Method for establishing rock multi-field coupling model and model thereof

Abstract

The invention discloses an establishment method of a rock multi-field coupling model and the model thereof, and belongs to the technical field of engineering geological survey. Through comprehensive application of multi-scale modeling, a nondestructive testing technology, a machine learning algorithm and intelligent optimization, the problems that existing multi-physical field coupling analysis is not deep enough, the precision of an observation method is poor, and a device is prone to being damaged are solved, the advantages of various observations are combined, the building and analysis precision of a rock multi-field coupling model is improved, and the rock multi-field coupling analysis precision is improved. The method has the advantages that the method is simple and convenient to operate, the intelligence and automation level of the model is enhanced, microstructure data and macroscopic response are combined, deeper understanding of rock behaviors is provided, meanwhile, more accurate and efficient decision support can be provided for rock engineering design and construction, and the method is worthy of popularization and application. And a novel analysis and simulation method is provided for the field of rock mechanics research. Through the comprehensive scheme, behaviors of rocks under complex geological conditions can be better predicted and managed, so that the safety and economical efficiency of engineering are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of engineering geological survey, and specifically relates to a method for establishing a rock multi-field coupling model and a model thereof. Background Art

[0002] The research on the multi-field coupling problem of rock has a history of decades, covering the effects of single physical field, two-field coupling and three-field coupling on rock. In deep mineral resource mining and underground space development, the environment in which the rock is located is extremely complex, involving high temperature, high osmotic pressure, high stress and complex water chemical environment. These factors work together to form the temperature-water flow-stress-chemistry (THMC) multi-field coupling effect.

[0003] Although some progress has been made in existing research, there are still deficiencies in the establishment of multi-field coupling constitutive models, crack evolution, and in-depth understanding of deformation mechanics mechanisms. Especially in deep rock mass engineering, the complexity of multi-field coupling has brought challenges to the stability analysis of rock engineering, and existing research has not yet fully revealed the laws of changes in the physical and mechanical properties of rocks under multi-field coupling.

[0004] In order to better understand the behavior of rocks under multi-field coupling, experiments and numerical simulations are the two main research methods. Experimental research studies the rock structure and evolution process from micro to macro by improving and developing multi-field coupling test systems and combining modern non-destructive detection technologies such as real-time CT scanning, SEM, and NMRI.

[0005] In terms of numerical simulation, with the development of computer technology, such as the software combining TOUGHREACT and FLAC3D and the program docking Comsol and Matlab, technical support is provided for multi-field coupling simulation ("A review of research on physical and mechanical properties and constitutive models of rocks under THMC multi-field coupling", Yan Bingqian et al., Journal of Engineering Science, 2020).

[0006] In view of the intelligent feedback analysis method for the long-term stability of rock engineering, some studies have proposed dynamic analysis methods based on field feedback information. These methods can timely combine field information with geological analysis models and provide suggestions for design, construction and long-term stability maintenance based on the analysis results ("Study on Intelligent Feedback Analysis Method and Application of Long-term Stability of Rock Engineering", Chen Bingrui, Chinese Journal of Rock Mechanics and Engineering, 2008). This method reflects the supplement and improvement of existing technologies, especially in model identification and parameter identification.

[0007] The establishment of a rock multi-field coupling model is the basis of the research. Some patent documents have conducted useful research on this and proposed some solutions.

[0008] For example, Chinese patent CN109284571A discloses a mathematical modeling method for multi-scale and multi-field coupled seepage of shale gas replaced by carbon dioxide. Based on the established multi-scale classification model of gas flow morphology in shale pores and fractures, the method establishes a multi-field coupled seepage mathematical model of a multi-component gas system of shale gas replaced by carbon dioxide in shale matrix nanopores, matrix nano-micron pores and fractures, and establishes a differential numerical model within the block center grid block and between grid blocks.

[0009] In summary, the existing technology has achieved certain results in the study of the mechanical properties of rocks under multi-field coupling, but it still needs further development. Future research should pay more attention to the in-depth analysis of multi-physical field coupling to improve the accuracy and practicality of the model.

