Deep coal seam fracture density azimuth seismic inversion method and device

Abstract

The invention provides a deep coal seam fracture density azimuth seismic inversion method and device, and relates to the technical field of seismic exploration, and the method comprises the steps: obtaining pre-stack seismic trace set data and logging data of a research work area; constructing an elastic stiffness matrix of which each stratum is a VTI medium based on the logging data; processing the porosity of the coalbed methane reservoir in the logging data and an elastic stiffness matrix of the coalbed methane reservoir as a VTI medium according to a linear slip theory to obtain an elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium so as to determine an initial model parameter vector; combining a reflection coefficient approximation formula based on pre-stack seismic trace set data and orthoanisotropy to construct an objective function used for inverting model parameters; solving the target function to obtain a target model parameter vector of the research work area; and the target model parameters of the coal bed gas reservoir are processed by using the target prediction model to obtain the fracture density of the coal bed gas reservoir, so that an effective technical means is provided for inversion of the fracture density of the deep coal bed.

Description

Technical Field

[0001] The present invention relates to the technical field of seismic exploration, and in particular to a method and device for seismic inversion of fracture density and azimuth in deep coal seams. Background Art

[0002] As a cleaner energy source compared to traditional fossil fuels, coalbed methane has become increasingly prominent in the energy structure, and its exploration and development have become a research hotspot. Due to the characteristics of low porosity and low permeability in deep coal seams, a large amount of coalbed methane is stored in fractures and requires hydraulic fracturing for extraction. Fracture density has become a key parameter in the prediction of engineering sweet spots for coalbed methane exploration and development and in coalbed methane hydraulic fracturing.

[0003] With the continuous in-depth research on deep coal seams, researchers' understanding of coal seams is no longer limited to isotropic media and transversely isotropic media (VTI) with a vertical symmetry axis. Research shows that deep coal seams develop a complex dual-porosity structure, including matrix pores and fractures. Due to the strong in-situ stress in deep coal seams, horizontal fractures tend to close, horizontal bedding and vertical fractures develop, so coal rock is regarded as an orthotropic (OA) medium.

[0004] Traditional amplitude variation with offset (AVO) inversion for coalbed gas reservoirs is based on the isotropic assumption. Even when considering anisotropic factors, it is limited to VTI media and rarely considers OA media. This simple characterization (isotropic or VTI) of coalbed methane reservoirs will reduce the assessment of coalbed methane production potential. Therefore, there is an urgent need for a method to predict fracture density by regarding coal rock as an orthotropic (OA) medium. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and device for seismic inversion of fracture density and azimuth in deep coal seams to accurately predict the fracture density of orthotropic deep coal seams.

[0006] In a first aspect, the present invention provides a method for seismic inversion of fracture density and azimuth in deep coal seams, including: acquiring pre-stack seismic trace gather data and logging data of a research work area; constructing an elastic stiffness matrix for each formation in the research work area as a VTI medium based on the logging data; processing the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium according to the linear slip theory to obtain an elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium; constructing an initial model parameter vector of the research work area based on the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium and the elastic stiffness matrices of other formations as VTI media; wherein, the model parameters include: azimuthal anisotropy gradient, and the difference in longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction; constructing an objective function for inverting the model parameters based on the pre-stack seismic trace gather data, the approximate formula of the reflection coefficient of orthotropic anisotropy, and the initial model parameter vector; solving the objective function to obtain an objective model parameter vector of the research work area; processing the objective model parameters of the coalbed methane reservoir in the objective model parameter vector using an objective prediction model to obtain the fracture density of the coalbed methane reservoir; wherein, each model parameter corresponds to a fracture density prediction model, and the objective prediction model represents the model with the highest goodness of fit among the fracture density prediction models corresponding to two model parameters.

[0007] In an optional implementation manner, processing the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium according to the linear slip theory to obtain an elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium includes: processing the porosity of the coalbed methane reservoir based on the empirical relationship between porosity and fracture density to obtain an estimated value of the fracture density of the coalbed methane reservoir; determining the compliance matrix of the fractures in the coalbed methane reservoir based on the estimated fracture density value, the bulk modulus of a preset fracture filler, the shear modulus of the preset fracture filler, the square of the ratio of the shear wave velocity to the longitudinal wave velocity of the coalbed methane reservoir, and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium; calculating the inverse matrix of the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium to obtain the compliance matrix of the coalbed methane reservoir as a VTI medium; determining the compliance matrix of the coalbed methane reservoir as a fractured medium based on the compliance matrix of the fractures in the coalbed methane reservoir and the compliance matrix of the coalbed methane reservoir as a VTI medium; calculating the inverse matrix of the compliance matrix of the fractured medium to obtain the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium.

[0008] In an alternative embodiment, based on the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium and the elastic stiffness matrix of other formations as VTI media, an initial model parameter vector for the study area is constructed, including: substituting the elastic stiffness coefficients in the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium into the calculation formula of the model parameters to obtain the model parameters of the coalbed methane reservoir; substituting the elastic stiffness coefficients in the elastic stiffness matrix of the target formation as a VTI medium into the calculation formula of the model parameters to obtain the model parameters of the target formation; where the target formation represents any one of the other formations; performing a moving average process on the model parameters of all formations in the study area to obtain the initial model parameter vector of the study area.

[0009] In an alternative embodiment, solving the objective function includes: calculating the first-order derivative of the objective function with respect to the model parameter vector to obtain the first function; constructing a pseudo-Hessian matrix based on the first function and the model parameter vector; constructing a second function for solving the model parameter vector based on the first function and the pseudo-Hessian matrix; performing iterative solution on the second function based on the initial model parameter vector and the pre-stack seismic gather data until a preset iteration termination condition is reached to obtain the target model parameter vector.

