Grouting intelligent calculation method and system based on coupling of neural network and numerical solution

Abstract

The present invention discloses an intelligent grouting calculation method and system based on the coupling of neural network and numerical solution, comprising: determining the fluid calculation control equation required for the calculation working condition; taking boundary conditions, grouting velocity, grouting pressure, initial flow field of dynamic water, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density as input data, performing numerical simulation of the input data in the initial stage through a numerical simulation method, taking the parameters of the last time step obtained from the numerical simulation in the initial stage as initial data, inputting them into a trained neural network model, and obtaining prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data; the present invention performs numerical simulation of the input data in the initial stage through a physical solver, and captures physical fields such as pressure, velocity, temperature, as well as local details and global spatiotemporal evolution trends between each field through a neural network model, thereby realizing efficient grouting numerical simulation.

Description

Technical Field

[0001] The present invention relates to the field of geotechnical engineering technology, and in particular to a grouting intelligent calculation method and system based on coupling of neural network and numerical solution. Background Art

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

[0003] With the rapid advancement of tunnel engineering technology, the geological conditions encountered are becoming increasingly complex. The complex and ever-changing mechanisms of water hazards under these conditions present unprecedented challenges for predictive decision-making during tunnel construction. This complexity not only increases safety risks during construction but can also lead to uncertainty in project schedules and costs. In this context, grouting technology, as an effective method for ground reinforcement and water hazard prevention, has become particularly important. Grouting prevents sudden water inrush and improves geological conditions by injecting a specific grout, thereby ensuring smooth construction.

[0004] To precisely control the grouting process and improve its efficiency, numerical grouting simulation technology has emerged. This technology, relying on advanced computer simulation, can simulate the flow and solidification of grouting fluid underground before construction, helping engineers optimize grouting plans. However, traditional simulation methods, such as statistical models and numerical simulation, have a number of limitations. Statistical models lack the flexibility to adapt to complex geological conditions, while numerical simulation, while highly accurate, is computationally complex and time-consuming. These limitations are particularly pronounced when dealing with large-scale or structurally complex geological conditions.

[0005] In recent years, with the development of deep learning technology, improving the efficiency and accuracy of grouting simulations through machine learning methods combined with simulated data has become a research hotspot. However, the performance of current deep learning models relies heavily on large amounts of high-quality training data. However, the acquisition of high-quality training data is difficult due to the complex construction environment and variable geological conditions. In addition, current deep learning models are often viewed as "black boxes" with a lack of transparency in their decision-making processes. Common deep learning models lack a deep understanding of physics, making it difficult to achieve rapid and accurate learning and predictions, and difficult to verify their prediction accuracy, resulting in a certain degree of blindness and uncertainty in the prediction results. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes an intelligent grouting calculation method and system based on the coupling of neural network and numerical solution. The physical solver is used to perform numerical simulation of the input data in the initial stage, and the neural network model is used to capture the physical fields such as pressure, velocity, temperature, as well as the local details and global spatiotemporal evolution trends between each field, thereby realizing efficient grouting numerical simulation.

[0007] In some embodiments, the following technical solutions are adopted:

[0008] A grouting intelligent calculation method based on the coupling of neural network and numerical solution, comprising:

[0009] Determining a fluid calculation control equation required for the calculation working condition; the fluid calculation control equation includes a momentum control equation, and a damping term is added to the momentum control equation;

[0010] The boundary conditions, grouting velocity, grouting pressure, initial dynamic water flow field, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density are used as input data. The input data is numerically simulated in the initial stage through the numerical simulation method. The parameters of the last time step obtained in the initial stage numerical simulation are used as initial data and input into the trained neural network model to obtain the prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data.

[0011] Among them, the loss function of the neural network model includes a data fitting loss term, a physical residual loss term and a boundary loss function term; the momentum control equation with the damping term added is used as the physical residual loss term.

