Intelligent identification system for weathering crust reservoir fracture distribution

Abstract

The invention relates to the technical field of geological analysis, in particular to a weathering crust reservoir fracture distribution intelligent identification system which comprises a fracture trend path construction module, a shielding extension fracture interpolation module, a cross-layer fracture directional connection module, a structural fracture space collection module and a fracture trend joint density analysis module. According to the method, directional connection of cross-layer cracks is achieved through joint judgment of three-dimensional space coordinates of the crack end point, the direction vector included angle and the ground plane normal included angle, the precision and reliability of a crack through structure are effectively improved, space distribution clustering of the cracks is achieved through statistics of the number of times of intersection of the structural unit cracks, concentration degree calculation and comparison of the concentration reference value, and the reliability of the crack through structure is improved. And combined with fracture path length, azimuth angle data and fracture quantity density statistics, combined density value calculation and integration of fracture trend and length weighting are constructed, so that reservoir fracture structure prediction precision and spatial positioning definiteness are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geological analysis, and in particular to an intelligent identification system for crack distribution in a weathering crust reservoir. Background Art

[0002] The field of geological analysis technology involves the systematic study of the composition, structure, distribution, and evolution of Earth's materials. In resource exploration, especially the development of oil, gas, and mineral resources, geological analysis uses lithology identification, structural analysis, and reservoir prediction to accurately model and invert underground structures. This technical field integrates a variety of quantitative analysis methods, including geophysical logging data processing, core image recognition, seismic attribute analysis, and artificial intelligence modeling, aiming to improve the accuracy and efficiency of geological structure identification, assist in decision-making and optimize mining plans, and enhance the controllability and economic efficiency of resource development.

[0003] The Weathering Crust Reservoir Fracture Distribution Intelligent Identification System is an intelligent analysis solution for identifying fracture development characteristics in weathering crust rock reservoirs. It aims to identify and annotate the orientation, scale, density, and connectivity of fractures in weathering crust reservoirs through image recognition, machine learning algorithms, and geological modeling methods. This system is primarily used to enhance the visualization and prediction capabilities of fractured reservoirs, providing a geological basis for well placement, production stimulation measures, and reservoir reconstruction in oil and gas exploration and development, thereby improving development efficiency.

[0004] Traditional identification systems are mainly based on macro-scale analyses such as seismic attribute analysis, lithologic identification, and structural analysis. They lack the ability to finely identify and process micro-scale fracture edge morphological characteristics, local gradient changes, and fracture continuity interruption areas, resulting in ambiguous representation of fracture extension trends and difficulty in accurately describing the spatial position and fine structure of reservoir fractures. Traditional systems lack refined quantitative analysis of fracture cross-layer connectivity, local concentration, and spatial differences in fracture density within structural units, resulting in reduced accuracy in fracture spatial distribution predictions, prone to misjudgment of fracture structure, and inaccurate reservoir spatial representation. In actual resource extraction and reservoir reconstruction, this results in large errors in well layout, insufficient reliability in reservoir prediction, and impacts on the overall economic efficiency of resource development and the effectiveness of decision-making. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent identification system for crack distribution in weathering crust reservoirs.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent identification system for fracture distribution in a weathering crust reservoir, the system comprising: The fracture trend path construction module obtains the weathering crust core image, calls the grayscale point array of the fracture edge in the image and calculates the gradient direction angle of adjacent points. It calculates the dominant extension direction of the fracture in each segment and projects it to the coordinates of the original image area to generate a fracture trend distribution path map. The occlusion extension crack interpolation module constructs a pixel-level point array to connect the fractured areas based on the crack trend distribution path map and marks them as completed crack pixels, thereby generating a crack connectivity layer for the occlusion area. The cross-layer fracture directional connection module calls the fracture connectivity layer of the obscured area, extracts the three-dimensional coordinates corresponding to the fracture endpoints in the three-dimensional weathering crust reservoir structure model, calculates the angle between the direction vectors of the endpoints and the angle between the normal and the ground plane, determines whether the angle is less than the penetration determination angle threshold, marks the penetration fracture path, and generates an interlayer penetration fracture connection map; The structural fracture spatial aggregation module extracts the lateral distribution coordinates and vertical projection points of each fracture path in the three-dimensional weathering crust reservoir structure model based on the interlayer through-fracture connection map, calculates the fracture concentration, and divides the fractures into different zones according to whether the concentration exceeds the structural fracture aggregation benchmark value to generate a reservoir structural fracture cluster distribution map.

[0007] As a further solution of the present invention, the fracture trend distribution path map includes a set of fracture extension directions, path continuity segment coordinates, dominant strike projection data, trend mapping pixel set and grayscale change synchronization identifier; the occluded area fracture connectivity layer map includes a fracture breakpoint connection pixel chain, occluded area connectivity pixel distribution, directional interpolation matching label, image occlusion connectivity mark layer and pixel-level fracture completion structure; the interlayer through-the-layer fracture connection map includes a set of layer path numbers, layer boundary angle evaluation labels and three-dimensional coordinate path nodes, normal deviation annotation matrix, and cross-layer connection path partitions; the reservoir structure fracture cluster distribution map includes a structural grid number index, fracture cluster partition identifier, fracture crossing frequency matrix, spatial density level mark and cluster fracture attribution label.

[0008] As a further solution of the present invention, the crack trend path construction module includes: The fracture edge extraction submodule obtains the weathering crust core image and extracts the two-dimensional fracture edge image data along the reservoir bedding strike. It extracts the fracture edge grayscale point array in the image and calculates the gradient direction angle of adjacent pixel points. The continuity of the direction change is determined based on the relative change value of the direction angle. The grayscale point segments whose change values ​​fall into the continuous interval of the fracture boundary are screened to generate the fracture boundary continuous segment value. The direction sequence generation submodule calls the continuous segment value of the crack boundary, obtains each direction angle value in each segment and calculates the direction change rate, performs truncation processing based on the comparison result of the direction change rate and the crack boundary fluctuation stability threshold, divides the direction evolution sequence into subsegments, and calculates the average direction angle and edge grayscale mean square error of each segment to generate the crack extension direction interval value; The path map formation submodule extracts the directional angle value of each segment based on the interval value of the crack extension direction and projects it to the coordinate area of ​​the original image, marks the pixel position set corresponding to the extension direction of the segment in the original image, merges the position set into an integrated image block and performs layer mapping processing to establish a crack trend distribution path map.