[0010] In an alternative embodiment, performing iterative solution on the second function based on the initial model parameter vector and the pre-stack seismic gather data includes: extracting non-90-degree azimuth seismic records from the pre-stack seismic gather data to obtain the first seismic record; extracting 90-degree azimuth seismic records from the pre-stack seismic gather data to obtain the second seismic record; calculating the difference between the first seismic record and the second seismic record to obtain the third seismic record; using the third seismic record as the true seismic record in the second function and performing iterative solution on the second function in combination with the initial model parameter vector.

[0011] In an alternative embodiment, it further includes: obtaining a first training sample set and a second training sample set; where the first training sample set includes multiple groups of first training samples, and each group of first training samples includes: the fracture density and azimuthal anisotropy gradient of the coalbed methane reservoir; the second training sample set includes multiple groups of second training samples, and each group of second training samples includes: the fracture density of the coalbed methane reservoir and the difference in the longitudinal wave velocity propagating along the normal direction and the strike direction of the fracture surface; training a first initial fracture density prediction model based on the first training sample set to obtain a first fracture density prediction model; training a second initial fracture density prediction model based on the second training sample set to obtain a second fracture density prediction model; respectively calculating the goodness of fit of the first fracture density prediction model and the second fracture density prediction model, and determining the target prediction model from the first fracture density prediction model and the second fracture density prediction model based on the calculation result of the goodness of fit.

[0012] In an alternative embodiment, both the first fracture density prediction model and the second fracture density prediction model are support vector regression models.

[0013] In a second aspect, the present invention provides a deep coal seam fracture density azimuth seismic inversion device, comprising: an acquisition module for acquiring pre-stack seismic trace gather data and logging data of a research work area; a first construction module for constructing an elastic stiffness matrix of each formation in the research work area as a VTI medium based on the logging data; a first processing module for processing the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium according to the linear slip theory to obtain an elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium; a second construction module for constructing an initial model parameter vector of the research work area based on the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium and the elastic stiffness matrices of other formations as VTI media; wherein the model parameters include: azimuthal anisotropy gradient, the difference in the longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction; a third construction module for constructing an objective function for inverting the model parameters based on the pre-stack seismic trace gather data, the reflection coefficient approximation formula of orthotropic anisotropy, and the initial model parameter vector; a solving module for solving the objective function to obtain an objective model parameter vector of the research work area; a second processing module for processing the objective model parameters of the coalbed methane reservoir in the objective model parameter vector by using the objective prediction model to obtain the fracture density of the coalbed methane reservoir; wherein each model parameter corresponds to a fracture density prediction model, and the objective prediction model represents the model with the highest goodness of fit among the fracture density prediction models corresponding to the two model parameters.

[0014] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein a computer program is stored on the memory and can run on the processor, and when the processor executes the computer program, it implements the deep coal seam fracture density azimuth seismic inversion method according to any one of the foregoing embodiments.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, and when the computer instructions are executed by a processor, they implement the deep coal seam fracture density azimuth seismic inversion method according to any one of the foregoing embodiments.

[0016] The present invention fully considers the characteristics of orthotropic media with vertical fractures in deep coal seams, adds vertical fractures to VTI media using the linear slip theory to construct the elastic stiffness matrix of orthotropic media. On this basis, an initial model parameter vector of the research area is constructed, and an objective function for inverting model parameters is constructed by combining prestack seismic gather data and the reflection coefficient approximation formula of orthotropic media. Among them, the model parameters include the following two azimuth attribute parameters affected by fractures: azimuthal anisotropy gradient, and the difference in longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction. Next, after solving the objective function to obtain the target model parameter vector of the research area, the target prediction model is used to process the target model parameters of the coalbed methane reservoir in the target model parameter vector to obtain the fracture density of the coalbed methane reservoir. The method of first inverting model parameters and then using the model to predict fracture density adopted by the present invention can effectively avoid the complex linearization operations of expressing and directly inverting fracture density, providing an effective technical means for inverting fracture density in deep coal seams. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of a method for azimuth seismic inversion of fracture density in deep coal seams provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the inversion effect of model parameters D and E provided by an embodiment of the present invention; Figure 3 It is a crossplot of parameter D and fracture density provided by an embodiment of the present invention; Figure 4 It is a crossplot of parameter E and fracture density provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the prediction effect of fracture density in the validation set by the model trained with parameter D provided by an embodiment of the present invention; Figure 6 It is a schematic diagram of the prediction effect of fracture density in the validation set by the model trained with parameter E provided by an embodiment of the present invention; Figure 7 It is a schematic diagram of the effect of predicting fracture density based on well-side trace data by the model trained with parameter E in an embodiment of the present invention; Figure 8It is a functional module diagram of a device for seismic inversion of fracture density and azimuth in deep coal seams provided by an embodiment of the present invention; Figure 9 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0021] The following will describe in detail some embodiments of the present invention with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0022] Embodiment 1 Figure 1 It is a flow chart of a method for seismic inversion of fracture density and azimuth in deep coal seams provided by an embodiment of the present invention. As Figure 1 shown, the method specifically includes the following steps: Step S102, obtain pre-stack seismic gather data and logging data of the research work area.

[0023] To determine the fracture density of the deep coal seam in the research work area, the pre-stack seismic gather data and logging data of the research work area are required in the embodiments of the present invention. Among them, the logging data includes anisotropic parameters of each formation in the research work area measured at the wellhead , , , longitudinal wave velocity , shear wave velocity , density and porosity data.

[0024] After obtaining the pre-stack seismic gather information of the research work area, the wavelet information can be extracted from it, and well-seismic calibration is performed in combination with the logging data. Well-seismic calibration is used to correspond the logging depth domain information with the time domain information. Therefore, by referring to the depth position of the coal seam on the logging formation interpretation result map, the corresponding time range of the coalbed methane reservoir on the seismic record can be determined.

