Inversion analysis method for initial stress field of underground powerhouse

Abstract

The invention provides an inversion analysis method for an initial stress field of an underground powerhouse, and the method comprises the steps: building a model diagram of a mountain area of the underground powerhouse in FLAAC3D, building a plurality of ground stress measurement points, actually measuring ground stress data, analyzing the actually measured ground stress, and screening out representative sample points; by calculating the actual lateral stress coefficient ki of the stress component of each measuring point, the fitted stress function can be imported into FLAC3D to form an approximate ancient stress field; a generative adversarial network is introduced to carry out fine adjustment on an ancient lateral stress coefficient, a current crustal stress field is optimized, and the requirements of engineering analysis are met. The uniform design has the advantages that the test times can be reduced to a great extent, and the training samples are uniformly dispersed. After each uniform design test, GAN training can be carried out, after training is completed, data of measuring points are input into GAN, an optimized lateral stress coefficient can be obtained, an optimized ancient crustal stress field can be obtained through calculation, and a current crustal stress field can be obtained after nonlinear elastic-plastic excavation simulation.

Description

Technical Field

[0001] The invention relates to the field of rock and soil mechanics, and in particular to an inversion analysis method for an initial stress field of an underground powerhouse. Background Art

[0002] The quantitative study of the magnitude of geostress is to conduct field measurement and monitoring on the one hand, and to perform inversion analysis and calculation of the initial geostress field based on limited observation data on the other hand, so as to obtain the initial geostress value and distribution law of the entire project area. The on-site observation of geostress can obtain more realistic geostress data of the measuring point, especially with the development of science and technology, the observation equipment and observation methods are becoming more and more advanced and accurate, but the biggest disadvantage of on-site observation is that the cost is too high. Therefore, how to accurately predict and analyze the distribution of geostress in the entire project area based on limited measurement points is of great significance. Summary of the invention

[0003] The main purpose of the present invention is to provide an inversion analysis method for the initial stress field of an underground powerhouse to solve the problems in the above-mentioned background technology.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: the method steps are as follows:

[0005] S1. In FLΑC 3D The model diagram of the underground powerhouse mountain area is established in the 3D numerical model. The X-axis is selected as the main powerhouse axis direction, the Y-axis is the upstream and downstream direction, and the Z-axis is vertically upward;

[0006] S2. Establish multiple geostress measurement points, measure geostress data, analyze the measured geostress, and select representative sample points;

[0007] S3. Calculate the actual lateral stress coefficient k of the stress component of each measuring point through formula (1): i The fitted stress function can be imported into FLΑC 3D In the middle, an approximate ancient stress field is formed;

[0008]

[0009] Among them, α i and b i is the regression factor, k i is the lateral stress coefficient of the six stress components, H is the burial depth;

[0010] S4. Input the numerical simulation parameters of each rock mass into FLΑC 3D In the ancient model, the coordinates of the units containing the rock mass and faults are output by the FISH language and then assigned to the model according to the parameters of the equivalent units. The equivalent units are numerically simulated using a transversely isotropic elastic constitutive model;

[0011] S5. In FLΑC 3D In the example, each unit area stores 6 stress components and each unit node stores unbalanced forces. 3D Guidelines in the User Manual for performing geostress balance calculations on the model;

[0012] S6. By using the generative adversarial grid (GAN), the optimized regression factor is further determined to obtain the optimized current initial geostress field.

[0013] Preferably, the specific steps of step S5 are as follows:

[0014] Α1. According to formula (1), the paleo-stress field can be calculated and imported into FLΑC 3D The rock mass is then input into the model;

[0015] Α2. Apply normal constraints to the boundaries around and on the bottom of the ancient model;

[0016] A3. Execute the command for the model, that is, calculate one step, and then record the unbalanced point on the unit node;

[0017] A4. Apply a force opposite to the unbalance in step A3 to each unit node in the ancient model;

[0018] Α5. Repeat steps Α3 and Α4 several times to make the stress components close enough to the stress components in the ancient model.

