Integrated collaborative transformation method and system for rock formation fracturing monitoring, evaluation and control

Abstract

The present invention discloses a method and system for integrated collaborative transformation of rock formation fracturing monitoring, evaluation, and regulation. The method comprises the following steps: real-time acquisition of microseismic signals during the fracturing process through a microseismic monitoring system; acquisition of the fracture moment tensor, geometric parameters, and local stress field characteristics based on focal mechanism inversion; construction of a discrete fracture network and calculation of the effective volume (SRV) of the rock formation transformation to establish a fracturing effect evaluation model; optimization of fracturing parameters through stress field inversion; establishment of a fracturing effect regulation model; acquisition of the relationship between the fracturing effect evaluation grade and controllable injection parameters; construction of an integrated collaborative transformation system for monitoring, evaluation, and regulation, and continuous generation of optimal solutions until the target is achieved or the fracturing reaction effect is optimized. The present invention achieves the organic integration of different links in the fracturing process, including real-time diagnosis, quantitative effect evaluation, and dynamic parameter adjustment, as well as collaborative feedback between technologies, effectively improving the accuracy and efficiency of rock formation fracturing transformation.

Description

Technical Field

[0001] The present invention relates to the field of fracturing technology, and in particular to a rock formation fracturing monitoring-evaluation-control integrated collaborative transformation method and system. Background Art

[0002] With the rapid growth in demand for unconventional oil and gas resources and deep geothermal reservoir development, hydraulic fracturing has become a key tool for increasing reservoir permeability and enhancing resource extraction efficiency. Traditional fracturing techniques primarily rely on empirical construction parameters and static geological models, using large-scale fracturing fluid injection to create complex fracture networks and expand the reservoir stimulation volume (SRV). However, actual rock formations are highly heterogeneous, and fracture propagation is influenced by multiple factors, including the local stress field, the distribution of natural fractures, and the mechanical properties of the rock. This makes it difficult to accurately predict fracture morphology during the fracturing process, and the stimulation results often deviate significantly from the design objectives.

[0003] Due to the limitations of the existing technology and insufficient data integration, it is difficult to achieve accurate evaluation and dynamic regulation of the effect of fracturing and reconstruction. Although patent CN119918467A proposes a dynamic and static coupling simulation method for hydraulic-detonation combined fracturing reconstruction, the effect of deep-ultra-deep reservoir fracturing reconstruction is improved through dynamic and static coupling simulation calculation of hydraulic-detonation fracturing; patent CN119393108A proposes a method for optimizing the volume fracturing technology of continental shale, which considers the hydraulic fracture complexity index, hydraulic fracture penetration expansion index, and multi-cluster hydraulic fracture balanced expansion index in parallel, providing an effective process optimization method for continental shale volume fracturing, which is conducive to improving The volume of continental shale fracturing transformation; Patent CN119244209A proposes a large-scale volume iterative fracturing transformation method for medium-deep coal seams. Through three-stage fracturing, it solves the problems of high injection pressure, difficult sand addition, and low stable production capacity in the fracturing process of medium-deep coal reservoirs; Patent CN117034717A discloses a single-cluster point fracturing transformation method for efficient production increase of continental shale oil. This method is based on the simulation to determine the optimal fracture setting method for production, and achieves balanced expansion of fracturing fractures. It is only applicable to fracturing transformation of single-cluster fractures. However, there are the following significant limitations: the evaluation model is single, SRV calculations are mostly based on simplified geometric assumptions, and the three-dimensional geometric characteristics of the fractures and the non-uniformity of permeability distribution are not fully considered, resulting in distorted evaluation of the transformation effect; the intelligent control capability is insufficient, and the optimization of fracturing parameters mostly relies on empirical formulas or static numerical simulations, and there is a lack of dynamic control models that integrate artificial intelligence. In response to the above problems, there is an urgent need for a collaborative transformation method and system that integrates real-time monitoring, precise evaluation and dynamic control. Summary of the Invention

[0004] In response to the problems and needs raised above, this solution proposes an integrated collaborative transformation method and system for rock fracturing monitoring, evaluation, and control. Due to the adoption of the following technical features, it can achieve the above technical objectives and bring about multiple other technical effects.

[0005] One object of the present invention is to provide an integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control, comprising the following steps:

[0006] S10: Exploring geological information of the rock formation, analyzing and determining the target rock formation for fracturing, deploying a microseismic monitoring system in the rock formation, injecting fracturing fluid into the rock formation, and using the microseismic monitoring system to monitor microseisms in real time and collect microseismic signal data during the fracturing process;

[0007] S20: Perform focal mechanism inversion based on microseismic signal data to obtain the fracture moment tensor, geometric parameters, and fracture mode of the rock formation, and invert the principal stress direction and stress shape factor of the local stress field based on the above fracture parameters;

[0008] S30: Based on the focal mechanism solution parameters and the geometric characteristics of the fractures, a discrete fracture network is constructed and divided into three-dimensional cube grids. The effective volume (SRV) of the rock formation transformation is calculated, and an evaluation model for the transformation effect of fractured rock formations is established to quantitatively evaluate the effect of rock formation hydraulic fracturing.

[0009] S40: Optimize fracturing parameters based on stress field inversion, adjust the fracturing direction so that the cracks extend along the principal stress direction, establish a fracturing effect control model, obtain the relationship between the fracturing effect and the controllable injection parameters, and obtain the parameter variables that have the greatest impact on the fracturing effect for selective control;

[0010] S50: While obtaining the evaluation of the fracturing effect through process monitoring, a plan for enhanced regulation is given, and an integrated monitoring-evaluation-regulation collaborative transformation system is constructed until the target or the optimization of the fracturing effect is achieved, realizing the organic integration of different links of monitoring, evaluation, and regulation and the collaborative feedback between technologies.

[0011] In one example of the present invention, in step S20, performing fracture focal mechanism inversion based on the microseismic signal data set to obtain fracture rupture moment tensor, geometric parameters, and fracture rupture mode in the rock layer space includes the following steps:

[0012] S211: Calculate the fracture characterization tensor: Fracture parameters are characterized by fracture source tensors The specific formula is as follows:

[0013] ,

[0014] Where, ij Characterize the crack source tensor No.i OK( i =1, 2, 3), No. j List( j =1, 2, 3) elements; b i 、 b j is the crack surface motion vector; n i 、 n j is the normal vector of the crack surface; A is the area of ​​newly generated active cracks;

[0015] S212: Solve the eigenvalues ​​of the crack characterization tensor and obtain the three eigenvalues ​​of the tensor:

[0016] ,

[0017] Where, 、 and Tensors the maximum, middle, and minimum eigenvalues ​​of ; b h 、 n h Subscript in h is a dummy symbol, which satisfies the Einstein summation convention, that is, ; is the motion vector of the moving crack surface b of L2 norm;

[0018] S213: Solving the geometric parameters of the fracture: In the generalized tensile shear rupture source model, the tensor The intermediate eigenvalue ψ2=0, the constraints must be satisfied in the model solution:

[0019] ,

[0020] Where, |b|ΔA is the rupture volume; n is the normal vector of the fault space; b is the motion vector; α is the shearing angle;

[0021] S214: According to the tension and shear angle α The value of determines the crack rupture mode: α =0°, the crack is pure tensile fracture; when 0°<α<22.5°, the crack is mainly tensile fracture; when 22.5°≤ α When the angle is less than 45°, the crack is mainly shear fracture; when α =45°, the crack is pure shear fracture.

