Prediction method and device for composite stratum tunnel support parameters

Abstract

The invention relates to the technical field of tunnel excavation, in particular to a prediction method and device for composite stratum tunnel support parameters, and the method comprises the steps: obtaining three-dimensional numerical model calculation parameters; sampling and combining the support parameters and the relationship between the tunnel and the stratum to obtain a three-dimensional numerical simulation calculation working condition group; establishing a three-dimensional numerical model to obtain a control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation working condition; determining the sensitivity of different support parameters to the control effect, and obtaining the influence weight of the different support parameters to the control effect; establishing a prediction model of the support parameters, and adjusting the calculation parameters of the three-dimensional numerical model to obtain a nonlinear prediction function of the support parameters; and predicting and optimizing the support parameters to obtain support parameters meeting preset conditions. Therefore, the problems of unstable surrounding rock, support damage, cost increase and the like caused by support design misalignment possibly caused by exploration errors caused by complex strata in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the technical field of tunnel excavation, and in particular to a method and device for predicting support parameters of a composite stratum tunnel. Background Art

[0002] The rock properties of the surrounding rock in composite strata vary in complexity, and the physical and mechanical properties of different surrounding rocks vary greatly. During tunnel excavation, the surrounding rock is prone to non-uniform deformation. Unreasonable design of support parameters will lead to further increase in surrounding rock deformation, which will in turn cause serious damage to the tunnel support structure and pose a serious safety threat to on-site construction personnel. However, excessive support parameters will cause waste of resources, affect the construction period, and lack economy.

[0003] In related technologies, geological surveys are usually carried out before tunnel excavation, and corresponding support parameters are formulated based on the on-site geological survey results and tunnel design standards. Most of the related technologies are built on this basis to scientifically and effectively guide tunnel construction.

[0004] However, in the relevant technologies, due to the complex geological environment of composite strata, there may be errors in the results of stratum parameter surveys, which can easily lead to unreasonable support parameter design, which may cause the surrounding rock deformation to not converge, serious damage to the support structure, waste of resources, and huge cost losses, which urgently needs to be improved. Summary of the invention

[0005] The present application provides a method and device for predicting support parameters of a composite stratum tunnel to solve the problems in the related technology that, due to the complex geological environment of the composite stratum, errors may exist in the results of the stratum parameter survey, which may easily lead to unreasonable support parameter design, and may cause the surrounding rock deformation to not converge, the support structure to be seriously damaged, resources to be wasted, and costs to be lost.

[0006] The first aspect of the present application provides a method for predicting support parameters of a composite stratum tunnel, comprising the following steps: obtaining three-dimensional numerical model calculation parameters, wherein the three-dimensional numerical model calculation parameters include at least one of tunnel structure design parameters, stratum parameters, construction methods, support parameters, tunnel-stratum relationship and on-site surrounding rock deformation data; using a Latin hypercube sampling algorithm to sample and combine the support parameters and the tunnel-stratum relationship to obtain a three-dimensional numerical simulation calculation condition grouping; establishing a three-dimensional numerical model based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation condition grouping to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition based on the three-dimensional numerical model; and using a Latin hypercube sampling algorithm to sample and combine the support parameters and the tunnel-stratum relationship to obtain a three-dimensional numerical simulation calculation condition grouping. The control effect is analyzed by using a Kriging model to determine the sensitivity of different support parameters to the control effect, and the influence weights of the different support parameters on the control effect are obtained based on the sensitivity; a prediction model of composite stratum tunnel support parameters is established based on the three-dimensional numerical model calculation parameters and the control effect, and the three-dimensional numerical model calculation parameters are adjusted according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters; the composite stratum tunnel support parameters are predicted and optimized using the nonlinear prediction function and the NSGA-III algorithm to obtain the composite stratum tunnel support parameters that meet preset conditions.