[0019] Preferably, the method for calculating the equivalent unit includes dividing the rock mass into hexahedral units, and due to the existence of faults, some rock mass units are cut by faults, and these units contain both the rock mass and the faults, forming composite units;

[0020] A set of mechanical parameters is assigned to a unit, so the mechanical parameters of the composite unit with both rock mass and fault need to be equivalent. The local coordinate system (x′y′z′) established on the fault plane of the composite unit simplifies the composite unit into a transversely isotropic equivalent unit with layered distribution.

[0021] H k is the unit layer thickness, which can be expressed as:

[0022] H k =V k / A (2)

[0023] Where subscript k is equal to 1 or 2, representing the parameters of rock mass and fault, respectively, V k is the volume of the rock mass or fault, and A is the contact area between the rock mass and the fault.

[0024] Preferably, for the z′ direction, the deformation and stress of the equivalent unit are:

[0025]

[0026] in, σ v1 and σ v2 are the stresses applied on the equivalent unit, rock mass and fault in the z′ direction, is the equivalent elastic modulus in the z′ direction;

[0027] Based on formula (3), the equivalent elastic modulus in the z′ direction is:

[0028]

[0029] Preferably, for the x′ and y′ directions, assuming that the elongation of the rock mass and the fault in the equivalent unit is equal, then

[0030]

[0031] in, ε h1 and ε h2 are the strains of the equivalent unit, rock mass and fault in the x′ and y′ directions, respectively, σ h1 and σ h2 are the stresses applied to the equivalent unit, rock mass and fault in the x′ and y′ directions, respectively,

[0032] Formula (5) can be written as:

[0033]

[0034] According to equations (5) and (6), the equivalent elastic modulus is:

[0035]

[0036] Combining equations (5) and (7), the equivalent Poisson's ratio μ can be expressed as

[0037]

[0038] Preferably, when performing GAN, the underground cavern and its surrounding measuring points and the measuring points near the boundary of the numerical model are selected as samples, and each regression factor α i or b i The value range of is between 0.5 and 1.5 times of itself. Multiple regression factors are used for uniform design experiments, so multiple regression models with different α can be designed. i or b i The value of the paleo-stress field;

[0039] Substitute each regression factor into equation (1) and equation (9) to calculate the stress component of each unit and import it into FLΑC 3D Calculation is performed in

[0040] σ i (x,y,z)=k i γH (9)

[0041] where σ1–σ6 are stress components σ x ,σ y ,σ z ,τ yz ,τ zx and τ xy , k i is the lateral stress coefficient of the six stress components, H is the burial depth, and γ is the bulk density.

[0042] Preferably, after training with real data samples, the X and Y coordinates are input, and the present burial depth and lateral stress coefficient of the measuring point are input into the present stress field of the measuring point, so as to obtain the regression factor of the paleo-geo-stress field;

[0043] After GAN training, the regression factor of the optimized paleoclimatic stress field can be predicted. Therefore, the optimized paleoclimatic stress field can be obtained by formula (1). By mining the optimized paleoclimatic stress field, the current geostress field can be obtained.

[0044] Preferably, the uniform design experiment includes designing different α i and b i Multiple combinations of values, α i and b i The measurement point parameters under different combinations are:

[0045] x=[x1,x2,…x n ] T (10)

[0046] y=[y1,y2,…y 1n ] T (11)

[0047]

[0048] Where x and y are the coordinate vectors of the measured point in the horizontal plane, n is the number of measurement points, and H p is the buried depth vector of the current measured point, k j is the lateral stress coefficient matrix of the current measuring point, j is the number of uniform design tests, α j and b j is the stress component σ at the ancient measuring point x ,σ y ,σ z ,τ yz,τ zx and τ xy The regression factor matrix of .