[0012] As an optional solution, it also includes: setting a% of the total time steps for numerical solution verification for the output results of the neural network model; establishing a three-stage step-by-step trust verification mechanism, specifically:

[0013] In the first stage, a fixed number of time-step nodes are used to perform preliminary numerical calculation verification. If the error of the verification result meets the requirements, the second stage is entered. Otherwise, the initial grouting condition parameters are adjusted and the grouting intelligent calculation is repeated.

[0014] The second stage increases trust in the model by gradually reducing the verification frequency until the model output is fully trusted. After full trust, simulation prediction is carried out. After the prediction is completed, the third stage begins.

[0015] In the third stage, the prediction results of the last time step are numerically verified. If the error of the verification result meets the requirements, the grouting simulation result is output; otherwise, the initial grouting condition parameters are adjusted and the grouting intelligent calculation is performed again; where a is the set value.

[0016] As an optional solution, when performing the initial numerical simulation of the input data, the time span of the initial stage is dynamically adjusted according to the actual complexity of the working conditions; specifically:

[0017] ;

[0018] ;

[0019] ;

[0020] in, As the basic time span, 、 、 、 、 、 、 、 、 、 、 are weight coefficients, is the inverse of the grouting rate, is the inverse of the grouting pressure, is the slurry selection parameter, is the geological condition complexity coefficient, is the viscosity of the slurry, is the curing time, is the chemical stability coefficient, is the stability of the mechanical properties of the formation, is the formation permeability, is the degree of crack development, is the disaster-prone structure coefficient.

[0021] As an optional solution, a damping term is added to the momentum control equation, specifically:

[0022] ;

[0023] in, is the density, For pressure, is the momentum flux tensor, which is the rate of change of fluid momentum per unit volume; is the pressure gradient, which represents the rate of change of pressure in the x, y, and z directions; is the velocity gradient, which represents the rate of change of the fluid velocity in each x, y, and z direction; is the viscosity function characterized by time t and slurry temperature T, which can be obtained through experiments, g is the acceleration of gravity, is the surface tension; To control the damping strength, is the damping term, where is the coefficient that controls the damping strength; ▽ is the gradient operator, and Ρv is the momentum density, that is, the momentum per unit volume.

[0024] As an optional solution, the loss function of the neural network model is specifically:

[0025] ;

[0026] in, is the data fitting loss term, is the physical residual loss term, To control the hyperparameters of the physical residual effect, It is the square of the residual between the output of the neural network model and the calculation result of the fluid calculation control equation; is the boundary loss function term, A hyperparameter that balances the weight of boundary condition loss in the total loss.

[0027] As an alternative, the data fitting loss term for:

[0028] ;

[0029] in, For the neural network The predicted value of the data point, is the corresponding actual observation value, is the total number of data points.

[0030] As an optional solution, the boundary loss function term for:

[0031] ;

[0032] in, is the model prediction value at the boundary position, The value specified for the boundary condition.

[0033] In other embodiments, the following technical solutions are adopted:

[0034] A grouting intelligent calculation system based on the coupling of neural network and numerical solution, comprising:

[0035] A fluid calculation control equation construction module is used to determine the fluid calculation control equation required for the calculation working condition; the fluid calculation control equation includes a momentum control equation, and a damping term is added to the momentum control equation;

[0036] The grouting intelligent calculation module is used to take boundary conditions, grouting velocity, grouting pressure, initial dynamic water flow field, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density as input data, perform numerical simulation of the input data in the initial stage through numerical simulation methods, and use the parameters of the last time step obtained from the initial stage numerical simulation as initial data to input into the trained neural network model to obtain prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data;

[0037] Among them, the loss function of the neural network model includes a data fitting loss term, a physical residual loss term and a boundary loss function term; the momentum control equation with the damping term added is used as the physical residual loss term.