[0022] In one example of the present invention, in step S20, inverting the principal stress direction and stress shape factor of the local stress field based on the above-mentioned crack parameters includes the following steps:

[0023] S221: Construct matrix based on crack rupture information G and vector s The extended form of P focal mechanism, expanded matrix G ={ G 1 , G 2 ,…, G p-1 , G p} and vector s ={ S 1 , S 2 ,…, S p-1 , S p}, where each submatrix G i , from the fault space normal vector n The component composition of

[0024] S222: Use Michael's linear inversion to solve the initial stress tensor, assuming that the stress tensor trace is zero, and the unknown components of the stress tensor t is a 5-dimensional vector, solved by generalized linear inversion:

[0025] ,

[0026] Where g is the acceleration due to gravity;

[0027] S223: Based on the first principal stress s 1 , the second principal stress s 2 and the third principal stress s 3 The size relationship of s 1 ≥ s 2 ≥ s 3 , calculate the stress shape factor T :

[0028] ,

[0029] Where T∈[0,1] is used to characterize the shape of the stress ellipsoid;

[0030] S224: Scale the three principal stresses according to the stress shape factor, and substitute the scaled three principal stresses into the normal stress, principal stress, and shear stress relationship of any section in elastic mechanics. Finally, the following normal stress is obtained. , shear stress Calculation expression:

[0031] ,

[0032] Where, l 、 m , r is the direction cosine.

[0033] In one example of the present invention, in step S30, based on the focal mechanism solution parameters and combined with the geometric characteristics of the fractures, a discrete fracture network is constructed and divided into three-dimensional cubic grids to calculate the effective volume (SRV) of the rock formation transformation, including the following steps:

[0034] S311: Generate a three-dimensional fracture model using a discrete fracture network and generate randomly distributed fracture segments based on the fracture density λ;

[0035] S312: Divide the target area into a uniform cube grid, each cube index is ( i , j , x ), use the three-dimensional ray casting algorithm to determine whether the crack segment intersects with the cube. If the starting point of the crack segment ( x 1 , y 1 , z 1 ) to the end point( x 2 , y 2 , z 2 ) has an intersection with the cube surface, the cube is marked as "intersecting" and the cube bounding box is used for preliminary screening;

[0036] S313: Calculate the fracture cross-sectional area. Based on the fracture area, calculate the effective volume (SRV) of the rock formation by the integral method. The expression is:

[0037] ,

[0038] Where, is the porosity increment, is the initial porosity, Δk is the permeability increment; k 0 is the initial permeability; V The volume of the area affected by the fracturing;

[0039] S314: Based on crack strength P 32 Calculate the permeability enhancement scalar:

[0040] ,

[0041] Where, A i For the i The cross-sectional area of ​​the crack in the cube; K fs For effective stereoscopic visualization.

[0042] In one example of the present invention, in step S30, an evaluation model for the effect of fractured rock formation transformation is established to quantitatively evaluate the effect of rock formation hydraulic fracturing transformation, including the following steps:

[0043] S321: Determine the rock formation transformation effect based on the rock formation transformation effective volume SRV. When the rock formation transformation effective volume SRV is greater than or equal to or When the effective volume SRV of the rock formation is less than or When the reservoir is fractured, it is considered that the effect of reservoir fracturing is poor;

[0044] S322: Based on stress shape factor T ,when T When it is close to 0, the principal stress s 1. s 2 is close, the stress field is in a biaxial compression state; when T = 0.5, the compressive stress axis, intermediate stress axis and tensile stress axis are relatively stable; when T When it is close to 1, the principal stress s 2. s 3 is close, the stress field is in uniaxial compression state;

[0045] S323: Definition of rupture instability coefficient based on Mohr-Coulomb failure criterion I , whose expression is:

[0046] ,

[0047] Where, s 、 t are the normal stress and shear stress of the fracture surface respectively; m is the rock friction coefficient;

[0048] When the rupture instability coefficient I=0, the fault zone is in the optimal bearing state; as the fracture instability coefficient I increases to the critical value of 1, the risk of rock mass instability shows a linear growth trend; among them, when the fracture instability coefficient I ≥ 0.9, it indicates that the stress field structure of the rock formation has deteriorated, and the probability of rock mass system instability has increased exponentially, which in turn leads to a significant increase in the probability of strong mine earthquakes and poor fracturing treatment effect; when the fracture instability coefficient I < 0.9, the fracture is stable and the fracturing treatment effect is good.

[0049] S324: Evaluation based on fracture permeability: Based on the preset fracture permeability formula, the fracture roughness coefficient corresponding to the rock formation confining pressure, the shear fracture surface, and the seepage simulation results, the fracture permeability k of the rock formation is determined:

[0050] ,

[0051] Where C is the cubic law correction coefficient, D is the fracture connectivity correction coefficient, K n is the crack normal stiffness of the shear crack surface, d h0 is the initial equivalent crack opening of the shear crack surface, s n is the confining pressure of the rock formation, J is the fracture roughness coefficient corresponding to the shear fracture surface;

[0052] S325: A comprehensive evaluation model for volume effect fracturing is constructed to quantitatively evaluate the fracturing effect through the reservoir conductivity after fracturing. The expression of reservoir conductivity Q after fracturing is:

[0053] ,

[0054] Where S is the fracture tendency type score of fracturing stimulation; is the proportion of earthquake sources with rupture instability coefficient I ≥ 0.9; is the effective volume; is the principal stress; is the stress-direction coupling coefficient; The crack extension direction.

[0055] In one example of the present invention, in step S40, the fracturing parameters are optimized based on the stress field inversion, including the following steps:

[0056] S411: constructing an integrated fracturing numerical simulation model based on the stress parameters and microseismic data of the rock formation, and performing parameter correction on the integrated fracturing numerical simulation model using the stress field inversion result;

[0057] S412: Input a combination of fracturing parameters to be tested, and generate a corresponding rock formation stimulation effective volume (SRV) according to the revised integrated fracturing numerical simulation model;

[0058] S413: Establish a dual-objective optimization mathematical model with the rock formation transformation effective volume SRV and the fracture instability coefficient I as the targets, and obtain the optimal parameters of the dual-objective optimization mathematical model, wherein the optimal fracturing operation parameters of the dual-objective optimization mathematical model are The expression is:

[0059] ,

[0060] Where, u is a set of optimization variables; U Represents the space of optimization variables that can be selected; w 1 and w 2 All are weight coefficients;

[0061] S414: The obtained rock formation transformation effective volume SRV is input into a dual-objective optimization mathematical model with optimal parameters, and optimal fracturing parameters are output.

[0062] In one example of the present invention, in step S40, the fracturing direction is adjusted so that the cracks extend along the principal stress direction, a fracturing effect control model is established, the relationship between the fracturing effect and the controllable injection parameters is obtained, and the parameter variables that have the greatest impact on the fracturing effect are obtained for selective control, including the following steps:

[0063] S421: Determine the fracturing direction according to the principal stress direction in step S20 i ,Under the action of triaxial stress, most hydraulic fractures extend along the direction parallel or approximately parallel to the maximum principal stress, and perpendicular to the minimum principal stress;

[0064] S422: Using the rock formation transformation effective volume SRV and the fracturing effect evaluation level as input data and the controllable injection parameters as output data, the data is normalized to determine the network input layer and calculate the hidden layer output. And predict the output layer , determine the overall error of the network, and judge whether the overall error meets the requirements. If not, recalculate the hidden layer output to train the BP neural network and obtain the relationship between the fracturing effect evaluation level and the controllable injection parameter X;

[0065] S423: Through sensitivity analysis, the parameter variables that have the greatest impact on the fracturing effect are obtained for selective regulation. A BP neural network model is established for the fracturing effect evaluation level based on the effective volume (SRV) of the rock formation, the comprehensive indicator monitoring parameter (F), and the controllable injection parameter (X). A parameter in the controllable injection parameter (X) is selected to be increased or decreased within a certain range to obtain the parameter that causes a significant change in the fracturing effect evaluation level.