[0049] Preferably, after each uniform design experiment, GAN training is performed, and the real data sample input to GAN can be expressed as:

[0050]

[0051] After the training is completed, the data of the measurement points are input into GAN to obtain the optimized α i and b i The optimized ancient geostress field can be calculated by formula (1), and then the current geostress field can be obtained after nonlinear elastic-plastic excavation simulation.

[0052] The present invention provides an inversion analysis method for the initial stress field of an underground powerhouse, introduces a generative adversarial network to fine-tune the ancient lateral stress coefficient, optimizes the current geostress field, and meets the needs of engineering analysis. The advantage of uniform design is that the number of tests can be greatly reduced and the training samples can be kept uniformly dispersed. After each uniform design test, GAN training can be performed. After the training is completed, the data of the measuring point is input into GAN, and the optimized lateral stress coefficient can be obtained. The optimized ancient geostress field can be obtained by calculation, and the current geostress field can be obtained after nonlinear elastoplastic excavation simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0054] Figure 1 is the relationship between the loss function and iteration of the GAN generator and discriminator of the present invention;

[0055] Figure 2 It is the calculation process of GAN of the present invention;

[0056] Figure 3 It is a schematic diagram of a composite unit of a fault-cut rock mass according to the present invention;

[0057] Figure 4 It is a schematic diagram of an equivalent unit of a fault-cut rock mass according to the present invention. DETAILED DESCRIPTION

[0058] like Figures 1 to 4 As shown in the figure, the initial stress field inversion analysis method of underground powerhouse is 3DThe model diagram of the underground powerhouse mountain area is established in the 3D numerical model. The X-axis of the 3D numerical model is selected as the main powerhouse axis direction, the Y-axis is the upstream and downstream direction, and the Z-axis is vertically upward. In this example, 10 ground stress measurement points are selected. Since the measured ground stress is obtained in the geodetic coordinate system, it needs to be converted into the coordinates in the model. According to the distribution characteristics of the ground stress at the measured points, representative sample points are selected and the actual lateral stress coefficient k of the six stress components of each measuring point is calculated. i Based on formula (1), we can get the relationship between current burial depth and k i The fitted stress function can be imported into FLΑC 3D In the strata, an approximate ancient stress field is formed.

[0059]

[0060] Among them, α i and b i is the regression factor, k i is the lateral stress coefficient of the six stress components, H is the burial depth;

[0061] In this example, the Z-direction range of the ancient model is from the bottom elevation of 1970m to the ancient surface. The upper 6 layers of the model are excavated ancient strata, which are used to simulate the erosion process of the valley. Input to FLΑC 3D The parameters of the ancient model are shown in Table 1. The coordinates of the units containing the rock mass and faults are output by the FISH language. Then, the parameters of the equivalent units are calculated and assigned to the model. The equivalent units are numerically simulated using a transversely isotropic elastic constitutive model.

[0062] Table 1: Parameters of numerical simulation

[0063]

[0064] In FLΑC 3D In the FLΑC model, each unit area stores 6 stress components and each unit node stores unbalanced force. If the model unit node does not apply unbalanced force in the X, Y, and Z directions, the stress in the unit area will change, and the model calculation results will deviate greatly from the actual results. In order to optimize the model in subsequent calculations, according to FLΑC 3D Following the guidelines in the User Manual, the model is subjected to the following geostress balance calculations:

[0065] (1) According to formula (1), the paleo-stress field can be calculated and imported into FLΑC 3D Then the rock mass parameters are input into the model;

[0066] (2) Apply normal constraints to the boundaries around and on the bottom of the ancient model;

[0067] (3) Execute the "step 1" command on the model, that is, calculate one step and then record the unbalanced force on the unit node;

[0068] (4) applying a force opposite to the unbalanced force in step (3) to each unit node in the ancient model;

[0069] (5) Repeat (3) and (4) several times to make the stress components close enough to those in the ancient model.

