A shale gas fracturing fracture geometry inversion method and device fusing microseism and production dynamics, equipment and storage medium

Abstract

The present application provides a kind of shale gas fracturing fracture geometry inversion method, device, equipment and storage medium of fusion microseism and production dynamics, it is related to shale gas technical field of oil and gas field exploration and development, the inversion method includes: establishing multistage multi-parameter fracturing fracture mixed fractal model;Parameterization is carried out to fracturing fracture model;Based on parameterized fracturing fracture model and microseismic data, microseismic observation equation is established;Based on parameterized fracturing fracture model and fracture flow mechanism, production dynamic observation equation is established;Establishes the double-sided regularization fracturing fracture inversion model of microseismic data and production dynamic data joint driving;Alternating iterative solution double-sided regularization fracturing fracture inversion model.The present application uses the way of microseismic data and production dynamic data to constrain fracture parameters simultaneously to carry out inversion to the geometry of fracturing fracture, and the accuracy is high.

Description

Technical Field

[0001] This invention relates to the field of shale gas technology in oil and gas field exploration and development, specifically to a method for inverting the geometric morphology of shale gas fracturing fractures by integrating microseismic data and production dynamics. Background Technology

[0002] For the inversion of shale gas fracturing fracture geometry, although traditional microseismic monitoring is an important method for studying shale gas fracturing fractures, it can usually only predict the approximate area of ​​the fractures, but cannot provide a precise answer to the fracture geometry. Therefore, it is necessary to combine other methods and technologies to improve the solution effect of shale gas fracturing fracture geometry.

[0003] For example, in Chinese patent publication number CN111175817B, published on December 22, 2020, entitled "An Invention Patent for a Microseismic Data-Assisted Method for Inverting Fracture Distribution in Tight Oil and Gas Reservoirs," the invention employs Hough transform to transform microseismic data into Hough space, obtaining Hough space functions to form the initial mean of the Hough space random field; it uses inverse Hough transform to generate samples of fracture distribution in physical space; it uses numerical simulation to predict the production forecast data corresponding to the samples of fracture distribution in physical space; it uses algebraic statistics to obtain the correlation matrix between the Hough space random field and the production forecast data; and it uses the correlation matrix to maximize the posterior probability of the Hough space random field using an iterative algorithm based on the sample set, thus forming a fracture distribution inversion method.

[0004] The invention patent with publication number CN111175817B uses microseismic data to assist in the inversion of fracture distribution in tight oil and gas reservoirs. However, due to the limited availability of observation data, the solution effect of the inversion method is limited.

[0005] With the development of applied mathematics, regularized inversion techniques have been widely used in petroleum engineering. Regularized fracture inversion methods driven by microseismic data can effectively represent the physical geometry of hydraulic fractures, but they struggle to describe their internal properties. Regularized fracture inversion methods driven by production dynamic data can effectively represent the seepage capacity of hydraulic fractures, but they are difficult to describe the distribution characteristics of these fractures.

[0006] Due to the limited availability of observational data, the traditional one-sided regularized crack inversion method has limited effectiveness, is susceptible to noise interference, and has low accuracy in the inversion results. Summary of the Invention

[0007] To address the shortcomings of the existing technologies, this invention provides a method, apparatus, equipment, and storage medium for inverting the geometric morphology of shale gas fracturing fractures by integrating microseismic data and production dynamics. The purpose of this invention is to solve the problems in the existing technologies, such as limited solution effects, susceptibility to noise interference, and low accuracy of traditional one-sided regularized fracture inversion methods due to the limited nature of observation data.

[0008] This invention is achieved through the following technical solution:

[0009] The first aspect of this invention provides a method for inverting the geometry of shale gas fracturing fractures by integrating microseismic data and production dynamics, comprising the following steps:

[0010] Step 1: Obtain the fracture classification length l, fracture classification width w, fracture classification height h, and fracture bifurcation angle of the target area or well section. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The distribution of hierarchical adaptive height p(h), the actual development direction of the crack θ, the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p ) and fracture observation data of microseismic events in the target area or well section g i Crack observation data f of production data j ;

[0011] Step 2: Based on the crack classification length l, crack classification width w, crack classification height h, and crack length variation factor α from Step 1... l Crack width variation factor α w Crack height variation factor α h The main development direction of the crack is θ0, and the actual deviation angle of crack development is q(θ). p A multi-level, multi-parameter hybrid fractal model of hydraulic fracturing fractures was established based on fractal theory.