[0007] Optionally, in one embodiment of the present application, the three-dimensional numerical model is established based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation condition grouping, including: using ANSYS software, combining the tunnel structure design parameters and the three-dimensional numerical simulation calculation condition grouping to establish multiple three-dimensional numerical grid models; importing the three-dimensional numerical grid model into the finite difference software FLAC-3D, and using the command stream function in the FLAC-3D to set the three-dimensional numerical grid model as a Mohr-Coulomb constitutive model to obtain the set three-dimensional numerical grid model; assigning values ​​to the set three-dimensional numerical grid model in combination with formation parameters, applying an initial geostress field to the set three-dimensional numerical grid model according to the actual tunnel burial depth and the formation parameters, iteratively calculating until the set three-dimensional numerical grid model reaches a preset initial geostress equilibrium state, the iteration is terminated, and the three-dimensional numerical grid model after the initial geostress equilibrium is obtained.

[0008] Optionally, in one embodiment of the present application, the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition is obtained based on the three-dimensional numerical model, including: using the actual excavation method to perform numerical calculations on the three-dimensional numerical grid model after the initial ground stress is balanced, so as to set the surrounding rock to be excavated as a Null model in turn; based on the Null model, assigning values ​​to the support structure according to preset support parameters until the three-dimensional numerical grid model after the initial ground stress is balanced reaches an elastic equilibrium state under the influence of excavation; based on the elastic equilibrium state, monitoring and statistically analyzing the displacement and stress of key parts of the tunnel after excavation, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition.

[0009] Optionally, in one embodiment of the present application, the expression of the Kriging model is:

[0010]

[0011] Among them, y(x) is the model response value, x is the function value of the unknown sample point, and f i (x) is the basis function of the function value x of the unknown sample point, P is the number of basis functions, β i is the corresponding regression coefficient, z(x) has a mean of 0 and a variance of σ 2 Gaussian random process.

[0012] Optionally, in one embodiment of the present application, a prediction model for composite stratum tunnel support parameters is established based on the three-dimensional numerical model calculation parameters and the control effect, and the three-dimensional numerical model calculation parameters are adjusted according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters, including: using the three-dimensional numerical model calculation parameters as training data samples to input the prediction model for composite stratum tunnel support parameters to predict the control effect of surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters; calculating the mean square error between the control effect of surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters and the field surrounding rock deformation data; when the mean square error is greater than or equal to a preset value, adjusting the three-dimensional numerical model calculation parameters according to the influence weights until the mean square error is less than a preset value, so as to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters.

[0013] A second aspect of the present application provides a prediction device for composite stratum tunnel support parameters, including: an acquisition module, used to acquire three-dimensional numerical model calculation parameters, wherein the three-dimensional numerical model calculation parameters include tunnel structure design parameters, stratum parameters, construction methods, support parameters, tunnel-stratum relationship and at least one of on-site surrounding rock deformation data; a combination module, used to sample and combine the support parameters and the tunnel-stratum relationship using a Latin hypercube sampling algorithm to obtain a three-dimensional numerical simulation calculation condition grouping; a construction module, used to establish a three-dimensional numerical model based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation condition grouping, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition based on the three-dimensional numerical model; an analysis module A block is used to analyze the control effect by using the Kriging model to determine the sensitivity of different support parameters to the control effect, and obtain the influence weights of the different support parameters on the control effect based on the sensitivity; an adjustment module is used to establish a prediction model of composite stratum tunnel support parameters based on the three-dimensional numerical model calculation parameters and the control effect, and adjust the three-dimensional numerical model calculation parameters according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters; a prediction module is used to predict and optimize the composite stratum tunnel support parameters by using the nonlinear prediction function and the NSGA-III algorithm to obtain the composite stratum tunnel support parameters that meet preset conditions.

[0014] Optionally, in one embodiment of the present application, the construction module includes: a construction unit, which is used to use ANSYS software to establish multiple three-dimensional numerical grid models in combination with the tunnel structure design parameters and the three-dimensional numerical simulation calculation condition grouping; a setting unit, which is used to import the three-dimensional numerical grid model into the finite difference software FLAC-3D, and use the command stream function in the FLAC-3D to set the three-dimensional numerical grid model as a Mohr-Coulomb constitutive model to obtain the set three-dimensional numerical grid model; a first assignment unit, which is used to assign values ​​to the set three-dimensional numerical grid model in combination with formation parameters, apply an initial geostress field to the set three-dimensional numerical grid model according to the actual tunnel burial depth and the formation parameters, and iterate the calculation until the set three-dimensional numerical grid model reaches a preset initial geostress equilibrium state, the iteration is terminated, and the three-dimensional numerical grid model after the initial geostress equilibrium is obtained.