[0009] As a further solution of the present invention, the shielding and extension crack interpolation module includes: The fracture boundary direction extraction submodule obtains the dominant direction angles at both ends of the fracture segment in the path based on the fracture trend distribution path map, extracts the direction angles and changes at both ends, calculates the angle difference between the two ends, and performs linear interpolation based on the angle change to obtain an interpolated direction angle sequence, thereby generating an interpolated fracture direction angle value. The grayscale consistency calculation submodule extracts the grayscale mean and grayscale variance at both ends of the fracture area based on the interpolated crack direction angle value, compares the grayscale consistency index with the preset grayscale consistency threshold, determines whether the crack extension condition is met, and generates a grayscale consistency matching value; The crack completion path construction submodule is based on the grayscale consistency matching value. If the crack extension condition is met, the interpolated direction angles at both ends are extracted and combined with the grayscale consistency data to construct a pixel-level point column connecting the fractured area, which is marked as the completed crack pixel point, and generate a crack connectivity layer in the occluded area.

[0010] As a further solution of the present invention, the cross-layer crack directional connection module includes: The coordinate extraction submodule calls the fracture connectivity layer of the occluded area, extracts the image coordinate values ​​and bedding plane annotation coordinate values ​​corresponding to the fracture endpoint in the three-dimensional weathering crust reservoir structure model, calculates the three-dimensional spatial coordinate values ​​of the endpoint according to the image coordinate values ​​and the grid distribution rules of the structural model, establishes a three-dimensional coordinate set of the endpoint of each fracture path, and obtains the endpoint spatial coordinate set; The angle judgment submodule extracts the spatial vectors between each pair of adjacent crack endpoints based on the endpoint spatial coordinate set, calculates the angle value of the direction vectors between the endpoints, and simultaneously extracts the normal vector of the structural layer where the endpoints are located, calculates the normal angle value between the normal vector and the direction vector, and jointly judges the direction vector angle value and the normal angle value. If both angle values ​​are less than the penetration judgment angle threshold, it is marked as a penetration path, thereby obtaining the penetration path comparison information; The path construction submodule calls the corresponding crack path number according to the through-path comparison information and locates the crack pixel position marked in the crack connectivity layer of the occluded area, extracts the spatial coordinate sequence of the path segments in the through-path, combines and sorts the path points according to the continuity of the spatial sequence, integrates the combined path segments to form a spatial path set of cross-layer cracks, and obtains the inter-layer through-crack connection map.

[0011] As a further solution of the present invention, the structural crack space collection module includes: The path coordinate extraction submodule extracts the three-dimensional coordinate sequence of the fracture path based on the interlayer through-fracture connection map, calls the grid boundary coordinate set in the three-dimensional weathering crust reservoir structure model and the path coordinates to perform lateral coordinate matching and vertical projection coordinate correspondence, establishes the lateral positioning value and vertical projection value of each fracture path in the three-dimensional weathering crust reservoir structure model, and obtains the fracture space projection coordinate set; The crossing frequency statistics submodule calls the fracture spatial projection coordinate set, matches the path coordinates with the unit boundary interval based on the grid unit of the three-dimensional weathering crust reservoir structure model, counts the number of fracture path crossings in each grid unit, calculates the unique path crossing frequency after deduplication based on the fracture numbers, and generates fracture crossing frequency information; The clustering and partitioning attribution submodule extracts the fracture path quantity, cross frequency, and regional area values ​​within each structural unit based on the fracture cross-frequency information, numerically measures the density of fracture distribution in the unit, calculates the fracture concentration value of each structural unit, makes attribution judgment based on the relationship between the fracture concentration value and the structural fracture aggregation benchmark value, obtains the structural clustering partition number, and establishes a reservoir structural fracture clustering distribution map.

[0012] As a further solution of the present invention, the formula for calculating the crack concentration value of each structural unit is: ; in, Indicates the The crack concentration value of each structural unit is Indicates the The normalized value of the area of ​​the structural unit, Indicates the The structural unit The crossover frequency of the cracks, Indicates the The structural unit The normalized value of the transverse coordinate of the crack, Indicates the The normalized value of the average value of the transverse coordinate of the crack in the structural unit, Indicates the The number of cracks in a structural unit.

[0013] As a further embodiment of the present invention, the system further comprises: The fracture strike joint density analysis module calls the reservoir structural fracture cluster distribution map, extracts the strike azimuth and path length of the fractures in each structural segment, counts the frequency of fractures in equally divided angle intervals, calculates the corresponding strike probability density of each interval, calculates the fracture distribution intensity based on the fracture number density in the corresponding segment, and integrates the data using the structural segment as an index to generate fracture strike density joint distribution information; The joint distribution information of the crack strike density specifically includes the crack azimuth probability item, the crack intensity value per unit area, the strike interval distribution level, the strike density superposition factor and the structural section crack quantitative data.

[0014] As a further solution of the present invention, the fracture trend joint density analysis module includes: The azimuth data extraction submodule calls the reservoir structure fracture cluster distribution map, extracts the three-dimensional coordinate sequence of the fracture path in each structural segment, obtains the coordinate difference between the starting point and the end point of the fracture path to calculate the vector direction, calculates the strike azimuth value and the path segment length value of each fracture based on the direction, and obtains the fracture strike and length set; The angle density calculation submodule divides the strike azimuth into equally spaced angle intervals based on the set of fracture strikes and lengths, counts the number of fractures in each angle interval, and calculates the joint density value corresponding to each angle interval based on the path length of the corresponding fracture. The angle interval density values ​​of each section are then unified to obtain a fracture joint density array. The distribution intensity integration submodule classifies and summarizes the joint density values ​​of each angle interval according to the segment to which it belongs based on the fracture joint density array and takes the structural segment number as the index order to establish the joint distribution information of the fracture strike density.