[0038] In other embodiments, the following technical solutions are adopted:

[0039] A terminal device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0040] In other embodiments, the following technical solutions are adopted:

[0041] A computer-readable storage medium stores a computer program / instruction thereon, which implements the steps of the above method when executed by a processor.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] (1) The method of the present invention constructs a neural network framework for accurately capturing the fluid dynamic characteristics. By adding a damping term to the momentum control equation, the numerical stability and physical credibility of the model are enhanced, and the excessive oscillation and non-physical behavior of the system are effectively controlled. The control equation of the slurry flow is embedded in the loss function as a physical constraint after regularization, realizing the understanding of the physical laws by the neural network. Based on the EDMD algorithm, the time-space analytical flow field of the sampled data is subjected to nonlinear modal decomposition, and the instantaneous dynamic changes of the slurry on the time scale and the structural and periodic dynamic characteristics on the spatial scale are obtained. In the process of capturing the flow field characteristics, the high-dimensional dilemma caused by random noise or non-critical features in the non-overfitting data is reduced, and the dimensionality of the data is reduced.

[0044] (2) The method of the present invention performs an initial numerical simulation of the input data through numerical simulation of physical equations. The trained model captures the physical fields such as pressure, velocity, temperature, as well as the local details and global spatiotemporal evolution trends between the fields. It replaces the physical solver to complete all subsequent iterative processes. Based on the simulation prediction results, further physical solution iteration and verification are performed to realize the mutual feedback verification between the physical solution and the neural network, ensuring the accuracy of the simulation data and realizing efficient grouting numerical simulation.

[0045] (3) The method of the present invention can dynamically adjust the time span of the initial stage according to the actual complexity of the working conditions. By integrating the dynamic grouting data and geological conditions, a dynamic adjustment time span calculation formula is proposed. Intelligent simulation is performed based on the time span, effectively ensuring the result accuracy under complex working conditions and the calculation efficiency under simple working conditions, and adapting to different geological conditions and grouting schemes.

[0046] Other features and advantages of additional aspects of the present invention will be given in part in the following description and in part will become obvious from the following description or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of the intelligent grouting calculation method based on the coupling of neural network and numerical solution in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0049] 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 application. 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 "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0050] Example 1

[0051] In one or more embodiments, a grouting intelligent calculation method based on the coupling of neural network and numerical solution is disclosed, combined with Figure 1 , specifically including the following process:

[0052] (1) Determine the fluid calculation control equations required for the calculation conditions; the fluid calculation control equations mainly include the continuity equation, momentum control equation, phase fraction equation, time transmission equation, state equation and energy equation, etc.

[0053] If there is no thermal effect in the multiphase flow problem being studied, the continuity equation, momentum control equation, phase fraction equation and time transport equation are mainly used.

[0054] If a three-phase flow problem is studied and there are thermal effects, the continuity equation, momentum control equation, phase fraction equation, time transfer equation, state equation and energy equation are mainly used to non-dimensionalize the control equation. Basic units such as speed, time, and pressure are selected to further define new dimensionless variables. The dimensionless variables are substituted into the original control equation to convert the variables and parameters in the control equation into unitless form, reduce the impact of different dimensions, and check the completeness and compatibility between the equations.

[0055] In this embodiment, a damping term is added to the momentum control equation and directly added to the control equation to enhance the numerical stability and physical credibility of the model and effectively control the excessive oscillation and non-physical behavior of the system. For example, the original momentum equation is:

[0056] ;

[0057] in, is the density, For pressure, is the viscosity function characterized by time t and slurry temperature T, which can be obtained through experiments, g is the acceleration of gravity, is the surface tension.

[0058] After adding the damping term, the equation becomes:

[0059] ;

[0060] in, To control the damping strength, is the time derivative of the velocity vector.

[0061] (2) The boundary conditions, grouting velocity, grouting pressure, initial flow field of dynamic water, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density are used as input data. The input data are numerically simulated in the initial stage by numerical simulation methods to obtain the calculation results of slurry velocity, grouting pressure, phase fraction and viscosity parameters. The parameters of the last time step obtained from the initial stage numerical simulation are used as initial data and input into the trained neural network model to obtain the prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data.