[0015] Optionally, in one embodiment of the present application, the construction module includes: a first calculation unit, used to perform numerical calculations on the three-dimensional numerical grid model after the initial ground stress is balanced using an actual excavation method, so as to set the surrounding rock to be excavated as a Null model in turn; a second assignment unit, used to assign values ​​to the support structure based on the Null model and according to preset support parameters, until the three-dimensional numerical grid model after the initial ground stress is balanced reaches an elastic equilibrium state under the influence of excavation; a statistical unit, used to monitor and count the displacements and stresses of key parts of the tunnel after excavation based on the elastic equilibrium state, and obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition.

[0016] Optionally, in one embodiment of the present application, the expression of the Kriging model is:

[0017]

[0018] Among them, y(x) is the model response value, x is the function value of the unknown sample point, and f i (x) is the basis function of the function value x of the unknown sample point, P is the number of basis functions, β i is the corresponding regression coefficient, z(x) has a mean of 0 and a variance of σ 2 Gaussian random process.

[0019] Optionally, in one embodiment of the present application, the adjustment module includes: a prediction unit, used to use the three-dimensional numerical model calculation parameters as training data samples to input the prediction model of the composite stratum tunnel support parameters to predict the control effect of the surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters; a second calculation unit, used to calculate the mean square error between the control effect of the surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters and the field surrounding rock deformation data; an optimization unit, used to adjust the three-dimensional numerical model calculation parameters according to the influence weight when the mean square error is greater than or equal to a preset value, until the mean square error is less than a preset value, so as to optimize the prediction model to obtain the nonlinear prediction function of the composite stratum tunnel support parameters.

[0020] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting composite stratum tunnel support parameters as described in the above embodiment.

[0021] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned method for predicting composite formation tunnel support parameters.

[0022] The fifth aspect of the present application provides a computer program product, which, when executed, is used to implement the above-mentioned method for predicting composite stratum tunnel support parameters.

[0023] The embodiment of the present application can obtain the calculation parameters of the three-dimensional numerical model, can sample and combine the support parameters and the relationship between the tunnel and the stratum, obtain the three-dimensional numerical simulation calculation condition grouping, and then establish a three-dimensional numerical model to obtain the control effect of the surrounding rock deformation under each three-dimensional numerical simulation calculation condition, thereby determining the sensitivity of different support parameters to the control effect, and obtaining the influence weight of different support parameters on the control effect, so as to establish a prediction model of the support parameters, adjust the calculation parameters of the three-dimensional numerical model, obtain the nonlinear prediction function of the support parameters, and predict and optimize the support parameters to obtain the support parameters that meet the preset conditions, so as to achieve accurate optimization and prediction of the support parameters, improve the accuracy of the tunnel structure safety assessment, and provide strong data-driven support for the decision-making of tunnel engineering under complex geological conditions. Thus, the problem in the related technology that due to the complex geological environment of the composite stratum, the formation parameter survey results may have errors, which may easily lead to unreasonable design of support parameters, which may cause the surrounding rock deformation to not converge, the support structure to be seriously damaged, the waste of resources, and the cost loss.

[0024] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0026] Figure 1 A flowchart of a method for predicting composite stratum tunnel support parameters provided according to an embodiment of the present application;

[0027] Figure 2 A block diagram of a device for predicting composite stratum tunnel support parameters provided according to an embodiment of the present application;

