Grouting digital twin virtual-real interaction pre-control analysis method and system

Abstract

The invention provides a grouting digital twinning virtual-real interaction pre-control analysis method and system, and relates to the technical field of geotechnical engineering, and the method comprises the steps: constructing a multi-scale geologic model; carrying out numerical simulation on the grouting process based on the multi-scale geologic model to obtain grouting parameters of simulation and on-site grouting monitoring data; carrying out fusion alignment on the simulated grouting parameters and field monitoring data, carrying out principal component analysis and eigenvalue decomposition, and selecting principal component eigenvectors to construct a vector matrix; performing grouting state prediction on the vector matrix subjected to dimension reduction by adopting particle filtering, establishing a state transition model to describe grouting parameter changes, calculating the likelihood of each particle according to the prediction state of the set particle, and updating the weight of the particle according to the likelihood; and calculating the prediction state of each time step length according to the updated particle weight, and evaluating the current grouting effect according to the prediction state to realize the real-time pre-control analysis of the grouting process.

Description

Technical Field

[0001] The present disclosure relates to the field of geotechnical engineering technology, and in particular to a grouting digital twin virtual-reality interactive pre-control analysis method and system. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Grouting technology is widely used in underground space and geotechnical engineering, especially in improving the mechanical properties of underground soil and preventing and controlling water and mud inrush disasters. However, with the increasing complexity of the engineering environment, traditional grouting process control methods face many challenges, especially under complex geological conditions, the slurry flow path and diffusion effect are difficult to predict, and the evaluation and adjustment of the grouting effect are often delayed, resulting in risks to engineering quality and safety. Digital twin technology has made significant progress in many fields by building a virtual model corresponding to the physical entity to achieve real-time interaction and dynamic synchronization between the two. Applying digital twin technology to the grouting process can achieve accurate simulation and dynamic monitoring of the grouting process. Through the two-way feedback of the virtual model and the entity data, the slurry flow, diffusion and its interaction with the geological environment can be tracked in real time, thus providing a scientific basis for the prediction, regulation and optimization of the grouting process.

[0004] Although digital twin technology has achieved success in other industries, its practical application in the grouting field is still in its early stages, especially in the interaction between the grouting entity and the virtual model. The following problems still exist: 1) Current interaction methods mainly rely on static models and traditional sensor data, lacking real-time and intelligence.

[0005] 2) Traditional grouting monitoring and control methods are difficult to adapt to the complex and dynamically changing geological environment, and cannot effectively integrate multi-source data for accurate prediction and optimization.

[0006] 3) It is difficult to break through the limitations of existing methods and establish an interactive control system with real-time feedback, efficient prediction and optimization. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes a virtual-reality interactive pre-control analysis method and system for grouting digital twins. According to the fusion of grouting simulation data and field monitoring data, they are aligned in a unified space, and the particle state is predicted by particle filtering. The difference between the predicted value of each particle and the field monitoring data is calculated, and the weight of the particle is updated according to the likelihood. The grouting state is predicted in real time, the grouting effect is evaluated, and the real-time pre-control analysis of the grouting process is realized.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions: The virtual-real interactive pre-control analysis method of grouting digital twin includes: Determine the target area for grouting and construct a multi-scale geological model; Perform numerical simulation on the grouting process based on the multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; The simulated grouting parameters are fused and aligned with the field monitoring data, the fused and aligned data are subjected to principal component analysis and eigenvalue decomposition, and the principal component eigenvectors are selected to construct a vector matrix; The vector matrix is ​​reduced in dimension, and the particle filter is used to predict the grouting parameter state of the reduced vector matrix. The change of grouting parameters is described by establishing a state transition model. The predicted state of the set particle is compared with the field monitoring data, the likelihood of each particle is calculated, and the particle weight is updated according to the likelihood. Based on the updated particle weights, a new particle set is generated and multiple iterations are performed. The predicted state of each time step is calculated according to the updated particle weights. The current grouting effect is evaluated based on the predicted state to evaluate whether the state of the current time step needs to be adjusted, thereby realizing real-time pre-control analysis of the grouting process.