[0012] Step 3: Parameterize the multi-level, multi-parameter fractal model of hydraulic fracture in Step 2 to obtain the parameterized fractal model of hydraulic fracture F(X);

[0013] Step 4: Based on the parametric fractal model F(X) of hydraulic fractals and the fracture observation data g based on microseismic events. i Establish the microseismic observation equations for the cracks, and then establish a regularized inversion model based on the microseismic observation equations;

[0014] Step 5: Based on the parametric fractal model of hydraulic fracturing fractures and the fracture observation data based on production data f jEstablish the production data observation equation for cracks, and establish a regularized inversion model based on the production data observation equation;

[0015] Step 6: Based on the regularized inversion model in Step 4 and the regularized inversion model in Step 5, introduce regularized functional representation to establish a bilateral regularized fracturing fracture inversion model jointly driven by microseismic data and production dynamic data.

[0016] Step 7: Solve the bilateral regularized fracturing fracture inversion model.

[0017] Furthermore, in step 2, in establishing a multi-level, multi-parameter hydraulic fractal model, the maximum number of layers n in the fractal tree model is set; the primary fracture length l0, width w0, height h0, main fracture development direction θ0, and actual fracture development deviation angle distribution q(θ) are defined. p Define the crack bifurcation angle. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h And the hierarchical adaptive height distribution p(h);

[0018] Furthermore, the degree of deviation of the actual fracture development direction θ from the main fracture development direction θ0 is θ p Follows Fisher distribution: Where K is Fisher's constant, used to control the shape of the distribution, which can be set in advance based on experience; the distribution probability P is calculated based on the pre-set distribution probability. The actual direction of crack development is θ = θ0 + (-1). m θ p Where m is a random positive integer, and α is the crack length variation factor. l Crack width variation factor α w Crack height variation factor α h Defined as:

[0019]

[0020] Among them l j+1 and l j w represents the length of crack level j+1 and crack level j. j+1 and w j This represents the width of crack level j+1 and the width of crack level j. and This represents the average height of cracks at level j+1 and level j, with h representing the height of each crack level. j Follows distribution Where σ is the standard deviation, which can be set in advance according to the actual situation.

[0021] Furthermore, in step 3, the hybrid fractal model of the hydraulic fractal is parameterized, specifically by the fracture bifurcation angle. Crack classification length l, crack classification width w, crack classification height h, crack length variation factor α l Crack width variation factor α w Crack height variation factor α h By constructing the parameter variable X, we obtain the parameterized hybrid fractal model F(X) of the fractal fracture:

[0022]

[0023] Where l represents the crack grading length [l1, l2, ..., l] n ], w represents the crack grading width [w1, w2, ..., w n ], h represents the crack grading height [h1, h2, ..., h n ], α l Represents the crack length variation factor, α w Represents the crack width variation factor, α h Indicates the crack height variation factor, Indicates the angle at which the crack bifurcates.

[0024] Furthermore, in step 4, the parametric fractal model F(X) of the hydraulic fractal and the fracture observation data g of the microseismic events are used. i i = 1, 2, ..., N g Establish the microseismic observation equations for the cracks:

[0025] G(F(X))=[g i ],

[0026] G represents the microseismic observation operator for fractures; a regularized inversion model can be established based on this equation:

[0027]

[0028] Where λ1 represents the regularization coefficient, and R1(X) represents the characteristic function used for L2 regularization. By default, R1(X) = X.

[0029] Furthermore, we introduce a functional representation:

[0030]

[0031] The iterative formula is obtained using nonlinear optimization and gradient descent. Where k is the number of iterations, η1 is the learning rate, and X (k) This represents the result of the k-th calculation. This represents the gradient operator with respect to X.

[0032] Furthermore, in step 5, a production model of the fracture flow mechanism is introduced based on the parameterized fractal model F(X) of the hydraulic fractal. and production observation data f j j = 1, 2, ..., N f Establish the production data observation equation for cracks:

[0033] M(t,F(X),c)=[f j ],

[0034] M represents the fracture production observation operator, t represents the time when the production observation data is observed, and c represents the characteristic parameters related to the region or well section. The characteristic parameters are fracture classification length l, fracture classification width w, fracture classification height h, and fracture bifurcation angle. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The hierarchical adaptive height distribution p(h), the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p A regularized inversion model can be established based on this equation:

[0035]

[0036] Where t j λ represents the time when the j-th production observation data is observed, λ2 represents the regularization coefficient, and R2(X) represents the characteristic function used for L2 regularization. The default value is R2(X) = X.