[0028] Figure 3 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0030] The following describes a method and device for predicting composite stratum tunnel support parameters according to an embodiment of the present application with reference to the accompanying drawings. In view of the related technologies mentioned in the above-mentioned background technology center, due to the complex geological environment of composite strata, there may be errors in the results of stratum parameter survey, which may easily lead to unreasonable support parameter design, which may cause the surrounding rock deformation to not converge, the support structure to be seriously damaged, the waste of resources, and the cost loss. The present application provides a prediction method for composite stratum tunnel support parameters. In this method, the three-dimensional numerical model calculation parameters can be obtained, and the support parameters and the relationship between the tunnel and the stratum can be sampled and combined to obtain a three-dimensional numerical simulation calculation condition grouping, and then a three-dimensional numerical model can be established to obtain the control effect of the surrounding rock deformation under each three-dimensional numerical simulation calculation condition, so as to determine the sensitivity of different support parameters to the control effect, and obtain the influence weight of different support parameters on the control effect, so as to establish a prediction model for the support parameters, adjust the three-dimensional numerical model calculation parameters, obtain the nonlinear prediction function of the support parameters, and predict and optimize the support parameters to obtain the support parameters that meet the preset conditions, so as to achieve accurate optimization and prediction of the support parameters, improve the accuracy of the tunnel structure safety assessment, and provide strong data-driven support for the decision-making of tunnel engineering under complex geological conditions. This solves the problem in related technologies that, due to the complex geological environment of composite strata, errors may exist in the results of stratum parameter surveys, which may easily lead to unreasonable support parameter design, and may cause non-convergence of surrounding rock deformation, serious damage to support structures, waste of resources, cost losses, and other problems.

[0031] Specifically, Figure 1 A schematic flow chart of a method for predicting support parameters of a composite stratum tunnel provided in an embodiment of the present application.

[0032] like Figure 1 As shown, the method for predicting the composite stratum tunnel support parameters includes the following steps:

[0033] In step S101, the three-dimensional numerical model calculation parameters are obtained, wherein the three-dimensional numerical model calculation parameters include at least one of tunnel structure design parameters, stratum parameters, construction methods, support parameters, tunnel-stratum relationship and on-site surrounding rock deformation data.

[0034] It can be understood that the construction method includes but is not limited to the excavation method and the construction sequence of the support structure, among which the excavation method includes but is not limited to the excavation mode, excavation footage, step height, step length, and the excavation mode includes but is not limited to the full-section excavation method, step method, three-step method, CRD method, etc.; the support parameters include but are not limited to the parameters such as advance support, initial support and secondary lining; the relationship between the tunnel and the formation includes the type of formation, the inclination of the formation, and the proportion of the formation; the on-site surrounding rock deformation data refers to the displacement and stress change data of the surrounding rock during tunnel construction obtained through displacement monitoring elements and stress monitoring elements.

[0035] The embodiments of the present application can adopt parameters such as tunnel structure design parameters, formation parameters, excavation methods, support parameters and the relationship between tunnel and formation of actual projects in numerical simulation, effectively simulate the on-site conditions of tunnel construction and excavation, and improve the accuracy of surrounding rock deformation data. Furthermore, the on-site surrounding rock deformation data can be compared and verified with the numerical simulation results, which is conducive to improving the accuracy of numerical simulation.

[0036] In step S102, the Latin hypercube sampling algorithm is used to sample and combine the support parameters and the relationship between the tunnel and the stratum to obtain a three-dimensional numerical simulation calculation condition grouping.

[0037] Specifically, the embodiment of the present application can use the Latin hypercube sampling algorithm to randomly and independently sample and combine in two non-overlapping sub-intervals (tunnel-stratum relationship and support parameters) under the premise of ensuring the uniformity of the sample points, wherein the samples of the Latin hypercube sampling are:

[0038]

[0039] Where n is the number of sample points; i is the number of sample points in the subinterval; j is the number of subintervals; d xj is the number of random independent permutations from 1 to n; e ij is a random number between [0,1].

[0040] The embodiment of the present application can use Latin hypercube sampling (LHS) to sample and combine support parameters and the relationship between tunnels and formations. Through the LHS sampling method with memory, it can ensure that the number of times each parameter in the support parameters and the relationship between tunnels and formations appears is the same, and ensure that the sampling values ​​can cover the entire distribution range of the input parameters, making the sampling points more representative. While ensuring the fitting of the sampling results, it can reasonably simplify the complexity of the arrangement and combination of different parameters, and realize efficient grouping of three-dimensional numerical simulation calculation conditions.