[0025] Step S104: Based on the logging data, construct the elastic stiffness matrix for each formation in the study area as a VTI medium.

[0026] After obtaining the logging data, in the embodiments of the present invention, first, based on the logging data, the elastic stiffness matrix for each formation in the study area as a VTI medium (i.e., transversely isotropic) is preliminarily calculated. The following are the calculation formulas for each element in the elastic stiffness matrix of the VTI medium. The values of the elements not shown in the matrix are 0. By substituting the logging data of each formation into the following formulas respectively, the elastic stiffness matrix for each formation in the study area as a VTI medium can be obtained.

[0027] , where, , , , , , , , , . That is, represents the elastic stiffness coefficient of the i-th row and j-th column in

[0028] Step S106: According to the linear slip theory, process the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium to obtain the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium.

[0029] Through existing research, it is known that the deep coal seams develop complex pore structures. Therefore, on the basis of considering the coalbed methane reservoir as a VTI medium, after roughly calculating the fracture density of the coalbed methane reservoir according to the empirical formula and the porosity of the coalbed methane reservoir obtained from logging, by adding vertical fractures in the VTI medium using the linear slip theory (such as Schoenberg's linear slip theory), the coalbed methane reservoir can be characterized as an orthotropic medium. Therefore, based on the porosity of the coalbed methane reservoir and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium, the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium can be constructed. .

[0030] Step S108: Based on the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium and the elastic stiffness matrices of other formations as VTI media, construct the initial model parameter vector of the study area.

[0031] Among them, the model parameters include: azimuthal anisotropy gradient, the difference in the longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction.

[0032] In the embodiments of the present invention, except that the coalbed methane reservoir is an orthotropic medium, the other strata in the study area are regarded as VTI media. In the orthotropic medium, there are the following two azimuth attribute parameters affected by fractures: the azimuth anisotropy gradient D and the difference E in the longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction. Therefore, in the embodiments of the present invention, the above two attribute parameters are used as the model parameters to be inverted.

[0033] In the above text, the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium has been obtained through calculation. For the other strata, because there is no addition of fractures, the elastic stiffness matrix of the other strata as an orthotropic medium is equivalent to its elastic stiffness matrix as a VTI medium.

[0034] The known parameters D and E are determined based on the elastic stiffness coefficients in the elastic stiffness matrix of the orthotropic medium. Therefore, after determining the elastic stiffness matrix of each stratum as an orthotropic medium, the parameters D and E of each stratum can be calculated through a preset formula. Next, a moving average process is performed on the parameters D and E of all strata. For example, a moving average with a span of 100 points is performed to construct the initial model parameter vector of the study area. The initial model parameter vector represents the vector constructed by the initial model parameters of each stratum.

[0035] Step S110: Based on the pre-stack seismic trace gather data, the reflection coefficient approximation formula for orthotropic media, and the initial model parameter vector, construct an objective function for inverting the model parameters.

[0036] Substitute the model parameters of each stratum in the initial model parameter vector into the reflection coefficient approximation formula for orthotropic media, and the reflection coefficients at different incident angles and azimuth angles at the logging position can be obtained, and then the coefficient matrix of the model parameters is constructed.

[0037] The known forward synthetic seismic record formula is: , where represents the forward synthetic seismic record, represents the forward operator, represents the model parameter vector, , represents the noise, represents the wavelet convolution matrix, represents the coefficient matrix of the model parameters, represents the difference matrix, .

[0038] In the embodiments of the present invention, in the Bayesian framework, it is assumed that the prior model distribution and the likelihood function both follow Gaussian distributions, and the posterior probability is positively correlated with the prior probability and the likelihood function ​ , according to the maximum a posteriori probability estimation, establish an objective function for inverting model parameters: , where represents the pre-stack seismic trace gather data, that is, the real seismic record, represents the noise covariance diagonal matrix, represents the initial model parameter vector, represents the model prior covariance matrix, which can be obtained from well logging curves or rock physics relationships.

[0039] Step S112, solve the objective function to obtain the target model parameter vector of the research work area.

[0040] Optionally, use the Gauss-Newton method to inversely iterate and solve the model parameters to obtain the target model parameter vector of the research work area, that is, the vector constructed by the target model parameters of each formation. The embodiment of the present invention does not specifically limit the solution method of the objective function, and the user can make an adaptive selection according to actual needs.

[0041] Step S114, use the target prediction model to process the target model parameters of the coalbed methane reservoir in the target model parameter vector to obtain the fracture density of the coalbed methane reservoir.

[0042] Among them, each model parameter corresponds to a fracture density prediction model, and the target prediction model represents the model with the highest goodness of fit among the two fracture density prediction models corresponding to the two model parameters.

[0043] It is known that there is a correlation between the model parameters of the coalbed methane reservoir and the fracture density. Therefore, in the embodiment of the present invention, two fracture density prediction models are pre-trained. One is a prediction model with input data of parameter D and output data of fracture density ; the other is a prediction model with input data of parameter E and output data of fracture density .

[0044] In order to select a prediction model suitable for the research work area, the embodiment of the present invention refers to the method of calculating the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium in the above text, and the method of calculating model parameters according to the elastic stiffness coefficient. By adding vertical fractures with different fracture densities to the coalbed methane reservoir of VTI type medium, a large number of orthotropic coal-rock elastic stiffness matrices with different fracture densities can be created , it is known that , according to the calculation formulas of parameter D and E, the corresponding model parameters can be calculated, so as to establish the training set and verification set of parameter D, E and fracture density.