[0037] Furthermore, we introduce a functional representation:

[0038]

[0039] The iterative formula is obtained using nonlinear optimization and gradient descent. Where k is the number of iterations, η² is the learning rate, and X... (k) This represents the result of the k-th calculation. This represents the gradient operator with respect to X.

[0040] Furthermore, in step 6, a bilateral regularized fracturing fracture inversion model jointly driven by microseismic data and production dynamic data is established based on a regularized functional:

[0041]

[0042] Furthermore, by combining the fracture parameters in the parameterized fractal model of hydraulic fracturing fractures in step 3, a more detailed inversion model can be derived:

[0043]

[0044] Furthermore, the specific process of solving the bilateral regularized fracturing fracture inversion model in step 7 is as follows:

[0045] Introducing the block representation notation X = [X1, X2], let X2=[w,α w Given iteration error thresholds ε1 and ε2, set the initial value X1. (0) and X2 (0) Using the regularized forms R1(X) and R2(X), the parameters X1 and X2 in the regularized iterative inversion formula are updated alternately as follows:

[0046]

[0047]

[0048] When ||X1 (k+1) -X1 (k) ||<ε1 and||X2 (k+1) -X2 (k) When ||<ε2, the iteration ends and X is output. Here X1 (k) X2 (k) This represents the result of the k-th iteration.

[0049] A second aspect of the present invention provides a shale gas fracturing fracture geometry inversion device that integrates microseismic data and production dynamics, comprising:

[0050] The first module is used to obtain the fracture classification length l, fracture classification width w, fracture classification height w, and fracture bifurcation angle of the target area or well section. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The distribution of hierarchical adaptive height p(h), the actual development direction of the crack θ, the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p ) and fracture observation data of microseismic events in the target area or well section g i Crack observation data f of production data j ;

[0051] The second module uses the crack classification length l, crack classification width w, crack classification height h, and crack length variation factor α obtained in the first module. l Crack width variation factor α w Crack height variation factor α h The main development direction of the crack is θ0, and the actual deviation angle of crack development is q(θ).p Based on fractal theory, a multi-level multi-parameter fractal model of hydraulic fracturing fractures was established, and the multi-level multi-parameter fractal model of hydraulic fracturing fractures was parameterized to obtain the parameterized fractal model of hydraulic fracturing fractures F(X).

[0052] The third module establishes microseismic observation equations based on the fracture observation data of microseismic events obtained from the first module and the parametric fractal model F(X) of the hydraulic fracturing fracture in the second module, and establishes a regularized inverse model based on the microseismic observation equations; it also establishes production data observation equations based on the fracture observation data of production data obtained from the first module and the parametric fractal model F(X) of the hydraulic fracturing fracture in the second module, and establishes a regularized inverse model based on the production data observation equations; and finally, through the two regularized inverse models, a bilateral regularized hydraulic fracturing fracture inversion model jointly driven by microseismic data and production dynamic data is established based on a regularized functional.

[0053] The fourth module solves the bilateral regularized fracturing fracture inversion model established in the third module.

[0054] A third aspect of the present invention provides a computer device including a processor, an input device, an output device, and a memory, wherein the processor, the input device, the output device, and the memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to perform some or all of the steps as described in the first aspect of the present invention.

[0055] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform some or all of the steps described in the first aspect of the present invention.

[0056] The beneficial effects of this invention are as follows:

[0057] This invention integrates microseismic and production data to invert the geometry of shale gas fracturing fractures; it uses a two-sided regularization method to solve the model, which improves the accuracy of the inversion results of shale gas fracturing fracture geometry; and the invention has strong generalization ability and broad application prospects. Attached Figure Description

[0058] Figure 1 This is a flowchart of the present invention;

[0059] Figure 2 This is a model diagram of an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Example 1

[0062] like Figures 1-2 As shown, the first aspect of the present invention provides a method for inverting the geometry of shale gas fracturing fractures by integrating microseismic data and production dynamics, comprising the following steps:

[0063] Step 1: Obtain the fracture classification length l, fracture classification width w, fracture classification height h, and fracture bifurcation angle of the target area or well section. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The distribution of hierarchical adaptive height p(h), the actual development direction of the crack θ, the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p ) and fracture observation data of microseismic events in the target area or well section g i Crack observation data f of production data j ;

[0064] Step 2: Based on the crack classification length l, crack classification width w, crack classification height h, and crack length variation factor α from Step 1... l Crack width variation factor α w Crack height variation factor α h The main development direction of the crack is θ0, and the actual deviation angle of crack development is q(θ). p A multi-level, multi-parameter hybrid fractal model of hydraulic fracturing fractures was established based on fractal theory.

