Quantitative evaluation method for laying effect of propping agent under global propping fracturing

Abstract

The invention discloses a quantitative evaluation method for the laying effect of a propping agent under global propping fracturing based on an image recognition technology, and the method comprises the steps: carrying out the preprocessing of a deposition image of a propping agent-fiber conveying experiment, and achieving the precise segmentation of a background and the vertical partitioning of a deposition region through the fusion of interactive sampling and gray gradient analysis; the top contour of the sediment is extracted by combining manual drawing and automatic edge detection; for each partition, constructing a gray-density conversion model based on the locally calibrated closest packing gray scale reference and the pore judgment gray scale reference, and calculating quantitative evaluation parameters; and summarizing and visualizing results. According to the method, non-contact, automatic and high-precision multi-parameter deposition analysis is realized by processing the deposition image of the proppant-fiber conveying experiment, the challenges of image unevenness and boundary blur are effectively overcome, quantitative evaluation of the paving effect of the proppant under global support fracturing can be realized, and the method is suitable for popularization and application. The method is also suitable for deposition monitoring and research in the fields of environment, mining industry, chemical industry and the like.

Description

Technical Field

[0001] This invention relates to the field of oil and gas field development engineering, and in particular to a quantitative evaluation method for the proppant placement effect under full-area support fracturing. Background Technology

[0002] Unconventional oil and gas production, represented by shale oil and gas and tight oil and gas, has seen significant growth, demonstrating enormous development potential and becoming a strategic successor area for future reserve and production increases globally. Horizontal well segmented multi-cluster fracturing technology is a core technology for achieving economical exploitation of unconventional reservoirs. Its characteristics include large-scale, high-volume fluid injection, multi-size proppant mixing, and high-intensity sand addition operations, aiming to expand the fracture support range and improve the flow capacity of the supported fractures. However, a key technical bottleneck has been exposed in fracturing engineering practice: the effective support volume is limited, and the post-fracturing oil and gas production declines rapidly. One of the core reasons for this problem is that both low-viscosity and high-viscosity gel-breaking fracturing fluids have limited proppant carrying capacity; that is, proppant particles settle rapidly and tend to accumulate at the bottom of the fracture, ultimately preventing the formation of effective support at the distal and vertical ends of the fracture, thus affecting the fracturing effect.

[0003] Replacing proppant particles with proppant-fiber clusters as the basic transport unit within the fracture is the core approach of whole-domain propped fracturing technology. Research and experiments in academia and industry have clearly demonstrated that fibers can assist in carrying proppant into the distal end of the fracture, effectively improving fracture morphology and reducing the risk of proppant blockage. With the continuous development of materials science, technical strategies based on functional group-directed modulation can effectively enhance the interfacial interaction between fibers and particles, significantly improving their interfacial bonding strength. Building upon this, and considering the engineering application background of large-scale slickwater fracturing, proppant-fiber clusters can migrate and lay out within the fracture as stable and independent unit structures. This key technological breakthrough directly promoted the birth and development of whole-domain propped fracturing technology.

[0004] Current evaluations of proppant-fiber hybrid transport within fractures primarily focus on settling velocity and layup morphology. Static settling studies of particles in fiber suspensions mainly examine the settling morphology and velocity variations of multiple particles or particle clusters under different fiber concentrations and types, particle sizes, and fluid rheological properties, calculating their drag coefficients in the suspension to determine optimal material parameters. Dynamic transport studies of particles in fiber suspensions emphasize and describe non-uniform fracture layup morphology, considering influencing factors beyond intrinsic material properties, including pumping rate and pumping method. However, existing methods fail to comprehensively evaluate the proppant-fiber cluster layup effect within fractures, thus failing to effectively highlight the core advantages of full-domain propped fracturing compared to traditional fracturing techniques, and consequently, hindering the theoretical support for parameter optimization design in full-domain propped fracturing. Summary of the Invention

[0005] To overcome the problems in the prior art, this invention provides a quantitative evaluation method for the proppant placement effect under full-domain supported fracturing, comprising the following steps:

[0006] S1. Image acquisition and preprocessing: A physical simulation experiment of proppant-fiber transport was conducted. After the deposited material stabilized, the deposition image was acquired, converted into a grayscale image, and the image area to be processed was interactively delineated.

[0007] S2. Background Segmentation and Vertical Partitioning: Interactive sampling is performed on the background area and deposition area of ​​the grayscale image respectively. The background analysis zone and contour recognition zone are automatically determined based on the grayscale statistical features of the sampling points. The grayscale gradient changes are analyzed along the background analysis zone to identify the vertical boundary of the deposition area. The entire deposition area is divided into N analysis blocks in the horizontal direction according to the vertical boundary.