[0045] After the training of the two models is completed, the goodness of fit of each can be calculated respectively. For example, parameter , and then select the larger one from them The corresponding model serves as the final target prediction model for predicting fracture density. Therefore, after obtaining the target model parameter vector, that is, obtaining the target model parameters of the coalbed methane reservoir. If the target prediction model is a prediction model with parameter D as the input data and fracture density as the output data, then the target prediction model is used to process the target model parameter D of the coalbed methane reservoir to obtain the fracture density of the coalbed methane reservoir; if the target prediction model is a prediction model with parameter E as the input data and fracture density as the output data, then the target prediction model is used to process the target model parameter E of the coalbed methane reservoir to obtain the fracture density of the coalbed methane reservoir.

[0046] The deep coal seam fracture density azimuth seismic inversion method provided by the embodiments of the present invention fully considers the characteristics of the orthotropic medium containing vertical fractures in the deep coal seam. The linear slip theory is used to add vertical fractures in the VTI medium to construct the elastic stiffness matrix of the orthotropic medium. On this basis, an initial model parameter vector of the research work area is constructed, and a target function for inverting model parameters is constructed by combining pre-stack seismic trace gather data and the approximate formula of the reflection coefficient of orthotropic media. Among them, the model parameters include the following two azimuth attribute parameters affected by fractures: azimuth anisotropy gradient, and the difference in the longitudinal wave velocities propagating along the normal direction of the fracture surface and the fracture strike direction. Next, after solving the objective function to obtain the target model parameter vector of the research work area, the target prediction model is used to process the target model parameters of the coalbed methane reservoir in the target model parameter vector to obtain the fracture density of the coalbed methane reservoir. The method of first inverting model parameters and then using the model to predict fracture density adopted by the embodiments of the present invention can effectively avoid the complex linearization operations of expressing and directly inverting fracture density, and provides an effective technical means for the inversion of deep coal seam fracture density.

[0047] In an optional implementation manner, in step S106 above, according to the linear slip theory, the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium are processed to obtain the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium, which specifically includes the following steps: Step S1061, based on the empirical relationship between porosity and fracture density, process the porosity of the coalbed methane reservoir to obtain an estimated value of the fracture density of the coalbed methane reservoir.

[0048] Specifically, the empirical relationship between porosity and fracture density is , where represents the fracture porosity, represents the fracture aspect ratio, represents the fracture density. Since the current calculation serves for the subsequent initial model and an accurate fracture density is not required, the fracture aspect ratio It can be roughly estimated according to empirical values. Substituting the porosity of the coalbed methane reservoir into the above formula, the estimated value of the fracture density of the coalbed methane reservoir can be obtained.

[0049] Step S1062: Based on the estimated value of the fracture density, the bulk modulus of the preset fracture filler, the shear modulus of the preset fracture filler, the square of the ratio of the shear wave velocity to the longitudinal wave velocity of the coalbed methane reservoir, and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium, determine the compliance matrix of the fractures in the coalbed methane reservoir.

[0050] In the embodiment of the present invention, the compliance matrix of the fracture is expressed as: , where represents the normal fracture compliance, represents the vertical tangential compliance, represents the horizontal tangential compliance, represents the square of the ratio of the shear wave velocity to the longitudinal wave velocity of the coalbed methane reservoir, represents the bulk modulus of the preset fracture filler, represents the shear modulus of the preset fracture filler, represents the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium is the elastic stiffness coefficient of the i-th row and j-th column in

[0051] Step S1063: Calculate the inverse matrix of the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium to obtain the compliance matrix of the coalbed methane reservoir as a VTI medium. That is, the compliance matrix of the coalbed methane reservoir as a VTI medium is expressed as: .

[0052] Step S1064: Based on the compliance matrix of the fractures in the coalbed methane reservoir and the compliance matrix of the coalbed methane reservoir as a VTI medium, determine the compliance matrix of the coalbed methane reservoir as a fractured medium. Among them, the compliance matrix of the coalbed methane reservoir as a fractured medium is expressed as: .

[0053] Step S1065: Calculate the inverse matrix of the compliance matrix of the fractured medium to obtain the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium. That is, the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium is expressed as . After derivation, it can be obtained that: , where represents the normal fracture weakness, represents the vertical tangential fracture weakness, represents the horizontal tangential fracture weakness.

[0054] In an alternative embodiment, in step S108, based on the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium and the elastic stiffness matrix of other formations as VTI media, an initial model parameter vector of the study area is constructed, which specifically includes the following steps: Step S1081: Substitute the elastic stiffness coefficients in the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium into the calculation formula of the model parameters to obtain the model parameters of the coalbed methane reservoir.

[0055] Step S1082: Substitute the elastic stiffness coefficients in the elastic stiffness matrix of the target formation as a VTI medium into the calculation formula of the model parameters to obtain the model parameters of the target formation; where the target formation represents any one of the other formations.

[0056] Step S1083: Perform a moving average process on the model parameters of all formations in the study area to obtain the initial model parameter vector of the study area.

[0057] Specifically, the embodiment of the present invention refers to the reflection coefficient approximation formula of orthotropy: , where , , represents the incident angle, represents the azimuth angle relative to the fracture normal plane, represents the longitudinal wave impedance, , represents the anisotropic shear modulus, , represents the longitudinal wave phase velocity along the fracture plane direction, , represents the azimuthal anisotropy gradient, , , , since it is positively correlated with the fracture density, it is often used to represent the relative fracture density or horizontal stress anisotropy, represents the difference in the longitudinal wave velocities propagating along the fracture plane normal direction and the fracture strike direction, , and the subscript i represents the parameters of the i-th layer underground.