[0009] According to some embodiments, the present disclosure adopts the following technical solutions: The grouting digital twin virtual-real interactive pre-control analysis system includes: Initialization module, used to determine the target area for grouting and build a multi-scale geological model; A data acquisition module is used to perform numerical simulation of the grouting process based on a multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; The data fusion module is used to fuse and align the simulated grouting parameters with the on-site monitoring data, perform principal component analysis and eigenvalue decomposition on the fused and aligned data, and select the principal component eigenvectors to construct a vector matrix; The state update module is used to reduce the dimension of the vector matrix, use particle filtering to predict the state of the grouting parameters of the vector matrix after the dimension reduction, and describe the change of the grouting parameters by establishing a state transition model. The predicted state of the set particle is compared with the field monitoring data, the likelihood of each particle is calculated, and the weight of the particle is updated according to the likelihood; The grouting prediction module is used to generate a new particle set based on the updated particle weights and perform multiple iterations. The predicted state of each time step is calculated according to the updated particle weights. The current grouting effect is evaluated based on the predicted state to evaluate whether the state of the current time step needs to be adjusted, thereby realizing real-time pre-control analysis of the grouting process.

[0010] According to some embodiments, the present disclosure adopts the following technical solutions: A computer program product includes a computer program, which, when executed by a processor, implements the grouting digital twin virtual-reality interactive pre-control analysis method.

[0011] According to some embodiments, the present disclosure adopts the following technical solutions: A non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the grouting digital twin virtual-reality interactive pre-control analysis method is implemented.

[0012] According to some embodiments, the present disclosure adopts the following technical solutions: An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the grouting digital twin virtual-reality interactive pre-control analysis method.

[0013] Compared with the prior art, the present invention has the following beneficial effects: A virtual-reality interactive pre-control analysis method for grouting digital twins disclosed in the present invention extracts key features through principal component analysis (PCA) and eigenvalue decomposition, and constructs a principal component eigenvector matrix, which not only achieves data dimensionality reduction and highlights the most representative variables, but also enhances the interpretability of the model, helping to more clearly identify and understand the key factors in the grouting process.

[0014] The disclosed method for virtual-real interaction pre-control analysis of grouting digital twins uses particle filtering combined with a state transition model to compare the predicted state with the on-site monitoring data, calculate the likelihood of each particle and update its weight. This method not only improves the intelligence and automation level of the grouting process, but also enables a refined evaluation of the grouting effect, real-time adjustment of the grouting parameters, and ensures construction quality and efficiency. At the same time, through multiple iterations and particle updates, the system has strong adaptability and robustness, effectively supporting the optimization and decision analysis of the grouting process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0016] Figure 1 It is a flow chart of the grouting pre-control analysis method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0018] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0019] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0020] Example 1 In one embodiment of the present disclosure, a grouting digital twin virtual-real interactive pre-control analysis method is provided, and the steps include: Step 1: Determine the target area for grouting and construct a multi-scale geological model; Step 2: numerically simulate the grouting process based on the multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; Step 3: Fuse and align the simulated grouting parameters with the field monitoring data, perform principal component analysis and eigenvalue decomposition on the fused and aligned data, and select the principal component eigenvectors to construct a vector matrix; Step 4: Reduce the dimension of the vector matrix, use particle filtering to predict the grouting parameter state of the reduced vector matrix, establish a state transition model to describe the change of grouting parameters, compare the predicted state of the set particles with the field monitoring data, calculate the likelihood of each particle, and update the particle weight according to the likelihood; Step 5: Based on the updated particle weights, a new particle set is generated and multiple iterations are performed. The predicted state of each time step is calculated according to the updated particle weights. The current grouting effect is evaluated based on the predicted state to assess whether the state of the current time step needs to be adjusted, thereby achieving real-time pre-control analysis of the grouting process.