[0008] S3. Human-machine collaborative extraction of sediment contours: The top contour line of the sediment is extracted by combining manual drawing with automatic edge detection; the results of the two methods are fused to generate a set of top contour coordinates of the sediment.

[0009] S4. Calculation of partition parameters and model construction: For each analysis block divided in step S2, the sediment volume space is determined according to the top contour coordinate set and the known sedimentary bottom edge, and the sedimentary height, cross-sectional area and volume of the block are calculated; within the sedimentary space of the block, the first reference gray value representing the densest particle packing state and the second reference gray value representing porosity are calculated; based on the first reference gray value and the second reference gray value, a gray-density conversion model is constructed to calculate the porosity, particle mass and fiber mass of the block;

[0010] S5. Results Fusion and Visualization: Summarize the calculation results of all analysis blocks to obtain the overall physical parameters of the sediments, and visualize the partitioning results, contours and parameters to quantitatively evaluate the proppant placement effect.

[0011] A further technical solution is that, in step S1, after converting the deposited image to a grayscale image, the image region to be processed is interactively delineated. The interactive sampling includes: sequentially clicking the left and right boundaries and the bottom of the deposition area in the grayscale image. A further technical solution is that, in step S2, the interactive sampling includes: a gesture input that draws an approximately vertical line in both the grayscale image background area and the deposition area.

[0012] The automatic determination of the background analysis band and contour recognition band includes: calculating the average and standard deviation of the maximum and minimum values ​​of the row coordinates of all pixels in the gesture input trajectory; and determining the upper and lower boundaries of the background analysis band and contour recognition band respectively using the definition of "average ± standard deviation" and the regions enclosed by their respective maximum and minimum row coordinates. A further technical solution is that, in step S2, the gray-level gradient change is analyzed using the interval difference method: along the background analysis band, the gray-level difference between K pixels is calculated as the gradient value; when the gradient value exceeds a set threshold, it is determined that a vertical boundary exists at that position; where K is an integer greater than or equal to 1.

[0013] A further technical solution is that, in step S3, after fusing the results of manual drawing and automatic detection, a contour coordinate interpolation step is also included: for each column of pixels, if there are multiple contour row coordinates, the average is taken; if there are no such coordinates, linear interpolation is performed based on the coordinates of adjacent columns.

[0014] In the above embodiments, a continuous and complete top contour line with single-pixel precision can be obtained through contour coordinate interpolation.

[0015] A further technical solution is that, in step S4, the calculation method of the first reference gray value is as follows: within the block, obtain the gray values ​​of all pixels in the deposition space, sort them, and take the average of the top M smallest gray values ​​that account for a certain proportion of the total number of collected pixels; wherein, the M value is adaptively allocated according to the proportion of the horizontal width of the block to the width of the entire deposition area.

[0016] A further technical solution is that, in step S4, the method for constructing the gray-scale-density conversion model is as follows: a second reference gray-scale value is set, which is the gray-scale value that may represent pores in the image. The calculation method for the second reference gray-scale value is as follows: within the block, the gray-scale values ​​of all pixels in the background space are obtained, and the average value is subtracted from the product of the empirical coefficient and the standard deviation. For any pixel in the deposition space, if its gray-scale value is less than or equal to the first reference gray-scale value, it is determined to be the densest packing and is given the maximum material density. If its gray-scale value is between the first and second reference gray-scale values, its material density and gray-scale value are linearly negatively correlated.

[0017] A further technical solution is that, in step S4, when calculating porosity, pixels with gray values ​​greater than or equal to the second reference gray value are directly identified as pore points.

[0018] On the other hand, the present invention provides a quantitative evaluation device for the proppant placement effect under full-area support fracturing, comprising the following modules:

[0019] Image processing module: Conducts physical simulation experiments of proppant-fiber transport, acquires deposition images after the deposited material stabilizes, converts the deposition images into grayscale images, and interactively delineates the image areas to be processed;

[0020] Region segmentation module: interactively samples the background and deposition areas of the grayscale image, automatically determines the background analysis zone and contour recognition zone based on the grayscale statistical features of the sampling points; analyzes the grayscale gradient changes along the background analysis zone to identify the vertical boundary of the deposition area; and divides the entire deposition area into N analysis blocks in the horizontal direction according to the vertical boundary.

