High-precision inversion method for natural fractures of hot dry rock based on geology-engineering integration

Abstract

The invention relates to the technical field of natural fracture distribution rules and geological exploration and development, and discloses a high-precision inversion method for natural fractures of hot dry rock based on geology-engineering integration, which comprises the following steps: (1) field data acquisition and preliminary geological modeling: constructing an initial fracture model based on geological data of a hot dry rock reservoir; (2) fracturing experiment and engineering inversion correction: on the basis of the preliminary fracture model, engineering inversion is carried out by using field fracturing test data and micro-seismic information, and inversion correction is carried out on the model; and (3) multi-time iteration closed-loop feedback optimization: performing multi-time mutual feedback correction on a geological modeling result and engineering inversion data to obtain a high-precision fracture distribution model of the hot dry rock reservoir. According to the scheme, geological modeling and engineering inversion are organically combined, a closed-loop feedback mechanism is constructed, and high-precision inversion of fracture distribution is achieved through multiple times of iterative optimization.

Description

Technical Field

[0001] The invention relates to the technical field of hot dry rock reservoir transformation, and in particular to a high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration. Background Art

[0002] As a geothermal resource with great development potential, hot dry rock has attracted much attention in recent years due to its clean, widespread and seasonal characteristics. Due to its low porosity and low permeability, natural fractures in HDR reservoirs become its key seepage and heat exchange channels. However, since the distribution and structure of fractures are controlled by geological factors, the precise characterization of HDR natural fractures has become a technical challenge to achieve efficient development.

[0003] Existing natural fracture characterization technologies mainly rely on two methods: geological modeling and engineering inversion. Geological modeling simulates the spatial distribution of fractures through geological data such as lithology and tectonic stress field, but it fully considers reservoir fracture parameters, is limited in accuracy and detail, and is difficult to reflect the actual development of fractures. Engineering inversion dynamically infers the distribution characteristics of fractures based on wellbore data such as fracturing experiments, but due to the lack of support from geological models, the inversion results often lack geological rationality. Relying solely on geological modeling or engineering inversion technology, it is difficult to fully and accurately describe the spatial distribution of natural fractures in hot dry rock reservoirs, and it is difficult to meet the demand for high-precision fracture models in hot dry rock development.

[0004] In view of this, constructing a high-precision inversion method for natural fractures in hot dry rocks based on geological-engineering integration can not only effectively make up for the shortcomings of existing technologies, but also effectively solve the technical problems of long period and high cost in studying natural fractures in fractured reservoirs in existing technologies. It is of great significance for the research and utilization of natural fractures in fractured reservoirs. Summary of the invention

[0005] The present invention relates to a high-precision inversion method for natural fractures in hot dry rock thermal reservoirs based on geology-engineering integration, aiming to solve the technical problem of insufficient precision in natural fracture characterization in the prior art.

[0006] To achieve the above object, the present invention adopts the following technical solution: a high-precision inversion method for natural fractures in hot dry rocks based on geological-engineering integration, comprising the following steps:

[0007] (i) Field data collection and preliminary geological modeling: construct an initial fracture model based on the geological data of the hot dry rock reservoir;

[0008] (ii) Fracturing experiment and engineering inversion correction: Based on the preliminary fracture model, the engineering inversion is carried out using the field fracturing test data and microseismic information to invert and correct the model;

[0009] (III) Multiple iterative closed-loop feedback optimization: The geological modeling results and engineering inversion data are subjected to multiple feedback corrections to obtain a high-precision fracture distribution model of the hot dry rock reservoir.

[0010] Preferably, as an improvement, in (i) field data collection and preliminary geological modeling, the method for acquiring geological data is: collecting natural fracture parameters of hot dry rock reservoirs through multi-scale data analysis including drone scanning, core sampling, and SEM scanning.

[0011] Preferably, as an improvement, the natural fracture parameters include the inclination, length, width, density and directional distribution of the fracture.

[0012] Preferably, as an improvement, in (ii) fracturing experiment and engineering inversion correction, the method for acquiring the field fracturing test data is: conducting a fracturing experiment in a target well, monitoring and recording the wellbore pressure curve, stress field changes and microseismic signals in real time, and capturing the dynamic evolution characteristics of the cracks during the fracturing process.

[0013] Preferably, as an improvement, in (ii) fracturing experiment and engineering inversion correction, the microseismic information monitoring method is: using microseismic monitoring to record the generation, extension direction and depth changes of cracks.