[0065] Step 3: Parameterize the multi-level, multi-parameter fractal model of hydraulic fracture in Step 2 to obtain the parameterized fractal model of hydraulic fracture F(X);

[0066] Step 4: Based on the parametric fractal model F(X) of hydraulic fractals and the fracture observation data g based on microseismic events. i Establish the microseismic observation equations for the cracks, and then establish a regularized inversion model based on the microseismic observation equations;

[0067] Step 5: Based on the parametric fractal model of hydraulic fracturing fractures and the fracture observation data based on production data f jEstablish the production data observation equation for cracks, and establish a regularized inversion model based on the production data observation equation;

[0068] Step 6: Based on the regularized inversion model in Step 4 and the regularized inversion model in Step 5, introduce regularized functional representation to establish a bilateral regularized fracturing fracture inversion model jointly driven by microseismic data and production dynamic data.

[0069] Step 7: Solve the bilateral regularized fracturing fracture inversion model.

[0070] Example 2

[0071] This embodiment further elaborates and supplements the implementation of the present invention based on Embodiment 1.

[0072] In step 2, in establishing a multi-level, multi-parameter fractal model of hydraulic fractals, the maximum number of layers n in the fractal tree model is set; the primary fracture length l0, width w0, height h0, main fracture development direction θ0, and actual fracture development deviation angle distribution q(θ) are defined. p Define the crack bifurcation angle. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h And the hierarchical adaptive height distribution p(h);

[0073] The degree of deviation of the actual fracture development direction θ from the main fracture development direction θ0. p Follows Fisher distribution: Where K is Fisher's constant, used to control the shape of the distribution, which can be set in advance based on experience; the distribution probability P is calculated based on the pre-set distribution probability. The actual direction of crack development is θ = θ0 + (-1). m θ p Where m is a random positive integer, and the crack length variation factor αl and crack width variation factor α w Crack height variation factor α h Defined as:

[0074]

[0075] Among them l j+1 and l j w represents the length of crack level j+1 and crack level j. j+1 and w j This represents the width of crack level j+1 and the width of crack level j. and This represents the average height of cracks at level j+1 and level j, with h representing the height of each crack level. jFollows distribution Where σ is the standard deviation, which can be set in advance according to the actual situation.

[0076] Example 2

[0077] This embodiment further elaborates and supplements the implementation of the present invention based on Embodiment 1.

[0078] In step 3, the hybrid fractal model of the hydraulic fractal is parameterized, that is, by the fracture bifurcation angle. Crack classification length l, crack classification width w, crack classification height h, crack length variation factor α l Crack width variation factor α w Crack height variation factor α h By constructing the parameter variable X, we obtain the parameterized hybrid fractal model F(X) of the fractal fracture:

[0079]

[0080] Where l represents the crack grading length [l1, l2, ..., l] n ], w represents the crack grading width [w1, w2, ..., w n ], h represents the crack grading height [h1, h2, ..., h n ], α l Represents the crack length variation factor, α w Represents the crack width variation factor, α h Indicates the crack height variation factor, Indicates the angle at which the crack bifurcates.

[0081] Example 3

[0082] This embodiment further elaborates and supplements the implementation of the present invention based on Embodiment 1 or Embodiment 2.

[0083] In step 4, the fracture observation data g based on the parameterized hydraulic fractal model F(X) and microseismic events are used. i i = 1, 2, ..., N g Establish the microseismic observation equations for the cracks:

[0084] G(F(X))=[g i ],

[0085] G represents the microseismic observation operator for fractures; a regularized inversion model can be established based on this equation:

[0086]

[0087] Where λ1 represents the regularization coefficient, and R1(X) represents the characteristic function used for L2 regularization. By default, R1(X) = X.