[0021] Contour acquisition module: Extracts the top contour line of the sediment by combining manual drawing with automatic edge detection; merges the two results to generate a set of top contour coordinates of the sediment.

[0022] Parameter Calculation Module: For each analysis block divided by the region division module, the sediment volume space is determined based on the top contour coordinate set and the known sedimentary bottom edge, and the sedimentary height, cross-sectional area, and volume of the block are calculated. Within the sedimentary space of the block, a first reference gray value representing the densest particle packing state and a second reference gray value representing porosity are calculated. Based on the first and second reference gray values, a gray-density conversion model is constructed to calculate the porosity, particle mass, and fiber mass of the block. Quantitative Modulus Evaluation: The calculation results of all analysis blocks are summarized to obtain the overall physical parameters of the sediment, and the zoning results, contours, and parameters are visualized to quantitatively evaluate the proppant placement effect.

[0023] On the other hand, the present invention provides an electronic device, the electronic device comprising:

[0024] At least one processor; and

[0025] A memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method according to any one of the preceding claims.

[0026] On the other hand, the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to perform the method described in any one of the preceding claims.

[0027] The technical solutions provided in this application have the following advantages compared with the prior art:

[0028] This application provides an interactive adaptive background segmentation technology that intelligently determines the background analysis zone by combining free-drawing gestures with statistical methods, thereby improving the stability and accuracy of background-sediment separation. Furthermore, the human-machine fusion-based sediment contour extraction mechanism in this application integrates the prior knowledge of manually drawn contours with the objectivity of Canny's automatic detection, ensuring accurate machine recognition of clear boundaries. Simultaneously, it allows for human intervention to reduce recognition errors at blurred boundaries, effectively overcoming the challenge of accurately locating blurred boundaries at the top of sediments.

[0029] This application proposes a gray-physical quantity inversion model based on localized zoning, defining the "densest packing gray" and "porosity gray" benchmarks by partitioning blocks. A linear density decay model is then established on this basis, significantly improving the calculation accuracy from gray to density and mass parameters, and solving the problem of poor adaptability of a single global model. Based on a three-level analysis architecture of "pixel-partition-overall": from pixel-level operations to independent partition modeling, and finally to overall aggregation, this architecture not only outputs macroscopic parameters but also reveals the lateral non-uniform distribution characteristics within sediments, thus facilitating a convenient and rapid quantitative evaluation of proppant placement effects under global supported fracturing. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart illustrating the method of this invention;

[0032] Figure 2 This is a schematic diagram of the image preprocessing effect in an embodiment of the present invention;

[0033] Figure 3 This is the background extraction image in an embodiment of the present invention;

[0034] Figure 4 This is a schematic diagram of manually drawn deposition contours in an embodiment of the present invention;

[0035] Figure 5 This is a block deposition extraction diagram in an embodiment of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] The purpose of this invention is to address the problems of existing technologies for evaluating proppant-fiber mixed transport simulation experiments, which rely on manual labor and are inefficient, as well as the inaccurate measurements caused by uneven sediment grayscale and blurred boundaries when using image analysis. The quantitative evaluation method for proppant placement effect under full-domain propping fracturing provided by this invention achieves fully automated analysis of sediments from images to parameters. Without physical contact, it can simultaneously acquire multi-dimensional parameters such as deposition height, area, volume, porosity, and particle and fiber mass from experimental images, thereby enabling quantitative evaluation of the proppant placement effect under full-domain propping fracturing.

[0038] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0039] As shown in Figure 1, the present invention provides a method for measuring fluid deposition parameters based on image recognition technology, comprising the following steps:

[0040] S1. Image Acquisition and Preprocessing:

[0041] In this implementation, a proppant-fiber mixed transport simulation experiment is first conducted in the laboratory. Experimental analysis is then performed after the particles and fibers have been deposited in the experimental fluid.

[0042] The specific experimental conditions in this embodiment are as follows: the deposition container is a transparent acrylic rectangular tank with dimensions of 2.8 m in length, 0.4 m in height, and 0.004 m in width; the deposition material is proppant particles (density 1.5 × 10⁻⁶ m²). 6 The mixture of g / m³ and trace fiber (content 0.5%) was used as a slurry; the fluid medium was water; the image acquisition device was a camera fixed in front, ensuring that the lens plane was parallel to the deposition surface, and a uniform light source was set up in the experimental environment.