[0014] Preferably, as an improvement, in (ii) fracturing experiment and engineering inversion correction, the engineering inversion method is: by comparing the pressure data and microseismic information collected in real time with the initial model, and combining the machine learning algorithm to adjust the natural fracture parameters in the fracture model, gradually correct the spatial position and morphology of the fracture, and obtain engineering inversion data.

[0015] Preferably, as an improvement, in (iii) multiple iterative closed-loop feedback optimization, a fracturing curve and microseismic fitting method based on machine learning is also included, including the following contents: taking the natural fracture density, length, height, inclination, strike, opening degree, etc. of the hot dry rock reservoir as variables, combined with an efficient fracturing simulation model, the pressure curve and fracture network distribution are output to form a database.

[0016] Preferably, as an improvement, in (ii) fracturing experiment and engineering inversion correction, the displacement discontinuity method is used to develop a deep reservoir hydraulic fracturing numerical simulation technology, fully considering the influence of stress shadows within the fracturing section, between sections, and between wells and natural fractures, and the displacement discontinuity is calculated using the following formula:

[0017] D x =u x (x,y,0 - )-u x (x,y,0 + )

[0018] Dy =u y (x,y,0 - )-u y (x,y,0 + )

[0019] D z =u z (x,y,0 - )-u z (x,y,0 + )

[0020] In the formula, D is the small change, u is the displacement; D x Specifically, it is expressed as: on the plane z = 0, at a fixed point (x, y), the difference between the partial derivative of u with respect to x when z approaches 0 from the negative direction and the partial derivative of u with respect to x when z approaches 0 from the positive direction; D y , D z Same as above;

[0021] According to the stress function solution, the displacement and stress induced by the fracture unit displacement discontinuity at any point in space (xyz) are calculated as follows:

[0022] u x =C{[2(1-v)I ,z -zI ,xx ]D x -zI ,xy D y -[(1-2v)I ,x +zI ,xz ]D z}

[0023] u y =C{-zI ,xy D x +[2(1-v)I ,z -zI ,yy ]D y -[(1-2v)I ,y +zI ,yz ]D z}

[0024] u z =C{[(1-2v)I ,x -zI ,xz ]D x +[(1-2v)I ,y -zI ,yz ]D y +[2(1-v)I ,z -zI ,zz ]D z}

[0025] σ xx =2C{[2I ,xz -zI ,xxx ]D x +[2vI ,yz -zI ,xxy ]D y +[I ,zz +(1-2v)I ,yy -zI ,xxz ]D zz}

[0026] σ yy =2C{[2vI ,xz -zI ,xyy ]D x +[2I ,yz -zI ,yyy ]D y +[I ,zz +(1-2v)I ,xx -zI ,yyz ]D z}

[0027] σ zz =2C{-zI ,xzz D x -zI ,yzz D y +[I ,zz -zI ,zzz ]D z}

[0028] τ xy =2C{[(1-v)I ,yz -zI ,xxy ]D x +[(1-v)I ,xz -zI ,xyy ]D y -[(1-2v)I ,xy +zI ,xyz ]D z}

[0029] τ yz =2C{-[vI ,xy +zI ,xyz ]D x +[I ,zz +vI ,xx -zI ,yyz ]D y -zI ,yzz D z}

[0030] τ zx =2C{[I ,zz+vI ,yy -zI ,xxz ]D x -[vI ,xy +zI ,xyz ]D y -zI ,xzz D z}

[0031] Where u is displacement, σ is tensile stress, and τ is shear stress.

[0032] The principles of this solution are:

[0033] This scheme continuously optimizes the fracture model through multiple mutual feedback loops of geological forward modeling (geological modeling) and engineering inversion (fracture correction), achieving high-precision characterization of fractures in hot dry rock reservoirs. Specifically, this method first uses geological modeling to comprehensively simulate factors such as the reservoir's lithology, stress field characteristics, and sedimentary environment to generate a preliminary fracture distribution model. In the engineering inversion stage, multiple rounds of fracture model corrections are performed using real-time collected data such as fracturing stress and wellbore pressure changes, so that the model gradually conforms to actual reservoir conditions. Through multiple iterative feedback adjustments, the accuracy and resolution of the fracture model are continuously improved, making the spatial distribution of fractures in the model closer to the actual geological conditions.