[0010] In addition, the further development of intelligent feedback analysis methods, combined with machine learning and artificial intelligence technologies, is expected to provide more efficient and accurate tools for stability analysis in rock engineering. Summary of the invention

[0011] The purpose of the present invention is to solve the problem that the analysis of multi-physical field coupling in existing rock engineering is not in-depth enough. In addition, the advantages of non-contact observation and contact observation are combined to overcome the problems in existing observation methods such as poor accuracy and easy damage of the device. A method for establishing a rock multi-field coupling model and its model are proposed. Through the comprehensive application of multi-scale modeling, non-destructive testing technology, machine learning algorithm and intelligent optimization, not only the accuracy of the establishment and analysis of the rock multi-field coupling model is improved, but also the intelligence and automation level of the model are enhanced. It also combines microstructural data with macroscopic response to provide a deeper understanding of rock behavior. At the same time, the present invention can provide more accurate and efficient decision support for rock engineering design and construction, and also provides a new analysis and simulation method for the field of rock mechanics research. Through this comprehensive solution, the behavior of rocks under complex geological conditions can be better predicted and managed, thereby improving the safety and economy of the project.

[0012] In order to solve the above technical problems, the present invention provides a method for establishing a rock multi-field coupling model and a model thereof, comprising:

[0013] S1. Obtain rock samples by sampling, obtain initial data and perform data preprocessing, and input the preprocessed data into a computer system;

[0014] S2. At the microscopic scale, based on the initial data obtained, the microscopic mechanical behavior of rocks is characterized by statistical or numerical methods;

[0015] S3, based on S2, convert the microscopic parameters to the upper scale, predict the response of the rock at the macroscale, and construct a multi-scale model;

[0016] S4, using the preprocessed data as input, based on the multi-scale model, performing finite element analysis to simulate the macroscopic response of rock under actual engineering conditions;

[0017] S5. Use machine learning algorithms to optimize machine learning model parameters and perform model verification.

[0018] Preferably, S1 comprises the following steps:

[0019] S11. Perform high-resolution imaging of rock surfaces and cracks, and detect the pore structure and fluid distribution inside the rock. At the same time, perform three-dimensional imaging of rock samples to obtain accurate spatial distribution data of pores and cracks.

[0020] S12, performing image segmentation on the acquired image data and three-dimensional reconstruction of the pore structure;

[0021] S13, normalizing the data obtained in S11 and S12;

[0022] S14. Input the preprocessed data into the computer system to provide necessary input conditions for the establishment and simulation of the multi-field coupling model.

[0023] Preferably, the data preprocessing includes image segmentation, three-dimensional reconstruction of pore structure and data normalization; obtaining initial data includes obtaining microstructure data and physical property data of rock samples through non-destructive testing technology in the laboratory and on-site.

[0024] Preferably, S2 includes: analyzing the microstructure data of the rock sample by a micromechanical model, and quantifying the microscopic properties of the rock by using a statistical method; predicting the local stress-strain relationship by a micromechanical model;

[0025] The expression of the micromechanical model is:

[0026] σ e =σ-αp;

[0027] Here, σ is the total stress, p is the pore pressure, and α is a coefficient related to the pore geometry.

[0028] Preferably, S3 includes:

[0029] S31. The relationship between macro stress and micro stress is derived through the Hill-Mandel condition, and the micro parameters are converted to the macro scale to determine the macro mechanical properties, which is specifically expressed as:

[0030] <σ micro >=σ macro ; In the formula, <σ micro > is the average value of micro stress, σ macrois the macro stress;

[0031] S32. Based on the macroscopic mechanical properties, verification is performed using experimental data obtained using standard rock mechanics tests.

[0032] Preferably, the standard rock mechanics test includes using uniaxial compression test data to verify the macro elastic modulus, and the specific expression is:

[0033] where Δσ is the change in applied stress and Δτ is the corresponding change in strain.