[0062] In this embodiment, the neural network model is constructed based on the nonlinear mode decomposition algorithm (EDMD).

[0063] The loss function of the neural network model is:

[0064] ;

[0065] in, is the data fitting loss term, is the physical residual loss term, To control the hyperparameters of the physical residual effect, It is the square of the residual between the output of the neural network model and the calculation result of the fluid calculation control equation; is the boundary loss function term, A hyperparameter that balances the weight of boundary condition loss in the total loss.

[0066] In this embodiment, a damping term is added to the momentum control equation and directly added to the control equation to enhance the numerical stability and physical credibility of the model and effectively control the excessive oscillation and non-physical behavior of the system. For example, the original momentum equation is:

[0067] ;

[0068] in, is the density, For pressure, is the viscosity function characterized by time t and slurry temperature T, which can be obtained through experiments, g is the acceleration of gravity, is the surface tension.

[0069] After adding the damping term, the equation becomes:

[0070] ;

[0071] in, To control the damping strength, is the time derivative of the velocity vector.

[0072] The modified governing equations are directly used to define the physical residual part of the loss function of the neural network:

[0073] ;

[0074] The loss function is constructed as:

[0075]

[0076] in, is the data fitting loss term, is the physical residual loss term, To control the hyperparameters of the physical residuals, including but not limited to the residuals of the equations of conservation of momentum, conservation of energy, conservation of mass, etc. It is the square of the residual between the output of the neural network model and the calculation result of the fluid calculation control equation.

[0077] Data fitting loss ;

[0078] in For the neural network The predicted value of the data point, is the corresponding actual observation value, is the total number of data points.

[0079] Physical residual loss = ;

[0080] in, For the The residuals of the physical control equations calculated based on the output of the neural network are used as evaluation points. is the total number of evaluation points, It is a hyperparameter used to adjust the weight of physical residuals in the total loss. Similarly, this residual includes but is not limited to the residuals of equations such as conservation of momentum, conservation of energy, and conservation of mass.

[0081] Constructing the boundary loss function :

[0082] ;

[0083] in, is the model prediction value at the boundary position, The values ​​specified for boundary conditions, where boundary conditions are known physical quantities or constraints that must be satisfied at the boundaries of a system or simulation region.

[0084] Through the above steps, physical constraints are embedded in the loss function, which constrains the solutions within the computational domain and on the boundary to follow physical laws.

[0085] In this embodiment, a parameter feature database is constructed by randomly sampling a numerical simulation case library, wherein the numerical simulation case library stores field data such as pressure field, velocity field, and phase fraction field of grouting at different time points and position points.

[0086] Data is extracted according to the set time step to obtain the data values ​​of flow field characteristic data (pressure, velocity, etc.) and spatiotemporal characteristic data (time span, spatial position). The outliers in the data set are checked and corrected. Based on the EDMD algorithm, the nonlinear modal decomposition of the time-space analytical flow field of the sampled data is realized.

[0087] First, the Gaussian radial basis function (RBF) is selected as the dictionary function of EDMD, and the expression is:

[0088] ;

[0089] in, is the center of the nucleus, is the standard deviation.

[0090] Input each data point into the RBF dictionary, for each point in the dataset , use all defined RBFs to calculate its eigenvectors:

[0091] ;

[0092] in, , For the A center point.

[0093] Combine the RBF eigenvectors of all points into a feature matrix :

[0094] ;

[0095] right Perform singular value decomposition:

[0096] ;

[0097] in, is the left singular vector, is a singular value, are right singular vectors.

[0098] Construct an approximation of the Koopman operator :

[0099] ;

[0100] in, is the data matrix for the next time step, for The conjugate transpose matrix of describes the row space characteristics of the data matrix, and the column vectors constitute the orthogonal basis of the data row space. is a right singular vector matrix whose column vectors form an orthogonal basis of the data column space.