[0034] Combined with specific application examples, such as the actual investigation of the hot dry rock fracture system in the Gonghe Basin of Qinghai, this patented method uses a variety of means such as drone scanning, core description, SEM scanning, and fracturing simulation to obtain and establish fracture distribution data of different scales. Through large-scale fracturing simulation and efficient machine learning algorithms, the fracture network parameters are adjusted, and the pressure curve, fracture network distribution and other data are iteratively output to generate a high-precision fracture model. In particular, the model is dynamically corrected using microseismic monitoring data and fracturing pump pressure curves, realizing a high-precision natural fracture inversion technology based on geological-engineering integration.

[0035] The advantages of this solution are:

[0036] 1. Compared with the existing technology that relies solely on geological modeling or engineering inversion technology, it is difficult to fully and accurately describe the spatial distribution of natural fractures in hot dry rock reservoirs, and it is difficult to meet the high-precision requirements of fracture models for hot dry rock development. This solution organically combines geological modeling and engineering inversion, constructs a closed-loop feedback mechanism, and achieves high-precision inversion of fracture distribution through multiple iterative optimizations. At the same time, this method can take into account both computational efficiency and simulation accuracy, making it possible to efficiently carry out fracture characterization in large-scale, deep hot dry rock reservoirs. This high-precision natural fracture inversion technology has broad application potential in the development of hot dry rock resources. Its accurate fracture model not only provides a scientific basis for the development and design of hot dry rock thermal reservoirs and the utilization of thermal energy, but also can significantly improve the efficiency and effectiveness of geothermal mining, and help promote fracture characterization and resource utilization in other unconventional reservoirs.

[0037] 2. This solution constructs for the first time a high-precision natural fracture inversion method based on a geological-engineering feedback closed loop, which enables the fracture distribution characterization of hot dry rock reservoirs to reach a new level of accuracy. Specifically, through multiple rounds of iterative feedback of geological and engineering data, not only the accuracy of the fracture model is enhanced, but also the geological rationality and engineering feasibility of the model are significantly improved. At the same time, the present invention introduces a machine learning algorithm, takes fracturing and microseismic data as key constraints, optimizes the model calculation efficiency, and accurately reconstructs the fracture distribution in a complex three-dimensional space. And the method of the present invention can be applied to a variety of hot dry rock reservoirs, providing a generalizable high-precision solution for the prediction of unconventional reservoir fractures.

[0038] 3. Using the high-precision fracture inversion method of the present invention, an accurate natural fracture model was successfully established in the hot dry rock reservoir in the Gonghe Basin of Qinghai Province, which can effectively predict the conductivity and thermal conductivity of the fractures, and provide a scientific basis for the efficient development and thermal energy utilization of the thermal reservoir. The model provides reliable support for subsequent fracturing design, reservoir evaluation and geothermal development, greatly improving the development efficiency and effect of the hot dry rock reservoir. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a process flow chart of a high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration in Example 1 of the present invention.

[0040] Figure 2 These are the typical geological features of the Gonghe Basin studied in Example 1 of the present invention.

[0041] Figure 3 This is the granite core from the Gonghe Basin studied in Example 1 of the present invention.

[0042] Figure 4 This is the electron microscope scanning result of the granite in Gonghe Basin studied in Example 1 of the present invention.

[0043] Figure 5 This is the outcrop characteristics of the Gonghe Basin studied in Example 1 of the present invention.

[0044] Figure 6 for Figure 4 Stratigraphic details of area 1 in the middle yellow circle (outcrop characteristics of the Gonghe Basin).

[0045] Figure 7 The length, dip and direction of the cracks in the granite profile of the Gonghe Basin studied in Example 1 of the present invention.

[0046] Figure 8 The fracture characteristic results of each granite profile in the Gonghe Basin are extracted in Example 1 of the present invention.

[0047] Fig. 9 The fracture locations of the Qinghai Gonghe granite downhole core studied in Example 1 of the present invention (the red line shows the fracture locations).

[0048] Fig.10 This is the result of extracting the natural fracture inclination characteristic in Example 1 of the present invention.

[0049] Fig.11 This is the SEM scanning result of the granite outcrop in Gonghe Basin studied in Example 1 of the present invention.

[0050] Fig.12 This is the result of the energy spectrum analysis of the granite in the Gonghe Basin studied in Example 1 of the present invention.

[0051] Fig.13 This is the well-connecting profile of the granite exploration wells in the Gonghe Basin studied in Example 1 of the present invention.

[0052] Fig.14 This is the geological model of the Qiabqia block obtained in Example 1 of the present invention.