[0015] As a further solution of the present invention, the formula for calculating the joint density value corresponding to each angle interval is: ; in, Indicates the The joint density value of the angle interval, Indicates the The number of cracks in the angle interval, Indicates the In the angle interval The path length of the crack, Indicates the In the angle interval The normalized value of the horizontal projection transverse coordinate of a crack in the structural section to which it belongs, Indicates the The normalized value of the average value of the projected transverse coordinate of the crack in the angle interval, Indicates the angle range The index of the crack, An index representing an angle interval.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by obtaining the grayscale points of the fracture edge of the core image and calculating the local gradient direction angle, the stable section of the fracture edge angle change is truncated and projected in the dominant direction, so as to achieve a fine characterization of the fracture distribution trend, and based on the grayscale mean and grayscale variance, the directional angle linear interpolation and pixel-level fracture completion processing of the occluded area are performed, so that the fracture path identification and reconstruction have integrity and continuity, and the directional connection of cross-layer fractures is achieved based on the three-dimensional spatial coordinates of the fracture end point and the angle of the direction vector and the normal angle of the ground surface, which effectively improves the accuracy and reliability of the fracture through-structure. The spatial distribution clustering of the fracture is achieved by counting the number of fracture intersections of the structural unit, calculating the concentration and comparing with the aggregation benchmark value. Combined with the fracture path length, azimuth angle data and fracture number density statistics, the joint density value calculation and integration of the fracture strike and length weighting are constructed, thereby achieving significant improvements in the fracture spatial structural characteristics, strike distribution intensity and fine characterization of the reservoir, and greatly improving the prediction accuracy of the reservoir fracture structure and the clarity of spatial positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.

[0018] Figure 1 is a system flow chart of the present invention; Figure 2 Schematic diagram of the system framework of the present invention; Figure 3 A flow chart of a fracture trend path construction module of the present invention; Figure 4 This is a flow chart of the shielding and extension crack interpolation module of the present invention; Figure 5 This is a flow chart of the cross-layer crack directional connection module of the present invention; Figure 6 This is a flow chart of the structural crack space aggregation module of the present invention; Figure 7This is a flow chart of the fracture trend joint density analysis module of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0020] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0021] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0022] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0023] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0024] See also Figure 1 , an intelligent identification system for fracture distribution in weathering crust reservoirs, the system includes: The fracture trend path construction module obtains weathering crust core images, extracts two-dimensional fracture edge image data along the reservoir bedding strike, calls the fracture edge grayscale point sequence in the image and calculates the gradient direction angle of adjacent points, extracts the angle change sequence and combines it with the local edge direction angle to form a direction evolution sequence. It then truncates and divides the stable sections according to the angle change rate, calls the average gradient direction and edge grayscale mean square error in each stable section, calculates the dominant extension direction of the fracture in each section, and projects it to the original image area coordinates to generate a fracture trend distribution path map. The occlusion extension crack interpolation module is based on the crack trend distribution path map. It obtains the dominant direction angles at both ends of the fracture segment in the image and the grayscale mean and grayscale variance of the interrupted area in the path. It then performs linear interpolation on the direction angles at both ends and combines them with the grayscale consistency index of the occlusion area to determine whether the direction consistency is higher than the crack extension threshold. If so, it constructs a pixel-level point array to connect the fracture area and marks it as the completed crack pixel point, generating a crack connectivity layer for the occlusion area. The cross-layer fracture directional connection module calls the fracture connectivity layer of the obscured area, extracts the three-dimensional coordinates corresponding to the fracture endpoints in the three-dimensional weathering crust reservoir structure model, calculates the angle between the direction vectors between the endpoints and the angle between the surface layer normal, and determines whether the angle is less than the penetration judgment angle threshold. If it is, it is marked as a penetration fracture path, and a cross-layer penetration fracture connection map is generated; The structural fracture spatial clustering module extracts the lateral distribution coordinates and vertical projection points of each fracture path in the three-dimensional weathering crust reservoir structure model based on the interlayer through-fracture connection map. It counts the number of fracture path intersections in each structural grid cell, calculates the fracture concentration, and divides the fractures into zones based on whether the concentration exceeds the structural fracture aggregation benchmark value to generate a reservoir structural fracture cluster distribution map. The fracture strike joint density analysis module calls the reservoir structural fracture cluster distribution map, extracts the strike azimuth and path length of the fractures in each structural segment, counts the frequency of fractures in equally divided angle intervals, calculates the corresponding strike probability density of each interval, combines the fracture number density in the corresponding segment, calculates the fracture distribution intensity, and integrates the data using the structural segment as the index to generate the fracture strike density joint distribution information; The fracture trend distribution path map includes a set of fracture extension directions, path continuity segment coordinates, dominant strike projection data, trend mapping pixel set, and grayscale change synchronization markers. The occluded area fracture connectivity layer includes a fracture breakpoint connection pixel chain, occluded area connected pixel distribution, directional interpolation matching labels, image occlusion connectivity marker layer, and pixel-level fracture completion structure. The interlayer through-the-layer fracture connection map includes a set of layer-penetrating path numbers, layer boundary angle assessment labels, three-dimensional coordinate path nodes, normal deviation annotation matrix, and cross-layer connection path partitions. The reservoir structure fracture cluster distribution map includes a structural grid number index, fracture cluster partition identifier, fracture crossing frequency matrix, spatial density level marker, and cluster fracture attribution label. The fracture strike density joint distribution information specifically includes the fracture azimuth probability item, unit area fracture intensity value, strike interval distribution level, strike density superposition factor, and structural segment fracture quantitative data.

[0025] See also Figure 2 and Figure 3 ,The crack trend path construction module includes the crack edge extraction submodule, the ,direction sequence generation submodule, and the path graph formation submodule; The fracture edge extraction submodule obtains the weathering crust core image and extracts the two-dimensional fracture edge image data along the reservoir bedding strike. It extracts the fracture edge grayscale point array in the image and calculates the gradient direction angle of adjacent pixel points. The continuity of the direction change is determined based on the relative change value of the direction angle. The grayscale point segments whose change values ​​fall into the continuous interval of the fracture boundary are screened to generate the fracture boundary continuous segment value. The two-dimensional fracture edge image data collected along the reservoir bedding direction in the weathering crust core image is obtained. First, the core image is divided into several equidistant scanning belt areas. Each scanning belt is arranged along the reservoir bedding direction. When extracting, it is necessary to determine whether the pixel direction of each scanning belt is less than 10° from the reservoir bedding azimuth. If it exceeds, the data of this section of the area is discarded. The continuous gray value array is read from the effective scanning belt. The horizontal scanning window size is 7×1 pixels and slides in sequence. Each time the window grayscale change gradient is calculated and the coordinate value of the steepest change point is recorded as the candidate fracture edge point. According to the image width of 1200 The actual parameters on site are set as 1200 scans, with a single scan step of 1 pixel and less than 10 cracks in each frame. The result of each scan is filtered out by logical operation to remove grayscale points with grayscale difference less than 20 between adjacent pixels, and a list of candidate crack edge points is obtained. On this basis, the gradient direction angle of adjacent pixel points is calculated. The gradient direction angle calculation uses the inverse tangent function formed by multiplying the grayscale difference of adjacent pixels by the position offset direction. In the example calculation, the two adjacent grayscale values ​​of a point are 220 and 180, and the distance between them is 3 pixels. The direction angle is arctan((220-180) / 3)= arctan(13.33) ≈ 85.7°. The angle values ​​of all edge points are calculated in sequence and an angle sequence is generated. The relative change value of the direction angle is then analyzed. The direction angle difference between every two consecutive points is used as the judgment basis. If the difference between adjacent direction angles is within ±10°, it is marked as direction continuous. If it exceeds, the fracture is divided into two segments. The judgment is based on setting the direction continuity interval to ±10°. The threshold ±10° is set based on the statistical results of the angle fluctuation of the fracture bending part in the manually annotated core image. The statistical sample size is 50 fracture paths. The maximum direction fluctuation is 26° and the minimum is 5°. The mode range is set as the judgment standard. Finally, the grayscale points in the continuous direction change segment are screened, and the start and end coordinates of each segment and the corresponding grayscale value segment are recorded in the form of a point list to generate the continuous segment value of the fracture boundary.