[0041] In step S103, a three-dimensional numerical model is established based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation conditions, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition based on the three-dimensional numerical model.

[0042] It is understandable that the tunnel structure design parameters include but are not limited to the geometric dimensions of the tunnel (such as diameter, length, cross-sectional shape), the tunnel route, the lining structure design (such as thickness, material), the expected loads (such as vehicle loads, soil pressure), the expected service life, etc.

[0043] The embodiment of the present application can use a three-dimensional numerical model established based on tunnel structure design parameters and three-dimensional numerical simulation calculation condition grouping to evaluate the control effect of surrounding rock deformation. Through high-precision numerical simulation, it helps to accurately predict the deformation of the surrounding rock under different support schemes and construction conditions, which can effectively improve the accuracy of tunnel design. Based on the simulation results, the support parameters and construction strategies can be adjusted in a targeted manner to achieve the best surrounding rock stabilization effect with the lowest support cost, thereby realizing the optimization of support design.

[0044] Optionally, in one embodiment of the present application, a three-dimensional numerical model is established based on tunnel structure design parameters and three-dimensional numerical simulation calculation condition grouping, including: using ANSYS software, combining tunnel structure design parameters and three-dimensional numerical simulation calculation condition grouping to establish multiple three-dimensional numerical grid models; importing the three-dimensional numerical grid model into the finite difference software FLAC-3D, and using the command stream function in FLAC-3D to set the three-dimensional numerical grid model to the Mohr-Coulomb constitutive model to obtain the set three-dimensional numerical grid model; assigning values ​​to the set three-dimensional numerical grid model in combination with the formation parameters, applying an initial geostress field to the set three-dimensional numerical grid model according to the actual tunnel burial depth and formation parameters, iteratively calculating until the set three-dimensional numerical grid model reaches a preset initial geostress equilibrium state, the iteration is terminated, and the three-dimensional numerical grid model after the initial geostress equilibrium is obtained.

[0045] It is understandable that ANSYS software can perform finite element analysis (FEA), simulate and analyze engineering problems in multiple fields, and support modeling and simulation of complex geometric structures. FLAC-3D is a three-dimensional finite difference analysis software that can be used for numerical simulation of geotechnical engineering and rock mechanics.

[0046] The embodiment of the present application can accurately capture the complex geometric morphology and mechanical properties of the tunnel and surrounding rock and soil by finely constructing a three-dimensional geometric model of the tunnel structure in ANSYS and converting it into a numerical mesh model, thereby improving the accuracy of the simulation. The Mohr-Coulomb constitutive model can be quickly set up in combination with the command stream function, which greatly improves the efficiency and flexibility of the model setting. It also can effectively ensure the stability and reliability of the simulation results by iteratively calculating until the model reaches a preset initial geostress equilibrium state.

[0047] Optionally, in one embodiment of the present application, the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition is obtained based on the three-dimensional numerical model, including: using the actual excavation method to perform numerical calculations on the three-dimensional numerical grid model after the initial ground stress is balanced, so as to set the surrounding rock to be excavated as a Null model in turn; based on the Null model, assigning values ​​to the support structure according to preset support parameters until the three-dimensional numerical grid model after the initial ground stress is balanced reaches an elastic equilibrium state under the influence of excavation; based on the elastic equilibrium state, monitoring and statistically analyzing the displacement and stress of key parts of the tunnel after excavation, and obtaining the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition.

[0048] It can be understood that the Null model refers to setting the part of the rock mass to be excavated to a state of "non-existence" or "no stress influence" in the model. The preset support parameters refer to a series of parameters predetermined when designing tunnel support, including but not limited to the arrangement, size, strength, stiffness, etc. of the support structure. The key parts include the arch crown, arch waist and arch bottom.

[0049] By simulating the excavation process and support effect, the embodiment of the present application can predict the displacement and stress distribution of the tunnel surrounding rock before construction, optimize design decisions, and reduce uncertainty and risks in construction. Based on the simulation results, the stress state and working efficiency of the support structure under different working conditions can be analyzed in detail, so that the support parameters can be adjusted to achieve a reasonable allocation of support resources.