[0053] Fig.15 This is the three-dimensional natural fracture model obtained in Example 1 of the present invention.

[0054] Fig.16 This is the initial fracture model obtained in the engineering inversion stage in Example 1 of the present invention.

[0055] Fig.17 The pressure curve results obtained by different fracture network parameters in the engineering inversion stage in Example 1 of the present invention.

[0056] Fig.18 This is a comparison chart of microseismic testing and simulation results in the engineering inversion stage in Example 1 of the present invention.

[0057] Fig.19 This is a schematic diagram of the process-weighted association for obtaining a pressure curve using machine learning training in the engineering inversion stage in Example 1 of the present invention.

[0058] Fig. 20 This is a comparison chart of the pressure test and simulation results in the engineering inversion stage in Example 1 of the present invention.

[0059] Fig.21 This is a program diagram of the machine learning algorithm in the engineering inversion stage in Example 1 of the present invention.

[0060] Fig. 22 This is a natural fracture characteristic adjustment scheme based on microseismicity in the engineering inversion stage in Example 1 of the present invention.

[0061] Fig.23 It is a refined fracture network parameter map obtained by multiple iterative closed-loop feedback optimization in Example 1 of the present invention.

[0062] Fig.24 This is a microseismic model diagram obtained by multiple iterative closed-loop feedback optimization in Example 1 of the present invention.

[0063] Fig.25 This is a crack propagation model diagram obtained by multiple iterative closed-loop feedback optimization in Example 1 of the present invention.

[0064] Fig.26 This is a comparison diagram of the pump pressure curves obtained by multiple iterative closed-loop feedback optimization in Example 1 of the present invention.

[0065] Fig. 27 This is the high-precision natural fracture DFN obtained after correction in Example 1 of the present invention. DETAILED DESCRIPTION

[0066] The present invention is further described in detail below in conjunction with examples, but the embodiments of the present invention are not limited thereto. Unless otherwise specified, the technical means used in the following examples and experimental examples are conventional means well known to those skilled in the art, and the materials, reagents, etc. used can be obtained from commercial sources.

[0067] In the development of hot dry rock thermal reservoirs, natural fractures are the main channels for seepage and heat conduction. However, due to the complex distribution of fractures, traditional single geological modeling or engineering inversion methods are difficult to achieve high-precision characterization. This solution establishes a set of accurate and efficient hot dry rock fracture inversion technologies through multiple iterative feedback between geological forward modeling (geological modeling) and engineering inversion (fracture correction). The present invention utilizes the feedback loop of geological information and fracturing data to form a set of high-precision fracture distribution models suitable for complex hot dry rock reservoirs, providing a scientific basis for the efficient exploitation of hot dry rock thermal reservoir resources. The hot dry rock reservoir in the Gonghe Basin of Qinghai is taken as an example to illustrate the specific scheme of the present invention.

[0068] Example 1

[0069] This scheme provides a high-precision inversion method for natural fractures in hot dry rocks based on geological-engineering integration. The process flow chart is as follows: Figure 1 As shown, the following steps are included:

[0070] (i) Field data collection and preliminary geological modeling: also known as the geological forward modeling stage, through multiple field surveys and sampling, key geological information of hot dry rock reservoirs is obtained, and then the natural fracture distribution law is obtained based on the natural fracture analysis of outcrop + logging interpretation;

[0071] Specifically, it includes the following contents: based on "UAV scanning, core description, full-diameter thin sections, and environmental scanning electron microscopy", the multi-scale heat reservoir structural characteristics were systematically studied; including "crack length, inclination, direction, aperture, spacing and density" and other characteristics, and based on this, the development and classification of the cracks were confirmed, and a preliminary three-dimensional natural fracture model was formed.

[0072] The details are as follows:

[0073] 1. On-site data collection:

[0074] Figure 2 Show the typical geological features of Gonghe Basin. Figure 3 Showing the granite core of Gonghe Basin, Figure 4 The granite electron microscope scanning results are shown. After analysis, the outcrop characteristics of Gonghe Basin are as follows: Figures 5-6 As shown, the field investigation shows that the granite outcrop is relatively broken, with many joints and fissures, which are crisscrossed vertically and horizontally, and filled with mud (partly mixed with quartz); the natural fracture system is mainly composed of high-angle fractures (fracture density 5 / m) and joints, which are the main channels for dry hot rock injection to take heat.

[0075] (1-1) Drone scanning: Drone scanning is performed on the hot dry rock outcrops in the Gonghe Basin in Qinghai Province to generate a three-dimensional geological model and identify and measure the geometric features of the fractures, such as inclination, direction, and spacing.

