Method, system and equipment for acquiring artificial fracture parameters

Abstract

The invention relates to the technical field of petroleum and natural gas engineering, in particular to a method, a system and equipment for acquiring artificial fracture parameters. The method comprises the following steps: acquiring initial fracture form data through a core experiment, wherein the initial fracture form data comprises the straightness, the branch number and the roughness parameter of a fracture; performing verification analysis based on morphology on the initial fracture morphology data, and adding morphological characteristics of irregular fractures to obtain fracture morphology data; according to the fracture form data, fracture conductivity simulation based on proppant distribution and stratum conditions is carried out, preliminary evaluation is carried out, and fracture conductivity data are generated; and carrying out dynamic adjustment processing based on crack pressure on the crack form data by using micro-seismic imaging to generate crack three-dimensional form model data. Through systematic core experiment and strict morphological verification, the obtained data has higher accuracy and reliability, and firm data support is provided for subsequent flow conductivity analysis and model construction.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas engineering, and particularly to a method, a system and a device for obtaining artificial fracture parameters. Background Art

[0002] Artificial fracture parameters play a key role in the process of hydraulic fracturing and are the basis for evaluating fracturing effects and optimizing design schemes. They include: fracture width, which refers to the lateral width of the fracture in the open state and is an important parameter affecting fluid flow and conductivity. It is usually determined through fluid mechanics models and on-site measurements. Fractures with larger widths can accommodate more fracturing proppants, increase the fluid flow path, and improve oil and gas production.

[0003] However, the traditional methods for obtaining artificial fracture parameters often have the following problems: Fracture morphology, including straightness, the number of branches, and fracture roughness, directly affects fluid flow and productivity. However, in complex formations, the fracture morphology is irregular and difficult to monitor. Usually, it can only be indirectly analyzed through core experiments and fluid simulations. Although methods such as microseismic imaging can reflect the fracture morphology to a certain extent, their resolution in multi-branched and multi-layer fracture networks is limited. Fracture conductivity is usually obtained through post-fracture tests, but the test results are greatly affected by fracture morphology, proppant distribution, and formation conditions. The actual in-situ conductivity may be affected by factors such as fracturing fluid backflow and proppant reflux, resulting in unstable conductivity. The test results often cannot fully reflect the true fracture conductivity. In addition, the conditions of fractures and proppants in laboratory simulations are different from those in the field, which affects the accuracy of conductivity evaluation. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide a method, a system and a device for obtaining artificial fracture parameters to solve at least one of the above technical problems.

[0005] To achieve the above object, a method for obtaining artificial fracture parameters includes the following steps: Step S1: Collect initial fracture morphology data through core experiments, including fracture straightness, the number of branches, and roughness parameters; perform verification analysis based on morphology on the initial fracture morphology data, and add morphological features of irregular fractures to obtain fracture morphology data. Step S2: Simulate the fracture conductivity based on the proppant distribution and formation conditions according to the fracture morphology data, and conduct a preliminary evaluation to generate fracture conductivity data; use microseismic imaging to perform dynamic adjustment processing on the fracture morphology data based on fracture pressure to generate fracture three-dimensional morphology model data, where the dynamic adjustment processing specifically refers to morphological reconstruction of the multi-branched and multi-layer structures of the fracture network. Step S3: Conduct multi-scale diversion capacity analysis based on the three-dimensional fracture morphology model data and fracture diversion capacity data to generate optimized diversion capacity data; monitor the fracture proppant backflow according to the optimized diversion capacity data to obtain the produced fluid flow rate data and proppant backflow data; Step S4: Evaluate the stability of the diversion capacity based on the produced fluid flow rate data and proppant backflow data according to the trend of flow rate changes, and analyze the long-term flow characteristics of the fracture to generate stability evaluation data; Step S5: Construct a fracture diversion capacity model based on the stability evaluation data and the optimized diversion capacity data, and conduct a difference comparison with the pre-acquired on-site measured data to correct the fracture diversion capacity model and generate fracture parameter optimization model data.

[0006] The acquisition of the initial fracture morphology data in the present invention provides basic data for subsequent analysis, ensuring that the true situation of the rock formation can be accurately reflected. Verifying the rationality of fracture characteristics through morphological analysis improves the reliability of the data and reduces errors in subsequent model establishment. The supplementation of the morphological characteristics of irregular fractures makes the data more comprehensive, helps to capture complex geological structures, and enhances the detail of the model. Through simulation, the flow performance of fractures under specific conditions can be evaluated, providing a scientific basis for subsequent engineering design and decision-making. Using microseismic imaging technology can reflect the changes of fractures under pressure in real time, ensuring that the generated three-dimensional model can better adapt to the actual formation conditions and improving the accuracy and reliability of the model. The reconstruction of multi-branch and multi-layer fracture networks enhances the understanding of complex fracture systems, facilitating further optimization and design. Through the diversion capacity analysis at different scales, the performance of fractures under different conditions can be identified, providing a basis for optimization design. The acquisition of the produced fluid flow rate and proppant backflow data can help to evaluate the diversion state of fractures in real time, timely detect potential problems, and ensure the safety and efficiency of production. The optimized diversion capacity data provides support for subsequent proppant placement and engineering decision-making, improving the overall economic benefit and operation efficiency. The evaluation of the trend of flow rate changes can help to judge the stability of fractures during long-term operation, providing an important reference for subsequent operations; the analysis of long-term flow characteristics helps to identify the regularity of fracture flow and potential risk factors, improving the safety of operations; the stability evaluation data provides a scientific basis for the adjustment of production strategies and risk management, ensuring the effective utilization of resources and environmental protection. Through comprehensive evaluation and optimization, the constructed diversion capacity model can more accurately reflect the actual diversion performance of fractures, providing a scientific basis for subsequent resource development. By comparing with on-site measured data, the deficiencies of the model can be effectively identified, necessary corrections can be made, and the accuracy and adaptability of the model can be improved. The generation of the fracture parameter optimization model provides a reference for further production optimization in the future, helping to improve the resource utilization efficiency and reduce production costs.

[0007] The present invention also provides a system for obtaining artificial fracture parameters, which is used to execute the method for obtaining artificial fracture parameters described above. The system for obtaining artificial fracture parameters includes: A morphology acquisition module, which is used to collect initial fracture morphology data through core experiments, including the straightness, number of branches, and roughness parameters of the fractures; perform verification analysis based on morphology on the initial fracture morphology data, and add morphological features of irregular fractures, so as to obtain fracture morphology data; A morphology reconstruction module, which is used to simulate the fracture conductivity based on the proppant distribution and formation conditions according to the fracture morphology data, and conduct a preliminary evaluation to generate fracture conductivity data; use microseismic imaging to perform dynamic adjustment processing based on fracture pressure on the fracture morphology data to generate fracture three-dimensional morphology model data, where the dynamic adjustment processing is specifically to reconstruct the morphology of the multi-branch and multi-layer structures of the fracture network; A conductivity monitoring module, which is used to perform multi-scale conductivity analysis according to the fracture three-dimensional morphology model data and the fracture conductivity data to generate optimized conductivity data; monitor the fracture proppant backflow according to the optimized conductivity data, so as to obtain the backflow liquid flow rate data and the proppant backflow data; A stability evaluation module, which is used to evaluate the stability of the conductivity based on the change trend of the flow rate through the backflow liquid flow rate data and the proppant backflow data, and analyze the long-term flow characteristics of the fracture to generate stability evaluation data; A parameter optimization module, which is used to construct a fracture conductivity model according to the stability evaluation data and the optimized conductivity data, and perform a difference comparison according to the pre-obtained on-site measured data to correct the fracture conductivity model and generate fracture parameter optimization model data.

[0008] The initial crack morphology data of the present invention provides basic characteristic information of the cracks, laying a foundation for subsequent analysis. By quantifying the crack straightness, branch number, and roughness, the geometric characteristics of the cracks can be accurately described. The morphological verification analysis ensures the reliability and accuracy of the collected data, increasing the depth of understanding of the crack morphology. Introducing the morphological characteristics of irregular cracks makes the model closer to the actual situation, thereby improving the authenticity of subsequent analysis and simulation. Through simulation and preliminary evaluation, the flow conductivity of the cracks can be quantitatively analyzed, providing a basis for optimizing the proppant distribution and enhancing fluid flow. This evaluation is crucial for designing the exploitation plan of the cracks and can effectively predict the exploitation effect. The microseismic imaging technology enables dynamic adjustment of the crack morphology under different formation pressures, and the generated three-dimensional model can truly reflect the complex structure of the cracks, helping engineers better understand and utilize the crack network. The multi-scale flow conductivity analysis can comprehensively understand the flow conductivity characteristics of the cracks at different scales, helping to identify the main factors affecting the flow conductivity, so as to provide a precise direction for subsequent optimization. By monitoring the flow rate of the produced fluid and the proppant backflow data, the flow conductivity performance of the cracks can be real-time feedback, ensuring that the operation strategy can be adjusted in time to maximize the resource recovery efficiency. The analysis of the flow rate change trend can timely detect potential flow instabilities, provide reliable early warning information, and prevent crack damage or failure caused by flow instability. The analysis of the long-term flow characteristics of the cracks provides data support for designing long-term exploitation plans, ensuring the safety and economy of the exploitation process. By combining the stability evaluation and flow conductivity optimization data, the constructed crack flow conductivity model is more accurate, reflects the actual situation, and provides a solid basis for subsequent operations. The difference comparison of on-site measured data ensures the real-time correction ability of the model, enhances the adaptability of the model in actual operations, and thus improves the efficiency and reliability of crack exploitation.

[0009] The present invention also provides an electronic device, including a processor and a memory. The processor is used to execute the computer program stored in the memory to implement the method for obtaining artificial fracture parameters described in any one of the above. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] By reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, other features, objects, and advantages of the present invention will become more apparent: Figure 1 It is a schematic flow chart of the steps of the method for obtaining artificial fracture parameters of the present invention; Figure 2 For Figure 1 it is a detailed schematic flow chart of step S1 in Figure 3 For Figure 1 it is a detailed schematic flow chart of step S2 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative work belong to the scope of protection of the present invention.