[0034] Preferably, S4 comprises the following steps:

[0035] S31. Based on the preprocessed data, use computer-aided design software to construct an accurate three-dimensional geometric model of the rock or rock structure and perform meshing to create a mesh model;

[0036] S32, defining material properties for the rock sample based on the grid model and applying actual engineering boundary conditions to the grid model;

[0037] S33. According to S32, a load is applied to the rock sample and a response analysis is performed to obtain a multi-scale model, that is, a rock multi-field coupling model; wherein the load includes a static load and a dynamic load.

[0038] Preferably, S5 comprises the following steps:

[0039] S51, selecting a machine learning algorithm, obtaining historical experimental data or field monitoring data, and training a machine learning model corresponding to the machine learning algorithm;

[0040] S52. After the machine learning model is trained, the machine learning algorithm adjusts and optimizes the parameters in the rock multi-field coupling model according to the input data and the model prediction error;

[0041] S53. Verify the optimized machine learning model; wherein the verification includes calculating the difference between the predicted value and the actual value.

[0042] A rock multi-field coupling model is established by a rock multi-field coupling model establishment method.

[0043] Beneficial effects of the present invention:

[0044] 1. This solution not only improves the accuracy of establishing and analyzing the rock multi-field coupling model, but also enhances the intelligence and automation level of the model through the comprehensive application of multi-scale modeling, non-destructive testing technology, machine learning algorithms and intelligent optimization. The implementation effect of the present invention is that it can provide more accurate and efficient decision support for rock engineering design and construction, and also provides a new analysis and simulation method for the field of rock mechanics research. Through this comprehensive solution, the behavior of rocks under complex geological conditions can be better predicted and managed, thereby improving the safety and economy of the project.

[0045] 2. This solution combines microstructural data with macroscopic responses through the application of multiscale modeling technology, providing a deeper understanding of rock behavior. The innovative effect is reflected in the ability to more accurately predict the mechanical response of rocks in actual geological engineering, especially under complex stress paths and multi-field coupling conditions. The establishment of multiscale models not only improves the understanding of rock failure modes, but also provides a more reliable theoretical basis for engineering design.

[0046] 3. This solution uses SEM, NMRI and CT scanning technologies to obtain high-resolution images of the internal structure of rocks, which are directly used for model initialization and verification. This advanced data acquisition method enables the model to be simulated based on the real rock microstructure, improving the prediction accuracy and reliability of the model. In addition, the application of non-destructive testing technology also reduces the deviations and damage that may be introduced by traditional sampling and testing.

[0047] 4. This solution uses machine learning algorithms to intelligently optimize model parameters, learn and identify the macroscopic mechanical properties of rocks, such as elastic modulus and creep parameters, from a large amount of data. Compared with traditional methods based on experience or theoretical derivation, machine learning algorithms can adjust model parameters more quickly and accurately to match actual observation data, thereby significantly improving the prediction accuracy and adaptability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0049] Figure 1 The figure is a flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] Example 1: Figure 1 As shown, a method for establishing a rock multi-field coupling model and a model thereof include:

[0052] S1, initial data collection and data preprocessing, including image segmentation, 3D reconstruction of pore structure and data normalization. Initial data collection includes obtaining microstructure and physical property data of rock samples in the laboratory and on site through non-destructive testing techniques such as SEM, NMRI and CT scanning. These data will provide the model with key information about the internal pores and cracks of the rock and the rock type. Subsequently, data preprocessing is performed to ensure data quality, including image segmentation, 3D reconstruction of pore structure and data normalization. The preprocessed data is then input into the multi-field coupling model, including the microstructural parameters and macroscopic physical properties of the rock.