[0066] In an example of the present invention, step S50 specifically includes the following steps:

[0067] S501: Within the required assessment period, using the assessment subunits as units, stratum reformation effective volume (SRV), fracture permeability, and fracture instability coefficient are classified into three levels, with scores of 3, 2, and 1, respectively, from strong to weak, according to the actual corresponding conditions. The stress shape factor is divided into two levels, with strong assigned a value of 3 and weak assigned a value of 2. As more monitoring and assessment data is collected and combined with actual geological conditions, the grade assessment and assigned scores will be further refined and adjusted.

[0068] S502: Based on the evaluation of the fracturing effect, a score between 5 and 12 is assigned, and the fracturing treatment plan is formulated accordingly. When the evaluation value is 11 to 12, the rock formation treatment effect is good and no treatment is required. When the evaluation value is 8 to 10, the rock formation treatment effect is moderate, and the key injection parameters are adjusted. When the evaluation value is 5 to 7, the rock formation treatment effect is poor, and the injection parameters are adjusted and the fracturing direction is changed.

[0069] S503: Continue to monitor the fracturing process, complete the re-evaluation of the fracturing transformation effect, continuously improve the fracturing effect transformation target, adjust the injection parameters, and continuously improve the fracturing transformation level until the fracturing effect is optimized. Build an integrated monitoring-evaluation-control collaborative transformation system to achieve the organic integration of different links of monitoring, evaluation, and control, and the collaborative feedback between technologies.

[0070] Another object of the present invention is to provide an integrated collaborative transformation system for monitoring, evaluating and controlling rock fracturing, including:

[0071] A microseismic monitoring module is configured to detect geological information of rock formations, analyze and determine target rock formations for fracturing, deploy a microseismic monitoring system in the rock formations, inject fracturing fluid into the rock formations, and use the microseismic monitoring system to monitor microseisms in real time and collect microseismic signal data during the fracturing process;

[0072] a signal processing module configured to perform focal mechanism inversion based on microseismic signal data, obtain fracture moment tensors, geometric parameters, and fracture rupture patterns of the rock formation, and invert principal stress directions and stress shape factors of the local stress field based on the fracture parameters;

[0073] The effect evaluation module is configured to construct a discrete fracture network and divide it into three-dimensional cube grids based on the parameters of the focal mechanism solution and the geometric characteristics of the fractures, calculate the effective volume (SRV) of the rock formation transformation, establish an evaluation model for the fractured rock formation transformation effect, and quantitatively evaluate the rock formation fracturing transformation effect;

[0074] The effect control module is configured to optimize the fracturing parameters based on stress field inversion, adjust the fracturing direction so that the cracks extend along the principal stress direction, establish a fracturing effect control model, obtain the relationship between the fracturing effect and the controllable injection parameters, and obtain the parameter variables that have the greatest impact on the fracturing effect for selective control;

[0075] The integrated monitoring-evaluation-control module is configured to obtain fracturing effect evaluation through process monitoring while providing enhanced control solutions, building an integrated monitoring-evaluation-control collaborative transformation system until the target or fracturing effect is achieved, realizing the organic integration of different links of monitoring, evaluation, and control and the coordinated feedback between technologies.

[0076] In one example of the present invention, the effect control module includes:

[0077] a parameter correction unit configured to construct a hydraulic fracturing integrated numerical simulation model based on the stress parameters of the rock formation and microseismic data, and perform parameter correction on the hydraulic fracturing integrated numerical simulation model using a stress field inversion result;

[0078] A volume transformation unit is configured to input a combination of fracturing parameters to be tested and generate a corresponding rock formation transformation effective volume SRV according to the modified integrated fracturing numerical simulation model;

[0079] The parameter acquisition unit is configured to establish a dual-objective optimization mathematical model with the rock formation transformation effective volume SRV and the fracture instability coefficient I as the target, and obtain the optimal parameters of the dual-objective optimization mathematical model, wherein the optimal fracturing operation parameters of the dual-objective optimization mathematical model are The expression is:

[0080] ,

[0081] Where, u is a set of optimization variables; U Represents the space of optimization variables that can be selected; w 1 and w 2 All are weight coefficients;

[0082] The parameter output unit is configured to input the obtained rock formation transformation effective volume SRV into a dual-objective optimization mathematical model with optimal parameters, and output optimal fracturing parameters.

[0083] Compared with the prior art, the present invention has the following beneficial effects:

[0084] Through moment tensor decomposition, the present invention innovatively combines focal mechanism inversion with crack dynamic parameters, determines the crack rupture mode based on the value of the tension-shear angle α, and effectively solves the problem of misjudgment of complex cracks; introduces stress shape factors to reflect the relative sizes of the principal stresses σ1, σ2, and σ3 and the stress field distribution state, significantly reducing errors and achieving high-precision characterization of non-uniform stress fields.

[0085] This method innovatively combines focal mechanism solutions, stress field inversion, and three-dimensional fracture network modeling. It evaluates the effectiveness of hydraulic fracturing using multiple dimensions: the effective volume (SRV) of the rock formation, the stress shape factor (T), the fracture instability coefficient (I), and the fracture permeability (K). A comprehensive evaluation model for hydraulic fracturing fracture effects is constructed to quantitatively assess the effects, breaking through the limitations of traditional methods that rely solely on the single parameter of effective volume (SRV) of the rock formation, thereby improving evaluation accuracy.

[0086] This method uses a BP neural network and artificial intelligence optimization algorithm to establish a quantitative relationship model between fracturing parameters and stimulation effects. Parameter sensitivity analysis quickly identifies key control variables, and combined with numerical simulation, generates an optimal construction plan. This reduces redundant data processing steps, shortens analysis cycles, and reduces equipment deployment and manual intervention costs, significantly improving the overall benefits of unconventional oil and gas reservoir development.

[0087] This method integrates monitoring, evaluation, and regulation through a closed-loop system encompassing microseismic monitoring, fracture inversion, effect evaluation, and effect control. This system also allows for collaborative feedback between technologies. Compared to traditional unidirectional fracturing techniques, this method enables dynamic correction of the fracturing process, automatically optimizing parameters through real-time feedback, and significantly improving fracturing efficiency.

[0088] Hereinafter, the best embodiment of the present invention will be described in more detail with reference to the accompanying drawings so that the features and advantages of the present invention can be easily understood. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings of the embodiments of the present invention. The drawings are only used to illustrate some embodiments of the present invention, but not to limit all embodiments of the present invention thereto.