[0043] After the experiment, the sediment was kept still while images were acquired. As shown in Figure 2, the color images acquired in the experiment were imported into the processing system and converted to grayscale images using the rgb2gray function. To eliminate interference from the container edge device, an interactive tool was invoked to guide the user to click sequentially on the left boundary, right boundary, and bottom of the sediment in the sedimentation area to determine the spatial range of the sedimentation.

[0044] S2. Background segmentation and vertical partitioning:

[0045] The interactive tool guides the user to draw an approximately vertical free curve in both the image background and deposition areas. The program automatically collects all pixels along the curve, calculates the maximum and minimum values ​​of the row coordinates for each of the two gesture input trajectories, and then defines the range from the minimum to the maximum value as the background analysis band and the contour recognition band, respectively. Figure 3 As shown, the average grayscale value of each column within the analysis band is extracted to obtain a grayscale profile, using the interval difference method (…). =1) Calculate the profile gradient, and initially determine the locations where the absolute gradient value exceeds the threshold (threshold=3) as the vertical boundary of the depositional zone. To avoid noise-induced misjudgments, a minimum boundary spacing is set ( =40 pixels) were filtered; finally, based on the filtered vertical boundaries, the image was horizontally divided into multiple independently analyzed blocks, such as Figure 5 As shown;

[0046] S3. Depositional contour extraction using human-machine collaboration:

[0047] First, the operator uses an interactive tool to roughly draw an open curve along the top of the sediment. The system then integerizes, removes duplicates, and sorts the curve coordinates by column before performing linear interpolation to ensure that each column has corresponding contour row coordinates, generating a manual contour mask, as shown in Figure 4. Simultaneously, within the row range defined interactively, the system uses the Canny operator to perform automatic edge detection on the entire image, extracting an automatic edge point set. During fusion, for each column, the row coordinates of the manual contour points and the automatic edge points are compared, and the smaller (i.e., higher position) one is taken as the final sediment top contour point for that column, forming a continuous final top contour line, as shown in Figure 5.

[0048] S4. Partition parameter calculation:

[0049] Spatial parameters: Scan column by column from the bottom edge of the sediment until the final top outline is encountered, and count all pixels belonging to the sediment. Based on the ratio between the actual container size (length 2.8m, height 0.4m) and the total number of image pixels, calculate the average height h, maximum height H, cross-sectional area S, and volume V of the sediment, using the following formulas:

[0050]

[0051] In the formula: The average height of the sediment; The coordinates of the bottom boundary row of the sedimentation; This represents the average row coordinates of the pixels at the top boundary of the deposition. The height of the container; The maximum row coordinate in the vertical direction of the entire container;

[0052]

[0053] In the formula: This represents the maximum height of the deposit; The coordinates of the bottom boundary row of the sedimentation; This represents the minimum row coordinate of the pixel at the top boundary of the deposition. The height of the container; The maximum row coordinate in the vertical direction of the entire container;

[0054]

[0055] In the formula: The cross-sectional area of ​​the deposit; The total number of pixels occupied by the deposition; The height of the container; The length of the container; The maximum row coordinate in the vertical direction of the entire container; This represents the maximum row coordinate in the horizontal direction of the entire container.

[0056]

[0057] In the formula: The volume of the sediment; The cross-sectional area of ​​the deposit; The width of the container.

[0058] In this embodiment, each block is processed sequentially, starting with the first... Taking a single block as an example:

[0059] Grayscale benchmark calibration: Within the pixels of this deposition block, the edge pixels (x=3 pixels wide) are excluded to reduce boundary effects, and the grayscale values ​​of the remaining pixels are sorted. The sampling quantity is adaptively determined based on the proportion of this block width to the total deposition width. Take the front The average of the minimum grayscale values ​​is used as the first reference grayscale value for this block. (i.e., the densest packed gray level); a second reference gray level is set, which is the gray level that may represent pores in the image. The second reference gray level is calculated as follows: within this block, obtain the gray levels of all pixels in the background space, and subtract the product of an empirical coefficient and the standard deviation from their average value. This second reference gray level is the pore determination threshold for this block. The calculation formula is:

[0060]

[0061] In the formula: This is the second baseline grayscale value; The average pixel value of the background space of this block; k is the empirical coefficient for determining porosity; The pixel standard deviation of the background space for this block. Physical parameter inversion:

[0062] Porosity : Count the grayscale values ​​within this block ≥ The porosity is the ratio of the number of pixels deposited to the total number of deposited pixels, and the formula is:

[0063]

[0064] In the formula: The porosity of the deposited area; The grayscale value within this block is ≥ The number of pixels; This represents the total number of pixels occupied by the deposition.