[0026] The direction sequence generation submodule calls the continuous segment value of the crack boundary, obtains each direction angle value in each segment and calculates the direction change rate. It performs truncation processing based on the comparison result of the direction change rate and the crack boundary fluctuation stability threshold, divides the direction evolution sequence into subsegments, and calculates the mean square error of the average direction angle and edge grayscale of each segment to generate the crack extension direction interval value. Call the continuous segment value of the crack boundary. First, extract the azimuth angle values ​​of all edge points in each segment and sort them according to their spatial order in the image. Perform a differential operation on the azimuth angle differences between adjacent point number sequences to obtain the direction change rate array. Then, smooth the array and use a sliding average window size of 5 pairs of direction change rate values ​​to remove local jump errors. Then, compare the smoothed direction change rate values ​​with the crack boundary fluctuation stability threshold one by one. The crack fluctuation stability threshold is set to a direction change rate within ±3°. The setting basis is In the statistics of the direction change rate of typical stable edges in the manually annotated path, the maximum is 4.8° and the minimum is 0.9°. Among them, the change rate of 95% of the samples is concentrated in ±3°, and this value is used as the boundary threshold. If the direction change rate of a continuous point segment is lower than the threshold, it is demarcated as a separate direction evolution segment, and the average direction angle and edge grayscale mean square error are calculated for each segment. The grayscale mean square error is calculated as follows: first calculate the average grayscale value of each pixel in the current segment, then square the difference between each grayscale and the average value and calculate the average value. If the grayscale sequence of a segment is [120, 125, 130], with a mean of 125, then the mean square error is ((120-125)²+(125-125)²+(130-125)²) / 3 = (25+0+25) / 3 = 16.7. This calculation is used to extract the characteristic values ​​of each directional evolution segment. Finally, the segment number, average direction angle and grayscale mean square error of each direction are paired and recorded to generate the interval value of the crack extension direction.

[0027] The path map formation submodule extracts the directional angle value of each segment based on the interval value of the crack extension direction and projects it into the coordinate area of ​​the original image. It then marks the pixel position set corresponding to the segment extension direction in the original image, merges the position set into an integrated image block, and performs layer mapping processing to establish a crack trend distribution path map. Based on the crack extension direction interval value, the average direction angle of each section is extracted as the extension direction parameter, and the corresponding direction angle is projected to the original coordinate area of ​​the image. The extension vector direction is set according to the quadrant where the direction angle is located. For example, if the direction angle is 60°, in the first quadrant, the vector direction is the positive direction of the x-axis plus the positive direction of the y-axis. Under the unit step size, according to the direction angle tan(60°)=1.73, each step is set to move 1 pixel in the x direction and 2 pixels in the y direction to generate continuous coordinate points. The starting point of the section is the coordinate source point, and the pixel point column is extended forward according to the above method. At the same time, it is extended backward symmetrically to construct a complete extended pixel path. The total length of the path is equal to the length of the original direction interval. If the average direction segment contains 10 grayscale points, the extension path length is 10 pixels. All path segments are marked at the pixel level in the image and layer merging is performed. That is, the projection points of all crack segments are superimposed on a new layer image to establish a unified image block, which is then layer-mapped and fused with the original image to complete the pixelated overlay output of the crack path trend and establish a crack trend distribution path map.

[0028] See also Figure 2 and Figure 4 ,The occlusion extension crack interpolation module includes the crack boundary direction extraction submodule, the grayscale consistency calculation submodule, and the crack completion path construction submodule; The fracture boundary direction extraction submodule obtains the dominant direction angles at both ends of the fracture segment in the path based on the fracture trend distribution path map, extracts the direction angles and changes at both ends, calculates the angle difference between the two ends, and performs linear interpolation based on the angle change to obtain the interpolated direction angle sequence and generate the interpolated fracture direction angle value. Based on the crack trend distribution path map, the interrupted area in the path is first obtained, and the dominant direction angle values ​​on the crack boundary are extracted at both ends of the interrupted section. The dominant direction angle is extracted based on the fracture edge area. Based on all the gradient direction angle values ​​within the pixel range, the most frequently occurring direction angle is counted using the majority method as the dominant angle. If the pixel direction angles at the left end of the fracture are concentrated at 72°±2° and at the right end at 84°±3°, 72° and 84° are set as the dominant angles respectively, and then the angle difference is calculated. Then, linear interpolation is performed based on the angle change. The number of interpolation points is set according to the length of the fracture area. If the fracture area width is 8 pixels, 8 direction angle values ​​need to be interpolated. The interpolation spacing is set to , that is, gradually add 1.5° from 72° to 84°, generating a complete interpolation sequence: , the above method is used to complete the direction information of each interruption area, and finally generate the interpolated crack direction angle value.

[0029] The grayscale consistency calculation submodule extracts the grayscale mean and grayscale variance at both ends of the fracture area based on the interpolated crack direction angle value, compares the grayscale consistency index with the preset grayscale consistency threshold, determines whether the crack extension condition is met, and generates a grayscale consistency matching value; According to the interpolated crack direction angle value, the left and right boundary images of the fracture area are extracted. The grayscale value set of the pixel area, the grayscale mean is calculated by the average of all pixel grayscale values, and the grayscale variance is calculated by the arithmetic mean of the square of the difference between each grayscale and the mean. Suppose the grayscale value of the left end area is , then its mean is 117, grayscale variance , the gray value of the right end area is , its mean is 117.2, the variance , the grayscale mean and variance of the left and right regions are substituted into the consistency index formula: The gray consistency threshold is set to 0.35, which is based on the gray parameter samples of 200 groups of known through cracks. The proportion greater than this value is 92%. It is considered that the extension condition is met, and eventually The values ​​are recorded as grayscale consistency matching values.