[0088] Furthermore, we introduce a functional representation:

[0089]

[0090] The iterative formula is obtained using nonlinear optimization and gradient descent. Where k is the number of iterations, η1 is the learning rate, and X (k) This represents the result of the k-th calculation. This represents the gradient operator with respect to X.

[0091] In step 5, a production model based on the parametric fractal model F(X) of the hydraulic fractal is introduced to introduce the fracture flow mechanism. and production observation data f j j = 1, 2, ..., N f Establish the production data observation equation for cracks:

[0092] M(t,F(X),c)=[f j ],

[0093] M represents the fracture production observation operator, t represents the time when the production observation data is observed, and c represents the characteristic parameters related to the region or well section. The characteristic parameters are fracture classification length l, fracture classification width w, fracture classification height h, and fracture bifurcation angle. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The hierarchical adaptive height distribution p(h), the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p Based on this equation, a regularized inversion model can be established:

[0094]

[0095] Where t j λ2 represents the time when the j-th production observation data is observed, λ2 represents the regularization coefficient, and R2(X) represents the characteristic function used for L2 regularization. The default value is R2(X) = X.

[0096] Furthermore, we introduce a functional representation:

[0097]

[0098] The iterative formula is obtained using nonlinear optimization and gradient descent. Where k is the number of iterations, η² is the learning rate, and X... (k)This represents the result of the k-th calculation. This represents the gradient operator with respect to X.

[0099] In step 6, a bilateral regularized fracturing fracture inversion model jointly driven by microseismic data and production dynamic data is established based on regularized functionals:

[0100]

[0101] Furthermore, by combining the fracture parameters in the parameterized fractal model of hydraulic fracturing fractures in step 3, a more detailed inversion model can be derived:

[0102]

[0103] The specific process of solving the bilateral regularized fracturing fracture inversion model in step 7 is as follows:

[0104] Introducing the block representation notation X = [X1, X2], let X2=[w,α w Given iteration error thresholds ε1 and ε2, set the initial value X1. (0) and X2 (0) Using the regularized forms R1(X) and R2(X), the parameters X1 and X2 in the regularized iterative inversion formula are updated alternately as follows:

[0105]

[0106] When ||X1 (k+1) -X1 (k) ||<ε1 and||X2 (k+1) -X2 (k) When ||<ε2, the iteration ends and X is output. Here X1 (k) X2 (k) This represents the result of the k-th iteration.

[0107] Example 4

[0108] This embodiment further elaborates and supplements the implementation of the present invention based on Embodiment 1, Embodiment 2 or Embodiment 3.

[0109] A second aspect of the present invention provides a shale gas fracturing fracture geometry inversion device that integrates microseismic data and production dynamics, comprising:

[0110] The first module is used to obtain the fracture classification length l, fracture classification width w, fracture classification height w, and fracture bifurcation angle of the target area or well section. Crack length variation factor α l Crack width variation factor α wCrack height variation factor α h The distribution of hierarchical adaptive height p(h), the actual development direction of the crack θ, the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p ) and fracture observation data of microseismic events in the target area or well section g i Crack observation data f of production data j ;

[0111] The second module uses the crack classification length l, crack classification width w, crack classification height h, and crack length variation factor α obtained in the first module. l Crack width variation factor α w Crack height variation factor α h The main development direction of the crack is θ0, and the actual deviation angle of crack development is q(θ). p Based on fractal theory, a multi-level multi-parameter fractal model of hydraulic fracturing fractures was established, and the multi-level multi-parameter fractal model of hydraulic fracturing fractures was parameterized to obtain the parameterized fractal model of hydraulic fracturing fractures F(X).

[0112] The third module establishes microseismic observation equations based on the fracture observation data of microseismic events obtained from the first module and the parametric fractal model F(X) of the hydraulic fracturing fracture in the second module, and establishes a regularized inverse model based on the microseismic observation equations; it also establishes production data observation equations based on the fracture observation data of production data obtained from the first module and the parametric fractal model F(X) of the hydraulic fracturing fracture in the second module, and establishes a regularized inverse model based on the production data observation equations; and finally, through the two regularized inverse models, a bilateral regularized hydraulic fracturing fracture inversion model jointly driven by microseismic data and production dynamic data is established based on a regularized functional.

[0113] The fourth module solves the bilateral regularized fracturing fracture inversion model established in the third module.