[0058] Among them, all represent orthotropic parameters, , , , , , . In the above expressions of the orthotropic parameters, Denote the elastic stiffness coefficients in the orthotropic elastic stiffness matrix. As can be known from the above description, except for the coalbed methane reservoir, the elastic stiffness matrix of other formations being VTI media is the same as that of other formations being orthotropic media. Therefore, by substituting the orthotropic elastic stiffness coefficients of each formation into the formulas of parameter D and parameter E, the model parameters of each formation can be obtained. Finally, through moving average processing, the initial model parameter vector of the research area can be obtained.

[0059] In an alternative implementation, for the above step S112 of solving the objective function, it specifically includes the following steps: Step S1121: Calculate the first-order derivative of the objective function with respect to the model parameter vector to obtain the first function.

[0060] Given , find the first-order derivative with respect to the model parameter vector, that is, .

[0061] Step S1122: Based on the first function and the model parameter vector, construct the pseudo-Hessian matrix.

[0062] In the embodiment of the present invention, the pseudo-Hessian matrix is expressed as: .

[0063] Step S1123: Based on the first function and the pseudo-Hessian matrix, construct the second function for solving the model parameter vector.

[0064] Specifically, the second function is expressed as: , where denotes the model parameter vector at the k-th iteration. When k = 0, .

[0065] Step S1124: Based on the initial model parameter vector and the pre-stack seismic gather data, perform iterative solution on the second function until the preset iteration termination condition is reached to obtain the target model parameter vector.

[0066] Optionally, the preset iteration termination condition is to reach a specified number of iterations.

[0067] In an alternative implementation, for the above step S1124 of performing iterative solution on the second function based on the initial model parameter vector and the pre-stack seismic gather data, it specifically includes the following steps: Step S11241: Extract the non-90-degree azimuth seismic records from the pre-stack seismic gather data to obtain the first seismic record.

[0068] Step S11242: Extract the 90-degree azimuth seismic records from the pre-stack seismic gather data to obtain the second seismic record.

[0069] Step S11243: Calculate the difference between the first seismic record and the second seismic record to obtain the third seismic record.

[0070] Step S11244: Use the third seismic record as the true seismic record in the second function, and iteratively solve the second function in combination with the initial model parameter vector.

[0071] Specifically, from the approximate formula of the reflection coefficient, it consists of two parts and components. is only related to the incident angle, is related to both the incident angle and the azimuth angle. To reduce the ill-posedness of the inversion, the embodiments of the present invention adopt a step-by-step inversion strategy for the two.

[0072] For part, according to the approximate formula of , when , , , the reflection coefficient is only related to related to the incident angle. Since the seismic record is synthesized by the convolution of the wavelet and the reflection coefficient, the seismic record with an azimuth angle of 90 degrees eliminates the part of the information. Therefore, it can be used to invert parameters A, B, and C. The inversion steps of parameters A, B, and C are as follows: The seismic records with different incident angles at 90 degrees azimuth for each trace are composed into a vector , ; The model parameter vector composed of parameters A, B, and C is expressed as , The initial value of The construction method refers to the calculation method of the initial model parameter vector in the above text. After determining , and then referring to the iterative formula of the model parameter vector and iterating a certain number of times, parameters A, B, and C can be obtained.

[0073] For part, since the is the same for the same incident angle part, and the at 90 degrees azimuth, so subtracting the reflection coefficient at 90 degrees azimuth with the same incident angle from the reflection coefficient at non-90 degrees azimuth can obtain . That is, .

[0074] Therefore, according to the distributive law of convolution, subtracting the seismic record at non-90 degrees azimuth from the seismic record at 90 degrees azimuth with the same incident angle can eliminate the seismic record affected by to obtain the seismic record only affected by The seismic records affected are denoted as the third seismic record .

[0075] Therefore, substituting the initial model parameter vector and the third seismic record into the second function, can be calculated. Then, substituting and the third seismic record into the second function to calculate . And so on, continuously iterating until the preset iteration termination condition is reached, the target model parameter vector can be obtained.

[0076] To verify the inversion effect of the model parameters in the embodiments of the present invention, the initial model for inversion is generated by moving average. Figure 2 FIG. is a schematic diagram of the inversion effect of model parameters D and E provided by the embodiments of the present invention. It can be seen from Figure 2 that the inversion results of the model parameters and the actual values can be well matched, but some high-frequency parts cannot be fully fitted due to factors such as the frequency limitation of the seismic wavelet.

[0077] In an alternative embodiment, the embodiments of the present invention further include the following steps: Step S201: Obtain a first training sample set and a second training sample set; wherein, the first training sample set includes multiple groups of first training samples, and each group of first training samples includes: the fracture density and azimuthal anisotropy gradient of the coalbed methane reservoir; the second training sample set includes multiple groups of second training samples, and each group of second training samples includes: the fracture density of the coalbed methane reservoir and the difference in the longitudinal wave velocities propagating along the normal direction and the fracture strike direction of the fracture surface.

[0078] Step S202: Train the first initial fracture density prediction model based on the first training sample set to obtain the first fracture density prediction model.

[0079] Step S203: Train the second initial fracture density prediction model based on the second training sample set to obtain the second fracture density prediction model.

[0080] Step S204: Calculate the goodness of fit of the first fracture density prediction model and the second fracture density prediction model respectively, and determine the target prediction model from the first fracture density prediction model and the second fracture density prediction model based on the calculation results of the goodness of fit.

[0081] Optionally, both the first fracture density prediction model and the second fracture density prediction model are support vector regression models.