[0065] Particle quality : Traverse each deposited pixel j in this block, and its grayscale value is ;like ≤ Then its density is considered to be ;like < < Its density is calculated using the following formula:

[0066]

[0067] In the formula: This is for calculating density based on grayscale ratio; This represents the densest packing density. The pixel corresponds to the grayscale value; The first baseline gray value (the densest stacked gray value); This is the second reference grayscale value (grayscale for determining porosity).

[0068] By summing the mass of the tiny volume represented by each pixel, we obtain... The particle mass is calculated using the following formula:

[0069]

[0070] In the formula: The mass of the deposited particles; The cross-sectional area of ​​the deposit; The width of the container; This is for calculating density based on grayscale ratio; This represents the total number of pixels occupied by the deposition.

[0071] Fiber quality : Determined by total particle mass Multiply by the fiber content in the sediment to obtain the result, as shown in the formula:

[0072]

[0073] In the formula: For the quality of deposited fibers; This represents the fiber content in the sediment.

[0074] S5. Results Summary and Visualization:

[0075] The total sediment volume V is obtained by summing the volume, mass, and other parameters of all blocks. 总 Particle mass M 总 The system can generate images, overlay and display block division boundaries and final deposition contours, and plot the height variation curves of each block, while outputting detailed parameters for the whole and each zone.

[0076] In this embodiment, by applying the method provided by the present invention to analyze the above experimental images, the following quantitative parameters can be obtained:

[0077] Sum of differences (number of pixels processed) D = 150342.00000

[0078] The average height of the sediment (cm) h = 9.22174

[0079] Maximum deposition height (cm) H = 11.05882

[0080] The area of ​​the deposit (square centimeters) S = 2456.56863

[0081] Volume of sediment (cubic centimeters) V = 982.62745

[0082] Porosity of the deposit (percentage) g = 9.27219

[0083] Mass of particles (grams) M = 972.11686

[0084] Fiber mass (grams) m = 4.86058

[0085] Particle mass per unit volume (grams per cubic centimeter) M_V = 0.98930

[0086] The above parameters can be used to quantitatively evaluate the proppant placement effect under full-area support fracturing.

[0087] Therefore, this invention discloses a quantitative evaluation method for proppant placement effect under full-domain supported fracturing based on image recognition technology. This method first preprocesses the sedimentary image, then achieves precise background segmentation and vertical partitioning of the sedimentary area by fusing interactive sampling and grayscale gradient analysis. Next, it robustly extracts the top contour of the sediment by combining manual drawing and automatic edge detection. Furthermore, for each partition, a grayscale-density conversion model is constructed based on a locally calibrated densest packing grayscale benchmark to calculate various parameters such as sedimentary height, area, volume, porosity, and particle and fiber quality. Finally, the results are summarized and visualized. This invention achieves non-contact, automated, and high-precision multi-parameter sedimentary analysis, effectively overcoming the challenges of image inhomogeneity and blurred boundaries, and is suitable for sedimentary monitoring and research in environmental, mining, and chemical industries.

[0088] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A quantitative evaluation method for the proppant placement effect under full-area supported fracturing, characterized in that, Includes the following steps: S1. Image acquisition and preprocessing: A physical simulation experiment of proppant-fiber transport was conducted. After the deposited material stabilized, the deposition image was acquired, converted into a grayscale image, and the image area to be processed was interactively delineated. S2. Background segmentation and vertical partitioning: Interactive sampling is performed on the background area and deposition area of ​​the grayscale image respectively, and the background analysis zone and contour recognition zone are automatically determined based on the grayscale statistical features of the sampling points. The grayscale gradient changes are analyzed along the background analysis band to identify the vertical boundary of the deposition area; based on the vertical boundary, the entire deposition area is divided into N analysis blocks in the horizontal direction. S3. Human-machine collaborative extraction of sediment contours: The top contour line of the sediment is extracted by combining manual drawing with automatic edge detection; the results of the two methods are fused to generate a set of top contour coordinates of the sediment. S4. Calculation of partition parameters and model construction: For each analysis block divided in step S2, the sediment volume space is determined according to the top contour coordinate set and the known sedimentary bottom edge, and the sedimentary height, cross-sectional area and volume of the block are calculated; within the sedimentary space of the block, the first reference gray value representing the densest particle packing state and the second reference gray value representing porosity are calculated; based on the first reference gray value and the second reference gray value, a gray-density conversion model is constructed to calculate the porosity, particle mass and fiber mass of the block; S5. Results Fusion and Visualization: Summarize the calculation results of all analysis blocks to obtain the overall physical parameters of the sediments, and visualize the partitioning results, contours and parameters to quantitatively evaluate the proppant placement effect.