[0012] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0013] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed related items.

[0014] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for obtaining artificial fracture parameters, and the method includes the following steps: Step S1: Collect initial fracture morphology data through core experiments, including the straightness, number of branches, and roughness parameters of the fractures; perform verification analysis based on morphology on the initial fracture morphology data, and add morphological features of irregular fractures to obtain fracture morphology data; Step S2: Simulate the fracture conductivity based on the proppant distribution and formation conditions according to the fracture morphology data, and perform a preliminary evaluation to generate fracture conductivity data; use microseismic imaging to perform dynamic adjustment processing based on fracture pressure on the fracture morphology data to generate fracture three-dimensional morphology model data, where the dynamic adjustment processing is specifically to perform morphological reconstruction on the multi-branch and multi-layer structures of the fracture network; Step S3: Perform multi-scale conductivity analysis according to the fracture three-dimensional morphology model data and the fracture conductivity data to generate optimized conductivity data; monitor the fracture proppant backflow according to the optimized conductivity data to obtain the backflow liquid flow rate data and the proppant backflow data; Step S4: Conducting a conductivity stability assessment based on the flow velocity variation trend through the backflow liquid velocity data and the proppant backflow data, and performing a long-term flow characteristic analysis of the fracture to generate stability assessment data; Step S5: construct a fracture conductivity model based on the stability assessment data and the conductivity optimization data, and perform a difference comparison based on the pre-acquired field measured data to modify the fracture conductivity model and generate fracture parameter optimization model data.

[0015] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for obtaining artificial crack parameters of the present invention. In this example, the method for obtaining artificial crack parameters includes the following steps: Step S1: collecting initial fracture morphology data through core experiments, including fracture straightness, branch number, and roughness parameters; performing morphological verification analysis on the initial fracture morphology data, and adding morphological features of irregular fractures to obtain fracture morphology data; The embodiment of the present invention uses microscopic imaging technology to collect microscopic images of core fractures to obtain initial fracture morphology data including the straightness, number of branches and roughness of the fractures. In the specific operation, a microscopic imaging device with a resolution of 1 μm is used to scan the fracture morphology characteristics of each layer of core samples layer by layer, and the image processing algorithm is used to remove noise and enhance the edge to improve the image clarity, and generate fracture morphology clarity enhanced data. On the basis of the clarity enhanced data, the fracture contour extraction algorithm is applied to obtain the main axis direction and edge curvature information of the fracture, and then the straightness is quantified. Subsequently, the number of branches of the fracture is counted and the secondary branches are identified by the image segmentation algorithm, and the microscopic irregularity of the fracture is evaluated based on the surface roughness algorithm to calculate the roughness. The initial fracture morphology data is subjected to morphological verification analysis, outliers and atypical fracture data are eliminated, and irregular fracture features are supplemented by model fitting, and the structure of micro cracks and secondary branches is added to the fracture morphology data.

[0016] Step S2: simulating the fracture conductivity based on proppant distribution and formation conditions according to the fracture morphology data, and making a preliminary evaluation to generate fracture conductivity data; using microseismic imaging to dynamically adjust the fracture morphology data based on fracture pressure to generate fracture three-dimensional morphology model data, wherein the dynamic adjustment processing is specifically to reconstruct the morphology of the multi-branch and multi-layer structure of the fracture network; In the embodiments of the present invention, based on the crack morphology data, a comprehensive analysis is carried out on the proppant distribution in the crack and the formation conditions. A proppant sample with a corresponding embedment degree is selected, and environmental parameters such as the surrounding formation pressure and temperature are collected to construct a simulation model of the fracture conductivity based on the proppant distribution and the formation mechanical properties. The preliminary evaluation of the conductivity is achieved through multiphase flow calculations, including considerations of fluid viscosity, flow velocity, and proppant settlement damage. On this basis, microseismic imaging technology is used to obtain microseismic signal data during the fracture propagation process, and the three-dimensional fracture morphology model is dynamically adjusted according to the fracture pressure. During the dynamic adjustment process, first, the spatial distribution of the microseismic signal data is analyzed through seismic source location to identify the multi-branch and multi-layer structures of the fracture; then, a three-dimensional morphology model of the fracture network is generated based on image processing and morphological reconstruction techniques to reflect the fracture morphology changes under actual formation conditions.

[0017] Step S3: Perform multi-scale conductivity analysis based on the three-dimensional fracture morphology model data and the fracture conductivity data to generate optimized conductivity data; monitor the proppant backflow in the fracture according to the optimized conductivity data, so as to obtain the backflow liquid velocity data and the proppant backflow data; In the embodiments of the present invention, according to the three-dimensional fracture morphology model data and the fracture conductivity data, a multi-scale conductivity analysis is carried out. Specifically, the finite element analysis and multi-scale analysis theory are used to divide the three-dimensional fracture network into multiple conductivity units, and the flow capacity of each unit is calculated. Factors such as the proppant distribution inside the fracture and the fluid permeability are considered in the analysis, and the scale results are summarized to form optimized conductivity data. Based on the optimized conductivity data, a backflow liquid collection system is arranged and the flow velocity of the backflow liquid is monitored through a flow velocity sensor. At the same time, the proppant backflow in the backflow liquid is monitored through a particle size analyzer and a proppant content analysis device to generate the backflow liquid velocity data and the proppant backflow data.

[0018] Step S4: Evaluate the stability of the conductivity based on the change trend of the flow velocity through the backflow liquid velocity data and the proppant backflow data, and analyze the long-term flow characteristics of the fracture to generate stability evaluation data; In the embodiments of the present invention, a time series analysis is carried out on the backflow liquid velocity data and the proppant backflow data to identify the change trend of the flow velocity, and thus the stability of the conductivity is evaluated. In the specific operation, the correlation between the flow velocity and the proppant content is dynamically modeled to identify the flow velocity changes caused by the proppant backflow, and the long-term impact on the conductivity is analyzed in combination with the proppant damage effect to generate stability evaluation data. In addition, according to the time characteristics of the flow velocity and proppant changes in the backflow data, the characteristic evolution of the fracture during the long-term flow process is further analyzed to provide a quantitative basis for the long-term stability of the fracture conductivity.

[0019] Step S5: Construct a fracture conductivity model based on the stability evaluation data and the diversion capacity optimization data, and perform a difference comparison based on the pre-obtained on-site measured data to correct the fracture conductivity model and generate fracture parameter optimization model data.

[0020] Based on the stability evaluation data in step S4 and the diversion capacity optimization data in step S3, the embodiment of the present invention constructs a fracture conductivity model. First, comparative analysis is performed using on-site measured data (including fracture conductivity, proppant distribution, fluid pressure, etc.) and model data to identify the sources of error. Then, data-driven parameter sensitivity analysis is used to determine the correction parameters for the model. The corrected parameter data is iterated multiple times to gradually optimize the fracture conductivity model, and finally the model accuracy is verified in the actual formation environment to generate fracture parameter optimization model data to provide a reliable prediction of the fracture conductivity.

[0021] The acquisition of the initial fracture morphology data in the present invention provides basic data for subsequent analysis, ensuring that the true situation of the rock formation can be accurately reflected. By morphological analysis, the rationality of fracture characteristics is verified, the reliability of data is improved, and the errors in subsequent model establishment are reduced. The supplementation of the morphological characteristics of irregular fractures makes the data more comprehensive, helps to capture complex geological structures, and enhances the detail of the model. Through simulation, the flow performance of fractures under specific conditions can be evaluated, providing a scientific basis for subsequent engineering design and decision-making. Using microseismic imaging technology can reflect the changes of fractures under pressure in real time, ensuring that the generated three-dimensional model can better adapt to the actual formation conditions and improving the accuracy and reliability of the model. The reconstruction of multi-branch and multi-layer fracture networks enhances the understanding of complex fracture systems, facilitating further optimization and design. Through the analysis of the diversion capacity at different scales, the performance of fractures under different conditions can be identified, providing a basis for optimization design. The acquisition of the flowback liquid velocity and proppant reflux data can help to evaluate the diversion state of fractures in real time, timely detect potential problems, and ensure the safety and efficiency of production. The optimized diversion capacity data provides support for subsequent proppant placement and engineering decision-making, improving the overall economic benefits and operation efficiency. The evaluation of the flow velocity change trend can help to judge the stability of fractures during long-term operation, providing an important reference for subsequent operations; the analysis of long-term flow characteristics helps to identify the regularity of fracture flow and potential risk factors, improving the safety of operations; the stability evaluation data provides a scientific basis for the adjustment of production strategies and risk management, ensuring the effective utilization of resources and environmental protection. Through comprehensive evaluation and optimization, the constructed diversion capacity model can more accurately reflect the actual diversion performance of fractures, providing a scientific basis for subsequent resource development. By comparing with the on-site measured data, the deficiencies of the model can be effectively identified, and necessary corrections can be made to improve the accuracy and adaptability of the model. The generation of the fracture parameter optimization model provides a reference for further production optimization in the future, helping to improve the resource utilization efficiency and reduce the production cost.

[0022] Preferably, step S1 includes the following steps: Step S11: Use microscopic imaging technology to collect images of the core fracture morphology, generating core fracture microscopic image data; Step S12: Perform preprocessing on the core fracture microscopic image data based on image noise removal and edge enhancement operations, generating enhanced fracture morphology clarity data; Step S13: Extract the fracture contour from the enhanced fracture morphology clarity data, and extract features such as fracture straightness, branch number, and roughness, thereby obtaining the initial fracture morphology data; Step S14: Supplement the morphological features of the irregular cracks based on the preliminary morphological data of the cracks, so as to obtain the crack morphological feature data, where the morphological feature supplement includes identifying microcracks and secondary branches based on the number of branches and roughness of the cracks; Step S15: Obtain formation pressure data, cross-verify the crack morphological feature data and the formation pressure data, and evaluate the effectiveness of the measured morphology under formation conditions, so as to obtain crack morphology verification data; Step S16: Synthesize the features of the crack morphology based on the crack morphology verification data and the crack morphological feature data to generate crack morphology data.