[0082] In one embodiment, Figure 3 and Figure 4They are the intersection diagrams of parameters D and E with fracture density respectively, which are used as the training set for support vector regression to train the model. Figure 5 and Figure 6 They are the prediction effect diagrams of the models trained with parameters D and E respectively for fracture density in the validation set. For parameter D, > 0.8. Regarding the data quality relative to the training data, it can be considered that there is a good prediction effect, and it can roughly fit the changing trend of D relative to fracture density. At the same time, it is noted that in the part where the fracture density < 0.1, the smaller D is, the better the prediction of fracture density is, and the linear relationship between the two is more obvious; compared with parameter D, parameter E has a better linear relationship with fracture density, and the prediction effect > 0.9. By comparison select the prediction model with better effect. In this example, finally, parameter E is selected as the target model parameter for predicting fracture density. Figure 7 This is the schematic diagram of the effect of predicting fracture density based on the data of the well-side trace by the model trained with parameter E in the embodiment of the present invention. That is, parameter E is selected as the target model parameter for predicting fracture density to train the support vector regression model, and then based on the E parameter inversed from the actual well-side trace, the fracture density is predicted. Figure 7 The predicted curve of fracture density in

[0083] fits well with the actual curve, indicating that using the target prediction model can effectively help predict the fracture density distribution of the underground coalbed methane reservoir from the model parameters inversed from the actual seismic profile.

[0084] Embodiment 2 The embodiment of the present invention also provides a device for azimuth seismic inversion of fracture density in deep coal seams. This device is mainly used to execute the method for azimuth seismic inversion of fracture density in deep coal seams provided in the above Embodiment 1. The following is a specific introduction to the device for azimuth seismic inversion of fracture density in deep coal seams provided by the embodiment of the present invention.

[0085] Figure 8 This is the functional module diagram of a device for azimuth seismic inversion of fracture density in deep coal seams provided by the embodiment of the present invention. As Figure 8As shown in the figure, the device mainly includes: an acquisition module 11, a first construction module 12, a first processing module 13, a second construction module 14, a third construction module 15, a solution module 16, and a second processing module 17, where: The acquisition module 11 is used to acquire pre-stack seismic trace gather data and logging data of the research work area.

[0086] The first construction module 12 is used to construct an elastic stiffness matrix with VTI media for each formation in the research work area based on the logging data.

[0087] The first processing module 13 is used to process the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix with VTI media for the coalbed methane reservoir according to the linear slip theory to obtain an elastic stiffness matrix with orthotropic media for the coalbed methane reservoir.

[0088] The second construction module 14 is used to construct an initial model parameter vector of the research work area based on the elastic stiffness matrix with orthotropic media for the coalbed methane reservoir and the elastic stiffness matrix with VTI media for other formations; where the model parameters include: azimuthal anisotropy gradient, and the difference in longitudinal wave velocities propagating along the normal direction and the fracture strike direction of the fracture plane.

[0089] The third construction module 15 is used to construct an objective function for inverting model parameters based on the pre-stack seismic trace gather data, the reflection coefficient approximation formula of orthotropic media, and the initial model parameter vector.

[0090] The solution module 16 is used to solve the objective function to obtain an objective model parameter vector of the research work area.

[0091] The second processing module 17 is used to process the objective model parameters of the coalbed methane reservoir in the objective model parameter vector by using the objective prediction model to obtain the fracture density of the coalbed methane reservoir; where each model parameter corresponds to a fracture density prediction model, and the objective prediction model represents the model with the highest goodness of fit among the fracture density prediction models corresponding to the two model parameters.

[0092] The embodiments of the present invention fully consider the characteristics of orthotropic media with vertical fractures in deep coal seams, and use the linear slip theory to add vertical fractures in VTI media to construct the elastic stiffness matrix of orthotropic media. On this basis, an initial model parameter vector of the research work area is constructed, and a target function for inverting model parameters is constructed by combining pre-stack seismic trace data and the reflection coefficient approximation formula of orthotropic media. Among them, the model parameters include the following two azimuth attribute parameters affected by fractures: azimuthal anisotropy gradient, and the difference in the longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction. Next, after solving the objective function to obtain the target model parameter vector of the research work area, the target prediction model is used to process the target model parameters of the coalbed methane reservoir in the target model parameter vector to obtain the fracture density of the coalbed methane reservoir. The method of first inverting model parameters and then using the model to predict fracture density adopted in the embodiments of the present invention can effectively avoid the complex linearization operations of expressing and directly inverting fracture density, and provides an effective technical means for inverting fracture density in deep coal seams.

[0093] Optionally, the first processing module 13 is specifically configured to: Process the porosity of the coalbed methane reservoir based on the empirical relationship between porosity and fracture density to obtain an estimated value of the fracture density of the coalbed methane reservoir.

[0094] Based on the estimated value of fracture density, the bulk modulus of the preset fracture filler, the shear modulus of the preset fracture filler, the square of the ratio of the shear wave velocity to the longitudinal wave velocity of the coalbed methane reservoir, and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium, determine the compliance matrix of the fractures in the coalbed methane reservoir.

[0095] Calculate the inverse matrix of the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium to obtain the compliance matrix of the coalbed methane reservoir as a VTI medium.

[0096] Based on the compliance matrix of the fractures in the coalbed methane reservoir and the compliance matrix of the coalbed methane reservoir as a VTI medium, determine the compliance matrix of the coalbed methane reservoir as a fractured medium.

[0097] Calculate the inverse matrix of the compliance matrix of the fractured medium to obtain the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium.

[0098] Optionally, the second construction module 14 is specifically configured to: Substitute the elastic stiffness coefficients in the elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium into the calculation formula of the model parameters to obtain the model parameters of the coalbed methane reservoir.

[0099] Substitute the elastic stiffness coefficients in the elastic stiffness matrix of the target formation as a VTI medium into the calculation formula of the model parameters to obtain the model parameters of the target formation; where the target formation represents any formation in other formations.

[0100] Perform a moving average process on the model parameters of all strata in the study area to obtain the initial model parameter vector of the study area.