[0101] right Perform eigenvalue decomposition and use numerical linear algebra libraries (such as NumPy, MATLAB, etc.) to perform Koopman operator Perform eigenvalue decomposition to extract the eigenvalues ​​and corresponding eigenvectors. For each eigenvalue, calculate the modulus of the eigenvalue. ,if If the damping coefficient is greater than 1, the corresponding mode is growing. If it is less than 1, the mode is decaying, indicating that the fluid is dynamically unstable. System optimization can be achieved by adjusting the damping coefficient. During the grouting process, the damping coefficient is primarily used to describe the resistance or dissipation effects encountered by the slurry during flow and diffusion. In particular, when the slurry passes through complex pores or fractures, the damping coefficient determines the rate of slurry flow decay. The damping coefficient can be related to the fluid viscosity, formation properties, and the interaction between the slurry and the medium.

[0102] This method captures the instantaneous dynamic changes of the slurry on a temporal scale and the structural and periodic dynamic features on a spatial scale. This eliminates the high-dimensionality dilemma caused by random noise or non-critical features in non-overfitted data during the process of capturing flow field characteristics, achieving data dimensionality reduction. The extracted data is converted into a format suitable for machine learning training, such as a CSV file, and standardized to a mean of 0 and a standard deviation of 1. Based on these steps, the extracted data is divided into training, test, and comparison sets based on time proportions, and the neural network model is trained.

[0103] Perform pre-training tests, train the same case with different time steps, adjust the network weights and bias parameters according to the pre-training test results, and continue training until the training is completed.

[0104] The input data is numerically simulated in the initial stage through the numerical simulation method. The time span of the initial stage is dynamically adjusted according to the actual complexity of the working conditions. The factors considered include: grouting flow rate, grouting pressure, grouting flow, slurry selection, and geological conditions.

[0105] ;

[0106] ;

[0107] ;

[0108] in, As the basic time span, 、 、 、 、 、 、 、 、 、 、 are weight coefficients, is the inverse of the grouting rate, is the inverse of the grouting pressure, is the slurry selection parameter, is the geological condition complexity coefficient, is the viscosity of the slurry, is the curing time, is the chemical stability coefficient, is the stability of the mechanical properties of the formation, is the formation permeability, is the degree of crack development, is the disaster-prone structure coefficient.

[0109] After determining the time span of the initial phase, set the final phase time to be consistent with the time span of the initial phase. Set the initial conditions and the time step to the time span of the initial phase. After completing the numerical simulation, input the parameters of the last time step of the initial phase as the initial data into the trained neural network model to obtain the prediction results of slurry velocity, grouting pressure, phase fraction, and viscosity data.

[0110] For the output of the neural network model, 10% of the total time steps are set for numerical solution verification. A three-stage step-by-step trust verification mechanism is established to ensure the reliability and accuracy of the model; the details are as follows:

[0111] Assuming the total time steps is 100, the first 10 time steps are used for validation.

[0112] In the first stage, a fixed number a1 of time step nodes is used for preliminary verification. If the error of the preliminary verification results is controlled within 5%, the second stage is entered.

[0113] In the second phase, trust in the model is enhanced by gradually reducing the verification frequency until the model output is fully trusted. Specifically, if the error between the model output and the numerical calculation is less than 5% within the set time step a2, the model output is considered credible and enters the full trust state.

[0114] In a state of complete confidence, no further numerical verification is performed, and subsequent simulation predictions proceed directly. After the predictions are complete, the third phase begins, where rigorous numerical verification of the prediction results for the final a3 time steps is performed. If the error in the verification results is still within 5%, the grouting simulation results are output; if not, the initial grouting conditions are recalculated.

[0115] The sum of the time steps of the three stages is 10% of the total time step, that is: a1+ a2+ a3=10.

[0116] Of course, for the specific error range requirement, this embodiment is set to 5%. In other implementations, it can also be set according to actual needs.