[0023] As an embodiment of the present invention, refer to Figure 2 shown, for Figure 1 the detailed step flow diagram of step S1 in Step S11: Use microscopic imaging technology to collect images of the core crack morphology to generate core crack microscopic image data; In the microscopic imaging process of the core cracks in the embodiment of the present invention, first, appropriate core samples are selected to ensure the representativeness and integrity of the samples. Then, a high-resolution scanning electron microscope (SEM) or confocal microscope is used. The resolution range of these devices is generally 0.5 to 1 μm. In the device settings, the low-gain mode is used to reduce image noise, and white light or laser is selected as the light source to optimize the imaging effect. During image acquisition, set an appropriate scanning speed (for example, 10 frames per second), and perform layer-by-layer scanning of 0.5 μm for each layer to ensure obtaining all-round crack data. All collected images are saved in the.tif format, and corresponding coordinate information is marked according to the sample characteristics to form a complete core crack microscopic image data set.

[0024] Step S12: Perform preprocessing on the core crack microscopic image data based on image noise removal and edge enhancement operations to generate crack morphology clarity enhancement data; In the embodiment of the present invention, noise removal and edge enhancement processing are performed on the obtained core crack microscopic image data. In the specific operation, first, a median filter is applied, and a window size of 5x5 is selected to smooth the image and remove random noise. Then, the Sobel operator is used for edge detection to obtain the clarity of the crack edge. The algorithm parameter is set to a threshold of 0.15 to ensure that effective edges can be identified. During the processing, image enhancement techniques such as histogram equalization are used to enhance the contrast of the image and make the crack structure more obvious. After the processing is completed, the generated crack morphology clarity enhancement data will be saved in a new image file for subsequent analysis.

[0025] Step S13: Extract the crack contour from the enhanced data of crack morphology clarity, and extract the features of crack straightness, branch number, and roughness, so as to obtain the initial crack morphology data; In the embodiment of the present invention, the crack contour extraction and feature extraction are performed on the enhanced data of crack morphology clarity. In the operation, first, the morphological opening operation is used to remove small noise particles, and then the watershed algorithm is applied to segment the image to separate the crack contour. By calculating the ratio of the contour length to the straight-line segment length, the straightness of the crack is obtained. The specific calculation method is: straightness = (contour length) / (straight-line segment length). For the branch number, by detecting the crack intersection points in the image, the Hough transform method is used to identify the intersection points and count the branch number. The roughness is calculated by analyzing the local fluctuations of the crack edge and using the fractal dimension method to calculate the complexity of the edge. Finally, these feature data are integrated into a structured data file to form the initial crack morphology data.

[0026] Step S14: Supplement the morphological features of the irregular cracks according to the preliminary morphology data of the cracks, so as to obtain the crack morphology feature data, where the morphological feature supplement includes the identification of micro-cracks and secondary branches based on the branch number and roughness of the cracks; In the embodiment of the present invention, the morphological features of the irregular cracks are supplemented for the initial crack morphology data. In the actual operation, the micro-crack and secondary branch identification algorithm based on the branch number and roughness is used. The specific steps are as follows: First, set a threshold, and mark the part with a roughness greater than 0.1 as potential micro-cracks. Then, use the image processing algorithm to refine the crack features, set a structural element with a radius of 1 pixel for morphological operations, so as to extract the secondary branch structure of the crack. Combining the edge detection results, confirm the positions of all potential micro-cracks, mark and record their sizes and morphologies. Finally, generate a crack morphology feature data set containing rich crack features for subsequent use.

[0027] Step S15: Obtain the formation pressure data, perform cross-validation on the crack morphology feature data and the formation pressure data, and evaluate the effectiveness of the measured morphology under formation conditions, so as to obtain the crack morphology verification data; In the process of obtaining the formation pressure data in the embodiment of the present invention, a suitable pressure sensor (such as a sensor with a pressure range of 0-200 MPa) is selected, and the sensor is buried around the core to monitor the formation pressure change in real time. Cross-validate the obtained pressure data with the crack morphology feature data, and use the finite element analysis method to simulate the crack morphology under different pressure conditions to evaluate the stability of the crack. In the specific operation, compare the simulation results with the on-site measured data, set a reasonable error range (for example, ±5%), confirm the effectiveness of the measured morphology under the actual formation conditions, and finally obtain the crack morphology verification data.

[0028] Step S16: Based on the crack morphology verification data and the crack morphology feature data, perform feature synthesis of the crack morphology to generate crack morphology data.

[0029] In the embodiment of the present invention, feature synthesis of the crack morphology is performed based on the crack morphology verification data and the crack morphology feature data. During the operation, the image stitching technology is used to merge the verified crack morphology features with the initial data. The image fusion algorithm based on the Laplace pyramid is adopted. First, pyramid decomposition is performed on each layer of the image, and appropriate fusion layers (such as the second layer and the third layer) are selected. The features of different layers are synthesized by the method of weighted average to ensure the retention of details and the continuity of the crack structure. During the synthesis process, the fusion coefficient is set to 0.7 to highlight the crack features. The generated crack morphology data will be saved in 3D format to ensure its applicability to subsequent diversion capacity analysis.

[0030] The microscopic imaging technology of the present invention (such as scanning electron microscope, optical microscope, etc.) can capture details at the micron level, enabling the accurate recording of the microscopic features of cracks (such as the texture and structure of cracks); providing a basis for morphological analysis: the microscopic images provide a rich data source for subsequent analysis, helping to identify the complexity and diversity of cracks, and ensuring high accuracy in subsequent analysis. Random noise in the image is eliminated through noise removal techniques (such as median filtering, mean filtering, etc.), while edge enhancement algorithms (such as Canny edge detection) are used to improve the visibility of crack edges in the image, ensuring clearer boundaries; clear image data can reduce errors in the subsequent analysis process, improve the accuracy of crack feature extraction, and make subsequent decisions more reliable. By using algorithms to extract the contours of cracks, important parameters such as the straightness, number of branches, and roughness of cracks can be quantitatively analyzed, providing quantifiable data support for subsequent research. The generation of initial crack morphology data lays an important foundation for subsequent model construction and predictive analysis, ensuring that subsequent work can rely on accurate data. By identifying the microfissures and secondary branches of irregular cracks, more complex crack structures can be captured, enhancing the understanding of the formation crack system and improving the comprehensiveness of overall morphological features; these detailed supplements help to more accurately simulate and analyze the behavior of cracks in the formation, and can reflect more real geological conditions. Through cross-validation, the effectiveness of the measured crack morphology under actual formation conditions can be confirmed, ensuring that the morphological features match the formation environment and improving the credibility of the research; combining formation pressure with crack morphology data can provide a more comprehensive geological background, helping to identify the relationship between crack behavior and formation conditions, and providing more reliable information for subsequent decisions. Through feature synthesis, data from different sources and types can be integrated to form more comprehensive and consistent crack morphology data, providing more accurate information for subsequent analysis. The generated crack morphology data provides a solid foundation for subsequent model construction, risk assessment, and resource development decisions, helping to improve the efficiency and scientific nature of decisions.

[0031] Preferably, step S13 includes the following steps: Extract the crack contour from the enhanced data of crack morphology clarity to obtain crack contour data; quantify the deviation of the main axis direction of the crack for the crack contour data to generate crack straightness data; count the number of branches of the crack for the crack contour data through image segmentation technology to obtain crack branch data; evaluate the surface micro-irregularity of the crack for the crack contour data through the surface roughness algorithm to obtain crack roughness data; merge the crack straightness data, crack branch data, and crack roughness data into initial crack morphology data.

[0032] In the embodiments of the present invention, for the crack image data after clarity enhancement, an edge detection algorithm is applied, and the Canny edge detector is selected with its parameter settings being a low threshold of 50 and a high threshold of 150 to ensure effective detection of the crack edges. Subsequently, morphological closing operation is used to fill the holes inside the contour, and a 3x3 structuring element is used to smooth the contour. Then, a contour tracking algorithm (such as the Suzuki algorithm) is adopted to extract the contour and generate a contour point set to ensure the integrity and coherence of the obtained crack contour data. Finally, the crack contour data is stored in the GeoJSON format for convenient subsequent data processing and analysis. In the obtained crack contour data, first, the principal component analysis (PCA) method is used to identify the main direction of the crack. By calculating the covariance matrix of the crack contour points and extracting its eigenvalues and eigenvectors, the direction corresponding to the eigenvector is the main axis direction of the crack. Then, the straightness of the crack is calculated. The reference line is set as the main axis direction, and the perpendicular distance from the contour points to the reference line is measured. The standard deviation of these distances is obtained by using statistical methods. Finally, the crack straightness data is generated using the ratio of the standard deviation to the main axis length, with the parameter set as straightness = standard deviation / main axis length, and it is stored as a structured database entry. For the crack contour data, the watershed algorithm is used for image segmentation. First, the contour data is smoothed by Gaussian filtering (with the parameter set as σ = 2) to remove the influence of noise. Then, a marker map for the watershed algorithm is generated using the gradient map, and the high-gradient regions in the image are marked as potential crack branches. Connected component analysis is applied to calculate the number and size of the branch regions, and each branch region is recorded as an independent object. Finally, the statistical results are exported as a CSV file containing the number, area, and position coordinates of each branch as the crack branch data. In the crack contour data, first, the crack contour is meshed with a grid size of 1x1 pixel to generate a surface height map. Then, the Ra (arithmetic mean roughness) and Rz (ten-point height roughness) algorithms are applied to evaluate the grid data. The specific calculation methods are as follows: , where N is the number of grid points, is the height of each grid point; = , where is the maximum height value within the selected measurement length, that is, the highest point among all grid points in the measurement area, is the minimum height value within the same measurement length, that is, the lowest point among all grid points in the measurement area. After the calculation is completed, the roughness data is organized in a tabular form, including and The values are stored as an Excel file for subsequent analysis. After calculating the crack straightness, branching, and roughness data, data merging techniques are employed. First, the Pandas library in Python is used to read each data file and construct a data frame. Then, different feature data are integrated into a new data frame through the common crack ID to ensure that all relevant information corresponds one by one. Next, the merged data is checked to ensure there are no missing values and duplicate records, and a filling strategy for missing values is set (such as filling with the mean). Finally, the initial crack morphology data after merging is saved in an SQL database or in CSV format for subsequent model analysis and verification.