[0076] Specifically, based on drone scanning, visual interpretation of the 3D model of the field outcrops (5 locations) in the Gonghe Basin was carried out, with a total of 217 sets of fracture data, and the profile fracture distribution was mapped, with detailed records of fracture length, width, density, dip, direction and other information. Figure 7 The results of extracting crack characteristics of each section are shown in Figure 8 shown.

[0077] Among them, the mean value of the gap size (taking length as an example) is calculated as follows:

[0078]

[0079] Where n is Number of gaps , x is The size of each gap The average value of the crack size calculated from the 217 groups of cracks in this embodiment is 7.6 m.

[0080] The probability density function of the gap size is as follows:

[0081]

[0082] (1-2) Core collection and scanning electron microscopy (SEM) analysis: Through core collection and SEM scanning, the porosity, microfracture structure and filling composition of the hot dry rock reservoir are carefully analyzed, and the fracture characteristic parameters are recorded.

[0083] Specifically, the Qinghai Gonghe granite underground core is as follows Fig. 9 The inclination characteristics of natural fractures are shown in Fig.10 The statistical results of crack parameters are shown in Table 1.

[0084] Table 1 Statistical results of crack parameters

[0085] parameter Eigenvalue Horizontal seam High angle seam Crack opening 0.1-1mm Crack count 9 45 Crack spacing 0.5-50m Crack density 1 / m 1 5

[0086] In addition, the SEM scanning results of granite outcrops are as follows Fig.11 The granite energy spectrum analysis is shown in Fig.12 shown.

[0087] The results show that the microscopic SEM scanning shows that the Gonghe hot dry rock is dense as a whole, with a surface area of ​​1-3%, and the pores are dissolution pores and intercrystalline micropores. Based on the characteristics of the underground core and outcrop, the cracks in the Gonghe hot dry rock in Qinghai are moderately developed, which is a fracture-type heat reservoir.

[0088] (1-3) Macro-geological feature analysis: record and statistically analyze the natural fracture density, high-angle fracture distribution, and joint fracture characteristics of hot dry rock outcrops.

[0089] After obtaining the above multi-scale and multi-dimensional fracture parameters, a preliminary fracture distribution model of hot dry rock reservoir is constructed. The model includes information such as fracture inclination, density, length, and opening, which is used to describe the initial spatial distribution and geometric characteristics of fractures.

[0090] Specifically, by investigating the locations of four exploration wells in Gonghe hot dry rock, a geological model of the Qiabqia block was established based on the correction level of the well-connected profile. At the same time, based on the statistical results of fracture characteristics, a preliminary three-dimensional natural fracture model was formed.

[0091] Among them, the natural fracture identification parameters and analysis results include the following:

[0092] (S1) Crack location distribution: The location is determined by the geometric center point of the crack surface;

[0093] (S2), crack occurrence, the calculation formula is as follows:

[0094]

[0095] (S3), geometric shape, the calculation formula is as follows:

[0096]

[0097] (S4), the range of seam width and its distribution, the calculation formula is as follows:

[0098]

[0099] Specifically, the well-connected profile results of the exploration wells in this embodiment are as follows: Fig.13 As shown in Figure 2, the geological model of the Qiabqia block is as follows: Fig.14 As shown in Figure 2, the three-dimensional natural fracture model is Fig.15 As shown in Figure 2, the initial crack model is as follows: Fig.16 shown.

[0100] (II) Fracturing experiment and engineering inversion correction, also known as the engineering inversion stage, i.e. the fracturing correction stage, is to carry out fracturing experiments to obtain engineering inversion data based on the preliminary fracture model. The specific steps are as follows:

[0101] (2-1) On-site fracturing test: A fracturing experiment was conducted in the target well (e.g., Well GH01 in the Gonghe Basin, Qinghai Province) (the fracturing simulation parameters are detailed in Table 2), and the pressure curve, stress field changes, and microseismic signals of the wellbore were monitored and recorded in real time to capture the dynamic evolution characteristics of the cracks during the fracturing process.

[0102] Table 2 Fracturing simulation parameters

[0103] density 2800kg / m3 Elastic modulus 40GPa Poisson's ratio 0.15 Matrix tensile strength 11MPa Permeability 0.5mD Natural crack tensile strength 3MPa Natural fracture cohesion 5MPa Minimum / maximum horizontal ground stress 110~130 / 100~120MPa

[0104] (2-2) Microseismic monitoring: Microseismic monitoring is used to record the generation, extension direction and depth changes of cracks, and compared with the initial model. The pressure curves obtained with different fracture network parameters are detailed in Fig.17 .