[0053] Specifically, the steps include:

[0054] S11, the initial data collection process first involves obtaining high-quality microstructural images from rock samples. Scanning electron microscopy (SEM) is used to perform high-resolution imaging of rock surfaces and cracks to capture the microscopic characteristics of the rock. Nuclear magnetic resonance imaging (NMRI) technology is used to detect the pore structure and fluid distribution inside the rock. In addition, computed tomography (CT) technology is used to perform three-dimensional imaging of rock samples to obtain accurate spatial distribution data of pores and cracks. During the acquisition process, the imaging parameters and conditions of each technology need to be recorded to ensure the consistency and comparability of the data.

[0055] S12, the acquired image data then enters the preprocessing stage, including image segmentation and three-dimensional reconstruction of the pore structure. Image segmentation is the use of image processing technology to distinguish the solid matrix and pore space of the rock, which can be achieved by threshold segmentation method, and its basic formula is:

[0056] T = threshold;

[0057] V = {x|I(x) > T};

[0058] Where T is the segmentation threshold, I(x) is the intensity value of the image at point x, and V is the pore area after segmentation. 3D reconstruction converts 2D image data into a 3D model and uses voxelization to convert tomography data into a 3D mesh model, providing a geometric basis for subsequent finite element analysis. In image processing, "threshold" is a parameter used for image segmentation to map the pixel values ​​of an image to two categories in a binary image (usually black and white). The threshold operation is a simple method that determines whether each pixel belongs to the foreground or background based on its intensity value.

[0059] Specifically, for each pixel in the grayscale image, if its grayscale value is higher than or equal to the threshold (T), the pixel is set to white (or a high value, indicating the foreground) in the binary image; if the grayscale value of the pixel is lower than the threshold, the pixel is set to black (or a low value, indicating the background) in the binary image.

[0060] The choice of threshold depends on the characteristics of the image and the goal of segmentation. It can be global (using a single threshold for the entire image) or local (using different thresholds for different areas of the image). The determination of the threshold can be based on histogram analysis of the image, Otsu's method, or other more advanced algorithms.

[0061] In rock microstructure image segmentation, threshold segmentation can help distinguish rock pores and cracks from rock matrix, thereby providing accurate binary images for subsequent 3D reconstruction and analysis.

[0062] S13, after completing image segmentation and 3D reconstruction, data normalization is performed to eliminate the dimension and magnitude differences between different rock samples or different imaging techniques. The normalization formula is:

[0063]

[0064] Here, X is the original data, X min and X max are the minimum and maximum values ​​in the data set, respectively, and X n It is the normalized data. Normalization ensures that data from different sources can be compared and analyzed on a unified scale. Finally, the preprocessed data is input into the multi-field coupling model, including the microstructure parameters and macroscopic physical properties of the rock, to provide the necessary input conditions for model establishment and simulation.

[0065] S2, after collecting and preprocessing the data, the next step is to build a multiscale model. First, at the microscale, statistical or numerical methods are used to characterize the micromechanical behavior of the rock based on the acquired microstructural data. Then, the microscopic parameters are upscaled to predict the response of the rock at the macroscale. This step involves determining the macromechanical properties of the rock, such as elastic modulus and strength parameters, which can be inferred from the microstructure through appropriate homogenization techniques.

[0066] Specifically, the steps include:

[0067] S21, through the analysis of the microstructural data of rock samples, uses statistical methods (such as maximum likelihood estimation or Bayesian inference) to quantify the microscopic properties of rocks (such as porosity and fracture density). These properties are then used to define the micromechanical behavior of the rock, and then the local stress-strain relationship is predicted by the micromechanical model.

[0068] The micromechanical model used in the present invention is the Hill mean stress formula, which is used to estimate the effective stress and is expressed as follows:

[0069] σ e =σ-αp;

[0070] Here, σ is the total stress, p is the pore pressure, and α is a coefficient related to the pore geometry.

[0071] The value of α usually ranges from 0 to 1. When α = 0, it means that the pore pressure has no effect on the effective stress; when α = 1, it means that all pore pressure is converted into effective stress, which is the possible situation in fully saturated rocks or soils.