[0021] As an embodiment, the specific implementation process of a grouting digital twin virtual-real interactive pre-control analysis method disclosed in the present invention is as follows: Step 1: Determine the target area for grouting and construct a multi-scale geological model; Specifically, special equipment is used for drilling, and a mine resistivity video imaging logging instrument is used for multi-drill drilling to collect geological information, collect panoramic imaging image information in the hole, GR curve, apparent resistivity curve, natural potential curve and other information, and obtain data such as drilling direction, inclination, and drilling depth to judge the stratum and lithology changes in the survey area, and obtain geological data of the grouting target area, including rock and soil layer structure, porosity, permeability, crack characteristics (width, direction, connectivity), soil particle size and distribution, rock and soil mechanics parameters (such as compression modulus, tensile strength), etc. A multi-scale geological model is constructed based on geological data. The multi-scale The multi-scale geological model includes a macroscopic geological model and a microscopic geological model. The macroscopic geological model simulates the overall structure of the rock and soil layer, the permeability characteristics of the rock and soil layer, the porosity and permeability coefficient, and simulates the large-scale flow and pressure distribution during the slurry injection process. The microscopic geological model simulates the detailed structure of the rock and soil layer, refines the modeling of small cracks and pores, obtains the porosity and pore distribution of the rock and soil layer, and uses a three-dimensional grid to represent the pore structure of the rock and soil layer. Each grid unit (such as a polyhedron) represents a small space between rock and soil particles, which is used to simulate the flow of slurry. The multi-scale geological model is obtained by associating and coupling the macroscopic geological model and the microscopic geological model.

[0022] Step 2: numerically simulate the grouting process based on the multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; Specifically, the initial conditions, i.e., the initial grouting pressure distribution, slurry concentration, etc., are set based on the constructed multi-scale geological model and the flow behavior of the slurry simulated in the multi-scale geological model, and the grouting parameters in the grouting process are predicted and simulated, including: Set the grouting boundary conditions, such as the pressure of the grouting boundary, the slurry injection rate, the porosity, the flow restriction of the rock and soil layer, etc. Set the time step, and gradually solve the flow and diffusion process of the slurry in each time step. The calculation results of each step will be used as the initial conditions for the next step.

[0023] The solution process is converted into a set of linear equations in the form of: AX=B, where A is the coefficient matrix, which contains information such as the flow equation and the diffusion equation; X is the vector of unknown variables (such as pressure and concentration); and B is the constant term, which is usually given by initial conditions, boundary conditions, etc.

[0024] The calculation results of the macro geological model and the micro geological model are associated and iteratively integrated to complete the final grouting behavior simulation. In each round of calculation, the pressure field, flow field, and permeability coefficient calculated by the macro geological model will be passed as input to the micro geological model. The calculation results of the micro geological model will affect the parameters of the multi-scale geological model. That is, if the permeability of certain areas in the micro geological model changes, the permeability of the corresponding areas in the macro geological model also needs to be adjusted. The multi-scale coupling process is regarded as an iterative process. Each iteration will transmit effective information between the macro geological model and the micro geological model, and timely feedback the model parameters for adjustment. Specifically, the specific iterative process of simulation coupling is as follows: The existing finite element method is used in the macro geological model to simulate and solve the flow behavior of the grouting fluid in the rock and soil layer. The macro geological model is solved by the existing finite element method to obtain information such as pressure distribution and flow velocity at different positions in the rock and soil layer. In the micro geological model, the diffusion equation is used to solve:

[0025] Where C(r,t) is the slurry concentration at position r and time t; D(r) is the diffusion coefficient of the soil pores; and ∇ is the gradient operator.

[0026] The micro-geological model calculates the concentration distribution of slurry in the pores of rock and soil layers by solving the diffusion equation.