[0117] The numerical simulation results and neural network simulation results were collated, and the neural network parameters were tuned and optimized based on the verification results and the actual engineering excavation findings.

[0118] Example 2

[0119] In one or more embodiments, a grouting intelligent computing system based on the coupling of a neural network and a numerical solution is disclosed, characterized in that it includes:

[0120] A fluid calculation control equation construction module is used to determine the fluid calculation control equation required for the calculation working condition; the fluid calculation control equation includes a momentum control equation, and a damping term is added to the momentum control equation;

[0121] The grouting intelligent calculation module is used to take boundary conditions, grouting velocity, grouting pressure, initial dynamic water flow field, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density as input data, perform numerical simulation of the input data in the initial stage through numerical simulation methods, and use the parameters of the last time step obtained from the initial stage numerical simulation as initial data to input into the trained neural network model to obtain prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data;

[0122] Among them, the loss function of the neural network model includes a data fitting loss term, a physical residual loss term and a boundary loss function term; the momentum control equation with the damping term added is used as the physical residual loss term.

[0123] The specific implementation of each of the above modules is the same as that in Example 1 and will not be described in detail.

[0124] Example 3

[0125] In one or more embodiments, a terminal device is disclosed, including a server. The server includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the intelligent grouting calculation method based on coupling a neural network with a numerical solution, as described in Example 1, is implemented. For the sake of brevity, the specific process is not further described.

[0126] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0127] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0128] During implementation, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or by instructions in the form of software.

[0129] Example 4

[0130] In one or more embodiments, a computer-readable storage medium is disclosed, in which a plurality of instructions are stored, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device for the grouting intelligent calculation method based on coupling of neural network and numerical solution described in Example 1.

[0131] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A grouting intelligent calculation method based on the coupling of neural network and numerical solution, characterized in that: include: Determine the fluid calculation control equations required for the calculation conditions; The fluid calculation control equation includes a momentum control equation, and a damping term is added to the momentum control equation; The boundary conditions, grouting velocity, grouting pressure, initial dynamic water flow field, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density are used as input data. The input data is numerically simulated in the initial stage through the numerical simulation method. The parameters of the last time step obtained in the initial stage numerical simulation are used as initial data and input into the trained neural network model to obtain the prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data. The loss function of the neural network model includes a data fitting loss term, a physical residual loss term, and a boundary loss function term; the momentum control equation with the damping term added is used as the physical residual loss term; It also includes: for the output results of the neural network model, setting a% of the total time steps for numerical solution verification; establishing a three-stage step-by-step trust verification mechanism, specifically: In the first stage, a fixed number of time-step nodes are used to perform preliminary numerical calculation verification. If the error of the verification result meets the requirements, the second stage is entered. Otherwise, the initial grouting condition parameters are adjusted and the grouting intelligent calculation is repeated. The second stage increases trust in the model by gradually reducing the verification frequency until the model output is fully trusted. After full trust, simulation prediction is carried out. After the prediction is completed, the third stage begins. In the third stage, the prediction results of the last time step are numerically verified. If the error of the verification result meets the requirements, the grouting simulation result is output; otherwise, the initial grouting condition parameters are adjusted and the grouting intelligent calculation is performed again; where a is the set value; When performing numerical simulation of the initial stage of input data, the time span of the initial stage is dynamically adjusted according to the actual complexity of the working conditions; specifically: ； ； ； in, As the basic time span, 、 、 、 、 、 、 、 、 、 、 are weight coefficients, is the inverse of the grouting rate, is the inverse of the grouting pressure, is the slurry selection parameter, is the geological condition complexity coefficient, is the viscosity of the slurry, is the curing time, is the chemical stability coefficient, is the stability of the mechanical properties of the formation, is the formation permeability, is the degree of crack development, is the disaster-prone structure coefficient; Indicates the time span of the initial phase.