[0072] The geometry and connectivity of the pores affect how fluid pressure acts on the rock skeleton. A more connected pore network may result in a higher value of α. The permeability of the rock affects the flow of pore fluids, thus affecting the value of α. Highly permeable rocks may allow for more efficient pressure transfer, resulting in α values ​​closer to 1. The loading history and path of the rock can also affect the value of α. For example, under cyclic loading or complex loading paths, the pore structure of the rock may change, thus affecting α.

[0073] S22, convert the microscopic parameters to an upward scale to predict the response of the rock at the macroscopic scale. Scale conversion is a key step in converting the mechanical behavior at the microscopic scale to the macroscopic scale. The present invention uses the Hill-Mandel condition to derive the relationship between macroscopic stress and microscopic stress, which can be expressed as:

[0074] <σ micro >=σ macro ;

[0075] Here, <σ micro > is the average value of micro stress, σ macro is the macroscopic stress. In this way, the equivalent properties of the macroscopic material can be calculated.

[0076] S23, after the macroscopic mechanical properties are determined, they are verified by experimental data. This includes using standard rock mechanics tests, such as uniaxial compression tests and triaxial compression tests, to measure the macroscopic response of the rock and compare it with the model predictions. For example, one possible approach is to use uniaxial compression test data to verify the macroscopic elastic modulus, which is:

[0077]

[0078] Where Δσ is the applied stress change and Δτ is the corresponding strain change. If the macroscopic properties predicted by the model agree with the experimental data, this will verify the validity of the multiscale model. Conversely, if there are discrepancies, adjustments to the microscopic parameters or homogenization process are needed to ensure the accuracy of the model.

[0079] S3, after the multi-scale model is established, finite element analysis (FEA) is implemented to simulate the macroscopic response of rock under actual engineering conditions. This includes creating a geometric model of rock, dividing the finite element mesh, defining material properties, and applying boundary conditions and loads. Creating a geometric model of rock is to apply the macroscopic mechanical properties obtained from the multi-scale model to the finite element analysis (FEA) of the actual rock structure. In this step, special attention should be paid to ensure that the geometric dimensions, material properties and load conditions of the model can truly reflect the actual engineering situation. Through FEA, the stress, strain distribution and possible failure mode of rock under multi-field coupling can be predicted.

[0080] S31, based on the data obtained from geological exploration and mapping, use computer-aided design (CAD) software to construct an accurate three-dimensional geometric model of the rock or rock structure. The model should include all relevant geological features, such as cracks, faults, and joints. Next, meshing is performed to divide the geometric model into a limited number of small elements, such as tetrahedrons or hexahedrons. The quality of meshing directly affects the accuracy and efficiency of FEA. In this step, an appropriate mesh density is used to ensure the accuracy of the calculation while avoiding unnecessary increase in the amount of calculation.

[0081] S32, after the mesh model is created, define the material properties for the rock material. This includes elastic modulus (E), Poisson's ratio (ν), shear modulus (G), and strength parameters such as cohesion (c) and internal friction angle (φ). These parameters can be obtained from laboratory tests and derived from the microscale through homogenization methods. Subsequently, practical engineering boundary conditions need to be imposed on the model, including fixed boundaries, free surfaces, stress boundary conditions, or displacement boundary conditions. These conditions simulate the constraints and loading conditions of rocks in actual geological environments.

[0082] S33, after the material properties and boundary conditions are defined, loads are applied and response analysis is performed. Loads can be static, such as self-weight stress, or dynamic, such as earthquake loads. In the case of multi-field coupling, the effects of temperature field, water flow field, and chemical field also need to be considered. Among them, temperature changes are expressed by the thermal expansion coefficient (α th ) causes additional thermal stress, which is calculated as follows:

[0083] σ th =α th ΔT; where ΔT is the temperature change. σ th Thermal stress caused by temperature change.

[0084] The FEA software will use this input data to calculate the stress and strain distribution inside the rock and predict possible failure modes, such as shear failure or tension failure. Through post-processing tools, the analysis results can be visualized to evaluate the stability and safety of the rock structure.