[0030] The crack completion path construction submodule is based on the grayscale consistency matching value. If the crack extension condition is met, the interpolated direction angles at both ends are extracted and combined with the grayscale consistency data to construct a pixel-level point sequence to connect the fractured area. These points are marked as completed crack pixels and a crack connectivity layer is generated for the occluded area. Based on the grayscale consistency matching value, if When the threshold is set to 0.35, the corresponding interpolated direction angle sequence is called, and each direction angle value is used as a projection parameter to generate a pixel-level connection point sequence. The connection path starts from the left end point of the fracture and is generated to the right along the direction angle. Each step is offset by the angle in the image. and Coordinates, for example, if the angle is 75°, then each step will result in a 1 pixel horizontal displacement and a vertical displacement of Pixels are selected using integer mapping rules. Each projection point records the corresponding direction angle and starting coordinate index. After completing the pixel extension operation corresponding to all direction angles, the points in the projection point column that cross the image edge or have a grayscale difference of more than 50 from the original image are removed. The remaining valid connection points constitute a pixel-level fracture connection path. The pixel position of the path is marked as the crack completion area and updated to the occlusion area identification layer. Finally, the occlusion area crack connection layer is generated.

[0031] See also Figure 2 and Figure 5,The cross-layer crack directional connection module includes a coordinate extraction submodule, an angle judgment submodule, and a path construction submodule; The coordinate extraction submodule calls the fracture connectivity layer in the occluded area to extract the image coordinate values ​​and bedding plane annotation coordinate values ​​corresponding to the fracture endpoint in the three-dimensional weathering crust reservoir structure model. The three-dimensional spatial coordinate values ​​of the endpoint are calculated based on the image coordinate values ​​and the grid distribution rules of the structural model. The three-dimensional coordinate set of the endpoint of each fracture path is established to obtain the endpoint spatial coordinate set. Call the fracture connectivity layer in the occluded area. First, according to the mapping relationship between the structural model of the three-dimensional weathering crust reservoir and the image coordinate system, obtain the pixel coordinates of the fracture end point in the image. Set the image coordinate system to two-dimensional space, where the coordinates of the end point of the fracture path in the image are and , and extract the bedding plane annotation coordinate value and Then, according to the grid distribution rules of the structural model, the image coordinates are matched with the three-dimensional coordinate system, and the two-dimensional coordinate values ​​are mapped to the three-dimensional space using the scaling method. The grid size is set to 10m×10m, and each pixel in the grid represents 10m. After mapping, the end point The three-dimensional space coordinates of ,end The three-dimensional space coordinates of , and its calculation formula is: ; ; ; in, is the origin reference coordinate, is the unit scaling factor for the corresponding direction, and the three-dimensional spatial coordinate value of the endpoint of each crack path is obtained. Through the above operations, the three-dimensional coordinate set of the endpoint of each crack path is finally established, and the complete endpoint spatial coordinate set is obtained.

[0032] The angle judgment submodule extracts the spatial vectors between each pair of adjacent crack endpoints based on the endpoint spatial coordinate set, calculates the angle value of the direction vectors between the endpoints, and simultaneously extracts the normal vector of the structural layer where the endpoints are located, calculates the normal angle value between the normal vector and the direction vector, and jointly judges the direction vector angle value and the normal angle value. If both angle values ​​are less than the penetration judgment angle threshold, it is marked as a penetration path, and the penetration path comparison information is obtained; Based on the endpoint spatial coordinate set, the spatial coordinate values ​​between each pair of adjacent crack endpoints are first extracted. For example, the endpoint spatial coordinates of two cracks are and , calculate the space vector as , according to the three-dimensional direction cosine formula of the space vector, calculate the angle between the direction vectors of the end points , the formula is: ; in, and is the direction vector between the end points, the angle It reflects the spatial angle between the two. Next, the normal vector of the structural bedding plane at each end point is extracted. and , and calculate the normal angle value based on the three-dimensional cosine relationship , the formula is: ; Next, the direction vector angle Angle with normal Perform joint judgment. If both are less than the penetration judgment angle threshold, set the penetration judgment angle threshold to 30°. That is, if and , then the path is considered to be a penetrable path, otherwise it is an impenetrable path. Through this method, the penetrable path comparison information between the crack paths is obtained. The matrix records the information of whether all crack paths can penetrate across layers.

[0033] The path construction submodule calls the corresponding crack path number based on the cross-linkable path comparison information and locates the crack pixel position marked in the crack connection layer of the occluded area. It extracts the spatial coordinate sequence of the path segments in the cross-linked path and combines and sorts the path points according to the continuity of the spatial sequence. It integrates the combined path segments to form a spatial path set of cross-layer cracks and obtains the inter-layer cross-linked crack connection map. According to the cross-path comparison information, the number of the corresponding crack path is first extracted, and the crack pixel position marked in the crack connection layer of the occluded area is located. The pixel position of a crack path in the layer is set as arrive , then extract the spatial coordinate sequence of the path segment in the through path, and use the spatial point connection method to combine and sort the continuous spatial coordinate points in the path. For example, the spatial coordinate sequence of a certain segment in the path is arrive Calculate the length of the path segments and sort them according to spatial sequence continuity, merging the start and end coordinates of each segment. Finally, sequentially integrate the spatial coordinates of all path segments into a set of spatial paths for cross-layer cracks. Based on this set, construct a connection map of the cracks, and finally obtain a spatial connectivity map of the cracks, which shows the connectivity of all crack paths and their cross-layer connectivity relationships.

