dimensional space distance between the knowledge path graphs corresponding to different fragments.

[0147] The fragment connection module M8 is used to connect the fragments of the knowledge path graph whose high-dimensional space distance is lower than a first preset threshold to obtain a first recombined meta-crack knowledge graph.

[0148] The crack identification module M9 is used to input the first recombined meta-crack knowledge graph into a crack intelligent identification model driven by graph representation learning to obtain crack types; the crack intelligent identification model driven by graph representation learning is a model established based on a graph convolutional neural network.

[0149] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A graph representation learning-driven electrical imaging logging fracture identification method, characterized in that: The graph representation learning-driven electrical imaging logging fracture identification method includes: Segmenting the acquired real-time electrical imaging logging fracture data into a plurality of first sequence electrical imaging segment images; Performing binarization processing on each of the first sequence of electrical imaging fragment images to obtain a first binarized image, wherein the first binarized image is a plurality of binarized images containing only cracks and holes; Denoising the image after the first binarization process to obtain a first binarization segment image; the first binarization segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects; Determining a first original path graph based on the first binarized segment graph; the first original path graph is an image obtained by connecting first nodes according to open interval path connectivity; the first nodes are bright pixels in the first binarized segment graph; Determine, based on prior engineering-geological knowledge, the spatial characteristics and morphological characteristics of each first node in the first original path diagram; the spatial characteristics are the horizontal and vertical coordinates of all first nodes in a two-dimensional spatial coordinate system; the morphological characteristics are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio, and inclination of each first node and its neighboring nodes within a circular verification threshold; Embed the spatial features and morphological features of each first node into the corresponding first node to obtain a first reconstructed knowledge path graph; Projecting the first reconstructed knowledge path graph into a high-dimensional feature space, and calculating the high-dimensional space distances between knowledge path graphs corresponding to different segments; Connecting segments of the knowledge path graph whose high-dimensional space distance is lower than a first preset threshold to obtain a first recombined meta-crack knowledge graph; The first recombinant meta-fracture knowledge graph is input into a graph representation learning-driven fracture intelligent identification model to obtain fracture types; the graph representation learning-driven fracture intelligent identification model is a model established based on a graph convolutional neural network.

2. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 1 is characterized in that: Performing denoising on the image after the first binarization process to obtain a first binarized segment image specifically includes: An edge detection algorithm is used to calculate all connected domains of open intervals in the first binarized image to obtain first labeled candidate individual objects; the first labeled candidate individual objects are a plurality of labeled candidate crack-hole-silt open interval individual objects; Calculating basic morphological features of the first marked candidate individual object; the basic morphological features include: length, longitudinal width, transverse width, longitudinal aspect ratio, and transverse aspect ratio; Based on prior geological knowledge, on-site well logging conditions, and the basic morphological characteristics, a first length threshold is set to remove hole-sediment noise to obtain a first binarized segment map.

3. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 1 is characterized in that: Determining a first original path graph according to the first binarized segment graph specifically includes: Projecting the first binarized segment image into a two-dimensional spatial coordinate system of the same size to obtain the spatial coordinates of each first pixel point; A first original path map is determined according to the spatial coordinates of each of the first pixel points.

4. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 1 is characterized in that: The calculation formula of the high-dimensional space distance of the knowledge path graph is: Among them, Dist M (G i ,G j ) is the high-dimensional space distance between the knowledge path graphs of the readout vector of graph i and the readout vector of graph j, G i is the readout vector of graph i, G j is the readout vector of image i, ∑ -1 is the covariance matrix of the overall data distribution in the high-dimensional data space.

5. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 1 is characterized in that: The determination process of the graph representation learning-driven crack intelligent identification model is as follows: Segmenting the acquired historical electrical imaging logging fracture data into a plurality of second sequence electrical imaging segment images; performing a binarization process on each of the second sequence of electrical imaging fragment images to obtain a second binarized image, wherein the second binarized image is a plurality of binarized images containing only cracks and holes; Denoising the second binarized image to obtain a second binarized segment image; the second binarized segment image is a plurality of images containing only natural cracks and broken natural crack segments as research objects; Determining a second original path graph based on the second binarized segment graph; the second original path graph is an image obtained by connecting the second nodes according to open-interval path connectivity; the second nodes are bright pixels in the second binarized segment graph; Determine, based on prior engineering-geological knowledge, the spatial characteristics and morphological characteristics of each second node in the second original path diagram; the spatial characteristics are the horizontal and vertical coordinates of all second nodes in a two-dimensional spatial coordinate system; the morphological characteristics are the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio, and inclination of each second node and its neighboring nodes within a circular verification threshold; Embed the spatial features and morphological features of each second node into the corresponding second node to obtain a second reconstructed knowledge path graph; Projecting the second reconstructed knowledge path graph into a high-dimensional feature space, and calculating the high-dimensional space distance between the knowledge path graphs corresponding to different segments; Connecting segments of the knowledge path graph whose high-dimensional space distance is lower than a second preset threshold to obtain a second recombinant meta-crack knowledge graph; The second reorganized meta-fragment knowledge graph is used as input, and the crack type corresponding to the second reorganized meta-fragment knowledge graph is used as output. The graph convolutional neural network is trained to obtain a graph representation learning-driven crack intelligent recognition model.

6. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 5 is characterized in that: Performing denoising on the second binarized image to obtain a second binarized segment image specifically includes: Using an edge detection algorithm to calculate all open interval connected domains in the second binarized image to obtain second labeled candidate individual objects; the second labeled candidate individual objects are a plurality of labeled candidate crack-hole-silt open interval individual objects; Calculating basic morphological features of the second marked candidate individual object; the basic morphological features include: length, longitudinal width, transverse width, longitudinal aspect ratio, and transverse aspect ratio; Based on prior geological knowledge, on-site well logging conditions, and the basic morphological characteristics, a second length threshold is set to remove hole-sediment noise, thereby obtaining a second binarized segment map.

7. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 5 is characterized in that: Determining a second original path graph according to the second binarized segment graph specifically includes: Projecting the second binarized segment image into a two-dimensional spatial coordinate system of the same size to obtain the spatial coordinates of each second pixel point; A second original path map is determined according to the spatial coordinates of each of the second pixel points.

8. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 5 is characterized in that: The graph convolutional neural network is composed of three layers of Chebyshev graph convolutional neural network and two layers of fully connected layers, and a cross-entropy loss function is used as the training function of the graph convolutional neural network; wherein the kernel K of the Chebyshev graph convolutional neural network is set to 4; and leaky rectifier units are used as activation functions between the Chebyshev graph convolutional neural networks.

9. The electrical imaging logging fracture identification method driven by graph representation learning according to claim 8, characterized in that: The expression of the activation function is: The expression of the loss function is: Among them, LeakyReLU(x) is the activation function, x is the input, α is a constant, CE_Loss(p,q) is the loss function, C is the total number of categories, p i is the true value of the sample, q i The predicted value output by the model.

10. A graph representation learning-driven electrical imaging logging fracture identification system, characterized in that: The graph representation learning-driven electrical imaging logging fracture identification system includes: A segmentation module, configured to segment the acquired real-time electrical imaging logging fracture data into a plurality of first sequence electrical imaging segment images; A binarization processing module is used to perform binarization processing on each of the first sequence of electrical imaging fragment images to obtain a first binarized image, wherein the first binarized image is a plurality of binarized images containing only cracks and holes; a denoising processing module, configured to perform denoising on the image after the first binarization processing to obtain a first binarized segment image; the first binarized segment image is a plurality of images containing only natural fractures and broken natural fracture segments as research objects; A first original path graph determining module is configured to determine a first original path graph based on the first binarized segment graph; the first original path graph is an image obtained by connecting first nodes according to open interval path connectivity; the first nodes are bright pixels in the first binarized segment graph; a spatial feature and morphological feature determination module, configured to determine the spatial features and morphological features of each first node in the first original path diagram based on prior engineering-geological knowledge; the spatial features being the horizontal and vertical coordinates of all first nodes in a two-dimensional spatial coordinate system; and the morphological features being the length, horizontal width, vertical width, horizontal aspect ratio, vertical aspect ratio, and inclination of each first node and its neighboring nodes within a circular verification threshold; an embedding module, configured to embed the spatial features and morphological features of each first node into the corresponding first node to obtain a first reconstructed knowledge path graph; A projection module, configured to project the first reconstructed knowledge path graph into a high-dimensional feature space and calculate the high-dimensional space distance between knowledge path graphs corresponding to different segments; a fragment connection module, configured to connect the fragments of the knowledge path graph whose high-dimensional spatial distance is lower than a first preset threshold to obtain a first recombined meta-crack knowledge graph; The crack identification module is used to input the first recombined meta-crack knowledge graph into a crack intelligent identification model driven by graph representation learning to obtain crack types; the crack intelligent identification model driven by graph representation learning is a model established based on a graph convolutional neural network.

Images