2. The quantitative evaluation method for the proppant placement effect under full-area supported fracturing according to claim 1, characterized in that, After converting the deposited image to a grayscale image in step S1, the image region to be processed is interactively delineated. The interactive sampling in step S2 includes: clicking on the left and right boundaries of the deposition and the bottom of the deposition in sequence in the grayscale image deposition region.

3. The quantitative evaluation method for the proppant placement effect under full-area supported fracturing according to claim 1, characterized in that, In step S2, the interactive sampling includes: a gesture input that draws an approximate vertical line in the grayscale image background area and the deposition area respectively; The automatic determination of the background analysis zone and the contour recognition zone includes: calculating the maximum and minimum values ​​of the row coordinates of all pixels in the gesture input trajectory, and determining the upper and lower boundaries of the background analysis zone and the contour recognition zone respectively by the area enclosed by the row coordinates of their respective maximum and minimum values.

4. The quantitative evaluation method for the proppant placement effect under full-area supported fracturing according to claim 1, characterized in that, In step S2, the gray-level gradient change is analyzed using the interval difference method: along the background analysis band, the gray-level difference between K pixels is calculated as the gradient value; when the gradient value exceeds the set threshold, it is determined that there is a vertical boundary at that position; where K is an integer greater than or equal to 1.

5. The quantitative evaluation method for the proppant placement effect under full-area supported fracturing according to claim 1, characterized in that, In step S3, after fusing the results of manual drawing and automatic detection, a contour coordinate interpolation step is also included: for each column of pixels, if there are multiple contour row coordinates, the average is taken; if there are no such coordinates, linear interpolation is performed based on the coordinates of adjacent columns.

6. The quantitative evaluation method for the proppant placement effect under full-area supported fracturing according to claim 1, characterized in that, In step S4, the first reference gray value is calculated as follows: within the block, the gray values ​​of all pixels in the deposition space are obtained, sorted, and the average of the top M smallest gray values, which account for a certain proportion of the total number of collected pixels, is taken; wherein, the M value is adaptively allocated according to the proportion of the horizontal width of the block to the width of the entire deposition area.

7. The quantitative evaluation method for the proppant placement effect under full-area support fracturing according to claim 1, characterized in that, In step S4, the gray-to-density conversion model is constructed as follows: a second reference gray value is set, which is the gray value representing the pores in the image. The second reference gray value is calculated as follows: within the block, the gray values ​​of all pixels in the background space are obtained, and the average value is subtracted from the product of the empirical coefficient and the standard deviation. For any pixel in the deposition space, if its gray value is less than or equal to the first reference gray value, it is determined to be the densest packing and is given the maximum material density. If its gray value is between the first and second reference gray values, then its material density and gray value have a linear negative correlation.

8. A quantitative evaluation device for the proppant placement effect under full-area support fracturing, comprising the following modules: Image processing module: Conducts physical simulation experiments of proppant-fiber transport, acquires deposition images after the deposited material stabilizes, converts the deposition images into grayscale images, and interactively delineates the image areas to be processed; Region segmentation module: interactively samples the background and deposition areas of the grayscale image, and automatically determines the background analysis zone and contour recognition zone based on the grayscale statistical features of the sampling points; The grayscale gradient changes are analyzed along the background analysis band to identify the vertical boundary of the deposition area; based on the vertical boundary, the entire deposition area is divided into N analysis blocks in the horizontal direction. Contour acquisition module: Extracts the top contour line of the sediment by combining manual drawing with automatic edge detection; merges the two results to generate a set of top contour coordinates of the sediment. Parameter calculation module: For each analysis block divided by the region division module, the sediment volume space is determined based on the top contour coordinate set and the known sedimentary bottom edge, and the sedimentary height, cross-sectional area and volume of the block are calculated; within the sedimentary space of the block, a first reference gray value representing the densest particle packing state and a second reference gray value representing porosity are calculated; based on the first reference gray value and the second reference gray value, a gray-density conversion model is constructed to calculate the porosity, particle mass and fiber mass of the block; Quantitative evaluation of modulus: Summarize the calculation results of all analysis blocks to obtain the overall physical parameters of the sediments, and visualize the partitioning results, contours and parameters to quantitatively evaluate the proppant placement effect.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method of any one of claims 1-8.

Images