[0033] The present invention extracts a clear crack profile that can accurately reflect the morphological characteristics of the crack, providing basic data for subsequent analysis; the clear profile data helps to capture subtle morphological changes and ensure the comprehensive presentation of crack characteristics. Quantifying the deviation of the main axis direction helps to understand the straightness of the crack and its impact on flow, supporting the establishment of a hydrodynamic model; the crack straightness data can provide important references for proppant placement and hydraulic fracturing design to ensure the effectiveness of the design. The statistics of the number of branches helps to evaluate the complexity of the crack network, identify multiple flow paths, and support flow simulation; understanding the branch structure can optimize the distribution of proppants and the flow path of fluids to improve the recovery rate. The surface roughness has an important impact on fluid flow. Evaluating the roughness can help to understand the flow resistance and flow distribution. The roughness data provides an important basis for proppant selection and injection scheme to ensure effectively overcoming the flow resistance. The initial crack morphology data after merging integrates multi-dimensional crack information, providing a comprehensive description of crack characteristics; these comprehensive data will provide a solid foundation for further analysis of conductivity, model construction, and decision support to ensure effectiveness under complex formation conditions. These steps ensure detailed and accurate initial crack morphology data by layer-by-layer analysis and quantification of crack characteristics. This not only improves the understanding of crack behavior but also provides a reliable basis for subsequent model construction, flow analysis, and engineering decision-making, thereby optimizing the efficiency and safety of resource development.

[0034] Preferably, step S2 includes the following steps: Step S21: Obtain the formation rock mechanics parameters and proppant distribution parameters to generate proppant-rock parameter data; Step S22: Establish a proppant embedment model based on the proppant-rock parameter data and calculate the crack closure pressure based on the formation conditions to generate initial evaluation data of crack conductivity; Step S23: Calculate the flow capacity based on the multiphase flow theory using the initial evaluation data, and conduct an analysis of permeability degradation based on the proppant settlement and damage effects, thereby obtaining the fracture conductivity data. The permeability degradation analysis is specifically to evaluate the long-term impact of proppants on fracture permeability by simulating the settlement behavior of proppants in fractures and the cumulative effect of microscopic damage; Step S24: Use microseismic imaging to perform dynamic adjustment processing of the fracture morphology data based on the fracture pressure to generate the three-dimensional fracture morphology model data. The dynamic adjustment processing is specifically to perform image processing and morphological reconstruction on the multi-branch and multi-layer structures of the fracture network.

[0035] As an embodiment of the present invention, referring to Figure 3 shown, for Figure 1 the detailed step flow diagram of step S2 in Step S21: Obtain the formation rock mechanical parameters and proppant distribution parameters to generate proppant-rock parameter data; In the embodiment of the present invention, the mechanical parameters of the rock sample are obtained through laboratory tests, such as compressive strength, tensile strength, and shear modulus. These parameters are usually obtained through uniaxial compression experiments and tensile experiments. The loading rate set in the experiment is 0.5 MPa / s until the rock sample ruptures. Then, the morphology of the proppant is observed using a scanning electron microscope (SEM), and the particle size distribution and porosity of the proppant are measured. The specific parameter setting is a particle size range of 1-2 mm. Next, the obtained rock mechanical parameters and proppant distribution parameters are integrated into a data table to form proppant-rock parameter data, and the data format is an Excel file for subsequent analysis and model construction.

[0036] Step S22: Establish a proppant embedment model based on the proppant-rock parameter data, and conduct a calculation of the fracture closure pressure based on the formation conditions to generate the initial evaluation data of the fracture conductivity; In the embodiment of the present invention, based on the proppant-rock parameter data, a numerical simulation method (such as the finite element method) is used to construct a proppant embedment model. The model parameters are set as the rock modulus of 30 GPa and the proppant diameter of 1.5 mm. When calculating the embedment degree, the elastic deformation and friction effect of the proppant in the fracture are considered. After the simulation is completed, according to the formation conditions (such as pressure and temperature), the fracture closure pressure is calculated using the compression mechanics principle. Assuming the fracture spacing is 5 cm and considering various formation pressures (such as 10 MPa and 20 MPa), the initial evaluation data of the fracture conductivity are finally generated and recorded in the database for subsequent performance analysis.

[0037] Step S23: Calculate the flow capacity based on the multiphase flow theory using the initial evaluation data, and conduct an analysis of permeability degradation based on proppant settlement and damage effects to obtain fracture conductivity data. The permeability degradation analysis specifically involves simulating the settlement behavior of proppants in the fracture and the cumulative effect of microscopic damage to evaluate the long-term impact of proppants on fracture permeability. In the embodiment of the present invention, a multiphase flow theory model is utilized, and the Navier-Stokes equation is adopted to numerically simulate fluid flow. The simulation conditions are set as a fluid viscosity of 0.89 cP and a fluid density of 1000 kg / m³, and the fracture flow capacity at different flow rates (such as 0.1 m / s and 0.5 m / s) is simulated. Subsequently, for the settlement behavior of proppants, the discrete element method (DEM) is used to simulate the movement and settlement process of proppant particles in the fracture, and the collision and friction effects between particles are considered. By this method, the cumulative effect of microscopic damage is evaluated, and the damage parameter is set to 0.05 (representing the generation probability of microscopic cracks). Finally, these data are integrated to calculate the permeability degradation rate of the fracture and generate fracture conductivity data, which are recorded in the analysis report for reference.

[0038] Step S24: Use microseismic imaging to perform dynamic adjustment processing on the fracture morphology data based on fracture pressure to generate fracture three-dimensional morphology model data. The dynamic adjustment processing specifically involves performing image processing and morphology reconstruction on the multi-branch and multi-layer structures of the fracture network.

[0039] In the embodiment of the present invention, the internal pressure change data of the fracture are collected through a microseismic monitoring system, the monitoring time interval is set to 1 hour, and the data acquisition frequency is 100 Hz. Then, an inversion algorithm (such as the L1 regularization method) is used to dynamically adjust the fracture morphology data, and imaging processing is performed on the multi-branch and multi-layer structures of the fracture based on the pressure change data. The specific operations include converting the fracture data into a three-dimensional coordinate system and using three-dimensional visualization software (such as MATLAB or ParaView) for morphology reconstruction, considering the geometric shape changes caused by the fracture pressure change during reconstruction. The finally generated fracture three-dimensional morphology model data will be saved as a VTK format file for subsequent analysis and use.

[0040] The rock mechanics parameters of the present invention provide a physical basis for fracture behavior, and the proppant distribution parameters are the key data sources for subsequent analysis; obtaining accurate parameters can improve the accuracy of the model and ensure the reliability of subsequent calculations and evaluations, especially under complex formation conditions. The calculation of fracture closure pressure helps to understand the stability of proppants in fractures, ensuring the persistence and conductivity of fractures after fracturing. The generated initial evaluation data provides a basis for subsequent conductivity analysis and optimization, guiding engineering decisions and implementation plans. Through the application of multiphase flow theory, the actual flow conditions can be more accurately simulated, improving the understanding of flow capacity. The permeability degradation analysis reveals the long-term performance of proppants in fractures, helping to evaluate its impact on flow capacity and providing an important basis for engineering optimization. Dynamic adjustment ensures the accuracy of the fracture three-dimensional model, reflecting the complexity of the actual fracture network. By dynamically adjusting the fracture morphology, the fracture behavior can be monitored in real time, and the fracturing and flow management strategies can be optimized in a timely manner, improving the efficiency and safety of resource extraction. These steps, by obtaining key parameters, establishing models, calculating closure pressure, and performing dynamic adjustment, form a systematic fracture conductivity evaluation framework. This not only enhances the understanding of formation and fracture behavior but also provides solid data support for subsequent optimization design and real-time monitoring, ultimately ensuring the effectiveness and sustainability of resource development.

[0041] Preferably, step S24 includes the following steps: Step S241: Use a microseismic monitoring array to collect microseismic signal data during the fracture propagation process, thereby obtaining microseismic signal characteristic data; In the embodiment of the present invention, during the fracture propagation process, multiple microseismic sensors are arranged to form a monitoring array. The spacing between the sensors is 20 meters to ensure coverage of the entire fracture propagation area. The data collected by the sensors includes the source time, source intensity, and frequency information. The data collection frequency is set to 500 Hz, and the collection duration is 10 minutes. The microseismic signals are recorded in real time using a data collection system to generate the original microseismic signal data. Subsequently, through digital signal processing techniques, the original signal is denoised and filtered. A band-pass filter is used and set to 10 - 100 Hz to improve the signal quality. Finally, the microseismic signal characteristic data, including the source location, magnitude, and frequency distribution, is obtained.