[0114] Example 5

[0115] To achieve the above objectives, according to another aspect of this application, a computer device is provided, including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the above-described method for inverting the geometry of shale gas fracturing fractures by integrating microseismic data and production dynamics.

[0116] In this embodiment, the processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0117] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and units, such as the program units corresponding to the above-described method embodiments of the present invention. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the methods described in the above-described method embodiments.

[0118] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0119] The one or more units are stored in the memory, and when executed by the processor, they perform the methods in Embodiment 1, Embodiment 2 or Embodiment 3 described above.

[0120] Example 6

[0121] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the steps in Embodiment 1, Embodiment 2 or Embodiment 3 described above.

Claims

1. A method for inverting the geometry of shale gas fracturing fractures by integrating microseismic data and production dynamics, characterized in that: Includes the following steps: Step 1: Obtain the fracture classification length l, fracture classification width w, fracture classification height h, and fracture bifurcation angle of the target area or well section. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The distribution of hierarchical adaptive height p(h), the actual development direction of the crack θ, the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p ) and fracture observation data of microseismic events in the target area or well section g i Crack observation data f of production data j ; Step 2: Based on the crack classification length l, crack classification width w, crack classification height h, and crack length variation factor α from Step 1... l Crack width variation factor α w Crack height variation factor α h The main development direction of the crack is θ0, and the actual deviation angle distribution of crack development is q(θ). p A multi-level, multi-parameter hybrid fractal model of hydraulic fracturing fractures was established based on fractal theory. Step 3: Parameterize the multi-level, multi-parameter fractal model of hydraulic fracture in Step 2 to obtain the parameterized fractal model of hydraulic fracture F(X); Step 4: Based on the parametric fractal model F(X) of hydraulic fractals and the fracture observation data g based on microseismic events. i Establish the microseismic observation equations for the cracks, and then establish a regularized inversion model based on the microseismic observation equations; Step 5: Based on the parametric fractal model of hydraulic fracturing fractures and the fracture observation data based on production data f j Establish the production data observation equation for cracks, and establish a regularized inversion model based on the production data observation equation; Step 6: Based on the regularized inversion model in Step 4 and the regularized inversion model in Step 5, introduce regularized functional representation to establish a bilateral regularized fracturing fracture inversion model jointly driven by microseismic data and production dynamic data. Step 7: Solve the bilateral regularized fracturing fracture inversion model.

2. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 1, characterized in that: In step 2, in establishing a multi-level, multi-parameter fractal model of hydraulic fractals, the maximum number of layers n in the fractal tree model is set; the primary fracture length l0, width w0, height h0, main fracture development direction θ0, and actual fracture development deviation angle distribution q(θ) are defined. p Define the crack bifurcation angle. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h And the hierarchical adaptive height distribution p(h).

3. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 2, characterized in that: The degree of deviation of the actual fracture development direction θ from the main fracture development direction θ0. p Follows Fisher distribution: Where K is Fisher's constant, used to control the shape of the distribution; calculated based on the pre-set distribution probability P. The actual direction of crack development is θ = θ0 + (-1). m θ p Where m is a random positive integer, and the crack length variation factor αl and crack width variation factor α w Crack height variation factor α h Defined as: Among them l j+1 and l j w represents the length of crack level j+1 and crack level j. j+1 and w j This represents the width of crack level j+1 and the width of crack level j. and This represents the average height of cracks at level j+1 and level j, with h representing the height of each crack level. j Follows distribution Where σ is the standard deviation.

4. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 1, characterized in that: In step 3, the hybrid fractal model of the hydraulic fractal is parameterized, that is, by the fracture bifurcation angle. Crack classification length l, crack classification width w, crack classification height h, crack length variation factor α l Crack width variation factor α w Crack height variation factor α h By constructing the parameter variable X, we obtain the parameterized hybrid fractal model F(X) of the fractal fracture: Where l represents the crack grading length [l1, l2, ..., l] n ], w represents the crack grading width [w1, w2, ..., w n ], h represents the crack grading height [h1, h2, ..., h n ], α l Represents the crack length variation factor, α w Represents the crack width variation factor, α h Indicates the crack height variation factor, Indicates the angle at which the crack bifurcates.

5. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 4, characterized in that: In step 4, the fracture observation data g based on the parameterized hydraulic fractal model F(X) and microseismic events are used. i i = 1, 2, ..., N g Establish the microseismic observation equations for the cracks: G(F(X))=[g i ], G represents the microseismic observation operator for fractures; a regularized inversion model can be established based on this equation: Where λ1 represents the regularization coefficient, and R1(X) represents the characteristic function used for L2 regularization. By default, R1(X) = X.

6. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 5, characterized in that: it introduces... Functional representation: The iterative formula is obtained using nonlinear optimization and gradient descent. Where k is the number of iterations, η1 is the learning rate, and X (k) This represents the result of the k-th calculation. This represents the gradient operator with respect to X.

7. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 4, characterized in that: In step 5, a production model based on the parametric fractal model F(X) of the hydraulic fractal is introduced to introduce the fracture flow mechanism. and production observation data f j j = 1, 2, ..., N f Establish the production data observation equation for cracks: M(t,F(X),c)=[f j ], M represents the fracture production observation operator, t represents the time when the production observation data is observed, and c represents the characteristic parameters related to the region or well section. A regularized inversion model can be established based on this equation: Where tj represents the time when the j-th production observation data is observed, λ2 represents the regularization coefficient, and R2(X) represents the characteristic function used for L2 regularization. By default, R2(X) = X.

8. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 7, characterized in that: Introducing functional representation: The iterative formula is obtained using nonlinear optimization and gradient descent. Where k is the number of iterations, η² is the learning rate, and X... (k) This represents the result of the k-th calculation. This represents the gradient operator with respect to X.

9. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 4, characterized in that: In step 6, a bilateral regularized fracturing fracture inversion model jointly driven by microseismic data and production dynamic data is established based on regularized functionals:

10. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 9, characterized in that: By combining the fracture parameters in the parameterized fractal model of hydraulic fracturing fractures in step 3, a more detailed inversion model can be obtained:

11. The shale gas fracturing fracture geometry inversion method integrating microseismic data and production dynamics as described in claim 9, characterized in that: The specific process of solving the bilateral regularized fracturing fracture inversion model in step 7 is as follows: Introducing the block representation notation X = [X1, X2], let X2=[w,α w Given iteration error thresholds ε1 and ε2, set the initial value X1. (0) and X2 (0) Using the regularized forms R1(X) and R2(X), the parameters X1 and X2 in the regularized iterative inversion formula are updated alternately as follows: when and When the iteration ends, X is output. X1 (k) X2 (k) This represents the result of the k-th iteration.

12. A shale gas fracturing fracture geometry inversion device integrating microseismic data and production dynamics, characterized in that: include: The first module is used to obtain the fracture classification length l, fracture classification width w, fracture classification height w, and fracture bifurcation angle of the target area or well section. Crack length variation factor α l Crack width variation factor α w Crack height variation factor α h The distribution of hierarchical adaptive height p(h), the actual development direction of the crack θ, the main development direction of the crack θ0, and the actual development deviation angle distribution of the crack q(θ) p ) and fracture observation data of microseismic events in the target area or well section g i Crack observation data f of production data j ; The second module uses the crack classification length l, crack classification width w, crack classification height h, and crack length variation factor α obtained in the first module. l Crack width variation factor α w Crack height variation factor α h The main development direction of the crack is θ0, and the actual deviation angle distribution of crack development is q(θ). p Based on fractal theory, a multi-level multi-parameter fractal model of hydraulic fracturing fractures was established, and the multi-level multi-parameter fractal model of hydraulic fracturing fractures was parameterized to obtain the parameterized fractal model of hydraulic fracturing fractures F(X). The third module establishes microseismic observation equations based on the fracture observation data of microseismic events obtained from the first module and the parametric fractal model F(X) of the hydraulic fracturing fracture in the second module, and establishes a regularized inverse model based on the microseismic observation equations; it also establishes production data observation equations based on the fracture observation data of production data obtained from the first module and the parametric fractal model F(X) of the hydraulic fracturing fracture in the second module, and establishes a regularized inverse model based on the production data observation equations; and finally, through the two regularized inverse models, a bilateral regularized hydraulic fracturing fracture inversion model jointly driven by microseismic data and production dynamic data is established based on a regularized functional. The fourth module solves the bilateral regularized fracturing fracture inversion model established in the third module.

13. A computer device, characterized in that: The device includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the method as described in any one of claims 1-11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-11.

Images