[0070] After the above process, the equilibrium calculation of the approximate paleoclimatic stress field is completed. By excavating the ancient strata layer by layer, the present-day geostress field can be obtained, and then the six stress components and lateral stress coefficients of each measured point can be obtained. However, these lateral stress coefficients are obtained by approximating the paleoclimatic stress field, so there may be some unacceptable errors, and the optimization regression factor needs to be further determined.

[0071] By using the Generative Adversarial Network (GAN) to optimize the current geostress field, it is necessary to construct enough real samples for training. The initial geostress inversion of this engineering example is to provide accurate geostress for underground cavern excavation, so the measurement points of the underground cavern and its surroundings are selected as samples. In addition, boundary effects will appear in the numerical excavation simulation, so the measurement points near the boundary of the numerical model are selected as samples.

[0072] Based on a large number of trial calculations, the floating range of the regression factor in formula (1) can be determined. i or b i The value range is between 0.5 and 1.5 times of itself. Take 12 regression factors as the factors of the uniform design experiment, and regard different regression factor values ​​as different levels. According to the principle of uniform design, the regression factor has 13 levels. Then, levels 1 to 13 correspond to regression factors 0.52, 0.60, 0.68, 0.76, 0.84, 0.92, 1.00, 1.08, 1.16, 1.24, 1.32, 1.40, and 1.48 times, respectively. The regression factors of each test can be substituted into equations (1) and (9) to calculate the stress components of each unit and imported into FLΑC 3D Calculations are performed. In each test, the calculated stress components and lateral stress coefficients of the measured points can be obtained. There are 8 valid measurement points, so 8 training samples can be created for each test, for a total of 13×8=104 samples.

[0073] After training with real data samples, input the x and y coordinates, input the current burial depth and lateral stress coefficient of the measuring point in the current stress field of the measuring point, and then the regression factor of the paleo-geo-stress field can be obtained. Then, the optimized paleo-geo-stress field can be obtained by formula (9). Figure 1The relationship between the loss function and iteration of the generator and discriminator in GΑN is shown. The generator G and the discriminator network D constantly compete to minimize the loss function of the two networks, indicating that the sample data output by the generator is stable. After GΑN training, the regression factor of the optimized paleoclimatic stress field can be predicted, so the optimized paleoclimatic stress field can be obtained by formula (1). By mining the optimized paleoclimatic stress field, the current geostress field can be obtained. The regression factors and calculated stress values ​​of the measuring points are listed in Tables 2 and 3, and the relative error Δ of the measuring points can be calculated as:

[0074]

[0075] in, is the calculated stress component, σ i are the measured stress components and ||…||2 is the 2-norm.

[0076] Table 2: Regression factors of paleo-stress field obtained using GAN and BP neural network

[0077]

[0078] Table 3: Stress component values ​​of each measuring point based on GAN and BP neural network

[0079]

[0080]

[0081] In order to compare with the GAN inversion method, the stress component regression factors obtained by BP neural network are also listed in Tables 2 and 3. For both methods, σ x , σ y and σ z The relative error is less than 15%, which is less than τ yz , τ xz and τ xy More accurate. According to statistics, the error of geostress measurement results can reach 25%-30%. The maximum relative error of the GAN measurement point is 17.46%, and the distribution law of the geostress field is reasonable. For the BP method, the relative error of measurement point 8 reaches 28.4%, and the average relative error of GAN is smaller than that of the BP method, especially τ yz , τ xz and τ xy .

[0082] Example 2

[0083] According to Example 1, it is further explained that based on the approximate ancient geostress field, the ancient strata can be excavated layer by layer through numerical simulation to obtain the current stress field. Since the ancient geostress field is an approximate estimate, the current geostress field obtained may have a large error. To address this problem, this example introduces a generative adversarial network (GAN) to fine-tune the ancient lateral stress coefficient, optimize the current geostress field, and meet the needs of engineering analysis.