[0090] Figure 1 Flowchart of the integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to an embodiment of the present invention;

[0091] Figure 2 A schematic structural diagram of a microseismic monitoring arrangement according to an embodiment of the present invention;

[0092] Figure 3A schematic diagram of crack type identification according to an embodiment of the present invention;

[0093] Figure 4 A schematic diagram of fracturing effect evaluation according to an embodiment of the present invention;

[0094] Figure 5 Schematic diagram of the distribution of principal stress directions and fracture instability coefficients according to an embodiment of the present invention;

[0095] Figure 6 Schematic diagram of dynamic control according to an embodiment of the present invention. DETAILED DESCRIPTION

[0096] In order to make the purpose, technical solution and advantages of the technical solution of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of specific embodiments of the present invention. The same figure marks in the drawings represent the same parts. It should be noted that the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0097] Unless otherwise defined, the technical or scientific terms used herein shall have the ordinary meaning understood by persons of ordinary skill in the field to which the invention belongs. The words "first", "second" and similar terms used in the patent application specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "a" or "an" do not necessarily indicate a quantity limitation. Words such as "include" or "comprising" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0098] According to the first aspect of the present invention, a rock formation fracturing monitoring, evaluation, and control integrated collaborative transformation method comprises the following steps:

[0099] S10: Exploring geological information of the rock formation, analyzing and determining the target rock formation for fracturing, deploying a microseismic monitoring system in the rock formation, injecting fracturing fluid into the rock formation, and using the microseismic monitoring system to monitor microseisms in real time and collect microseismic signal data during the fracturing process;

[0100] S20: Perform focal mechanism inversion based on microseismic signal data to obtain the fracture moment tensor, geometric parameters, and fracture mode of the rock formation, and invert the principal stress direction and stress shape factor of the local stress field based on the above fracture parameters;

[0101] S30: Based on the focal mechanism solution parameters and the geometric characteristics of the fractures, a discrete fracture network is constructed and divided into three-dimensional cube grids. The effective volume (SRV) of the rock formation transformation is calculated, and an evaluation model for the transformation effect of fractured rock formations is established to quantitatively evaluate the effect of rock formation hydraulic fracturing.

[0102] S40: Optimize fracturing parameters based on stress field inversion, adjust the fracturing direction so that the cracks extend along the principal stress direction, establish a fracturing effect control model, obtain the relationship between the fracturing effect and the controllable injection parameters, and obtain the parameter variables that have the greatest impact on the fracturing effect for selective control;

[0103] S50: While obtaining the evaluation of the fracturing effect through process monitoring, a plan for enhanced regulation is given, and an integrated monitoring-evaluation-regulation collaborative transformation system is constructed until the target or the optimization of the fracturing effect is achieved, realizing the organic integration of different links of monitoring, evaluation, and regulation and the collaborative feedback between technologies.

[0104] This method innovatively combines the focal mechanism inversion with the dynamic parameters of the crack through moment tensor decomposition, determines the crack rupture mode based on the value of the tension-shear angle α, and effectively solves the problem of misjudgment of complex cracks; introduces the stress shape factor, which reflects the relative size of the principal stresses σ1, σ2, and σ3 and the stress field distribution state, significantly reducing errors and achieving high-precision characterization of the non-uniform stress field.

[0105] This method innovatively combines focal mechanism solutions, stress field inversion, and three-dimensional fracture network modeling. It evaluates the effectiveness of hydraulic fracturing using multiple dimensions: the effective volume (SRV) of the rock formation, the stress shape factor (T), the fracture instability coefficient (I), and the fracture permeability (K). A comprehensive evaluation model for hydraulic fracturing fracture effects is constructed to quantitatively assess the effects, breaking through the limitations of traditional reliance on a single parameter, the effective volume (SRV), and improving evaluation accuracy.

[0106] This method uses a BP neural network and artificial intelligence optimization algorithm to establish a quantitative relationship model between fracturing parameters and stimulation effects. Parameter sensitivity analysis quickly identifies key control variables, and combined with numerical simulation, generates an optimal construction plan. This reduces redundant data processing steps, shortens analysis cycles, and reduces equipment deployment and manual intervention costs, significantly improving the overall benefits of unconventional oil and gas reservoir development.

[0107] This method integrates monitoring, evaluation, and regulation through a closed-loop system encompassing microseismic monitoring, fracture inversion, effect evaluation, and effect control. This system also allows for collaborative feedback between technologies. Compared to traditional unidirectional fracturing techniques, this method enables dynamic correction of the fracturing process, automatically optimizing parameters through real-time feedback, and significantly improving fracturing efficiency.

[0108] In one example of the present invention, in step S10, a microseismic monitoring system is deployed, fracturing fluid is injected, and real-time microseismic monitoring is performed to collect microseismic signals during the fracturing process, including the following steps:

[0109] S101: Based on the actual conditions of the key monitoring areas and mining spaces, select a reasonable number of microseismic sensors, install microseismic signal data acquisition instruments, and optimize the spatial layout of the microseismic sensors to determine the optimal microseismic network layout plan to ensure comprehensive monitoring of the target area;

[0110] S102: Drill a long hole into the rock formation in the key monitoring area and install the microseismic sensor at the bottom of the long hole. The drilling depth is several meters to several hundred meters.

[0111] S103: After the microseismic sensor is installed, the power supply, microseismic data acquisition instrument, GPS time synchronization signal and other subsystems are connected to form the entire microseismic monitoring system. After debugging and testing to ensure normal operation, the microseismic monitoring system is started to continuously collect rock fracture microseismic waveform data.

[0112] like Figure 2 As shown, a hole is drilled in the tunnel and the borehole enters the coal seam along the coal seam floor. A sliding composite drilling process is adopted, and directional drilling technology is used to control the drilling trajectory to extend along the coal seam. A sealer is lowered into the end of the mudstone layer to seal the hole. Single-component and three-component sensors S1-S8 are arranged in the tunnel in sequence for monitoring. A large amount of fracturing fluid is pressed into the coal seam through the drill hole. When the injection rate of the fracturing fluid is greater than the rate of coal seam filtration, the fluid pressure in the hole gradually increases. When the critical pressure of coal body rupture is reached, the coal body becomes unstable and cracks of a certain scale are formed around the drill hole. The sensors in the tunnel capture various microseismic data of this process in real time.

[0113] In one example of the present invention, Figure 3 As shown, in step S20, the fracture focal mechanism inversion is performed based on the microseismic signal data set to obtain the fracture rupture moment tensor, geometric parameters and fracture rupture mode in the rock layer space, including the following steps:

[0114] S211: Calculate the fracture characterization tensor: Fracture parameters are characterized by fracture source tensors The specific formula is as follows:

[0115] ,

[0116] Where, ij Characterize the crack source tensor No. i OK( i =1, 2, 3), No. j List( j =1, 2, 3) elements; b i 、 b j is the crack surface motion vector; n i 、 n j is the normal vector of the crack surface; A is the area of ​​newly generated active cracks;

[0117] S212: Solve the eigenvalues ​​of the crack characterization tensor and obtain the three eigenvalues ​​of the tensor:

[0118] ,

[0119] Where, 、 and Tensors the maximum, middle, and minimum eigenvalues ​​of ; b h 、 n h Subscript in h is a dummy symbol, which satisfies the Einstein summation convention, that is, ; is the motion vector of the moving crack surface b of L2 norm;

[0120] S213: Solving the geometric parameters of the fracture: In the generalized tensile shear rupture source model, the tensor The intermediate eigenvalue ψ2=0, the constraints must be satisfied in the model solution:

[0121] ,

[0122] Where, |b|ΔA is the rupture volume; n is the normal vector of the fault space; b is the motion vector; α is the shearing angle;

[0123] S214: Although n and b are interchangeable and cannot be uniquely determined, and their direction vectors e are also different, the angle between n and b is consistent, both 2α. Therefore, the value of α can be used to quantify the proportion of the crack tension-shear component and determine the crack type: according to the tension-shear angle αThe value of determines the crack rupture mode: α =0°, the crack is pure tensile fracture; when 0°<α<22.5°, the crack is mainly tensile fracture; when 22.5°≤ α When the angle is less than 45°, the crack is mainly shear fracture; when α =45°, the crack is pure shear fracture.