[0101] Optionally, the solving module 16 includes: A calculation unit for calculating the first-order derivative of the objective function with respect to the model parameter vector to obtain a first function.

[0102] A first construction unit for constructing a pseudo-Hessian matrix based on the first function and the model parameter vector.

[0103] A second construction unit for constructing a second function for solving the model parameter vector based on the first function and the pseudo-Hessian matrix.

[0104] A solving unit for iteratively solving the second function based on the initial model parameter vector and the pre-stack seismic gather data until a preset iteration termination condition is reached to obtain the target model parameter vector.

[0105] Optionally, the solving unit is specifically used for: Extract non-90-degree azimuth seismic records from the pre-stack seismic gather data to obtain a first seismic record.

[0106] Extract 90-degree azimuth seismic records from the pre-stack seismic gather data to obtain a second seismic record.

[0107] Calculate the difference between the first seismic record and the second seismic record to obtain a third seismic record.

[0108] Use the third seismic record as the true seismic record in the second function and perform iterative solution of the second function in combination with the initial model parameter vector.

[0109] Optionally, the device is further used for: Obtain a first training sample set and a second training sample set; wherein, the first training sample set includes multiple groups of first training samples, and each group of first training samples includes: the fracture density and azimuthal anisotropy gradient of the coalbed methane reservoir; the second training sample set includes multiple groups of second training samples, and each group of second training samples includes: the fracture density of the coalbed methane reservoir and the difference in the longitudinal wave velocities propagating along the normal direction of the fracture plane and the fracture strike direction.

[0110] Train a first initial fracture density prediction model based on the first training sample set to obtain a first fracture density prediction model.

[0111] Train a second initial fracture density prediction model based on the second training sample set to obtain a second fracture density prediction model.

[0112] Calculate the goodness of fit of the first fracture density prediction model and the second fracture density prediction model respectively, and determine the target prediction model from the first fracture density prediction model and the second fracture density prediction model based on the calculation results of the goodness of fit.

[0113] Optionally, both the first fracture density prediction model and the second fracture density prediction model are support vector regression models.

[0114] Embodiment III Refer to Figure 9 , an embodiment of the present invention provides an electronic device, which includes: a processor 60, a memory 61, a bus 62, and a communication interface 63. The processor 60, the communication interface 63, and the memory 61 are connected through the bus 62. The processor 60 is configured to execute an executable module stored in the memory 61, such as a computer program.

[0115] Among them, the memory 61 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 63 (which can be wired or wireless), a communication connection between the system network element and at least one other network element is realized, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0116] The bus 62 may be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 9 only a bidirectional arrow is used in

[0117] Among them, the memory 61 is used to store a program. After receiving an execution instruction, the processor 60 executes the program. The method executed by the device defined by the process disclosed in any embodiment of the foregoing embodiments of the present invention can be applied to the processor 60 or implemented by the processor 60.

[0118] The processor 60 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 60 or the instructions in the form of software. The above-mentioned processor 60 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute each method, step, and logic block diagram disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 61, and the processor 60 reads the information in the memory 61 and combines its hardware to complete the steps of the above method.

[0119] A computer program product of a deep coal seam fracture density and azimuth seismic inversion method and device provided by an embodiment of the present invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the method described in the foregoing method embodiments. For specific implementation, reference can be made to the method embodiments and will not be elaborated here.

[0120] In addition, in each embodiment of the present invention, each functional unit may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0121] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0122] It should be noted that: similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0123] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present invention is usually placed during use. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third", etc. are only used for descriptive distinction and cannot be understood as indicating or implying relative importance.

[0124] In addition, the terms "horizontal", "vertical", "hanging", etc. do not mean that the component is required to be absolutely horizontal or hanging, but can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but can be slightly inclined.

[0125] In the description of the present invention, it should also be noted that unless otherwise clearly specified and limited, the terms "set", "install", "connect", "couple" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for seismic inversion of fracture density and azimuth in deep coal seams, characterized in that, Including: Obtaining pre-stack seismic gather data and logging data of the research work area; Constructing an elastic stiffness matrix with each formation in the research work area being a VTI medium based on the logging data; Processing the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix with the coalbed methane reservoir being a VTI medium according to the linear slip theory to obtain an elastic stiffness matrix with the coalbed methane reservoir being an orthotropic medium; Constructing an initial model parameter vector of the research work area based on the elastic stiffness matrix with the coalbed methane reservoir being an orthotropic medium and the elastic stiffness matrices with other formations being VTI media; wherein, the model parameters include: azimuthal anisotropy gradient, the difference in the longitudinal wave velocities propagating along the normal direction and the strike direction of the fracture plane; Constructing an objective function for inversely solving the model parameters based on the pre-stack seismic gather data, the approximate formula of the reflection coefficient of orthotropy, and the initial model parameter vector; Solving the objective function to obtain the objective model parameter vector of the research work area; Processing the objective model parameters of the coalbed methane reservoir in the objective model parameter vector by using an objective prediction model to obtain the fracture density of the coalbed methane reservoir; wherein, each model parameter corresponds to a fracture density prediction model, and the objective prediction model represents the model with the highest goodness of fit among the fracture density prediction models corresponding to two model parameters.