[0034] See also Figure 2 and Figure 6,The structural crack space aggregation module includes the path coordinate extraction submodule, the ,crossing number statistics submodule, and the clustering partition attribution submodule; The path coordinate extraction submodule extracts the three-dimensional coordinate sequence of the fracture path based on the interlayer through-fracture connection map. It then uses the grid boundary coordinate set in the three-dimensional weathering crust reservoir structure model to match the path coordinates with the lateral coordinates and the vertical projection coordinates. It then establishes the lateral positioning value and vertical projection value of each fracture path in the three-dimensional weathering crust reservoir structure model to obtain the fracture spatial projection coordinate set. Based on the through-crack connection map, first extract all the three-dimensional spatial coordinate point sequences contained in the crack path. Assume that each crack path consists of several coordinate points, and its three-dimensional coordinate format is ,in is the horizontal coordinate, is the vertical coordinate, As vertical coordinates, the grid boundary coordinate set defined in the reservoir structure model is called. This set describes the horizontal and vertical grid points of the entire three-dimensional model in space. The horizontal and vertical boundaries are divided into spatial grids at intervals of 10m. Next, the coordinates of each point in the fracture path are calculated. The coordinates are matched with the horizontal boundary interval of the model grid to determine whether the current coordinate value is within the horizontal coordinate interval of a certain unit. If it meets the requirements, and , then mark the point as belonging to Unit, while recording its path number information, all points in the crack path perform the same coordinate matching process, and after each matching, the original coordinates of the point are converted into relative positioning values ​​in the structural model, that is, the horizontal positioning value is constructed based on the grid center and the vertical coordinate is linearly projected on the unit, such as the path point If it falls into the 5th layer unit of the 12th column, its horizontal positioning value is the center coordinate of the 12th column , the vertical projection value of 55 corresponds to the normalized scale value of 0.5 for this layer. After processing all path points in this way, a complete lateral positioning value sequence and vertical projection coordinate set are finally established for each crack path to obtain the crack space projection coordinate set.

[0035] The intersection count submodule calls the fracture spatial projection coordinate set, matches the path coordinates with the unit boundary interval based on the grid unit of the three-dimensional weathering crust reservoir structure model, counts the number of fracture path intersections in each grid unit, calculates the unique path intersection frequency after deduplication based on the fracture numbers, and generates fracture crossing frequency information; The fracture space projection coordinate set is called to traverse each grid cell in the reservoir structure model. The lateral positioning values ​​of all path points in each cell are matched to see if they are within the coordinate interval of the cell. If the match is successful, it is counted as a path crossing event. After the statistics are completed, the total number of crossing paths in each cell is recorded. Then, the path numbers appearing in each grid cell are deduplicated, and the number of independent path numbers in the cell is calculated as the path uniqueness crossing frequency. For example, if the path number recorded in a cell is [3, 3, 7, 8, 7], the unique path number is [3,7,8], the crossing frequency is 5, and the unique frequency is 3. The crossing frequency and path uniqueness frequency of all cells are recorded in a two-dimensional matrix. The matrix uses the grid row and column numbers as indexes, and the matrix elements are the crossing frequency values ​​and the unique frequency values. Finally, the fracture crossing frequency information is generated.

[0036] The clustering and partitioning attribution submodule extracts the number of fracture paths, cross-frequency values, and regional area values ​​within each structural unit based on the fracture cross-frequency information, numerically measures the density of fracture distribution in the unit, calculates the fracture concentration value of each structural unit, and makes attribution judgments based on the relationship between the fracture concentration value and the structural fracture aggregation benchmark value. It then obtains the structural clustering partition number and establishes a reservoir structural fracture clustering distribution map. The formula for calculating the crack concentration value of each structural unit is: ; in, Indicates the The crack concentration value of each structural unit is Indicates the The normalized value of the area of ​​the structural unit, Indicates the The structural unit The crossover frequency of the cracks, Indicates the The structural unit The normalized value of the transverse coordinate of the crack, Indicates the The normalized value of the average value of the transverse coordinate of the crack in the structural unit, Indicates the The number of cracks in a structural unit; The fracture concentration value is specifically used to quantitatively describe the density of the spatial distribution of fractures in the weathering crust reservoir structure model, especially reflecting the spatial state of the aggregation or dispersion of fractures in a specific structural unit (such as a grid or mesh area). The higher the fracture concentration value, the stronger the degree of spatial aggregation of fractures in the specific unit and the denser the spatial distribution of fractures, which may indicate better reservoir permeability and fluid migration conditions in the unit; the lower the concentration value, the more dispersed the fractures are in space, the lower the fracture density, and the poorer the spatial connectivity.

[0037] According to the crack cross frequency information, the number of crack paths of each structural unit is extracted , path crossover frequency And the normalized value of the unit area , according to the normalized value of the horizontal coordinate of each path The average of the transverse coordinates of all paths in the unit , construct the lateral deviation, using the formula: ; Among them, all participating items mean: Indicates the The crack concentration value of the unit, For the The normalized value obtained by dividing the unit area by the maximum unit area, For the Unit The crossover frequency of the cracks, For the Unit The normalized value of the horizontal coordinate of the crack, is the normalized value of the average value of the transverse coordinates of all cracks, is the number of cracks in the unit. Substitute the example data to illustrate: Assume that the area of ​​a unit is 90 square meters and the maximum unit area is 150 square meters, then , there are 3 cracks, the cross frequency values ​​are 2, 3, and 1, the normalized transverse coordinates are 0.3, 0.5, and 0.7, and the average value is 0.5, then: ; The calculated The value is compared with the structural crack aggregation benchmark value. The benchmark value is set according to the average value plus the standard deviation of the concentration value of all units in the model. The benchmark value is set to 1.2. If The unit is judged as a non-aggregate area. Finally, all clustering information is integrated into a map format using the structural unit number as the index to obtain the reservoir structural fracture cluster distribution map.

[0038] See also Figure 2 and Figure 7 ,The fracture strike joint density analysis module includes the azimuth data extraction submodule, the angle density calculation submodule, and the distribution intensity integration submodule; The azimuth data extraction submodule calls the reservoir structure fracture cluster distribution map, extracts the three-dimensional coordinate sequence of the fracture path in each structural segment, obtains the coordinate difference between the starting point and the end point of the fracture path, calculates the vector direction, and calculates the strike azimuth value and path segment length value of each fracture based on the direction, thus obtaining the fracture strike and length set; Calling the reservoir structure fracture cluster distribution map, first read the boundary coordinate range of each structural segment, extract the three-dimensional coordinate sequence of all fracture paths in the segment, assuming that the fracture path consists of a starting point and an end point, the coordinate form is and , get the path vector difference as , calculate the azimuth value according to the vector direction , calculated as For example, if the starting point of a crack path is (120,180,30) and the end point is (130,200,33), then , , corresponding to the strike angle , the path segment length is calculated using the three-dimensional Euclidean distance formula, i.e. , bring in the data At the same time, the calculation results are classified by structural segment and stored in the structure number index table, and the strike angles and path lengths of multiple crack paths are calculated and stored, and finally organized into a set of crack strikes and lengths.