[0124] In one example of the present invention, Figure 4 As shown, in step S20, the principal stress direction and stress shape factor of the local stress field are inverted based on the above-mentioned crack parameters, including the following steps:

[0125] S221: Construct matrix based on crack rupture information G and vector s The extended form of P focal mechanism, expanded matrix G ={ G 1 , G 2 ,…, G p-1 , G p} and vector s ={ S 1 , S 2 ,…, S p-1 , S p}, where each submatrix G i , from the fault space normal vector n The component composition of

[0126] S222: Use Michael's linear inversion to solve the initial stress tensor, assuming that the stress tensor trace is zero, and the unknown components of the stress tensor t is a 5-dimensional vector, solved by generalized linear inversion:

[0127] ,

[0128] Where g is the acceleration due to gravity;

[0129] S223: Based on the first principal stress s 1 , the second principal stress s 2 and the third principal stress s 3 The size relationship of s 1 ≥ s2 ≥ s 3 , calculate the stress shape factor T :

[0130] ,

[0131] Where T∈[0,1] is used to characterize the shape of the stress ellipsoid;

[0132] S224: Scale the three principal stresses according to the stress shape factor, and substitute the scaled three principal stresses into the normal stress, principal stress, and shear stress relationship of any section in elastic mechanics. Finally, the following normal stress is obtained. , shear stress Calculation expression:

[0133] ,

[0134] Where, l 、 m , r is the direction cosine.

[0135] In one example of the present invention, in step S30, based on the focal mechanism solution parameters and combined with the geometric characteristics of the fractures, a discrete fracture network is constructed and divided into three-dimensional cubic grids to calculate the effective volume (SRV) of the rock formation transformation, including the following steps:

[0136] S311: Generate a three-dimensional fracture model using a discrete fracture network and generate randomly distributed fracture segments based on the fracture density λ;

[0137] S312: Divide the target area into a uniform cube grid, each cube index is ( i , j , x ), use the three-dimensional ray casting algorithm to determine whether the crack segment intersects with the cube. If the starting point of the crack segment ( x 1 , y 1 , z 1 ) to the end point( x 2 , y 2 , z 2 ) has an intersection with the cube surface, the cube is marked as "intersecting" and the cube bounding box is used for preliminary screening;

[0138] S313: Calculate the fracture cross-sectional area. Based on the fracture area, calculate the effective volume (SRV) of the rock formation by the integral method. The expression is:

[0139] ,

[0140] Where, is the porosity increment, is the initial porosity, Δk is the permeability increment; k 0 is the initial permeability; V The volume of the area affected by the fracturing;

[0141] S314: Based on crack strength P 32 Calculate the permeability enhancement scalar:

[0142] ,

[0143] Where, A i For the i The cross-sectional area of ​​the crack in the cube; K fs For effective stereoscopic visualization.

[0144] in, K fs ∈[0,1], the higher the value, the stronger the fracture conductivity. The discrete fracture parameters are interpolated to the regular grid to generate a continuous fracture field. fs Color the cube with values ​​to achieve 3D visualization of SRV.

[0145] In one example of the present invention, Figure 5 As shown, in step S30, an evaluation model for the transformation effect of fractured rock formations is established to quantitatively evaluate the effect of the fracture transformation effect of the rock formations, including the following steps:

[0146] S321: Determine the rock formation transformation effect based on the rock formation transformation effective volume SRV. When the rock formation transformation effective volume SRV is greater than or equal to or When the effective volume SRV of the rock formation is less than or When the reservoir is fractured, the effect of reservoir fracturing is considered to be poor;

[0147] S322: Based on stress shape factor T ,when T When it is close to 0, the principal stress s 1. s 2 is close, the stress field is in a biaxial compression state; when T = 0.5, the compressive stress axis, intermediate stress axis and tensile stress axis are relatively stable; when T When it is close to 1, the principal stress s 2. s3 is close, the stress field is in a uniaxial compression state; when the T value decreases, it indicates that the stress distribution after fracturing tends to biaxial compression, which effectively disperses stress concentration, reduces the risk of rupture, and the fracturing effect is better; when the T value increases: it indicates that the uniaxial compression effect is enhanced, fracturing may aggravate local stress concentration, increase the risk of mine earthquakes, and the fracturing effect is better;

[0148] S323: Definition of rupture instability coefficient based on Mohr-Coulomb failure criterion I , whose expression is:

[0149] ,

[0150] Where, s 、 t are the normal stress and shear stress of the fracture surface respectively; m is the rock friction coefficient;

[0151] When the rupture instability coefficient I =0, the fault zone is in the optimal bearing state; as the fracture instability coefficient I increases to the critical value of 1, the risk of rock mass instability shows a linear growth trend; among them, when the fracture instability coefficient I ≥ 0.9, it indicates that the stress field structure of the rock formation has deteriorated, and the probability of rock mass system instability has increased exponentially, which in turn leads to a significant increase in the probability of strong mine earthquakes and poor fracturing treatment effect; when the fracture instability coefficient I < 0.9, the fracture is stable and the fracturing treatment effect is good.

[0152] S324: Evaluation based on fracture permeability: Based on the preset fracture permeability formula, the fracture roughness coefficient corresponding to the rock formation confining pressure, the shear fracture surface, and the seepage simulation results, the fracture permeability k of the rock formation is determined:

[0153] ,

[0154] Where C is the cubic law correction coefficient, D is the fracture connectivity correction coefficient, K n is the crack normal stiffness of the shear crack surface, d h0 is the initial equivalent crack opening of the shear crack surface, s n is the confining pressure of the rock formation, J is the fracture roughness coefficient corresponding to the shear fracture surface;

[0155] The higher the fracture permeability, the faster the penetration rate, indicating that the rock formation fracturing transformation effect is better.

[0156] S325: A comprehensive evaluation model for volume effect fracturing is constructed to quantitatively evaluate the fracturing effect through the reservoir conductivity after fracturing. The expression of reservoir conductivity Q after fracturing is:

[0157] ,

[0158] Where S is the fracture tendency type score of fracturing stimulation; is the proportion of earthquake sources with rupture instability coefficient I ≥ 0.9; is the effective volume (m³); is the principal stress; is the stress-direction coupling coefficient; The crack extension direction.

[0159] In one example of the present invention, in step S40, the fracturing parameters are optimized based on the stress field inversion, including the following steps:

[0160] S411: constructing an integrated fracturing numerical simulation model based on the stress parameters and microseismic data of the rock formation, and performing parameter correction on the integrated fracturing numerical simulation model using the stress field inversion result;

[0161] S412: Input a combination of fracturing parameters to be tested, and generate a corresponding rock formation stimulation effective volume (SRV) according to the revised integrated fracturing numerical simulation model;

[0162] S413: Establish a dual-objective optimization mathematical model with the rock formation transformation effective volume SRV and the fracture instability coefficient I as the targets, and obtain the optimal parameters of the dual-objective optimization mathematical model, wherein the optimal fracturing operation parameters of the dual-objective optimization mathematical model are The expression is:

[0163] ,

[0164] Where, u is a set of optimization variables; U Represents the space of optimization variables that can be selected; w 1 and w 2 All are weight coefficients;

[0165] S414: The obtained rock formation transformation effective volume SRV is input into a dual-objective optimization mathematical model with optimal parameters, and optimal fracturing parameters are output.