[0050] In step S104, the control effect is analyzed using the Kriging model to determine the sensitivity of different support parameters to the control effect, and the influence weights of different support parameters on the control effect are obtained based on the sensitivity.

[0051] It can be understood that the Kriging model, as an unbiased estimation model with the minimum estimation variance, has the characteristics of combining global approximation with local random errors, and can be expressed as the sum of a parameterized linear regression model and a nonparametric random process.

[0052] Optionally, in one embodiment of the present application, the expression of the Kriging model is:

[0053]

[0054] Among them, y(x) is the model response value, x is the function value of the unknown sample point, and f i (x) is the basis function of the function value x of the unknown sample point, P is the number of basis functions, β i is the corresponding regression coefficient, z(x) has a mean of 0 and a variance of σ 2 The covariance of the Gaussian random process can be expressed as:

[0055]

[0056] Among them, θ k is the undetermined parameter used for model fitting, which indicates the sensitivity of the output value of the function to the k-th dimension input variable; M is the number of input sample points; is the distance between two sample points in the kth dimension.

[0057] Furthermore, according to the above principle, the embodiment of the present application only needs to solve the unknown parameter θ k .

[0058] Therefore, the embodiment of the present application can analyze the control effect of surrounding rock deformation under various three-dimensional numerical simulation calculation conditions based on the Kriging model, determine the sensitivity of each support parameter to the control effect of surrounding rock deformation, and obtain the influence weight of each support parameter on the control effect of surrounding rock deformation. The support parameters, the relationship between the tunnel and the stratum, and the control effect of surrounding rock deformation are input into the Kriging model, and the undetermined parameter θ corresponding to the optimal result of surrounding rock deformation control under various working conditions is solved. k , and the given parameter θ k Sort the parameters by size, determine the order of influence of the parameters related to the surrounding rock deformation control effect under different working conditions, identify the support parameters that have the greatest influence on the surrounding rock deformation control effect, determine the sensitivity of each support parameter to the surrounding rock deformation control effect, and obtain the influence weight of each support parameter on the surrounding rock deformation control effect based on the sensitivity of each support parameter to the surrounding rock deformation control effect.

[0059] The embodiment of the present application can input the working condition grouping and surrounding rock deformation control effect obtained through the Latin hypercube sampling algorithm into the Kriging model, effectively determine the sensitivity of each support parameter to the surrounding rock deformation control effect, and obtain the influence weight of each support parameter on the surrounding rock deformation control effect, thereby being able to accurately quantify the influence of different support parameters on the stability of the surrounding rock, and realize a refined evaluation of the control effect, providing a quantitative basis for the support design under the comprehensive consideration of multiple factors, and improving the scientificity and rationality of the design.

[0060] In step S105, a prediction model of composite stratum tunnel support parameters is established based on the three-dimensional numerical model calculation parameters and control effects, and the three-dimensional numerical model calculation parameters are adjusted according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of composite stratum tunnel support parameters.

[0061] It can be understood that a composite stratum refers to a stratum structure composed of two or more different types of soil or rock, such as a mixture of clay, sandstone, limestone, etc.

[0062] Optionally, in one embodiment of the present application, a prediction model for composite stratum tunnel support parameters is established based on the three-dimensional numerical model calculation parameters and control effects, and the three-dimensional numerical model calculation parameters are adjusted according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters, including: using the three-dimensional numerical model calculation parameters as training data samples to input the prediction model for the composite stratum tunnel support parameters to predict the control effect of the surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters; calculating the mean square error between the control effect of the surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters and the on-site surrounding rock deformation data; when the mean square error is greater than or equal to a preset value, adjusting the three-dimensional numerical model calculation parameters according to the influence weights until the mean square error is less than the preset value to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters.