[0039] The angle density calculation submodule divides the strike azimuth into equally spaced angle intervals based on the set of fracture strikes and lengths. It then counts the number of fractures in each angle interval and, combined with the corresponding fracture path length, calculates the joint density value corresponding to each angle interval. The angle interval density values ​​for each segment are then consolidated to obtain a fracture joint density array. The formula for calculating the joint density value corresponding to each angle interval is: ; in, Indicates the The joint density value of the angle interval, Indicates the The number of cracks in the angle interval, Indicates the In the angle interval The path length of the crack, Indicates the In the angle interval The normalized value of the horizontal projection transverse coordinate of a crack in the structural section to which it belongs, Indicates the The normalized value of the average value of the projected transverse coordinate of the crack in the angle interval, Indicates the angle range The index of the crack, The index representing the angle interval; The joint density value refers to the strength of the fracture path distribution within a specific angle interval. By jointly considering the two dimensions of fracture strike azimuth and fracture length, the development intensity of the fracture group in a specific direction is comprehensively evaluated. The joint density value can comprehensively measure the concentrated distribution of fractures in different strike intervals, and is used to identify the dominant fracture strike and spatial distribution characteristics, providing a clear direction for the formulation of fracture network development strategies during oil and gas production.

[0040] According to the set of crack strike and length, the strike angle value is divided into equidistant angle intervals at fixed intervals. The width of each interval is set to 10°, and the intervals are [0°-10°), [10°-20°), ... [170°-180°). In each angle interval, the number of cracks that meet the range is counted. Let The number of cracks in the interval is , extract the first Crack path length Its normalized horizontal projection coordinate within the structure segment , the normalization method is to divide the original projection coordinate by the maximum horizontal coordinate. If the maximum horizontal coordinate is 1000 and the coordinate of a path is 700, the normalized value is 0.7. Then count all the paths in the interval. Average value , and finally into the formula: ; Taking the third angle interval as an example, there are three cracks with normalized coordinates of 0.6, 0.7, and 0.9, corresponding to lengths of 15, 18, and 12. The average coordinates are ,but: ; The joint density value of each interval is calculated in this way , and store them into an array structure to obtain the crack joint density array.

[0041] The distribution intensity integration submodule classifies and summarizes the joint density values ​​of each angle interval according to the segment to which it belongs, based on the fracture joint density array and with the structural segment number as the index order, to establish the joint distribution information of fracture strike density. According to the crack joint density array, read the corresponding array items in sequence according to the structural segment number, merge all the angle interval density values ​​belonging to the same segment number, construct the angle density vector of the segment, and then arrange the density vectors of multiple segments in order from small to large according to the structural number to construct a two-dimensional density matrix, with the horizontal axis of the matrix being the angle interval index , the vertical axis is the structural section number , each matrix element Store the first Joint density value of the angle interval When there is no crack in a certain angle interval in a certain section, it is assigned a value of 0 for filling. After all matrix elements are filled in, a complete matrix distribution data structure is formed, and finally the joint distribution information of crack direction density is established.

[0042] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0043] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0044] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0045] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0046] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0047] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0048] 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, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0049] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0050] If the functions are implemented as software functional units and sold or used as independent products, they 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 the 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 enabling 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 media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical disks.

[0051] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An intelligent identification system for fracture distribution in weathering crust reservoirs, characterized in that: The system comprises: The fracture trend path construction module obtains the weathering crust core image, calls the grayscale point array of the fracture edge in the image and calculates the gradient direction angle of adjacent points. It calculates the dominant extension direction of the fracture in each segment and projects it to the coordinates of the original image area to generate a fracture trend distribution path map. The occlusion extension crack interpolation module constructs a pixel-level point array to connect the fractured areas based on the crack trend distribution path map and marks them as completed crack pixels, thereby generating a crack connectivity layer for the occlusion area. The cross-layer fracture directional connection module calls the fracture connectivity layer of the obscured area, extracts the three-dimensional coordinates corresponding to the fracture endpoints in the three-dimensional weathering crust reservoir structure model, calculates the angle between the direction vectors of the endpoints and the angle between the normal and the ground plane, determines whether the angle is less than the penetration determination angle threshold, marks the penetration fracture path, and generates an interlayer penetration fracture connection map; The structural fracture spatial aggregation module extracts the lateral distribution coordinates and vertical projection points of each fracture path in the three-dimensional weathering crust reservoir structure model based on the interlayer through-fracture connection map, calculates the fracture concentration, and divides the fractures into different zones according to whether the concentration exceeds the structural fracture aggregation benchmark value to generate a reservoir structural fracture cluster distribution map.

2. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 1 is characterized in that: The fracture trend distribution path map includes a set of fracture extension directions, path continuity segment coordinates, dominant strike projection data, trend mapping pixel sets and grayscale change synchronization identifiers; the occluded area fracture connectivity layer map includes a fracture breakpoint connection pixel chain, occluded area connectivity pixel distribution, directional interpolation matching labels, image occlusion connectivity marker layers and pixel-level fracture completion structures; the interlayer through-the-layer fracture connection map includes a set of layer-penetrating path numbers, layer boundary angle evaluation labels and three-dimensional coordinate path nodes, normal deviation annotation matrix, and cross-layer connection path partitions; the reservoir structure fracture cluster distribution map includes a structural grid number index, fracture cluster partition identifier, fracture crossing frequency matrix, spatial density level marker and cluster fracture attribution label.

3. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 2, characterized in that: The fracture trend path construction module includes: The fracture edge extraction submodule obtains the weathering crust core image and extracts the two-dimensional fracture edge image data along the reservoir bedding strike. It extracts the fracture edge grayscale point array in the image and calculates the gradient direction angle of adjacent pixel points. The continuity of the direction change is determined based on the relative change value of the direction angle. The grayscale point segments whose change values ​​fall into the continuous interval of the fracture boundary are screened to generate the fracture boundary continuous segment value. The direction sequence generation submodule calls the continuous segment value of the crack boundary, obtains each direction angle value in each segment and calculates the direction change rate, performs truncation processing based on the comparison result of the direction change rate and the crack boundary fluctuation stability threshold, divides the direction evolution sequence into subsegments, and calculates the average direction angle and edge grayscale mean square error of each segment to generate the crack extension direction interval value; The path map formation submodule extracts the directional angle value of each segment based on the interval value of the crack extension direction and projects it to the coordinate area of ​​the original image, marks the pixel position set corresponding to the extension direction of the segment in the original image, merges the position set into an integrated image block and performs layer mapping processing to establish a crack trend distribution path map.

4. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 3, characterized in that: The shielding and extension crack interpolation module includes: The fracture boundary direction extraction submodule obtains the dominant direction angles at both ends of the fracture segment in the path based on the fracture trend distribution path map, extracts the direction angles and changes at both ends, calculates the angle difference between the two ends, and performs linear interpolation based on the angle change to obtain an interpolated direction angle sequence, thereby generating an interpolated fracture direction angle value. The grayscale consistency calculation submodule extracts the grayscale mean and grayscale variance at both ends of the fracture area based on the interpolated crack direction angle value, compares the grayscale consistency index with the preset grayscale consistency threshold, determines whether the crack extension condition is met, and generates a grayscale consistency matching value; The crack completion path construction submodule is based on the grayscale consistency matching value. If the crack extension condition is met, the interpolated direction angles at both ends are extracted and combined with the grayscale consistency data to construct a pixel-level point column connecting the fractured area, which is marked as the completed crack pixel point, and generate a crack connectivity layer in the occluded area.

5. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 4, characterized in that: The cross-layer crack directional connection module includes: The coordinate extraction submodule calls the fracture connectivity layer of the occluded area, extracts the image coordinate values ​​and bedding plane annotation coordinate values ​​corresponding to the fracture endpoint in the three-dimensional weathering crust reservoir structure model, calculates the three-dimensional spatial coordinate values ​​of the endpoint according to the image coordinate values ​​and the grid distribution rules of the structural model, establishes a three-dimensional coordinate set of the endpoint of each fracture path, and obtains the endpoint spatial coordinate set; The angle judgment submodule extracts the spatial vectors between each pair of adjacent crack endpoints based on the endpoint spatial coordinate set, calculates the angle value of the direction vectors between the endpoints, and simultaneously extracts the normal vector of the structural layer where the endpoints are located, calculates the normal angle value between the normal vector and the direction vector, and jointly judges the direction vector angle value and the normal angle value. If both angle values ​​are less than the penetration judgment angle threshold, it is marked as a penetration path, thereby obtaining the penetration path comparison information; The path construction submodule calls the corresponding crack path number according to the through-path comparison information and locates the crack pixel position marked in the crack connectivity layer of the occluded area, extracts the spatial coordinate sequence of the path segments in the through-path, combines and sorts the path points according to the continuity of the spatial sequence, integrates the combined path segments to form a spatial path set of cross-layer cracks, and obtains the inter-layer through-crack connection map.

6. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 5, characterized in that: The structural crack space collection module includes: The path coordinate extraction submodule extracts the three-dimensional coordinate sequence of the fracture path based on the interlayer through-fracture connection map, calls the grid boundary coordinate set in the three-dimensional weathering crust reservoir structure model and the path coordinates to perform lateral coordinate matching and vertical projection coordinate correspondence, establishes the lateral positioning value and vertical projection value of each fracture path in the three-dimensional weathering crust reservoir structure model, and obtains the fracture space projection coordinate set; The crossing frequency statistics submodule calls the fracture spatial projection coordinate set, matches the path coordinates with the unit boundary interval based on the grid unit of the three-dimensional weathering crust reservoir structure model, counts the number of fracture path crossings in each grid unit, calculates the unique path crossing frequency after deduplication based on the fracture numbers, and generates fracture crossing frequency information; The clustering and partitioning attribution submodule extracts the fracture path quantity, cross frequency, and regional area values ​​within each structural unit based on the fracture cross-frequency information, numerically measures the density of fracture distribution in the unit, calculates the fracture concentration value of each structural unit, makes attribution judgment based on the relationship between the fracture concentration value and the structural fracture aggregation benchmark value, obtains the structural clustering partition number, and establishes a reservoir structural fracture clustering distribution map.

7. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 6, characterized in that: The formula for calculating the crack concentration value of each structural unit is: ； in, Indicates the The crack concentration value of each structural unit is Indicates the The normalized value of the area of ​​the structural unit, Indicates the The first structural unit The crossover frequency of the cracks, Indicates the The first structural unit The normalized value of the transverse coordinate of the crack, Indicates the The normalized value of the average value of the transverse coordinate of the crack in the structural unit, Indicates the The number of cracks in a structural unit.

8. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 7, characterized in that: The system further comprises: The fracture strike joint density analysis module calls the reservoir structural fracture cluster distribution map, extracts the strike azimuth and path length of the fractures in each structural segment, counts the frequency of fractures in equally divided angle intervals, calculates the corresponding strike probability density of each interval, calculates the fracture distribution intensity based on the fracture number density in the corresponding segment, and integrates the data using the structural segment as an index to generate fracture strike density joint distribution information; The joint distribution information of the crack strike density specifically includes the crack azimuth probability item, the crack intensity value per unit area, the strike interval distribution level, the strike density superposition factor and the structural section crack quantitative data.

9. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 8, characterized in that: The fracture trend joint density analysis module includes: The azimuth data extraction submodule calls the reservoir structure fracture cluster distribution map, extracts the three-dimensional coordinate sequence of the fracture path in each structural segment, obtains the coordinate difference between the starting point and the end point of the fracture path to calculate the vector direction, calculates the strike azimuth value and the path segment length value of each fracture based on the direction, and obtains the fracture strike and length set; The angle density calculation submodule divides the strike azimuth into equally spaced angle intervals based on the set of fracture strikes and lengths, counts the number of fractures in each angle interval, and calculates the joint density value corresponding to each angle interval based on the path length of the corresponding fracture. The angle interval density values ​​of each section are then unified to obtain a fracture joint density array. The distribution intensity integration submodule classifies and summarizes the joint density values ​​of each angle interval according to the segment to which it belongs based on the fracture joint density array and takes the structural segment number as the index order to establish the joint distribution information of the fracture strike density.

10. The intelligent identification system for crack distribution in weathering crust reservoirs according to claim 9, characterized in that: The formula for calculating the joint density value corresponding to each angle interval is: ； in, Indicates the The joint density value of the angle interval, Indicates the The number of cracks in the angle interval, Indicates the In the angle interval The path length of the crack, Indicates the In the angle interval The normalized value of the horizontal projection transverse coordinate of a crack in the structural section to which it belongs, Indicates the The normalized value of the average value of the projected transverse coordinate of the crack in the angle interval, Indicates the angle range The index of the crack, An index representing an angle interval.

Images