[0084] GAN consists of a generator and a discriminator trained on an adversarial learning mechanism, such as Figure 2 As shown in the figure; the goal of GΑN is to estimate and predict the distribution law of the acquired data, and use the generator G to generate new data from the same distribution law. The generator G transforms the random variable z into new data that can be forged by continuously learning the probability distribution of the real data. The discriminator D is a binary classifier used to distinguish whether the input data is real or generated data. The two networks are enhanced simultaneously through mutual competition during training, so that the two networks constitute a dynamic game process until the Nash equilibrium is reached. Both the generator and the discriminator can be designed in combination with the current deep neural network. The calculation process of GΑN can be summarized as a binary minimax game, and the objective function can be defined as:

[0085]

[0086] Among them, V(D,G) is the cross entropy loss of the two categories, P dαtα(x) is the real data distribution, P g(z) is the random variable distribution, G (z) is a generator based on random variables, E(·) represents the calculated expected value; when P dαtα =P g The global optimal solution is reached when the loss functions of the generator and discriminator of GΑN are expressed as log(D(G(z))) and log(D(x))+log(1-D(G(z))).

[0087] Example 3

[0088] Further explanation according to Example 1: The parameter differences between faults and rock masses are very large. If the influence of faults is not considered in the inversion of the current stress field, large errors will occur. Therefore, before simulating the excavation of ancient strata, the fault parameters should be assigned to the corresponding units. In numerical simulation analysis, they are often simplified to thin units, but faults and underground caves usually do not intersect in an orthogonal form. Due to the limited thickness of faults and the complex intersection relationship, this method of handling faults may bring difficulties to the mesh generation of the model. In this example, the rock mass is divided into hexahedral units. Due to the existence of faults, some rock mass units are cut by faults. These units contain both rock mass and faults, forming composite units, such as Figure 3 As shown in Figure 1. For a unit, only one set of mechanical parameters can be assigned, so the mechanical parameters of the composite unit with both rock mass and fault need to be equivalent. The local coordinate system (x′y′z′) established on the fault plane of the composite unit simplifies the composite unit into a layered, transversely isotropic equivalent unit with parameters such as Figure 4 As shown. k is the unit layer thickness, which can be expressed as:

[0089] H k =V k / A (2)

[0090] Where subscript k is equal to 1 or 2, representing the parameters of rock mass and fault, respectively, V k is the volume of the rock mass or fault, and A is the contact area between the rock mass and the fault.

[0091] For the z′ direction, the deformation and stress of the equivalent element are:

[0092]

[0093] in, σ v1 and σ v2 are the stresses applied on the equivalent unit, rock mass and fault in the z′ direction, is the equivalent elastic modulus in the z′ direction;

[0094] Based on formula (3), the equivalent elastic modulus in the z′ direction is:

[0095]

[0096] For the x′ and y′ directions, assuming that the elongation of the rock mass and the fault in the equivalent unit is equal, then

[0097]

[0098] in, ε h1 and ε h2are the strains of the equivalent unit, rock mass and fault in the x′ and y′ directions, respectively, σ h1 and σ h2 are the stresses applied to the equivalent unit, rock mass and fault in the x′ and y′ directions, respectively,

[0099] Formula (5) can be written as:

[0100]

[0101] According to equations (5) and (6), the equivalent elastic modulus is:

[0102]

[0103] Combining equations (5) and (7), the equivalent Poisson's ratio μ can be expressed as

[0104]

[0105] Example 4

[0106] Further explanation in combination with Examples 1 and 2: When performing GAN, the underground cavern and its surrounding measurement points and the measurement points near the boundary of the numerical model are selected as samples, and each regression factor α i or b i The value range of is between 0.5 and 1.5 times of itself. Multiple regression factors are used for uniform design experiments, so multiple regression models with different α can be designed. i or b i The value of the paleo-stress field;

[0107] Substitute each regression factor into equation (1) and equation (9) to calculate the stress component of each unit and import it into FLΑC 3D Calculation is performed in

[0108] σ i (x,y,z)=k i γH (9)

[0109] where σ1–σ6 are stress components σ x ,σ y ,σ z ,τ yz ,τ zx and τ xy , k i is the lateral stress coefficient of the six stress components, H is the burial depth, and γ is the bulk density.