[0042] Step S242: Conduct a spatial distribution analysis of the microseismic signal characteristic data based on the source location algorithm and reconstruct the fracture network according to the formation pressure data, thereby obtaining the fracture spatial distribution data; In an embodiment of the present invention, based on the obtained microseismic signal characteristic data, a source location algorithm (such as the least squares method or the weighted average method) is applied to estimate the source location. The specific method includes using the ranging information of at least three sensors to calculate the source coordinates through triangulation technology, and setting the error tolerance to 5 meters. Then, the formation pressure data (for example, the pressure at a formation depth of 2000 meters is 30 MPa) is combined with the source location information, and a numerical simulation method is applied to reconstruct the fracture network and construct a geometric model of the fractures. Finally, the generated fracture spatial distribution data will include the position information, extension direction, width and other characteristics of the fractures.

[0043] Step S243: Identify multi-branch fractures and analyze the interlayer connectivity based on the fracture spatial distribution data, and perform morphological reconstruction based on image processing to generate fracture network morphology data; In an embodiment of the present invention, through image processing technology, the fracture spatial distribution data is analyzed. First, the threshold segmentation method is used to identify the main branches in the fracture network, and the threshold is set to 0.5 to screen out important fracture features. Then, a connectivity analysis algorithm (such as the Flood Fill algorithm) is applied to analyze the interlayer connectivity of the multi-branch fractures to identify the connections between the fractures. Next, morphological operations are used to reconstruct the morphology of the fractures, and closing and opening operations are applied to remove noise and small-area connections. Finally, the generated fracture network morphology data will include the geometric features of the fractures, such as length, width and connection conditions, and is recorded in the database.

[0044] Step S244: Perform dynamic expansion simulation of fractures based on the stress field using the fracture network morphology data, and perform real-time correction of the fracture pressure to obtain fracture dynamic evolution data; In an embodiment of the present invention, a finite element analysis software (such as COMSOL Multiphysics) is used to perform a dynamic expansion simulation on the fracture network morphology data, with the initial stress field set to 10 MPa and the simulation environment temperature set to 25°C. By constructing a numerical model of the fractures and setting boundary conditions and loading conditions, the dynamic evolution process of the fractures under different stress states is simulated. During the simulation, the pressure change inside the fractures is monitored in real time, and real-time data is obtained using pressure sensors for correction to ensure that the model matches the actual fracture expansion process. The finally generated fracture dynamic evolution data will include the fracture expansion rate, direction and real-time pressure change information, and is recorded as time series data.

[0045] Step S245: Perform feature fusion on the fracture dynamic evolution data and the fracture network morphology data, and perform three-dimensional visualization to generate fracture three-dimensional morphology model data.

[0046] In the embodiments of the present invention, the dynamic evolution data of fractures and the fracture network morphology data are integrated into a database, and a feature fusion algorithm (such as the principal component analysis method) is used to reduce the dimension of the data to extract important features. Then, a three-dimensional visualization software (such as ParaView or the mplot3d module of Matplotlib) is applied to convert the fused data into a three-dimensional model, and three-dimensional view parameters (such as viewing angle, lighting, and color mapping) are set to enhance the visualization effect. Finally, the generated three-dimensional fracture morphology model data is exported as an STL format file for subsequent analysis and application.

[0047] The microseismic monitoring of the present invention can capture the dynamic changes during the fracture propagation process in real time, provide timely feedback, and help evaluate the fracturing effect; the collected signal data provides a rich information source for subsequent analysis and helps to understand the formation and evolution mechanism of fractures. Through spatial distribution analysis, the distribution and propagation of fractures can be accurately located, enhancing the understanding of the fracture network within the formation. The reconstruction of the fracture network provides a basis for subsequent simulation and prediction, improving the accuracy and reliability of the model. The identification and connectivity analysis of multi-branch fractures reveal the complex structure of the fracture network and help to understand the flow path of fluids in the fractures; the morphology reconstruction provides a detailed network structure for subsequent flow capacity analysis and helps to optimize the proppant distribution and flow strategy. Simulating the dynamic propagation process of fractures can reveal the evolution mechanism of fractures under different formation conditions and help to optimize the fracturing design; the real-time correction of pressure ensures the consistency between the model and the actual situation, improving the accuracy and reliability of the prediction. The three-dimensional visualization enables the intuitive display of the complex fracture network structure and dynamic evolution process, facilitating understanding by decision-makers and engineers; the visualization results provide a basis for subsequent engineering decisions, help to optimize the fracturing and production strategies, and improve the efficiency and safety of resource development. These steps, through microseismic monitoring, spatial analysis, dynamic simulation, and three-dimensional visualization, form a complete framework for fracture dynamic evolution and network structure analysis. This not only enhances the understanding of the fracture propagation process but also provides strong data support and decision-making basis for subsequent optimization design and resource development.

[0048] Preferably, step S3 includes the following steps: Step S31: Divide the three-dimensional fracture morphology model data into diversion units based on the fracture network distribution characteristics, and calculate the unit diversion capacity according to the fracture diversion capacity data to generate diversion unit characteristic data; In the embodiment of the present invention, based on the crack geometric distribution characteristics in the three-dimensional morphology model, the clustering algorithm (such as the k-means algorithm) is used to segment the crack area to determine the boundary of the diversion unit, and the area of each unit is set to 1000 mm². Subsequently, the crack diversion capacity data is imported, and the diversion performance of each diversion unit is calculated by the finite difference method. The main parameters include the flow rate (m³ / d) and the permeability (D). Finally, the generated diversion unit characteristic data includes the diversion capacity value, the distribution position, and the permeability information of each unit.

[0049] Step S32: Perform scale conversion on the diversion unit characteristic data based on the multi-scale analysis theory, and perform crack network connectivity analysis to obtain multi-scale diversion capacity data; In the embodiment of the present invention, scale conversion is performed on each diversion unit characteristic data, and wavelet transform is used for processing to obtain the diversion characteristic parameters at different scales. Then, through the connectivity analysis algorithm, the Flood Fill method is used to identify the connected crack units at different scales, and the connectivity and the change of the permeability coefficient of adjacent units are mainly analyzed. Finally, the generated multi-scale diversion capacity data includes the diversion capacity characteristics and the connectivity distribution of the cracks at different scales.

[0050] Step S33: Establish an optimization model for the crack diversion capacity based on the multi-scale diversion capacity data, and perform diversion capacity correction based on the proppant distribution to generate optimized diversion capacity data; In the embodiment of the present invention, the multi-scale diversion capacity data is imported, and the differential method is applied to establish an optimization model for the crack diversion capacity, and the target flow rate range is set at 20 - 30 m³ / d. Through the proppant distribution data, the density and particle size of the proppant in the crack are considered in the diversion calculation, and the diversion capacity of each diversion unit in the model is corrected. The finally generated optimized diversion capacity data includes the corrected unit diversion rate and the proppant concentration of each unit.

[0051] Step S34: Arrange a flowback liquid collection system at the well site, perform real-time flow rate monitoring and sample collection on the flowback liquid, and perform multi-point sampling based on the flow rate sensor array to generate flowback liquid flow rate monitoring data; In the embodiment of the present invention, a real-time flowback liquid collection system is installed at the well site, including a plurality of flow rate sensors distributed on the collection pipeline, and the sensor spacing is 50 cm. The flow rate of the flowback liquid is measured in real time through the sensor array, and the flow rate data collection interval is set to 5 seconds. The collected data is transmitted to the data processing center through a wireless transmission system to generate flowback liquid flow rate monitoring data including multi-point sampling.

[0052] Step S35: Analyze the proppant content of the flowback liquid sample, and calculate the proppant recovery rate based on the particle size distribution to obtain proppant recovery data; In the embodiments of the present invention, the produced fluid sample is taken to the laboratory, and a laser particle size analyzer is used to analyze the proppant particle size. According to the distribution of the proppant particle size, the particle size range is divided into 3 - 5 levels, and the recovery rate of each level is calculated. The recovery rate calculation is based on the proportional relationship between the sampling volume and the flow rate data. Finally, the obtained proppant recovery data includes the recovery rate of each particle size level, the total proppant content in the sample, and its volume percentage.

[0053] Step S36: Perform time - series correlation analysis on the produced fluid flow rate monitoring data and the proppant recovery data, and perform dynamic feature extraction based on the relationship between the flow rate and the proppant content to generate produced fluid feature data. In the embodiments of the present invention, time - series matching is performed on the produced fluid flow rate monitoring data and the proppant recovery data, and cross - correlation analysis is used to determine the correlation between the flow rate change and the proppant content. Then, the relationship between the flow rate and the proppant content is analyzed by curve fitting (such as polynomial fitting) to extract the main flow rate features (such as peak flow rate, flow rate volatility). Finally, the generated produced fluid feature data includes the dynamic relationship between the flow rate and the proppant concentration.

[0054] Step S37: Perform proppant distribution prediction based on mass conservation according to the produced fluid feature data, so as to obtain proppant back - flow data. In the embodiments of the present invention, the produced fluid feature data is used to calculate the dynamic distribution of the proppant in the fracture through the mass conservation equation, and the initial condition is set as the proppant content at the initial stage of production. The model considers the change in fluid flow rate and the proppant recovery data, and simulates the movement process of the proppant in the fracture by the difference method to obtain the proppant distribution at each moment. Finally, the generated proppant back - flow data includes the proppant back - flow rate, the back - flow volume, and the distribution state in the fracture.

[0055] Step S38: Perform feature fusion on the produced fluid flow rate monitoring data and the proppant back - flow data, and perform flow feature analysis based on multi - parameter coupling to generate produced fluid flow rate data.

[0056] In the embodiments of the present invention, feature fusion is performed on the produced fluid flow rate monitoring data and the proppant back - flow data, and the weighted average method is used to calculate the feature weights of the two, and the comprehensive flow features are synthesized. Then, multi - parameter coupling analysis is performed based on the flow rate, proppant concentration, and flow stability parameters, and the clustering analysis method is mainly used to identify different flow stages. Finally, the generated produced fluid flow rate data includes the flow rate, stability index, and flow feature parameters of each stage.