[0105] (2-3) Data inversion and correction: Engineering inversion is performed through real-time collected pressure data and microseismic information, and the parameters in the fracture model (such as fracture length, density, and opening) are adjusted in combination with machine learning algorithms to gradually correct the spatial position and morphology of the fractures. In this step, the machine learning model is used to iteratively optimize the fracture model parameters based on the pressure curve and microseismic signals to make the model closer to the actual fracture characteristics.

[0106] Specifically, the displacement discontinuity method is used to develop a deep reservoir hydraulic fracturing numerical simulation technology, which fully considers the influence of stress shadows within the fracturing section, between sections, and between wells, as well as natural fractures. The model limits the calculation domain to the fracture surface to achieve the purpose of reducing the dimension, which can greatly improve the calculation efficiency while ensuring the simulation accuracy.

[0107] Among them, the displacement discontinuity (unit local coordinate system) used in this scheme includes the following:

[0108] D x =u x (x,y,0 - )-u x (x,y,0 + )

[0109] D y =u y (x,y,0 - )-u y (x,y,0 + )

[0110] D z =u z (x,y,0 - )-u z (x,y,0 + )

[0111] In the formula, D is the small change, u is the displacement; D x Specifically, it is expressed as: on the plane z = 0, at a fixed point (x, y), the difference between the partial derivative of u with respect to x when z approaches 0 from the negative direction and the partial derivative of u with respect to x when z approaches 0 from the positive direction. y , D z Same as above.

[0112] This scheme adopts the semi-infinite space Green's function, which is as follows:

[0113]

[0114] According to the stress function solution, the displacement and stress induced by the fracture unit displacement discontinuity at any point in space (xyz) are calculated as follows:

[0115] u x =C{[2(1-v)I ,z -zI ,xx ]D x -zI ,xy D y -[(1-2v)I ,x +zI ,xz ]D z}

[0116] u y =C{-zI ,xy D x +[2(1-v)I ,z -zI ,yy ]D y -[(1-2v)I ,y+zI ,yz ]D z}

[0117] u z =C{[(1-2v)I ,x -zI ,xz ]D x +[(1-2v)I ,y -zI ,yz ]D y +[2(1-v)I ,z -zI ,zz ]D z}

[0118] σ xx =2C{[2I ,xz -zI ,xxx ]D x +[2vI ,yz -zI ,xxy ]D y +[I ,zz +(1-2v)I ,yy -zI ,xxz ]D zz}

[0119] σ yy =2C{[2vI ,xz -zI ,xyy ]D x +[2I ,yz -zI ,yyy ]D y +[I ,zz +(1-2v)I ,xx -zI ,yyz ]D z}

[0120] σ zz =2C{-zI ,xzz D x -zI ,yzz D y +[I ,zz -zI ,zzz ]D z}

[0121] τ xy =2C{[(1-v)I ,yz -zI ,xxy ]D x +[(1-v)I ,xz -zI ,xyy ]D y -[(1-2v)I ,xy +zI ,xyz ]Dz}

[0122] τ yz =2C{-[vI ,xy +zI ,xyz ]D x +[I ,zz +vI ,xx -zI ,yyz ]D y -zI ,yzz D z}

[0123] τ zx =2C{[I ,zz +vI ,yy -zI ,xxz ]D x -[vI ,xy +zI ,xyz ]D y -zI ,xzz D z}

[0124] Where u is displacement, σ is tensile stress, and τ is shear stress.

[0125] Comparison of microseismic test and simulation results Fig.18 The principle of obtaining the pressure curve is shown in Fig.19 , the comparison between stress test and simulation results is as follows Fig. 20 shown.

[0126] (iii) Multiple iterative closed-loop feedback optimization: Based on the above-mentioned fracturing curves and microseismic fitting, the geological modeling results and engineering inversion data are subjected to multiple feedback corrections to obtain a high-precision fracture distribution model of the hot dry rock reservoir.

[0127] The specific contents include the following:

[0128] (3-1) Data integration and feedback correction: Based on each round of fracturing experiments and inversion results, the latest data is fed back into the geological model, and multiple rounds of corrections are performed to update the spatial distribution and geometric characteristics of the fractures.