[0027] According to the adjustment results of the macro geological model, the macro geological model is solved again, and the new macro results are used as the diffusion equation input of the micro geological model to continue the calculation and solution. Then the results of the micro geological model are fed back to the macro geological model again, and the iteration is repeated. In each round of iteration, the parameter changes between the models are checked to determine whether they have converged. That is, at the end of each round of iteration, the changes in the parameters of the macro geological model and the micro geological model, such as the pressure field, concentration distribution, and permeability coefficient, are calculated. If the change is less than the preset threshold, it is considered to have converged, and an error threshold is set. When the error of the model result is lower than the threshold, the iteration is stopped.

[0028] In this embodiment, the convergence judgment standard can be set as: k+1 -X k | / |X k |<ε, where X k represents the result of the kth iteration, and ε is the preset convergence error threshold. When the difference between the results of two iterations is less than the preset error threshold, the iteration process is considered to be converged and the iteration can be stopped.

[0029] This embodiment can simulate and solve the grouting process more accurately through the coupled iterative solution of the macro geological model and the micro geological model, and finally iterate to obtain the simulated grouting parameters, including simulation results of grouting speed, grouting pressure, phase fraction, viscosity parameters and other data.

[0030] Furthermore, the simulated grouting parameters are used to carry out engineering grouting in the actual target area, and sensors are used to obtain in real time the grouting pressure, grouting rate, slurry diffusion and other information monitored on site under the actual slurry diffusion conditions.

[0031] Step 3: Fuse and align the simulated grouting parameters with the field monitoring data, perform principal component analysis and eigenvalue decomposition on the fused and aligned data, and select the principal component eigenvectors to construct a vector matrix; Specifically, 1) First, the simulated grouting parameters and the field monitoring data are preprocessed and aligned, where the preprocessing includes cleaning and interpolation; the alignment operation is denoising alignment, which means unifying the format of the preprocessed field monitoring data and the numerical simulation results, aligning them in the time and space coordinate system, and mapping them to the same spatial domain; 2) Perform principal component analysis and eigenvalue decomposition on the preprocessed aligned data to map these high-dimensional data into a low-dimensional space, retaining only the most important information. The specific steps are as follows: First, the grouting parameters of the simulation after preprocessing and alignment are fused with the field monitoring data to form a data matrix. Each column in the data matrix represents a different grouting parameter (such as pressure, flow, temperature, etc.), and each row represents a sample or observation time. For each column of grouting parameter features (each variable), the mean and standard deviation of the feature are calculated, and then standardized:

[0032] in, is the original data; is the mean of the feature; is the standard deviation.

[0033] Furthermore, the covariance matrix is ​​calculated and the eigenvalue decomposition is performed on the covariance matrix to obtain a set of eigenvalues ​​and corresponding eigenvectors. According to the size of the eigenvalues, the eigenvectors corresponding to the first few eigenvalues ​​are selected as principal components, and the principal component eigenvectors are combined into a vector matrix.

[0034] Among them, the covariance matrix is ​​calculated:

[0035] in, is the data matrix; is the number of samples; is the characteristic number; is the transpose of the data matrix.

[0036] Furthermore, the covariance matrix C is decomposed into eigenvalues:

[0037] in, represents the feature vector; Represents the eigenvalue.

[0038] After eigendecomposition, we get a set of eigenvalues The corresponding eigenvector According to the size of the eigenvalue, select the eigenvectors corresponding to the first few eigenvalues ​​as the principal component eigenvectors required for dimensionality reduction, and form the principal component eigenvectors into a vector matrix . Vector Matrix The dimension is ,in The dimension after dimensionality reduction is the above standardized data matrix With vector matrix Multiply the original Dimensional feature data is mapped to In the new space of dimension, the dimension reduction of data is realized:

[0039] Among them, if There are n monitoring data and simulation data, which can be expressed as:

[0040] Step 4: Use particle filtering to predict the state of grouting parameters on the vector matrix after dimensionality reduction. By establishing a state transition model to describe the changes in grouting parameters, the predicted state of the set particles is compared with the field monitoring data, the likelihood of each particle is calculated, and the weight of the particle is updated according to the likelihood; the particle represents the state of the grouting parameters in the data, such as pressure, flow rate, and slurry viscosity, and the state of each particle is .