[0057] The division of the diversion units in the present invention can more accurately reflect the characteristics of the fracture network, which helps with subsequent flow capacity analysis; through the calculation of the diversion capacity, quantitative diversion capacity data is provided for each unit to assist in optimizing the well site design and proppant selection. Multi-scale analysis can comprehensively consider the diversion capacity at different scales and provide a more comprehensive understanding of the flow characteristics; the connectivity analysis of the fracture network reveals the flow paths of the fluid between different units and optimizes the flow management strategy. The optimization model can provide a more accurate estimate of the diversion capacity to ensure effectiveness in practical applications; the correction based on the proppant distribution can ensure that the flow model is consistent with the actual proppant effect and improve the overall engineering efficiency. Real-time flow velocity monitoring can quickly provide feedback on the flow conditions of the produced fluids to ensure timely adjustment of the production strategy; multi-point sampling enhances the representativeness of the data and helps analyze the flow velocity changes at different positions. The calculation of the proppant recovery rate provides an important indicator for evaluating the fracturing effect and helps optimize the proppant usage strategy; the proppant content analysis ensures the quality control of the returned fluids and helps formulate subsequent treatment measures. Through time-series correlation analysis, the relationship between the flow velocity and the proppant content can be revealed to provide a basis for subsequent optimization; the extraction of dynamic characteristics helps capture the key changes during the flow process and optimize the decision-making process. The application of mass conservation ensures the prediction accuracy of the proppant distribution and provides a scientific basis for subsequent adjustments; the proppant backflow data can help optimize the production strategy of the well site and ensure efficient fluid recovery. Feature fusion enhances the comprehensiveness of the data and provides a deeper understanding of the flow characteristics; the flow characteristic analysis based on multi-parameter coupling helps formulate intelligent production decisions, improve production efficiency and safety. These steps, through diversion capacity analysis, real-time monitoring, proppant recovery analysis and data fusion, provide a systematic method for the flow management of the fracture network. This not only improves the understanding of fracture behavior but also optimizes the efficiency of fracturing operations and resource recovery, ensuring the economy and sustainability of the project.

[0058] Preferably, step S4 includes the following steps: Step S41: Identify the trend of flow velocity changes in the produced fluid velocity data based on time-series analysis, and evaluate the flow stability according to the proppant backflow data to generate flow stability characteristic data; In the embodiments of the present invention, a time series analysis method is adopted to analyze the changing trend of the flow rate of the fluid flowing back monitored in real time. In specific operations, the ARIMA model or the Holt-Winters model is used to identify the periodic changes and trends of the flow rate. By using the trend term, periodic term, and random disturbance part in the flow rate data, the long and short periods and volatility characteristics of the flow changes are extracted respectively. Then, combined with the proppant backflow data, indicators such as the volatility and trend term of the proppant backflow are calculated, so as to construct the characteristics of the stability of the fluid flowing back. The obtained flow stability characteristic data includes parameters such as the long-term trend of the flow rate, the amplitude of the periodic fluctuation, and the coefficient of variation of the fluctuation of the proppant content in the fluid flowing back, providing basic data for subsequent attenuation and reliability analysis.

[0059] Step S42: Establish a fracture conductivity attenuation model based on the flow stability characteristic data, and conduct long-term conductivity prediction based on the proppant damage mechanism to obtain conductivity attenuation data; In the embodiments of the present invention, a mathematical model for the attenuation of fracture conductivity over time is constructed based on the flow stability characteristic data of the fluid flowing back. This model combines the damage mechanisms of proppants, such as proppant crushing, particle gaps being filled, and extrusion damage, etc., to predict the gradual attenuation process of fracture conductivity. In specific operations, parameters such as the particle fragmentation degree and the particle compression deformation rate are used as model inputs, and the stress-strain model and the particle damage accumulation function are applied to simulate the long-term impact of proppants on the fracture permeability. The finally generated conductivity attenuation data includes the permeability attenuation curve at different time stages, the proppant damage ratio, and the attenuation rate of the fracture network conductivity.

[0060] Step S43: Use the conductivity attenuation data to conduct a flow resistance analysis based on the multiphase flow theory to generate flow resistance characteristic data; In the embodiments of the present invention, through a multiphase flow model (such as the two-phase Darcy-Weisbach model), the conductivity attenuation data is used to calculate the resistance distribution of proppants and fluids in the fracture. In specific operations, the conductivity in the fracture is first divided into multiple flow units, and the flow resistance coefficient is calculated in each unit, involving variables such as the pressure gradient and the flow rate. For the resistance analysis of the proppant-fluid mixture, the interaction force, shear force, and interfacial friction force between the solid proppant particles and the liquid are calculated respectively, so as to obtain the flow resistance distribution data of each conductivity unit. The generated flow resistance characteristic data includes the resistance coefficients of different flow units, the pressure loss per unit length, and the spatial distribution map of the fluid resistance.

[0061] Step S44: Correct the fracture conductivity based on the influence of formation stress on the flow resistance characteristic data, and conduct a long-term conductivity stability assessment to obtain conductivity stability data; In an embodiment of the present invention, in combination with formation stress data, the fracture conductivity of the flow resistance characteristic data is corrected. By measuring the curve of the formation stress changing with time, the dynamic influence of the stress on the fracture width and permeability is taken into account. In specific operations, a non-linear influence model of the stress on the conductivity is established, and the change of the conductivity of the fracture under different stress conditions is predicted through rock mechanics parameters (such as Young's modulus, Poisson's ratio, etc.). Subsequently, the stability of the long-term conductivity of the fracture is evaluated, and the attenuation rate and final stability of the fracture conductivity under long-term load are calculated using the model data. The generated conductivity stability data includes the long-term prediction curve of the fracture conductivity stability and the conductivity correction factor under the action of stress.

[0062] Step S45: Perform uncertainty analysis based on Monte Carlo simulation using the conductivity stability data, and conduct reliability assessment of the fracture conductivity, so as to obtain reliability assessment data; In an embodiment of the present invention, Monte Carlo simulation is carried out through the conductivity stability data to simulate the multi-scenario uncertainty of the fracture conductivity. In specific operations, the random distributions of main parameters such as flow velocity and permeability are set, and 1000 Monte Carlo iterations are used for calculation. The fluctuation of the fracture conductivity is simulated under different scenarios such as pressure and flow velocity. According to the simulation results, the reliability of the fracture conductivity is analyzed, and the attenuation of the conductivity under different confidence intervals is calculated. The obtained reliability assessment data includes the reliability curve, uncertainty distribution, and multi-scenario conductivity reliability prediction of the fracture conductivity within the 95% confidence interval.

[0063] Step S46: Perform feature fusion on the reliability assessment data and the conductivity stability data, and conduct stability evaluation based on multi-parameter synthesis to generate comprehensive stability evaluation data; In an embodiment of the present invention, the reliability assessment data and the conductivity stability data are first subjected to data comprehensive processing through a feature fusion algorithm (such as principal component analysis or weighted superposition) to extract key stability indicators. In specific operations, a comprehensive stability evaluation model including multiple parameters is constructed by combining the long-term conductivity stability, attenuation rate of the fracture, and reliability analysis data. The finally generated comprehensive stability evaluation data includes the comprehensive conductivity stability index of the fracture, the stability change curve at different time periods, and its prediction results, providing an evaluation of the overall conductivity of the fracture.

[0064] Step S47: Provide optimization suggestions for fracture parameters based on risk analysis according to the comprehensive stability evaluation data, and conduct long-term production performance prediction, so as to obtain stability evaluation data.

[0065] In the embodiments of the present invention, crack risk analysis is carried out in combination with comprehensive evaluation data to identify key parameters that significantly affect the diversion capacity (such as proppant distribution, crack width, etc.). In specific operations, through sensitivity analysis, the main factors affecting the stability of the diversion capacity are found, and optimization suggestions for these parameters are put forward. For example, it is recommended to improve the compressive performance of the proppant or adjust the particle size distribution of the proppant. Finally, a prediction model of the crack diversion capacity is used to numerically simulate the long-term production performance of the crack, and the obtained stability evaluation data includes the long-term production prediction value of the crack diversion capacity, the improvement effect of the optimization suggestions on the diversion capacity, and the corresponding production performance indicators.

[0066] Through time series analysis, the present invention can reveal the law of flow velocity change, help judge the change trend of flow behavior, and provide a basis for decision-making; flow stability evaluation helps to identify potential problems at an early stage, such as the flow instability of proppants, and ensure the safety and efficiency of subsequent operations. By establishing an attenuation model, the change of the diversion capacity during long-term use can be predicted, providing a scientific basis for formulating effective management strategies; the analysis based on the proppant damage mechanism can identify the key factors leading to the attenuation of the diversion capacity, which helps to optimize the proppant selection and use strategies. The analysis of flow resistance can reveal the flow behavior of the fluid in the crack, which helps to optimize the fluid injection and reflux strategies and improve production efficiency; the application of multiphase flow theory enhances the understanding of complex flow systems and provides theoretical support for designing more effective oil production schemes. By considering the influence of formation stress, the diversion capacity can be corrected more accurately to ensure the reliability and adaptability of the model; the long-term diversion capacity stability evaluation can ensure the continuous effectiveness under different formation conditions and provide guarantee for production. Uncertainty analysis can reveal the change range of the diversion capacity under different conditions, help identify potential risks, and improve the scientific nature of decision-making; through reliability evaluation, the effectiveness of the model in actual production can be verified, providing support for subsequent optimization. Feature fusion can integrate multi-dimensional data, provide a more comprehensive stability evaluation, and reduce the misleading caused by a single index; the comprehensive stability evaluation provides multi-dimensional information support for management decision-making, which helps to formulate a more reasonable production plan. Through risk analysis, targeted optimization suggestions for crack parameters can be put forward to improve production efficiency and resource utilization rate; the long-term production performance prediction provides an important reference for project planning and helps to achieve sustainable development and maximize economic benefits. These steps provide a systematic method for the flow management of cracks through flow velocity analysis, diversion capacity modeling, flow resistance research, and uncertainty analysis. This not only enhances the understanding of crack behavior, but also optimizes the utilization of resources and production strategies, ensuring the economy and sustainability of the project. Overall, these steps enhance the monitoring, evaluation, and optimization of the crack diversion capacity, providing a solid theoretical basis and practical guidance for future oil and gas exploitation.