[0166] In one example of the present invention, in step S40, the fracturing direction is adjusted so that the cracks extend along the principal stress direction, a fracturing effect control model is established, the relationship between the fracturing effect and the controllable injection parameters is obtained, and the parameter variables that have the greatest impact on the fracturing effect are obtained for selective control, including the following steps:

[0167] S421: Determine the fracturing direction according to the principal stress direction in step S20 iUnder the action of triaxial stress, most hydraulic fractures extend in the direction parallel or approximately parallel to the maximum principal stress and perpendicular to the minimum principal stress. i The expression is:

[0168] ;

[0169] S422: With the rock formation transformation effective volume SRV and the fracturing effect evaluation level as input data and the controllable injection parameters as output data, the data is normalized. The expression is:

[0170] ,

[0171] Where, is the normalized variable; is the actual value; and Variables The maximum and minimum values ​​of ;

[0172] Determine the network input layer and calculate the hidden layer output And predict the output layer :

[0173] The number of layer nodes, , , is the hidden layer transfer function, and the transfer function is ;

[0174] Determine the overall network error O, which is expressed as:

[0175] ,

[0176] Where, P is the actual output of the network; P’ is the expected output;

[0177] Determine whether the overall error meets the requirements. If not, recalculate the hidden layer output and use it to train the BP neural network to obtain the relationship between the fracturing effect evaluation level and the controllable injection parameter X;

[0178] S423: Through sensitivity analysis, the parameter variables that have the greatest impact on the fracturing effect are obtained for selective regulation. A BP neural network model is established for the fracturing effect evaluation level based on the effective volume (SRV) of the rock formation, the comprehensive indicator monitoring parameter (F), and the controllable injection parameter (X). A parameter in the controllable injection parameter (X) is selected to be increased or decreased within a certain range to obtain the parameter that causes a significant change in the fracturing effect evaluation level.

[0179] In one example of the present invention, Figure 6As shown, step S50 specifically includes the following steps:

[0180] S501: Within the required assessment period, using the assessment subunits as units, stratum reformation effective volume (SRV), fracture permeability, and fracture instability coefficient are classified into three levels, with scores of 3, 2, and 1, respectively, from strong to weak, according to the actual corresponding conditions. The stress shape factor is divided into two levels, with strong assigned a value of 3 and weak assigned a value of 2. As more monitoring and assessment data is collected and combined with actual geological conditions, the grade assessment and assigned scores will be further refined and adjusted.

[0181] S502: Based on the evaluation of the fracturing effect, a score between 5 and 12 is assigned, and the fracturing treatment plan is formulated accordingly. When the evaluation value is 11 to 12, the rock formation treatment effect is good and no treatment is required. When the evaluation value is 8 to 10, the rock formation treatment effect is moderate, and the key injection parameters are adjusted. When the evaluation value is 5 to 7, the rock formation treatment effect is poor, and the injection parameters are adjusted and the fracturing direction is changed.

[0182] S503: Continue to monitor the fracturing process, complete the re-evaluation of the fracturing transformation effect, continuously improve the fracturing effect transformation target, adjust the injection parameters, and continuously improve the fracturing transformation level until the fracturing effect is optimized. Build an integrated monitoring-evaluation-control collaborative transformation system to achieve the organic integration of different links of monitoring, evaluation, and control, and the collaborative feedback between technologies.

[0183] According to the second aspect of the present invention, a rock formation fracturing monitoring, evaluation, and control integrated collaborative transformation system includes:

[0184] A microseismic monitoring module is configured to detect geological information of rock formations, analyze and determine target rock formations for fracturing, deploy a microseismic monitoring system in the rock formations, inject fracturing fluid into the rock formations, and use the microseismic monitoring system to monitor microseisms in real time and collect microseismic signal data during the fracturing process;

[0185] a signal processing module configured to perform focal mechanism inversion based on microseismic signal data, obtain fracture moment tensors, geometric parameters, and fracture rupture patterns of the rock formation, and invert principal stress directions and stress shape factors of the local stress field based on the fracture parameters;

[0186] The effect evaluation module is configured to construct a discrete fracture network and divide it into three-dimensional cube grids based on the parameters of the focal mechanism solution and the geometric characteristics of the fractures, calculate the effective volume (SRV) of the rock formation transformation, establish an evaluation model for the fractured rock formation transformation effect, and quantitatively evaluate the rock formation fracturing transformation effect;

[0187] The effect control module is configured to optimize the fracturing parameters based on stress field inversion, adjust the fracturing direction so that the cracks extend along the principal stress direction, establish a fracturing effect control model, obtain the relationship between the fracturing effect and the controllable injection parameters, and obtain the parameter variables that have the greatest impact on the fracturing effect for selective control;

[0188] The integrated monitoring-evaluation-control module is configured to obtain fracturing effect evaluation through process monitoring while providing enhanced control solutions, building an integrated monitoring-evaluation-control collaborative transformation system until the target or fracturing effect is achieved, realizing the organic integration of different links of monitoring, evaluation, and control and the coordinated feedback between technologies.

[0189] Through moment tensor decomposition, the system innovatively combines focal mechanism inversion with crack dynamic parameters, determines the crack rupture mode based on the value of the tension-shear angle α, and effectively solves the problem of misjudgment of complex cracks; introduces stress shape factors to reflect the relative size of the principal stresses σ1, σ2, and σ3 and the stress field distribution state, significantly reducing errors and achieving high-precision characterization of non-uniform stress fields.

[0190] This system innovatively combines focal mechanism solutions, stress field inversion, and three-dimensional fracture network modeling. It evaluates the effectiveness of hydraulic fracturing using multiple dimensions: the effective volume (SRV) of the rock formation, the stress shape factor (T), the fracture instability coefficient (I), and the fracture permeability (K). A comprehensive evaluation model for hydraulic fracturing fracture effects is constructed to quantitatively assess the effects, breaking through the traditional reliance on a single parameter, the effective volume (SRV), and improving evaluation accuracy.

[0191] This system uses a BP neural network and artificial intelligence optimization algorithm to establish a quantitative relationship model between fracturing parameters and stimulation effects. Through parameter sensitivity analysis, key control variables are quickly identified, and numerical simulation is combined to generate an optimal construction plan. This reduces redundant data processing steps, shortens analysis cycles, and reduces equipment deployment and manual intervention costs, significantly improving the overall benefits of unconventional oil and gas reservoir development.

[0192] This system, through a closed-loop system of microseismic monitoring, fracture inversion, effect evaluation, and effect control, organically integrates monitoring, evaluation, and control, and provides collaborative feedback between technologies. Compared to traditional unidirectional fracturing techniques, this method enables dynamic correction of the fracturing process, automatically optimizes parameters through a real-time feedback mechanism, and significantly improves fracturing efficiency.

[0193] In one example of the present invention, the effect control module includes:

[0194] a parameter correction unit configured to construct a hydraulic fracturing integrated numerical simulation model based on the stress parameters of the rock formation and microseismic data, and perform parameter correction on the hydraulic fracturing integrated numerical simulation model using a stress field inversion result;

[0195] A volume transformation unit is configured to input a combination of fracturing parameters to be tested and generate a corresponding rock formation transformation effective volume SRV according to the modified integrated fracturing numerical simulation model;

[0196] The parameter acquisition unit is configured to establish a dual-objective optimization mathematical model with the rock formation transformation effective volume SRV and the fracture instability coefficient I as the target, and obtain the optimal parameters of the dual-objective optimization mathematical model, wherein the optimal fracturing operation parameters of the dual-objective optimization mathematical model are The expression is:

[0197] ,

[0198] Where, u is a set of optimization variables; U Represents the space of optimization variables that can be selected; w 1 and w 2 All are weight coefficients;

[0199] The parameter output unit is configured to input the obtained rock formation transformation effective volume SRV into a dual-objective optimization mathematical model with optimal parameters, and output optimal fracturing parameters.

[0200] It should be noted that the integrated collaborative transformation system for monitoring, evaluating and controlling rock fracturing of the present invention can also perform any processing in the integrated collaborative transformation method for monitoring, evaluating and controlling rock fracturing described previously, and the specific details are not repeated here.