[0041] Specifically, each particle in the reduced-dimensional vector matrix is ​​given the same weight:

[0042] in, The weight set for the particle, N represents the total number of particles, i For one of the particles, Furthermore, a state transition model is established , the objects being described are grouting pressure, flow rate and slurry viscosity, then the state can be expressed as , the evolution form of state update prediction for grouting pressure, flow rate and slurry viscosity is:

[0043] Among them, due to the positive correlation between pressure and flow rate, the grouting pressure update is expressed as: ; in, Indicates the stress of the current moment; Indicates the pressure at the next moment; Indicates the influence coefficient of pressure on flow rate; Indicates the flow rate at the current moment.

[0044] The grouting flow rate decays exponentially with the increase of pressure, and the flow rate update is expressed as: ; in, Indicates the flow rate at the current moment; Indicates the flow rate at the next moment; It represents the attenuation coefficient of pressure to flow rate change.

[0045] The viscosity of the slurry increases with time, and the viscosity update is expressed as: ; in, Indicates the slurry viscosity at the current moment; Indicates the slurry viscosity at the next moment; It represents the influence coefficient of flow velocity on slurry viscosity; It represents the attenuation coefficient of pressure on the change of slurry viscosity; Represents the time-dependent viscosity adjustment factor. , , Denoted as process noise, it represents random disturbances or modeling errors in the system.

[0046] Furthermore, the predicted state of the described particle is obtained by performing an evolutionary form of state update prediction on the grouting pressure, flow rate and slurry viscosity. The predicted state of the described particle is compared with the field monitoring data, the likelihood of each particle (i.e., the difference between the predicted value of the particle and the monitoring data) is calculated, and the particle weight is updated according to the likelihood.

[0047] Among them, the likelihood function of the particle is expressed as:

[0048]

[0049] in, Represented as field monitoring data; represents the predicted state of the particle; represents the noise variance of the monitoring data; represents simulation data; represents the noise variance of the simulated data.

[0050] Furthermore, the particle weight update formula is:

[0051] in, Indicates the particle prediction value and on-site monitoring data The likelihood between Represents particle prediction values ​​and simulation data The likelihood between Indicates the weight of the particle at the last moment.

[0052] Furthermore, according to the weight of the current particle update, a new particle set is generated, and multiple iterations are performed to achieve the fusion prediction of numerical simulation data and field monitoring data. The fusion prediction state of each time step is calculated according to the updated particle weight through the weighted average method:

[0053] in, represents the optimal prediction state of the current grouting process, represents the weight of the particle at the current moment, Indicates the predicted state of the particle at the current moment.

[0054] As an embodiment, the current grouting effect is evaluated according to the fusion prediction result to evaluate whether the state of the current time step needs to be adjusted: For the grouting pressure, according to the prediction results of the next time step, the grouting pressure of the next stage is adjusted by comprehensively considering the equipment capacity, the bearing capacity of the formation, and the design requirements of the grouting effect: Equipment Capability Assessment:

[0055] in, Indicates current pressure; Maximum pressure bearing capacity of equipment Assessment of ground bearing capacity:

[0056] in, Indicates the current grouting pressure; Indicates the compressive strength of the rock formation; It represents the permeability coefficient of the formation; Indicates the permeability of the rock formation.

[0057] Evaluation of grouting effect design requirements:

[0058] in, Indicates the actual diffusion range; Indicates the diffusion range of design requirements.