[0129] (3-2) Machine learning driven optimization: Taking the fracturing pressure curve and microseismic signal as input, a machine learning model is established. Through large-scale fracturing simulation, a database is formed to automatically fit the geometric parameters of the fracture model. This step is continuously iterated and adjusted to gradually make the fracture distribution consistent with the actual measurement results.

[0130] (3-3) Model verification and accuracy improvement: After each round of optimization, the model accuracy is verified by comparing with field data to ensure that the closed-loop optimized fracture model can truly reflect the geometric and mechanical characteristics of the hot dry rock reservoir fractures.

[0131] During the process, this solution also provides a fracturing curve and microseismic fitting method based on machine learning, including the following contents: taking the natural fracture density, length, height, inclination, strike, and opening degree of hot dry rock reservoir as variables, combined with an efficient fracturing simulation model, the pressure curve and fracture network distribution are output to form a database.

[0132] Among them, machine learning algorithm programs such as Fig.21 As shown, the specific steps include:

[0133] S1, start;

[0134] S2, divide the training set and test set;

[0135] S3. Input the training set into the LSSVM model. The LSSVM model is mainly completed using the JAVA algorithm, including the following calculation process: initialize the JAVA algorithm parameters and hyperparameters - iterate and optimize according to the objective function - meet the progress requirements or the maximum number of iterations - output the optimal result;

[0136] S4. Determine the hyperparameters of the LSSVM model;

[0137] S5. End.

[0138] The natural fracture characteristics adjustment scheme based on microseismic Fig. 22 As shown, the correlation function of natural fractures is adjusted specifically according to the mismatch information.

[0139] This solution adopts the method of constructing fracturing simulation, which takes into account both computational efficiency and simulation accuracy; and constructs a machine learning algorithm, which takes into account both training efficiency and prediction accuracy.

[0140] Specifically, the fracturing simulation and machine learning algorithm are integrated, and the microseismic data and pump pressure curve of the GH01 well are used as constraints to iteratively adjust the distribution characteristics of natural fractures to form a high-precision natural fracture model based on the integration of geology and engineering. This solution uses a machine learning model to iteratively optimize the fracture model parameters based on the pressure curve and microseismic signals to make the model closer to the actual fracture characteristics, and optimizes the model calculation efficiency to accurately reconstruct the fracture distribution in a complex three-dimensional space. 。

[0141] Specifically, the results of iterative adjustment of refined fracture network parameters, microseismicity, fracture extension, and pump pressure curve comparison are as follows: Figures 23-26 The corrected natural fracture model is shown in Fig. 27, this model can accurately describe the key parameters of the fractures, such as spatial position, inclination, opening, density, etc., and reconstruct the real distribution structure of the fractures in three-dimensional space, which conforms to the actual geological and engineering conditions. This scheme adopts the above scheme, and obtains the distribution law of natural fractures by using natural fracture analysis based on outcrop + logging interpretation in the geological forward modeling stage; and then obtains the corrected high-precision natural fracture DFN based on machine learning fracturing microseismic + pump pressure curve correction in the engineering inversion stage. This scheme adopts the method of constructing fracturing simulation, which takes into account both computational efficiency and simulation accuracy; and constructs a machine learning algorithm, which takes into account both training efficiency and prediction accuracy. This scheme combines the geological forward modeling stage and the engineering inversion stage to obtain the corrected high-precision natural fracture DFN, effectively realizing the geological-engineering integrated analysis of natural fractures in fracture-type reservoirs, and providing a theoretical basis for the research and analysis of natural fractures in reservoirs and their subsequent development.

[0142] The above is only an embodiment of the present invention, and the common knowledge such as the known specific technical solutions and / or characteristics in the solution is not described in detail here. It should be pointed out that for those skilled in the art, without departing from the technical solution of the present invention, several modifications and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A high-precision inversion method for natural fractures in hot dry rocks based on geological-engineering integration, characterized by: The steps include: (i) Field data collection and preliminary geological modeling: construct an initial fracture model based on the geological data of the hot dry rock reservoir; (ii) Fracturing experiment and engineering inversion correction: Based on the preliminary fracture model, the engineering inversion is carried out using the field fracturing test data and microseismic information to invert and correct the model; (III) Multiple iterative closed-loop feedback optimization: The geological modeling results and engineering inversion data are subjected to multiple feedback corrections to obtain a high-precision fracture distribution model of the hot dry rock reservoir.