[0067] Preferably, step S5 includes the following steps: Step S51: Use on-site testing equipment to collect actual fracture parameters, including data such as fracture conductivity, proppant distribution, and fluid pressure, and generate on-site measured data. In the embodiment of the present invention, at the on-site after fracture fracturing construction, a fracture conductivity testing device, a pressure sensor, and a proppant distribution detection device are installed to ensure that the collected parameters truly reflect the actual situation inside the fracture. The conductivity testing device includes a flowmeter and a flow velocity sensor. By adjusting the fluid flow rate and measuring the change in its resistance passing through the fracture, the actual fracture conductivity is calculated. The proppant distribution uses X-ray or acoustic imaging technology to scan the distribution of proppant inside the fracture, and detect the particle distribution density and distribution uniformity of the proppant. The pressure sensor is placed at the inlet and outlet of the fracture to record the pressure change of the fluid inside the fracture, forming a set of time-series fluid pressure data. The finally generated on-site measured data includes fracture conductivity values, proppant distribution density data, and dynamic change information of the fluid pressure inside the fracture, providing a data basis for subsequent analysis.

[0068] Step S52: Construct a fracture conductivity model based on the stability evaluation data and the conductivity optimization data, so as to obtain the initial model data. In the process of constructing the conductivity model in the embodiment of the present invention, based on the stability evaluation data and the conductivity optimization data, a fracture conductivity model is established by combining physical modeling and numerical simulation. First, the fracture structure characteristics (such as proppant breakage rate, fracture width change, etc.) reflected in the stability evaluation data are used as the basic boundary conditions of the model, and at the same time, the conductivity optimization data is used as the input data. Use fluid mechanics software (such as ANSYS Fluent or COMSOL Multiphysics) to establish a three-dimensional fluid flow model inside the fracture, and apply the finite element analysis method to numerically simulate the change of fracture conductivity. The generated initial model data includes parameters such as flow resistance, permeability, and density distribution of proppant at different positions of the fracture, laying a foundation for subsequent error analysis.

[0069] Step S53: Compare the error between the on-site measured data and the initial model data, and conduct a data-driven parameter sensitivity analysis to generate model correction parameter data. In the embodiments of the present invention, the initial model data and the on-site measured data are used to calculate the error between the actual performance and the theoretical simulation of the fracture conductivity model. In the specific operation, the deviation values of each key parameter (such as conductivity, proppant distribution density, pressure change) are calculated, and statistical methods are used to quantify the error (such as mean square error, absolute mean error, etc.). During the comparison process, based on the data-driven sensitivity analysis method (such as local sensitivity analysis or Sobol method), the sensitivity of each parameter in the model to the error is evaluated one by one to identify the key parameters affecting the fracture conductivity. The generated model correction parameter data includes the sensitivity index of each key parameter and its adjustment range, which are used to optimize the parameter setting of the fracture conductivity model to reduce the error.

[0070] Step S54: Optimize and adjust the fracture conductivity model by using the model correction parameter data, and perform model verification based on the on-site measured data to generate fracture parameter optimization model data.

[0071] In the embodiments of the present invention, according to the model correction parameter data, the parameters with high sensitivity in the conductivity model are optimized and adjusted. The optimization process uses an iterative method to gradually adjust the sensitive parameters to minimize the difference from the on-site measured data. The adjusted fracture conductivity model is used for numerical simulation calculation again, and the simulation results are verified for the matching degree with the on-site measured data to evaluate the accuracy of the optimized model. Based on the model verification results, multiple tests are carried out to verify the adaptability of the model under different proppant densities, fracture widths, and pressure conditions, ensuring that the optimized model can effectively reflect the actual conductivity of the fracture. The finally generated fracture parameter optimization model data includes the predicted conductivity value after model correction, the pressure distribution in the fracture, and the proppant density distribution data.

[0072] The on-site test of the present invention provides parameter data under actual operating conditions, ensuring the authenticity and reliability of the data and providing a solid foundation for subsequent analysis; through real-time acquisition, it can timely reflect the changes in the crack state, provide dynamic support for production decisions, and ensure the flexibility and adaptability of operations. The constructed model integrates multiple key factors, enabling a more comprehensive and systematic understanding of the fracture conductivity, which helps with subsequent optimization and adjustment; the model provides a theoretical basis that can be used to predict and evaluate the performance of fractures under different operating conditions, providing guidance for design decisions. Error comparison can clarify the gap between the model and the actual data, thereby identifying the key parameters that need to be adjusted and improving the accuracy of the model; parameter sensitivity analysis helps identify which parameters have the greatest impact on the model output. Concentrating resources on optimizing these key parameters can effectively improve the prediction ability and application effect of the model. Model optimization and adjustment can continuously improve the prediction of fracture conductivity, ensure that the model adapts to the changing actual conditions, and enhance the overall production efficiency; through comparison and verification with on-site measured data, the effectiveness and reliability of the optimized model are ensured, providing confidence for subsequent applications and enhancing the scientific nature of decision-making. These steps establish a dynamic and adjustable fracture conductivity prediction model through the process of actual data acquisition, model construction and optimization, and error analysis. This series of operations not only improves the understanding of fracture behavior but also optimizes the use of resources and production efficiency, ensuring the economic viability and sustainability of the entire extraction process. Overall, steps S51 to S54 strengthen the connection between the model and the actual situation, forming a closed-loop feedback mechanism, making the management of fracture conductivity more scientific and effective.

[0073] The present invention also provides a system for obtaining artificial fracture parameters for implementing the method for obtaining artificial fracture parameters described above. The system for obtaining artificial fracture parameters includes: A morphology acquisition module for collecting initial fracture morphology data through core experiments, including the straightness, number of branches, and roughness parameters of the fractures; performing verification analysis based on morphology on the initial fracture morphology data and adding morphological features of irregular fractures to obtain fracture morphology data; A morphology reconstruction module for simulating the fracture conductivity based on the proppant distribution and formation conditions according to the fracture morphology data and performing a preliminary evaluation to generate fracture conductivity data; using microseismic imaging to perform dynamic adjustment processing based on fracture pressure on the fracture morphology data to generate fracture three-dimensional morphology model data, where the dynamic adjustment processing specifically involves reconstructing the morphology of the multi-branch and multi-layer structures of the fracture network; The diversion monitoring module is used to perform multi-scale diversion capacity analysis based on the three-dimensional fracture morphology model data and the fracture diversion capacity data to generate diversion capacity optimization data; and perform fracture proppant backflow monitoring based on the diversion capacity optimization data to obtain the produced fluid flow rate data and the proppant backflow data; The stability evaluation module is used to perform the diversion capacity stability evaluation based on the produced fluid flow rate data and the proppant backflow data according to the flow rate change trend, and perform the long-term flow characteristics analysis of the fracture to generate the stability evaluation data; The parameter optimization module is used to construct a fracture diversion capacity model based on the stability evaluation data and the diversion capacity optimization data, and perform difference comparison according to the pre-acquired on-site measured data to correct the fracture diversion capacity model and generate the fracture parameter optimization model data.

[0074] The initial fracture morphology data of the present invention provides the basic characteristic information of the fracture and provides a basis for subsequent analysis. By quantifying the fracture straightness, the number of branches and the roughness, the geometric characteristics of the fracture can be accurately described. The morphological verification analysis ensures the reliability and accuracy of the collected data and increases the depth of understanding of the fracture morphology. Introducing the morphological characteristics of irregular fractures makes the model closer to the actual situation, thereby improving the authenticity of subsequent analysis and simulation. Through simulation and preliminary evaluation, the diversion capacity of the fracture can be quantitatively analyzed, providing a basis for optimizing the proppant distribution and enhancing fluid flow. This evaluation is crucial for designing the fracture exploitation plan and can effectively predict the exploitation effect. The microseismic imaging technology enables the dynamic adjustment of the fracture morphology under different formation pressures, and the generated three-dimensional model can truly reflect the complex structure of the fracture, helping engineers better understand and utilize the fracture network. The multi-scale diversion capacity analysis can more comprehensively understand the diversion characteristics of the fracture at different scales, help identify the main factors affecting the diversion capacity, and thus provide a precise direction for subsequent optimization. By monitoring the produced fluid flow rate and the proppant backflow data, the diversion performance of the fracture can be real-time feedback, ensuring that the operation strategy can be adjusted in time to maximize the resource recovery efficiency. The analysis of the flow rate change trend can timely detect potential flow instabilities, provide reliable early warning information, and prevent fracture damage or failure caused by flow instability. The analysis of the long-term flow characteristics of the fracture provides data support for designing long-term exploitation plans, ensuring the safety and economy of the exploitation process. By combining the stability evaluation and the diversion capacity optimization data, the constructed fracture diversion capacity model is more accurate, reflects the actual situation, and provides a solid basis for subsequent operations. The difference comparison of the on-site measured data ensures the real-time correction ability of the model, enhances the adaptability of the model in actual operations, and thus improves the efficiency and reliability of fracture exploitation.

[0075] The present invention also provides an electronic device, including a processor and a memory, where the processor is configured to execute a computer program stored in the memory to implement the method for obtaining artificial fracture parameters described in any one of the above.