[0059] The comprehensive evaluation formula is obtained:

[0060] If the result Indicates that the current grouting pressure may be too high and needs to be reduced. It indicates that the current grouting pressure may be too low and needs to be increased.

[0061] The grouting pressure is adjusted according to the evaluation results, the initial parameters of the numerical simulation are reset according to the adjusted grouting parameters, and a new state prediction is performed and a fusion analysis with the monitoring data is performed to obtain a new fusion prediction result. The grouting effect is then evaluated and adjusted again, and the above process is repeated to achieve real-time pre-control analysis of the grouting process.

[0062] Example 2 In one embodiment of the present disclosure, a grouting digital twin virtual-real interactive pre-control analysis system is provided, comprising: Initialization module, used to determine the target area for grouting and build a multi-scale geological model; A data acquisition module is used to perform numerical simulation of the grouting process based on a multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; The data fusion module is used to fuse and align the simulated grouting parameters with the on-site monitoring data, perform principal component analysis and eigenvalue decomposition on the fused and aligned data, and select the principal component eigenvectors to construct a vector matrix; The state update module is used to reduce the dimension of the vector matrix, use particle filtering to predict the state of the grouting parameters of the vector matrix after the dimension reduction, and describe the change of the grouting parameters by establishing a state transition model. The predicted state of the set particle is compared with the field monitoring data, the likelihood of each particle is calculated, and the weight of the particle is updated according to the likelihood; The grouting prediction module is used to generate a new particle set based on the updated particle weights and perform multiple iterations. The predicted state of each time step is calculated according to the updated particle weights. The current grouting effect is evaluated based on the predicted state to evaluate whether the state of the current time step needs to be adjusted, thereby realizing real-time pre-control analysis of the grouting process.

[0063] Example 3 In one embodiment of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the grouting digital twin virtual-reality interactive pre-control analysis method.

[0064] Example 4 In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the grouting digital twin virtual-reality interactive pre-control analysis method is implemented.

[0065] Example 5 In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the grouting digital twin virtual-reality interactive pre-control analysis method.

[0066] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0068] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. Grouting digital twin virtual-real interactive pre-control analysis method, characterized in that: include: Determine the target area for grouting and construct a multi-scale geological model; Perform numerical simulation on the grouting process based on the multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; The simulated grouting parameters are fused and aligned with the field monitoring data, the fused and aligned data are subjected to principal component analysis and eigenvalue decomposition, and the principal component eigenvectors are selected to construct a vector matrix; The vector matrix is ​​reduced in dimension, and the particle filter is used to predict the grouting parameter state of the reduced vector matrix. The change of grouting parameters is described by establishing a state transition model. The predicted state of the set particle is compared with the field monitoring data, the likelihood of each particle is calculated, and the particle weight is updated according to the likelihood. Based on the updated particle weights, a new particle set is generated and multiple iterations are performed. The predicted state of each time step is calculated according to the updated particle weights. The current grouting effect is evaluated based on the predicted state to evaluate whether the state of the current time step needs to be adjusted, thereby realizing real-time pre-control analysis of the grouting process.

2. The grouting digital twin virtual-real interactive pre-control analysis method according to claim 1 is characterized in that: The geological data of the grouting target area is obtained, and a multi-scale geological model is constructed based on the geological data. The multi-scale geological model includes a macroscopic geological model and a microscopic geological model. The macroscopic geological model simulates the overall structure of the rock and soil layer, the permeability characteristics, porosity and permeability coefficient of the rock and soil layer, and simulates the large-scale flow and pressure distribution during the slurry injection process. The microscopic geological model simulates the detailed structure of the rock and soil layer, refines the modeling of small cracks and pores, obtains the porosity and pore distribution of the rock and soil layer, and uses a three-dimensional grid to represent the pore structure of the rock and soil layer.