[0063] It can be understood that the training data sample refers to a known data set used to teach the model how to predict the output from the input, among which the three-dimensional numerical model calculation parameters and their corresponding surrounding rock deformation control effects constitute the input-output sample pair of the model. The control effect of surrounding rock deformation refers to the degree of suppression of rock deformation around the tunnel after the implementation of specific support measures, which is a key indicator for measuring the effectiveness of support. The preset value refers to an allowable error limit set during the model optimization process, which is used to judge the acceptability of the difference between the predicted model output (i.e., the surrounding rock deformation control effect obtained by model prediction) and the actual observed data (on-site surrounding rock deformation data), among which the preset value is 0.01.

[0064] The embodiments of the present application can determine the importance weight of each parameter through sensitivity analysis in the optimization of tunnel support parameters, which helps to make appropriate adjustments during optimization. Through continuous iterative optimization, it can more accurately simulate the complex relationship between support parameters and surrounding rock deformation control effects in actual tunnel projects, effectively improve the accuracy of prediction, enhance decision-making efficiency, and provide a basis for dynamically adjusting support parameters when facing complex and changeable geological conditions, thereby increasing the adaptability and flexibility of construction.

[0065] In step S106, the composite stratum tunnel support parameters are predicted and optimized using the nonlinear prediction function and the NSGA-III algorithm to obtain composite stratum tunnel support parameters that meet preset conditions.

[0066] It can be understood that the preset conditions refer to a series of target thresholds and constraints that are pre-set according to the specific needs of the engineering project before predicting and optimizing the tunnel support parameters.

[0067] In the actual implementation process, the embodiment of the present application can use the NSGA-III algorithm to predict the optimal support parameters of the composite stratum tunnel. The optimal support parameters of the composite stratum tunnel are obtained by taking the optimal support parameters as the control target, and the nonlinear prediction function of the optimal support parameters of the composite stratum tunnel is used as the objective function of the NSGA-III algorithm. The three-dimensional numerical model calculation parameters are used as constraints to construct an optimal support parameter mapping model for the composite stratum tunnel, and predict the optimal support parameters of any composite stratum tunnel.

[0068] The embodiment of the present application uses a nonlinear prediction function combined with the NSGA-III algorithm to predict and optimize the support parameters of the composite stratum tunnel, which helps to explore the optimal solution, ensure the comprehensiveness and optimality of the solution, and can find the best support parameter combination that meets the preset conditions in a relatively short time, which helps to improve design efficiency and reduce economic losses and safety risks.

[0069] According to the prediction method of composite stratum tunnel support parameters proposed in the embodiment of the present application, the three-dimensional numerical model calculation parameters can be obtained, the support parameters and the relationship between the tunnel and the stratum can be sampled and combined, and the three-dimensional numerical simulation calculation condition grouping can be obtained, and then the three-dimensional numerical model can be established to obtain the control effect of the surrounding rock deformation under each three-dimensional numerical simulation calculation condition, so as to determine the sensitivity of different support parameters to the control effect, and obtain the influence weight of different support parameters on the control effect, so as to establish a prediction model of the support parameters, adjust the three-dimensional numerical model calculation parameters, obtain the nonlinear prediction function of the support parameters, and predict and optimize the support parameters to obtain the support parameters that meet the preset conditions, so as to achieve accurate optimization and prediction of the support parameters, improve the accuracy of the tunnel structure safety assessment, and provide strong data-driven support for the decision-making of tunnel engineering under complex geological conditions. Thus, the problem in the related technology that due to the complex geological environment of the composite stratum, the formation parameter survey results may have errors, which may easily lead to unreasonable design of support parameters, and may cause the surrounding rock deformation to not converge, the support structure to be seriously damaged, the waste of resources, the loss of cost and other problems.

[0070] Next, a device for predicting composite stratum tunnel support parameters proposed in an embodiment of the present application will be described with reference to the accompanying drawings.

[0071] Figure 2 It is a block diagram of a device for predicting composite stratum tunnel support parameters according to an embodiment of the present application.

[0072] like Figure 2 As shown, the prediction device 10 for composite stratum tunnel support parameters includes: an acquisition module 100 , a combination module 200 , a construction module 300 , an analysis module 400 , an adjustment module 500 and a prediction module 600 .