[0076] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Thus, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0077] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for obtaining artificial crack parameters, characterized in that: The following steps are involved: Step S1: collecting initial fracture morphology data through core experiments, including fracture straightness, branch number, and roughness parameters; performing morphological verification analysis on the initial fracture morphology data, and adding morphological features of irregular fractures to obtain fracture morphology data; Step S2: simulating the fracture conductivity based on proppant distribution and formation conditions according to the fracture morphology data, and making a preliminary evaluation to generate fracture conductivity data; using microseismic imaging to dynamically adjust the fracture morphology data based on fracture pressure to generate fracture three-dimensional morphology model data, wherein the dynamic adjustment processing is specifically to reconstruct the morphology of the multi-branch and multi-layer structure of the fracture network; Step S3: performing multi-scale conductivity analysis based on the fracture three-dimensional morphological model data and the fracture conductivity data to generate conductivity optimization data; Monitor the fracture proppant return flow based on the conductivity optimization data to obtain the return liquid velocity data and proppant return flow data; Step S4: Conducting a conductivity stability assessment based on the flow velocity variation trend through the backflow liquid velocity data and the proppant backflow data, and performing a long-term flow characteristic analysis of the fracture to generate stability assessment data; Step S5: construct a fracture conductivity model based on the stability assessment data and the conductivity optimization data, and perform a difference comparison based on the pre-acquired field measured data to modify the fracture conductivity model and generate fracture parameter optimization model data.

2. The method for obtaining artificial crack parameters according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using microscopic imaging technology to collect images of core fracture morphology and generate core fracture microscopic image data; Step S12: preprocessing the core fracture microscopic image data based on image noise removal and edge enhancement operations to generate fracture morphology clarity enhanced data; Step S13: extracting the crack contour from the crack morphology clarity enhancement data, and extracting the features of the crack straightness, the number of branches, and the roughness, so as to obtain the initial crack morphology data; Step S14: supplementing the morphological features of the irregular cracks according to the preliminary morphological data of the cracks, thereby obtaining morphological feature data of the cracks, wherein the morphological feature supplementation includes identifying micro cracks and secondary branches based on the number of branches and roughness of the cracks; Step S15: Acquire formation pressure data, cross-validate the fracture morphology characteristic data and formation pressure data, and evaluate the effectiveness of the measured morphology under formation conditions, thereby obtaining fracture morphology verification data; Step S16: Performing feature synthesis of the crack morphology based on the crack morphology verification data and the crack morphology feature data to generate crack morphology data.

3. The method for obtaining artificial crack parameters according to claim 2, characterized in that: Step S13 includes the following steps: The crack contour is extracted from the crack morphology clarity enhanced data to obtain crack contour data; the main axis direction deviation of the crack is quantified on the crack contour data to generate crack straightness data; the number of crack branches is counted on the crack contour data through image segmentation technology to obtain crack branch data; the surface microscopic irregularity of the crack is evaluated on the crack contour data through a surface roughness algorithm to obtain crack roughness data; the crack straightness data, crack branch data and crack roughness data are merged into initial crack morphology data.

4. The method for obtaining artificial crack parameters according to claim 3, characterized in that: Step S2 includes the following steps: Step S21: Acquire formation rock mechanical parameters and proppant distribution parameters to generate proppant-rock parameter data; Step S22: establishing a proppant embedding model based on the proppant-rock parameter data, and calculating the fracture closure pressure based on the formation conditions to generate initial evaluation data of fracture conductivity; Step S23: Calculate the flow capacity based on the multiphase flow theory through the initial evaluation data, and perform a permeability degradation analysis based on proppant settlement and damage effects, so as to obtain fracture conductivity data, wherein the permeability degradation analysis specifically evaluates the long-term effect of the proppant on the fracture permeability by simulating the settlement behavior of the proppant in the fracture and the cumulative effect of microscopic damage; Step S24: using microseismic imaging to dynamically adjust the fracture morphology data based on fracture pressure to generate three-dimensional fracture morphology model data, wherein the dynamic adjustment processing specifically includes image processing and morphology reconstruction of the multi-branch and multi-layer structure of the fracture network.

5. The method for obtaining artificial crack parameters according to claim 4, characterized in that: Step S24 includes the following steps: Step S241: using a microseismic monitoring array to collect microseismic signal data during the crack expansion process, thereby obtaining microseismic signal characteristic data; Step S242: performing spatial distribution analysis on the microseismic signal characteristic data based on a source location algorithm, and reconstructing the fracture network according to the formation pressure data, thereby obtaining fracture spatial distribution data; Step S243: performing multi-branch crack identification and inter-layer connectivity analysis based on the crack spatial distribution data, and performing morphological reconstruction based on image processing to generate crack network morphological data; Step S244: using the fracture network morphology data to simulate the dynamic expansion of fractures based on the stress field, and performing real-time correction of the fracture pressure, thereby obtaining the dynamic evolution data of fractures; Step S245: feature fusion of the fracture dynamic evolution data and the fracture network morphology data, and three-dimensional visualization to generate fracture three-dimensional morphology model data.

6. The method for obtaining artificial crack parameters according to claim 5, characterized in that: Step S3 includes the following steps: Step S31: dividing the fracture 3D morphological model data into diversion units based on fracture network distribution characteristics, and calculating the unit diversion capacity according to the fracture diversion capacity data to generate diversion unit characteristic data; Step S32: performing scale conversion on the drainage unit characteristic data based on multi-scale analysis theory, and performing fracture network connectivity analysis, thereby obtaining multi-scale drainage capacity data; Step S33: establishing a fracture conductivity optimization model according to the multi-scale conductivity data, and performing conductivity correction based on proppant distribution to generate conductivity optimization data; Step S34: Arrange a flowback liquid collection system at the well site to perform real-time flow rate monitoring and sample collection on the flowback liquid, and perform multi-point sampling based on a flow rate sensor array to generate flowback liquid flow rate monitoring data; Step S35: analyzing the proppant content of the flowback liquid sample and calculating the proppant recovery rate based on the particle size distribution, thereby obtaining proppant recovery data; Step S36: performing time series correlation analysis on the flowback liquid flow rate monitoring data and the proppant recovery data, and extracting dynamic features based on the flow rate-proppant content relationship to generate flowback feature data; Step S37: performing proppant distribution prediction based on mass conservation according to the flowback characteristic data, thereby obtaining proppant return flow data; Step S38: feature fusion of the flowback liquid velocity monitoring data and the proppant return data, and flow feature analysis based on multi-parameter coupling to generate flowback liquid velocity data.

7. The method for obtaining artificial crack parameters according to claim 6, characterized in that: Step S4 includes the following steps: Step S41: identifying the flow rate change trend of the flowback liquid flow rate data based on time series analysis, and evaluating the flow stability based on the proppant return data to generate flow stability characteristic data; Step S42: establishing a fracture conductivity attenuation model according to the flow stability characteristic data, and performing long-term conductivity prediction based on the proppant damage mechanism, thereby obtaining conductivity attenuation data; Step S43: using the flow conductivity attenuation data to perform flow resistance analysis based on multiphase flow theory to generate flow resistance characteristic data; Step S44: Correcting the fracture conductivity based on the influence of formation stress on the flow resistance characteristic data, and conducting a long-term conductivity stability assessment to obtain conductivity stability data; Step S45: using the conductivity stability data to perform uncertainty analysis based on Monte Carlo simulation, and performing reliability evaluation of fracture conductivity, thereby obtaining reliability evaluation data; Step S46: feature fusion of the reliability evaluation data and the diversion stability data, and stability evaluation based on multi-parameter synthesis to generate comprehensive stability evaluation data; Step S47: Providing crack parameter optimization suggestions based on risk analysis according to the comprehensive stability evaluation data, and performing long-term production performance prediction, thereby obtaining stability evaluation data.

8. The method for obtaining artificial crack parameters according to claim 7, characterized in that: Step S5 includes the following steps: Step S51: using field testing equipment to collect actual fracture parameters, including fracture conductivity, proppant distribution, fluid pressure and other data, to generate field measured data; Step S52: constructing a fracture conductivity model according to the stability evaluation data and the conductivity optimization data, thereby obtaining initial model data; Step S53: performing error comparison between the field measured data and the model initial data, and performing data-driven parameter sensitivity analysis to generate model correction parameter data; Step S54: Optimizing and adjusting the fracture conductivity model using the model correction parameter data, and performing model verification based on field measured data to generate fracture parameter optimization model data.

9. A system for acquiring parameters of artificial cracks, characterized in that: Used to execute the method for obtaining artificial crack parameters according to claim 1, the artificial crack parameter obtaining system comprises: The morphology acquisition module is used to collect initial fracture morphology data through core experiments, including fracture straightness, number of branches, and roughness parameters; perform morphology-based verification analysis on the initial fracture morphology data, and add morphological features of irregular fractures to obtain fracture morphology data; The morphology reconstruction module is used to simulate the fracture conductivity based on the proppant distribution and formation conditions according to the fracture morphology data, and to make a preliminary evaluation to generate fracture conductivity data; the fracture morphology data is dynamically adjusted based on the fracture pressure using microseismic imaging to generate three-dimensional fracture morphology model data, wherein the dynamic adjustment processing is specifically to reconstruct the morphology of the multi-branch and multi-layer structure of the fracture network; The flow monitoring module is used to perform multi-scale flow conductivity analysis based on the fracture 3D morphology model data and fracture flow conductivity data to generate flow conductivity optimization data; perform fracture proppant backflow monitoring based on the flow conductivity optimization data to obtain flowback liquid velocity data and proppant backflow data; The stability assessment module is used to evaluate the conductivity stability based on the flow velocity change trend through the backflow liquid velocity data and the proppant return flow data, and to analyze the long-term flow characteristics of the fracture to generate stability assessment data; The parameter optimization module is used to construct a fracture conductivity model based on the stability assessment data and the conductivity optimization data, and to make a difference comparison based on the pre-acquired field measured data, to modify the fracture conductivity model, and to generate fracture parameter optimization model data.

10. A device for obtaining parameters of artificial cracks, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for obtaining artificial crack parameters as claimed in any one of claims 1 to 8.

Images