3. The grouting digital twin virtual-real interactive pre-control analysis method according to claim 1 is characterized in that: Based on the multi-scale geological model and the flow behavior of the slurry simulated in the multi-scale geological model, the grouting parameters in the grouting process are predicted and simulated to obtain the simulated grouting parameters, including grouting pressure, grouting rate, phase fraction and viscosity parameters. The simulated grouting parameters are used to carry out grouting in the actual target area engineering, and the grouting pressure, grouting rate and slurry diffusion information monitored on site under the actual slurry diffusion conditions are obtained.

4. The grouting digital twin virtual-real interactive pre-control analysis method according to claim 1, characterized in that: The simulated grouting parameters are fused and aligned with the field monitoring data, and the fused and aligned data are subjected to principal component analysis and eigenvalue decomposition, including: the simulated grouting parameters and the field monitoring data are formed into a data matrix, each column in the data matrix represents a different grouting parameter, and each row represents a sample or observation time; for each column of the grouting parameter characteristics, the mean and standard deviation of each column of the grouting parameter characteristics are calculated, and the covariance matrix is ​​calculated, and the eigenvalue decomposition of the covariance matrix is ​​performed to obtain a set of eigenvalues ​​and corresponding eigenvectors, and according to the size of the eigenvalues, the eigenvectors corresponding to the first few eigenvalues ​​are selected as the principal components, and the principal component eigenvectors are formed into a vector matrix.

5. The grouting digital twin virtual-real interactive pre-control analysis method according to claim 1, characterized in that: Reduce the dimension of the vector matrix and set the same weight for each particle in the reduced vector matrix: in, The weight set for the particle, N represents the total number of particles, i For one of the particles, a state transfer model is established to describe the changes in grouting parameters. The described particle objects are grouting pressure, flow rate and slurry viscosity. The state update prediction of grouting pressure, flow rate and slurry viscosity is carried out to obtain the predicted state of the described particle. The predicted state of the described particle is compared with the field monitoring data, the likelihood of each particle is calculated, and the weight of the particle is updated according to the likelihood.

6. The grouting digital twin virtual-real interactive pre-control analysis method according to claim 1, characterized in that: According to the weight of the current particle update, a new particle set is generated, and multiple iterations are performed to achieve the fusion of numerical simulation data and field monitoring data. The predicted state of each time step is calculated according to the updated particle weight through the weighted average method: in, represents the optimal prediction state of the current grouting process, represents the weight of the particle at the current moment, Indicates the predicted state of the particle at the current moment.

7. Grouting digital twin virtual-real interactive pre-control analysis system, characterized by: include: Initialization module, used to determine the target area for grouting and build a multi-scale geological model; A data acquisition module is used to perform numerical simulation of the grouting process based on a multi-scale geological model, obtain the simulated grouting parameters, perform on-site grouting based on the simulated grouting parameters, and obtain on-site monitoring data; The data fusion module is used to fuse and align the simulated grouting parameters with the on-site monitoring data, perform principal component analysis and eigenvalue decomposition on the fused and aligned data, and select the principal component eigenvectors to construct a vector matrix; The state update module is used to reduce the dimension of the vector matrix, use particle filtering to predict the state of the grouting parameters of the vector matrix after the dimension reduction, and describe the change of the grouting parameters by establishing a state transition model. The predicted state of the set particle is compared with the field monitoring data, the likelihood of each particle is calculated, and the weight of the particle is updated according to the likelihood; The grouting prediction module is used to generate a new particle set based on the updated particle weights and perform multiple iterations. The predicted state of each time step is calculated according to the updated particle weights. The current grouting effect is evaluated based on the predicted state to evaluate whether the state of the current time step needs to be adjusted, thereby realizing real-time pre-control analysis of the grouting process.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by the processor, the grouting digital twin virtual-reality interactive pre-control analysis method described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the grouting digital twin virtual-reality interactive pre-control analysis method as described in any one of claims 1 to 6 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the grouting digital twin virtual-reality interactive pre-control analysis method as described in any one of claims 1 to 6.

Images