2. The grouting intelligent calculation method based on the coupling of neural network and numerical solution according to claim 1 is characterized in that: Add a damping term to the momentum control equation, specifically: ； in, is the density, For pressure, is the momentum flux tensor, which is the rate of change of fluid momentum per unit volume; is the pressure gradient, which represents the rate of change of pressure in the x, y, and z directions; is the velocity gradient, which represents the rate of change of the fluid velocity in each x, y, and z direction; is the viscosity function characterized by time t and slurry temperature T, which can be obtained through experiments, g is the acceleration of gravity, is the surface tension; To control the damping strength, is the damping term, where is the coefficient that controls the damping strength; ▽ is the gradient operator, is the momentum density, that is, the momentum per unit volume.

3. The grouting intelligent calculation method based on coupling of neural network and numerical solution according to claim 1 is characterized in that: The loss function of the neural network model is specifically: ； in, is the data fitting loss term, is the physical residual loss term, To control the hyperparameters of the physical residual effect, It is the square of the residual between the output of the neural network model and the calculation result of the fluid calculation control equation; is the boundary loss function term, A hyperparameter that balances the weight of boundary condition loss in the total loss.

4. The grouting intelligent calculation method based on coupling of neural network and numerical solution according to claim 3 is characterized in that: The data fitting loss term for: ； in, For the neural network The predicted value of the data point, is the corresponding actual observation value, is the total number of data points.

5. The grouting intelligent calculation method based on coupling of neural network and numerical solution according to claim 3 is characterized in that: The boundary loss function term for: ； in, is the model prediction value at the boundary position, The value specified for the boundary condition.

6. A grouting intelligent computing system based on the coupling of neural network and numerical solution, characterized in that: include: Fluid calculation control equation building module, used to determine the fluid calculation control equation required for calculation conditions; The fluid calculation control equation includes a momentum control equation, and a damping term is added to the momentum control equation; The grouting intelligent calculation module is used to take boundary conditions, grouting velocity, grouting pressure, initial dynamic water flow field, gravity field, slurry diffusion morphology, temperature field, slurry viscosity, constant volume specific heat capacity, thermal conductivity and density as input data, perform numerical simulation of the input data in the initial stage through numerical simulation methods, and use the parameters of the last time step obtained from the initial stage numerical simulation as initial data to input into the trained neural network model to obtain prediction results of slurry velocity, grouting pressure, phase fraction and viscosity data; The loss function of the neural network model includes a data fitting loss term, a physical residual loss term, and a boundary loss function term; the momentum control equation with the damping term added is used as the physical residual loss term; It also includes: for the output results of the neural network model, setting a% of the total time steps for numerical solution verification; establishing a three-stage step-by-step trust verification mechanism, specifically: In the first stage, a fixed number of time-step nodes are used to perform preliminary numerical calculation verification. If the error of the verification result meets the requirements, the second stage is entered. Otherwise, the initial grouting condition parameters are adjusted and the grouting intelligent calculation is repeated. The second stage increases trust in the model by gradually reducing the verification frequency until the model output is fully trusted. After full trust, simulation prediction is carried out. After the prediction is completed, the third stage begins. In the third stage, the prediction results of the last time step are numerically verified. If the error of the verification result meets the requirements, the grouting simulation result is output; otherwise, the initial grouting condition parameters are adjusted and the grouting intelligent calculation is performed again; where a is the set value; When performing numerical simulation of the initial stage of input data, the time span of the initial stage is dynamically adjusted according to the actual complexity of the working conditions; specifically: ； ； ； in, As the basic time span, 、 、 、 、 、 、 、 、 、 、 are weight coefficients, is the inverse of the grouting rate, is the inverse of the grouting pressure, is the slurry selection parameter, is the geological condition complexity coefficient, is the viscosity of the slurry, is the curing time, is the chemical stability coefficient, is the stability of the mechanical properties of the formation, is the formation permeability, is the degree of crack development, is the disaster-prone structure coefficient; Indicates the time span of the initial phase.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images