[0085] S4, the last step is to use machine learning algorithms to intelligently optimize model parameters and perform model verification. By inputting experimental data or field monitoring data into the machine learning model, the parameters in the rock multi-field coupling model, such as permeability coefficient and creep parameters, are automatically adjusted to improve the prediction accuracy of the model. In addition, the accuracy and reliability of the model are verified using independent data sets or through comparative analysis with actual engineering cases. Through this step, it can be ensured that the model is not only theoretically sound but also effective in practical applications.

[0086] S41, the beginning of the intelligent optimization process is to select a suitable machine learning algorithm. Commonly used algorithms include neural networks, support vector machines (SVM), decision trees, and random forests. The choice of algorithm depends on the characteristics of the data and the optimization goal. Once the algorithm is selected, the next step is the training phase, in which historical experimental data or field monitoring data are used to "train" the machine learning model. This process involves dividing the data set into a training set and a test set, and using the training set to adjust the model parameters to minimize the prediction error. For example, for a neural network, the weights and biases can be updated by the backpropagation algorithm, and its basic update rule can be expressed as:

[0087]

[0088] Among them, w is the weight, η is the learning rate, F is the error function, and t is the number of iterations.

[0089] S42, after the model training is completed, the machine learning algorithm can automatically adjust the parameters in the rock multi-field coupling model. For example, the permeability coefficient k and creep parameters A, n (usually used in the creep law) can be optimized based on the input data and the model prediction error. This process can be achieved by gradient descent or other optimization algorithms, the purpose is to find a set of parameter values ​​that minimizes the difference between the model prediction and the actual observed data. The optimization of creep parameters can be based on the integral form of the creep law, such as:

[0090]

[0091] Among them, μ c is the creep strain, σ is the applied stress and B is a time-dependent constant.

[0092] In the integral form of the creep law, the determination of the time-dependent constant B is usually based on experimental data or obtained by fitting the actual observed creep behavior. The following are several steps and methods for determining the time-dependent constant B. One method or a combination of two or more methods can be selected according to the actual engineering situation or conditions:

[0093] (1) Creep test: First, a creep test is conducted to obtain creep strain data of the rock or material at different stress levels. Then, the strain readings at different time points in the creep test and the corresponding stress levels are collected. The test data are fitted to the predictions of the creep law using nonlinear least squares or other curve fitting techniques to determine the parameters A, n, and B.

[0094] (2) Numerical optimization method

[0095] Gradient descent method: The creep model parameters are optimized using the gradient descent method, and the parameter values ​​are updated by calculating the gradient of the loss function (such as mean square error) relative to the parameters.

[0096] Global optimization algorithm: Use global optimization algorithms (such as particle swarm optimization, genetic algorithm) to avoid local minima and ensure that the global optimal solution is found.

[0097] (3) Parameter sensitivity analysis

[0098] Sensitivity Analysis: Perform parameter sensitivity analysis to determine how much each parameter affects the model predictions. This helps identify the parameters that are most critical to the model output.

[0099] (4) Adjustment in practical application

[0100] Actual data calibration: In actual applications, parameter B is adjusted based on the latest monitoring data or engineering feedback to ensure the continued accuracy and applicability of the model.

[0101] S43, Finally, the intelligently optimized model needs to be validated to test its accuracy and reliability. This can be done by comparing the model predictions with independent test data sets or observations from actual engineering cases. The validation process involves calculating the difference between the predicted and actual values, such as the mean square error (MSE) or the coefficient of determination (R 2 ). For example, MSE can quantify the prediction error and is defined as:

[0102]

[0103] Where N is the number of data points, P rei and A ci are the predicted value and actual value of the ith data point, respectively. If the MSE is low, it means that the model's prediction is consistent with the actual observation, thus verifying the model's effectiveness. Through this step, the reliability and effectiveness of the model in practical engineering applications can be ensured.