2. The deep coal seam fracture density azimuth seismic inversion method according to claim 1, wherein Processing the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix with the coalbed methane reservoir being a VTI medium according to the linear slip theory to obtain an elastic stiffness matrix with the coalbed methane reservoir being an orthotropic medium, including: Processing the porosity of the coalbed methane reservoir based on the empirical relationship between porosity and fracture density to obtain an estimated value of the fracture density of the coalbed methane reservoir; Determining the compliance matrix of the fractures in the coalbed methane reservoir based on the estimated fracture density value, the bulk modulus of the preset fracture filler, the shear modulus of the preset fracture filler, the square of the ratio of the shear wave velocity to the longitudinal wave velocity of the coalbed methane reservoir, and the elastic stiffness matrix with the coalbed methane reservoir being a VTI medium; Calculating the inverse matrix of the elastic stiffness matrix with the coalbed methane reservoir being a VTI medium to obtain the compliance matrix with the coalbed methane reservoir being a VTI medium; Determining the compliance matrix of the coalbed methane reservoir as a fractured medium based on the compliance matrix of the fractures in the coalbed methane reservoir and the compliance matrix with the coalbed methane reservoir being a VTI medium; Calculating the inverse matrix of the compliance matrix of the fractured medium to obtain an elastic stiffness matrix with the coalbed methane reservoir being an orthotropic medium.

3. The deep coal seam fracture density azimuth seismic inversion method according to claim 1, characterized in that Constructing an initial model parameter vector of the research work area based on the elastic stiffness matrix with the coalbed methane reservoir being an orthotropic medium and the elastic stiffness matrices with other formations being VTI media, including: Substituting the elastic stiffness coefficients in the elastic stiffness matrix with the coalbed methane reservoir being an orthotropic medium into the calculation formula of the model parameters to obtain the model parameters of the coalbed methane reservoir; Substitute the elastic stiffness coefficients in the elastic stiffness matrix of the target formation which is a VTI medium into the calculation formula of the model parameters to obtain the model parameters of the target formation; wherein, the target formation represents any one of the other formations; Perform a moving average process on the model parameters of all formations in the study area to obtain the initial model parameter vector of the study area.

4. The deep coal seam fracture density azimuth seismic inversion method according to claim 1, characterized in that Solving the objective function includes: Calculating the first-order derivative of the objective function with respect to the model parameter vector to obtain a first function; Constructing a pseudo-Hessian matrix based on the first function and the model parameter vector; Constructing a second function for solving the model parameter vector based on the first function and the pseudo-Hessian matrix; Performing iterative solution on the second function based on the initial model parameter vector and the pre-stack seismic trace gather data until a preset iteration termination condition is reached to obtain the target model parameter vector.

5. The deep coal seam fracture density azimuth seismic inversion method according to claim 4, characterized in that Performing iterative solution on the second function based on the initial model parameter vector and the pre-stack seismic trace gather data includes: Extracting non-90-degree azimuth seismic records from the pre-stack seismic trace gather data to obtain a first seismic record; Extracting 90-degree azimuth seismic records from the pre-stack seismic trace gather data to obtain a second seismic record; Calculating the difference between the first seismic record and the second seismic record to obtain a third seismic record; Using the third seismic record as the true seismic record in the second function and performing iterative solution on the second function in combination with the initial model parameter vector.

6. The method for seismic inversion of fracture density azimuth in deep coal seams according to claim 1, wherein It also includes: Obtaining a first training sample set and a second training sample set; wherein, the first training sample set includes multiple groups of first training samples, and each group of first training samples includes: the fracture density and azimuthal anisotropy gradient of the coalbed methane reservoir; the second training sample set includes multiple groups of second training samples, and each group of second training samples includes: the fracture density of the coalbed methane reservoir and the difference in the longitudinal wave velocities propagating along the normal direction and the strike direction of the fracture surface; Training a first initial fracture density prediction model based on the first training sample set to obtain a first fracture density prediction model; Training a second initial fracture density prediction model based on the second training sample set to obtain a second fracture density prediction model; Calculating the goodness of fit of the first fracture density prediction model and the second fracture density prediction model respectively, and determining the target prediction model from the first fracture density prediction model and the second fracture density prediction model based on the calculation results of the goodness of fit.

7. The method for seismic inversion of fracture density azimuth in deep coal seams according to claim 6, characterized in that Both the first fracture density prediction model and the second fracture density prediction model are support vector regression models.

8. A device for seismic inversion of fracture density and azimuth in deep coal seams, characterized in that, It includes: An acquisition module for acquiring pre-stack seismic trace gather data and logging data of the study area; A first construction module for constructing an elastic stiffness matrix of each formation in the study area as a VTI medium based on the logging data; A first processing module for processing the porosity of the coalbed methane reservoir in the logging data and the elastic stiffness matrix of the coalbed methane reservoir as a VTI medium according to the linear slip theory to obtain an elastic stiffness matrix of the coalbed methane reservoir as an orthotropic medium; A second construction module, configured to construct an initial model parameter vector of the study area based on the elastic stiffness matrix of the coalbed methane reservoir being an orthotropic medium and the elastic stiffness matrix of other formations being a VTI medium; wherein the model parameters include: azimuthal anisotropy gradient, and the difference in the longitudinal wave velocities propagating in the normal direction of the fracture surface and the fracture strike direction. A third construction module, configured to construct an objective function for inverting the model parameters based on the prestack seismic gather data, the reflection coefficient approximation formula for orthotropic anisotropy, and the initial model parameter vector. A solution module, configured to solve the objective function to obtain an objective model parameter vector of the study area. A second processing module, configured to process the objective model parameters of the coalbed methane reservoir in the objective model parameter vector by using an objective prediction model to obtain the fracture density of the coalbed methane reservoir; wherein each model parameter corresponds to a fracture density prediction model, and the objective prediction model represents the model with the highest goodness of fit among the fracture density prediction models corresponding to two model parameters.

9. An electronic device, comprising a memory and a processor, wherein a computer program capable of running on the processor is stored on the memory, characterized in that, When the processor executes the computer program, it implements the deep coal seam fracture density azimuth seismic inversion method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by the processor, it implements the deep coal seam fracture density azimuth seismic inversion method according to any one of claims 1 to 7.

Images