[0201] The exemplary implementation scheme of the integrated collaborative transformation method and system for rock fracturing monitoring, evaluation and control proposed in the present invention is described in detail above with reference to the preferred embodiments. However, it can be understood by those skilled in the art that, without departing from the concept of the present invention, various modifications and variations can be made to the above-mentioned specific embodiments, and various technical features and structures proposed in the present invention can be combined in various ways without exceeding the scope of protection of the present invention, which is determined by the appended claims.

Claims

1. A rock formation fracturing monitoring-evaluation-control integrated collaborative transformation method, characterized in that: The steps include: S10: Exploring geological information of the rock formation, analyzing and determining the target rock formation for fracturing, deploying a microseismic monitoring system in the rock formation, injecting fracturing fluid into the rock formation, and using the microseismic monitoring system to monitor microseisms in real time and collect microseismic signal data during the fracturing process; S20: Perform focal mechanism inversion based on microseismic signal data to obtain the fracture moment tensor, geometric parameters, and fracture mode of the rock formation, and invert the principal stress direction and stress shape factor of the local stress field based on the above fracture parameters; S30: Based on the focal mechanism solution parameters and the geometric characteristics of the fractures, a discrete fracture network is constructed and divided into three-dimensional cube grids. The effective volume (SRV) of the rock formation transformation is calculated, and an evaluation model for the transformation effect of fractured rock formations is established to quantitatively evaluate the effect of rock formation hydraulic fracturing. S40: Optimizing the fracturing parameters based on stress field inversion, adjusting the fracturing direction so that the cracks extend along the principal stress direction, establishing a fracturing effect control model, obtaining the relationship between the fracturing effect and the controllable injection parameters, and obtaining the parameter variables that have the greatest impact on the fracturing effect for selective control; wherein, optimizing the fracturing parameters based on stress field inversion includes the following steps: S411: constructing an integrated fracturing numerical simulation model based on the stress parameters and microseismic data of the rock formation, and performing parameter correction on the integrated fracturing numerical simulation model using the stress field inversion result; S412: Input a combination of fracturing parameters to be tested, and generate a corresponding rock formation stimulation effective volume (SRV) according to the revised integrated fracturing numerical simulation model; S413: Establish a dual-objective optimization mathematical model with the rock formation transformation effective volume SRV and the fracture instability coefficient I as the targets, and obtain the optimal parameters of the dual-objective optimization mathematical model, wherein the optimal fracturing operation parameters of the dual-objective optimization mathematical model are The expression is: ， Where, u is a set of optimization variables; U Represents the space of optimization variables that can be selected; w 1 and w 2 All are weight coefficients; S414: Inputting the obtained rock formation transformation effective volume SRV into a dual-objective optimization mathematical model with optimal parameters to output optimal fracturing parameters; S50: While obtaining the evaluation of the fracturing effect through process monitoring, a plan for enhanced regulation is given, and an integrated monitoring-evaluation-regulation collaborative transformation system is constructed until the target or the optimization of the fracturing effect is achieved, realizing the organic integration of different links of monitoring, evaluation, and regulation and the collaborative feedback between technologies.

2. The integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to claim 1, characterized in that: In step S20, fracture focal mechanism inversion is performed based on the microseismic signal data set to obtain fracture moment tensors, geometric parameters, and fracture rupture modes in the rock layer space, including the following steps: S211: Calculate the fracture characterization tensor: Fracture parameters are characterized by fracture source tensors The specific formula is as follows: ， Where, ij Characterize the crack source tensor No. i OK( i =1, 2, 3), No. j List( j =1, 2, 3) elements; b i 、 b j is the crack surface motion vector; n i 、 n j is the normal vector of the crack surface; ΔA is the area of ​​newly generated active cracks; S212: Solve the eigenvalues ​​of the crack characterization tensor and obtain the three eigenvalues ​​of the tensor: ， Where, 、 and Tensors the maximum, middle, and minimum eigenvalues ​​of ; b h 、 n h Subscript in h is a dummy symbol, which satisfies the Einstein summation convention, that is, ; is the motion vector of the dynamic crack surface b of L2 norm; S213: Solving the geometric parameters of the fracture: In the generalized tensile shear rupture source model, the tensor The intermediate eigenvalue ψ2=0, the constraints must be satisfied in the model solution: ， Where, |b|ΔA is the rupture volume; n is the normal vector of the fault space; b is the motion vector; α is the shearing angle; S214: According to the tension and shear angle α The value of determines the crack rupture mode: α =0°, the crack is pure tensile fracture; when 0°<α<22.5°, the crack is mainly tensile fracture; when 22.5°≤ α When the angle is less than 45°, the crack is mainly shear fracture; when α =45°, the crack is pure shear fracture.

3. The integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to claim 1, characterized in that: In step S20, the principal stress direction and stress shape factor of the local stress field are inverted based on the above-mentioned crack parameters, including the following steps: S221: Construct matrix based on crack rupture information G and vector s The extended form of P focal mechanisms, expanded matrices G ={ G 1 , G 2 ,…, G p-1 , G p } and vector s ={ S 1 , S 2 ,…, S p-1 , S p }, where each submatrix G i , from the fault space normal vector n The component composition of S222: Use Michael's linear inversion to solve the initial stress tensor, assuming that the stress tensor trace is zero, and the unknown components of the stress tensor t is a 5-dimensional vector, solved by generalized linear inversion: ， Where g is the acceleration due to gravity; S223: Based on the first principal stress σ 1 , the second principal stress σ 2 and the third principal stress σ 3 The size relationship of σ 1 ≥ σ 2 ≥ σ 3 , calculate the stress shape factor T : ， Where T∈[0,1] is used to characterize the shape of the stress ellipsoid; S224: Scale the three principal stresses according to the stress shape factor, and substitute the scaled three principal stresses into the normal stress, principal stress, and shear stress relationship of any section in elastic mechanics. Finally, the following normal stress is obtained. , shear stress Calculation expression: ， Where, l 、 m , r is the direction cosine.

4. The integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to claim 1, characterized in that: In step S30, based on the focal mechanism solution parameters and the geometric characteristics of the fractures, a discrete fracture network is constructed and divided into three-dimensional cubic grids to calculate the effective volume (SRV) of the rock formation. The steps include: S311: Generate a three-dimensional fracture model using a discrete fracture network and generate randomly distributed fracture segments based on the fracture density λ; S312: Divide the target area into a uniform cube grid, each cube index is ( i , j , ξ ), use the three-dimensional ray casting algorithm to determine whether the crack segment intersects with the cube. If the starting point of the crack segment ( x 1 , y 1 , z 1 ) to the end point( x 2 , y 2 , z 2 ) has an intersection with the cube surface, the cube is marked as "intersecting" and the cube bounding box is used for preliminary screening; S313: Calculate the fracture cross-sectional area. Based on the fracture area, calculate the effective volume (SRV) of the rock formation by the integral method. The expression is: ， Where, is the porosity increment, is the initial porosity, Δk is the permeability increment; k 0 is the initial permeability; V The volume of the area affected by the fracturing; S314: Based on crack strength P 32 Calculate the permeability enhancement scalar: ， Where, A i For the i The cross-sectional area of ​​the crack in the cube; K fs For effective stereoscopic visualization.