[0110] After training with real data samples, the X and Y coordinates are input, and the present burial depth and lateral stress coefficient of the measuring point are input into the present stress field of the measuring point to obtain the regression factor of the paleo-geo-stress field;

[0111] After GAN training, the regression factor of the optimized paleoclimatic stress field can be predicted. Therefore, the optimized paleoclimatic stress field can be obtained by formula (1). By mining the optimized paleoclimatic stress field, the current geostress field can be obtained.

[0112] Uniform design experiments include designing different α i and b i Multiple combinations of values, α i and b i The measurement point parameters under different combinations are:

[0113] x=[x1,x2,…x n ] T (10)

[0114] y=[y1,y2,…y 1n ] T (11)

[0115]

[0116] Where x and y are the coordinate vectors of the measured point in the horizontal plane, n is the number of measurement points, and H p is the buried depth vector of the current measured point, k j is the lateral stress coefficient matrix of the current measuring point, j is the number of uniform design tests, α j and b j is the stress component σ at the ancient measuring point x ,σ y ,σ z ,τ yz ,τ zx and τ xy The regression factor matrix of .

[0117] After each uniform design experiment, GAN is trained and the real data sample input to GAN can be expressed as:

[0118]

[0119] After the training is completed, the data of the measurement points are input into GAN to obtain the optimized α i and b i The optimized ancient geostress field can be calculated by formula (1), and then the current geostress field can be obtained after nonlinear elastic-plastic excavation simulation.

[0120] The above embodiments are only preferred technical solutions of the present invention and should not be regarded as limiting the present invention. The protection scope of the present invention shall be the technical solutions recorded in the claims, including equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. The inversion analysis method of the initial stress field of the underground powerhouse is as follows: S1. In FLΑC 3D The model diagram of the underground powerhouse mountain area is established in the 3D numerical model. The X-axis is selected as the main powerhouse axis direction, the Y-axis is the upstream and downstream direction, and the Z-axis is vertically upward; S2. Establish multiple geostress measurement points, measure geostress data, analyze the measured geostress, and select representative sample points; S3. Calculate the actual lateral stress coefficient k of the stress component of each measuring point through formula (1): i The fitted stress function can be imported into FLΑC 3D In the middle, an approximate ancient stress field is formed; in, α i and b i is the regression factor, k i is the lateral stress coefficient of the six stress components, H is the burial depth; S4. Input the numerical simulation parameters of each rock mass into FLΑC 3D In the ancient model, the coordinates of the units containing the rock mass and faults are output by the FISH language and then assigned to the model according to the parameters of the equivalent units. The equivalent units are numerically simulated using a transversely isotropic elastic constitutive model; S5. In FLΑC 3D In the example, each unit area stores 6 stress components and each unit node stores unbalanced forces. 3D Guidelines in the User Manual for performing geostress balance calculations on the model; S6. By using the generative adversarial grid (GAN), the optimized regression factor is further determined to obtain the optimized current initial geostress field.

2. The inversion analysis method for initial stress field of underground powerhouse according to claim 1 is characterized by: The specific steps of step S5 are as follows: Α1. According to formula (1), the paleo-stress field can be calculated and imported into FLΑC 3D The rock mass is then input into the model; Α2. Apply normal constraints to the boundaries around and on the bottom of the ancient model; A3. Execute the command for the model, that is, calculate one step, and then record the unbalanced point on the unit node; A4. Apply a force opposite to the unbalance in step A3 to each unit node in the ancient model; Α5. Repeat steps Α3 and Α4 several times to make the stress components close enough to the stress components in the ancient model.