2. The high-precision inversion method for natural fractures in hot dry rocks based on geological-engineering integration according to claim 1 is characterized by: In (i) field data collection and preliminary geological modeling, the method for obtaining geological data is to collect natural fracture parameters of hot dry rock reservoirs through multi-scale data analysis including drone scanning, core sampling, and SEM scanning.

3. The high-precision inversion method for natural fractures in hot dry rocks based on geological-engineering integration according to claim 2 is characterized by: The natural fracture parameters include the inclination angle, length, width, density and directional distribution of the fracture.

4. The high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration according to claim 3 is characterized by: In (ii) fracturing experiment and engineering inversion correction, the method for acquiring the field fracturing test data is: conducting a fracturing experiment in a target well, monitoring and recording the wellbore pressure curve, stress field changes and microseismic signals in real time, and capturing the dynamic evolution characteristics of the cracks during the fracturing process.

5. The high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration according to claim 4 is characterized by: In (ii) fracturing experiment and engineering inversion correction, the microseismic information monitoring method is: using microseismic monitoring to record the generation, extension direction and depth changes of cracks.

6. A high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration according to claim 5, characterized in that: In (ii) fracturing experiment and engineering inversion correction, the engineering inversion method is: by comparing the real-time collected pressure data and microseismic information with the initial model, and combining the machine learning algorithm to adjust the natural fracture parameters in the fracture model, the spatial position and morphology of the fracture are gradually corrected to obtain the engineering inversion data.

7. A high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration according to claim 6, characterized in that: In (iii) multiple iterative closed-loop feedback optimization, it also includes a fracturing curve and microseismic fitting method based on machine learning, including the following: using the natural fracture density, length, height, inclination, strike, and opening degree of the hot dry rock reservoir as variables, combined with an efficient fracturing simulation model, the pressure curve and fracture network distribution are output to form a database.

8. The high-precision inversion method for natural fractures in hot dry rocks based on geology-engineering integration according to claim 7 is characterized by: In (II) fracturing experiments and engineering inversion correction, the displacement discontinuity method is used to develop the deep reservoir hydraulic fracturing numerical simulation technology, fully considering the influence of stress shadows within the fracturing section, between sections, and between wells as well as natural fractures, and the displacement discontinuity is calculated using the following formula: D x =u x (x,y,0 - )-u x (x,y,0 + ) D y =u y (x,y,0 - )-u y (x,y,0 + ) D z =u z (x,y,0 - )-u z (x,y,0 + ) In the formula, D is the small change, u is the displacement; D x Specifically, it is expressed as: on the plane z = 0, at a fixed point (x, y), the difference between the partial derivative of u with respect to x when z approaches 0 from the negative direction and the partial derivative of u with respect to x when z approaches 0 from the positive direction; D y , D z Same as above; According to the stress function solution, the displacement and stress induced by the fracture unit displacement discontinuity at any point in space (xyz) are calculated as follows: you x =C{[2(1-v)I ,z -zI ,xx ]D x -zI ,xy D y -[(1-2v)I ,x +zI ,xz ]D z } you y =C{-zI ,xy D x +[2(1-v)I ,z -zI ,yy ]D y -[(1-2v)I ,y +zI ,yz ]D z } u z =C{[(1-2v)I ,x -zI ,xz ]D x +[(1-2v)I ,y -zI ,yz ]D y +[2(1-v)I ,z -zI ,zz ]D z } σ xx =2C{[2I ,xz -zI ,xxx ]D x +[2vI ,yz -zI ,xxy ]D y +[I ,zz +(1-2v)I ,yy -zI ,xxz ]D zz } σ yy =2C{[2vI ,xz -zI ,xyy ]D x +[2I ,yz -zI ,yyy ]D y +[I ,zz +(1-2v)I ,xx -zI ,yyz ]D z } σ zz =2C{-zI ,xzz D x -zI ,yzz D y +[I ,zz -zI ,zzz ]D z } τ xy =2C{[(1-v)I ,yz -zI ,xxy ]D x +[(1-v)I ,xz -zI ,xyy ]D y -[(1-2v)I ,xy +zI ,xyz ]D z } τ yz =2C{-[vI ,xy +zI ,xyz ]D x +[I ,zz +vI ,xx -zI ,yyz ]D y -zI ,yzz D z } τ zx =2C{[I ,zz +vI ,yy -zI ,xxz ]D x -[vI ,xy +zI ,xyz ]D y -zI ,xzz D z } Where u is displacement, σ is tensile stress, and τ is shear stress.

Images