5. The integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to claim 1, characterized in that: In step S30, an evaluation model for the fractured rock formation transformation effect is established to quantitatively evaluate the fractured rock formation transformation effect, including the following steps: S321: Determine the rock formation transformation effect based on the rock formation transformation effective volume SRV. When the rock formation transformation effective volume SRV is greater than or equal to η When the effective volume SRV of the rock formation is less than η When the reservoir is fractured, the effect of reservoir fracturing is considered to be poor; S322: Based on stress shape factor T ,when T When it is close to 0, the principal stress σ 1. σ 2 is close, the stress field is in a biaxial compression state; when T = 0.5, the compressive stress axis, intermediate stress axis and tensile stress axis are relatively stable; when T When it is close to 1, the principal stress σ 2. σ 3 is close, the stress field is in uniaxial compression state; S323: Definition of rupture instability coefficient based on Mohr-Coulomb failure criterion I , whose expression is: ， Where, σ 、 τ are the normal stress and shear stress of the fracture surface respectively; μ is the rock friction coefficient; When the rupture instability coefficient I =0, the fault zone is in the optimal bearing state; as the fracture instability coefficient I increases to the critical value of 1, the risk of rock mass instability shows a linear growth trend; among them, when the fracture instability coefficient I ≥ 0.9, it indicates that the stress field structure of the rock formation has deteriorated, and the probability of rock mass system instability has increased exponentially, which in turn leads to a significant increase in the probability of strong mine earthquakes and poor fracturing treatment effect; when the fracture instability coefficient I < 0.9, the fracture is stable and the fracturing treatment effect is good. S324: Evaluation based on fracture permeability: Based on the preset fracture permeability formula, the fracture roughness coefficient corresponding to the rock formation confining pressure, the shear fracture surface, and the seepage simulation results, the fracture permeability k of the rock formation is determined: ， Where C is the cubic law correction coefficient, D is the fracture connectivity correction coefficient, K n is the crack normal stiffness of the shear crack surface, d h0 is the initial equivalent crack opening of the shear crack surface, σ n is the confining pressure of the rock formation, J is the fracture roughness coefficient corresponding to the shear fracture surface; S325: A comprehensive evaluation model for volume effect fracturing is constructed to quantitatively evaluate the fracturing effect through the reservoir conductivity after fracturing. The expression of reservoir conductivity Q after fracturing is: ， Where S is the fracture tendency type score of fracturing stimulation; is the proportion of earthquake sources with rupture instability coefficient I ≥ 0.9; is the effective volume; is the principal stress; is the stress-direction coupling coefficient; The crack extension direction.

6. The integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to claim 1, characterized in that: In step S40, the fracturing direction is adjusted so that the cracks extend along the principal stress direction, a fracturing effect control model is established, the relationship between the fracturing effect and the controllable injection parameters is obtained, and the parameter variables that have the greatest impact on the fracturing effect are obtained for selective control, including the following steps: S421: Determine the fracturing direction according to the principal stress direction in step S20 θ ,Under the action of triaxial stress, most hydraulic fractures extend along the direction parallel or approximately parallel to the maximum principal stress, and perpendicular to the minimum principal stress; S422: Using the rock formation transformation effective volume SRV and the fracturing effect evaluation level as input data and the controllable injection parameters as output data, the data is normalized to determine the network input layer and calculate the hidden layer output. And predict the output layer , determine the overall error of the network, and judge whether the overall error meets the requirements. If not, recalculate the hidden layer output to train the BP neural network and obtain the relationship between the fracturing effect evaluation level and the controllable injection parameter X; S423: Through sensitivity analysis, the parameter variables that have the greatest impact on the fracturing effect are obtained for selective regulation. A BP neural network model is established for the fracturing effect evaluation level based on the effective volume (SRV) of the rock formation, the comprehensive indicator monitoring parameter (F), and the controllable injection parameter (X). A parameter in the controllable injection parameter (X) is selected to be increased or decreased within a certain range to obtain the parameter that causes a significant change in the fracturing effect evaluation level.

7. The integrated collaborative transformation method for rock formation fracturing monitoring, evaluation and control according to claim 1, characterized in that: The step S50 specifically includes the following steps: S501: Within the required assessment period, using the assessment subunits as units, classify the rock formation transformation effective volume (SRV), fracture permeability, and fracture instability coefficient into three levels according to the actual corresponding conditions, from strong to weak, and assign them 3, 2, and 1 points from strong to weak; The stress shape factor is divided into two levels, with a strong value of 3 and a weak value of 2. As more monitoring and evaluation data is collected and combined with actual geological conditions, the grade assessment and assigned scores will be further refined and adjusted. S502: Based on the evaluation of the fracturing effect, a score between 5 and 12 is assigned, and the fracturing treatment plan is formulated accordingly. When the evaluation value is 11 to 12, the rock formation treatment effect is good and no treatment is required. When the evaluation value is 8 to 10, the rock formation treatment effect is moderate, and the key injection parameters are adjusted. When the evaluation value is 5 to 7, the rock formation treatment effect is poor, and the injection parameters are adjusted and the fracturing direction is changed. S503: Continue to monitor the fracturing process, complete the re-evaluation of the fracturing transformation effect, continuously improve the fracturing effect transformation target, adjust the injection parameters, and continuously improve the fracturing transformation level until the fracturing effect is optimized. Build an integrated monitoring-evaluation-control collaborative transformation system to achieve the organic integration of different links of monitoring, evaluation, and control, and the collaborative feedback between technologies.

8. A rock formation fracturing monitoring, evaluation and control integrated collaborative transformation system, characterized in that: include: A microseismic monitoring module is configured to detect geological information of rock formations, analyze and determine target rock formations for fracturing, deploy a microseismic monitoring system in the rock formations, inject fracturing fluid into the rock formations, and use the microseismic monitoring system to monitor microseisms in real time and collect microseismic signal data during the fracturing process; a signal processing module configured to perform focal mechanism inversion based on microseismic signal data, obtain fracture moment tensors, geometric parameters, and fracture rupture patterns of the rock formation, and invert principal stress directions and stress shape factors of the local stress field based on the fracture parameters; The effect evaluation module is configured to construct a discrete fracture network and divide it into three-dimensional cube grids based on the parameters of the focal mechanism solution and the geometric characteristics of the fractures, calculate the effective volume (SRV) of the rock formation transformation, establish an evaluation model for the fractured rock formation transformation effect, and quantitatively evaluate the rock formation fracturing transformation effect; The effect control module is configured to optimize the fracturing parameters based on stress field inversion, adjust the fracturing direction so that the cracks extend along the principal stress direction, establish a fracturing effect control model, obtain the relationship between the fracturing effect and the controllable injection parameters, and obtain the parameter variables that have the greatest impact on the fracturing effect for selective control; wherein, the effect control module includes: a parameter correction unit configured to construct a hydraulic fracturing integrated numerical simulation model based on the stress parameters of the rock formation and microseismic data, and perform parameter correction on the hydraulic fracturing integrated numerical simulation model using a stress field inversion result; A volume transformation unit is configured to input a combination of fracturing parameters to be tested and generate a corresponding rock formation transformation effective volume SRV according to the modified integrated fracturing numerical simulation model; The parameter acquisition unit is configured to establish a dual-objective optimization mathematical model with the rock formation transformation effective volume SRV and the fracture instability coefficient I as the target, and obtain the optimal parameters of the dual-objective optimization mathematical model, wherein the optimal fracturing operation parameters of the dual-objective optimization mathematical model are The expression is: ， Where, u is a set of optimization variables; U Represents the space of optimization variables that can be selected; w 1 and w 2 All are weight coefficients; a parameter output unit configured to input the obtained rock formation reformation effective volume SRV into a dual-objective optimization mathematical model with optimal parameters, and output optimal fracturing parameters; The integrated monitoring-evaluation-control module is configured to obtain fracturing effect evaluation through process monitoring while providing enhanced control solutions, building an integrated monitoring-evaluation-control collaborative transformation system until the target or fracturing effect is achieved, realizing the organic integration of different links of monitoring, evaluation, and control and the coordinated feedback between technologies.

Images