3. The inversion analysis method for initial stress field of underground powerhouse according to claim 1 is characterized by: The method of calculating equivalent units includes dividing the rock mass into hexahedral units. Due to the existence of faults, some rock mass units are cut by faults. These units contain both rock mass and faults, forming composite units. A set of mechanical parameters is assigned to a unit, so the mechanical parameters of the composite unit with both rock mass and fault need to be equivalent. The local coordinate system (x′y′z′) established on the fault plane of the composite unit simplifies the composite unit into a transversely isotropic equivalent unit with layered distribution. H k is the unit layer thickness, which can be expressed as: H k =V k / A (2) Where subscript k is equal to 1 or 2, representing the parameters of rock mass and fault, respectively, V k is the volume of the rock mass or fault, and A is the contact area between the rock mass and the fault.

4. The method for inversion of geostress field by producing an adversarial grid according to claim 3, characterized in that: For the z′ direction, the deformation and stress of the equivalent element are: in, and σ v2 are the stresses applied on the equivalent unit, rock mass and fault in the z′ direction, is the equivalent elastic modulus in the z′ direction; Based on formula (3), the equivalent elastic modulus in the z′ direction is:

5. The method for inversion of geostress field by producing an adversarial grid according to claim 3, characterized in that: For the x′ and y′ directions, assuming that the elongation of the rock mass and the fault in the equivalent unit is equal, then in, and ε h2 are the strains of the equivalent unit, rock mass and fault in the x′ and y′ directions, respectively, σ h1 and σ h2 are the stresses applied to the equivalent unit, rock mass and fault in the x′ and y′ directions, respectively, Formula (5) can be written as: According to equations (5) and (6), the equivalent elastic modulus is: Combining equations (5) and (7), the equivalent Poisson's ratio μ can be expressed as:

6. The method for inversion of geostress field of production antagonistic grid according to claim 1, characterized in that: When performing GAN, the underground cavern and its surrounding measurement points and the measurement points near the boundary of the numerical model are selected as samples. i or b i The value range of is between 0.5 and 1.5 times of itself. Multiple regression factors are used for uniform design experiments, so multiple regression models with different α can be designed. i or b i The value of the paleo-stress field; Substitute each regression factor into equation (1) and equation (9) to calculate the stress component of each unit and import it into FLΑC 3D Calculation is performed in σ i (x,y,z)=k i γH (9) where σ1–σ6 are the stress components σ x ,σ y ,σ z ,τ yz ,τ zx and τ xy , k i is the lateral stress coefficient of the six stress components, H is the burial depth, and γ is the bulk density.

7. The method for inversion of geostress field by producing an adversarial grid according to claim 6, characterized in that: After training with real data samples, the X and Y coordinates are input, and the present burial depth and lateral stress coefficient of the measuring point are input into the present stress field of the measuring point to obtain the regression factor of the paleo-geo-stress field; After GAN training, the regression factor of the optimized paleoclimatic stress field can be predicted. Therefore, the optimized paleoclimatic stress field can be obtained by formula (1). By mining the optimized paleoclimatic stress field, the current geostress field can be obtained.

8. The method for inversion of geostress field by producing an adversarial grid according to claim 6, characterized in that: Uniform design experiments include designing different α i and b i Multiple combinations of values, α i and b i The measurement point parameters under different combinations are: x=[x1,x2,…x n ] T (10) y=[y1,y2,…y 1n ] T (11) Where x and y are the coordinate vectors of the measured point in the horizontal plane, n is the number of measurement points, and H p is the buried depth vector of the current measured point, k j is the lateral stress coefficient matrix of the current measuring point, j is the number of uniform design tests, α j and b j is the stress component σ at the ancient measuring point x ,σ y ,σ z ,τ yz ,τ zx and τ xy The regression factor matrix of .

9. The method for inversion of geostress field of producing an adversarial grid according to claim 8, characterized in that: After each uniform design experiment, GAN is trained and the real data sample input to GAN can be expressed as: After the training is completed, the data of the measurement points are input into GAN to obtain the optimized α i and b i The optimized ancient geostress field can be calculated by formula (1), and then the current geostress field can be obtained after nonlinear elastic-plastic excavation simulation.

Images