[0104] The above specific embodiments are preferred embodiments of the present invention, and are not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to the present specific embodiments. All equivalent changes made in accordance with the shape, structure, and method of the present invention are within the protection scope of the present invention.

Claims

1. A method for establishing a rock multi-field coupling model, characterized in that: The steps include: S1. Obtain rock samples by sampling, obtain initial data and perform data preprocessing, and input the preprocessed data into a computer system; S2. At the microscopic scale, based on the initial data obtained, the microscopic mechanical behavior of rocks is characterized by statistical or numerical methods; S3, based on S2, convert the microscopic parameters to the upper scale, predict the response of the rock at the macroscale, and construct a multi-scale model; S4, using the preprocessed data as input, based on the multi-scale model, performing finite element analysis to simulate the macroscopic response of rock under actual engineering conditions; S5. Use machine learning algorithms to optimize machine learning model parameters and perform model verification.

2. The method for establishing a rock multi-field coupling model according to claim 1, characterized in that: The S1 comprises the following steps: S11. Perform high-resolution imaging of rock surfaces and cracks, and detect the pore structure and fluid distribution inside the rock. At the same time, perform three-dimensional imaging of rock samples to obtain accurate spatial distribution data of pores and cracks. S12, performing image segmentation on the acquired image data and three-dimensional reconstruction of the pore structure; S13, normalizing the data obtained in S11 and S12; S14. Input the preprocessed data into the computer system to provide necessary input conditions for the establishment and simulation of the multi-field coupling model.

3. The method for establishing a rock multi-field coupling model according to claim 2, characterized in that: The data preprocessing includes image segmentation, three-dimensional reconstruction of pore structure and data normalization; obtaining initial data includes obtaining microstructure data and physical property data of rock samples through non-destructive testing technology in the laboratory and on site.

4. The method for establishing a rock multi-field coupling model according to claim 1, characterized in that: The S2 includes: Analyze the microstructural data of rock samples through micromechanical models, quantify the microscopic properties of rocks using statistical methods, and predict local stress-strain relationships through micromechanical models; The expression of the micromechanical model is: s e =σ-αp; Here, σ is the total stress, p is the pore pressure, and α is a coefficient related to the pore geometry.

5. The method for establishing a rock multi-field coupling model according to claim 1, characterized in that: The S3 includes: S31. The relationship between macro stress and micro stress is derived through the Hill-Mandel condition, and the micro parameters are converted to the macro scale to determine the macro mechanical properties, which is specifically expressed as: <s micro >=s macro ; In the formula, <σ micro > is the average value of micro stress, σ macro is the macro stress; S32. Based on the macroscopic mechanical properties, verification is performed using experimental data obtained using standard rock mechanics tests.

6. The method for establishing a rock multi-field coupling model according to claim 5, characterized in that: The standard rock mechanics test involves using uniaxial compression test data to verify the macro elastic modulus, which is expressed as: where Δσ is the change in applied stress and Δτ is the corresponding change in strain.

7. The method for establishing a rock multi-field coupling model according to claim 1, characterized in that: The S4 comprises the following steps: S31. Based on the preprocessed data, use computer-aided design software to construct an accurate three-dimensional geometric model of the rock or rock structure and perform meshing to create a mesh model; S32, defining material properties for the rock sample based on the grid model and applying actual engineering boundary conditions to the grid model; S33. Apply load to the rock sample according to S32 and perform response analysis; wherein the load includes static load and dynamic load.

8. The method for establishing a rock multi-field coupling model according to claim 1, characterized in that: The S5 comprises the following steps: S51, selecting a machine learning algorithm, obtaining historical experimental data or field monitoring data, and training a machine learning model corresponding to the machine learning algorithm; S52. After the machine learning model is trained, the machine learning algorithm adjusts and optimizes the parameters in the rock multi-field coupling model according to the input data and the model prediction error; S53. Verify the optimized machine learning model; wherein the verification includes calculating the difference between the predicted value and the actual value.

9. A rock multi-field coupling model, characterized in that Established by the method of claim 1.

Images