[0073] Specifically, the acquisition module 100 is used to obtain three-dimensional numerical model calculation parameters, wherein the three-dimensional numerical model calculation parameters include at least one of tunnel structure design parameters, formation parameters, construction methods, support parameters, tunnel-formation relationship and on-site surrounding rock deformation data.

[0074] The combination module 200 is used to sample and combine the support parameters and the relationship between the tunnel and the stratum using the Latin hypercube sampling algorithm to obtain a three-dimensional numerical simulation calculation condition grouping.

[0075] The construction module 300 is used to establish a three-dimensional numerical model based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation condition grouping, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition based on the three-dimensional numerical model.

[0076] The analysis module 400 is used to analyze the control effect using the Kriging model to determine the sensitivity of different support parameters to the control effect, and obtain the influence weight of different support parameters on the control effect based on the sensitivity.

[0077] The adjustment module 500 is used to establish a prediction model for composite stratum tunnel support parameters based on the three-dimensional numerical model calculation parameters and control effects, and adjust the three-dimensional numerical model calculation parameters according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function for the composite stratum tunnel support parameters.

[0078] The prediction module 600 is used to predict and optimize the composite stratum tunnel support parameters by using the nonlinear prediction function and the NSGA-III algorithm to obtain the composite stratum tunnel support parameters that meet the preset conditions.

[0079] Optionally, in one embodiment of the present application, the construction module 300 includes: a construction unit, a setting unit and a first assignment unit.

[0080] The construction unit is used to establish multiple three-dimensional numerical grid models by using ANSYS software, combining tunnel structure design parameters and three-dimensional numerical simulation calculation conditions;

[0081] A setting unit is used to import the three-dimensional numerical grid model into the finite difference software FLAC-3D, and use the command stream function in FLAC-3D to set the three-dimensional numerical grid model as a Mohr-Coulomb constitutive model to obtain the set three-dimensional numerical grid model;

[0082] The first assignment unit is used to assign values ​​to the set three-dimensional numerical grid model in combination with the formation parameters, apply an initial geostress field to the set three-dimensional numerical grid model according to the actual tunnel burial depth and the formation parameters, and iterate the calculation until the set three-dimensional numerical grid model reaches a preset initial geostress equilibrium state. The iteration is terminated to obtain the three-dimensional numerical grid model after the initial geostress equilibrium.

[0083] Optionally, in one embodiment of the present application, the construction module 300 includes: a first calculation unit, a second assignment unit and a statistical unit.

[0084] The first calculation unit is used to perform numerical calculation on the three-dimensional numerical grid model after the initial ground stress balance by using the actual excavation method, so as to sequentially set the surrounding rock to be excavated as a Null model;

[0085] The second assignment unit is used to assign values ​​to the support structure based on the Null model according to the preset support parameters until the three-dimensional numerical grid model after the initial ground stress balance reaches an elastic equilibrium state under the influence of excavation;

[0086] The statistical unit is used to monitor and count the displacement and stress of key parts of the tunnel after excavation based on the elastic equilibrium state, and obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition.

[0087] Optionally, in one embodiment of the present application, the expression of the Kriging model is:

[0088]

[0089] Among them, y(x) is the model response value, x is the function value of the unknown sample point, and f i (x) is the basis function of the function value x of the unknown sample point, P is the number of basis functions, β i is the corresponding regression coefficient, z(x) has a mean of 0 and a variance of σ 2 Gaussian random process.

[0090] Optionally, in one embodiment of the present application, the adjustment module 500 includes: a prediction unit, a second calculation unit and an optimization unit.

[0091] The prediction unit is used to use the three-dimensional numerical model calculation parameters as training data samples to input the prediction model of composite stratum tunnel support parameters to predict the control effect of surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters;

[0092] The second calculation unit is used to calculate the control effect of surrounding rock deformation corresponding to the calculation parameters of the three-dimensional numerical model and the mean square error of the surrounding rock deformation data on site;

[0093] The optimization unit is used to adjust the calculation parameters of the three-dimensional numerical model according to the influence weight when the mean square error is greater than or equal to the preset value, until the mean square error is less than the preset value, so as to optimize the prediction model to obtain the nonlinear prediction function of the composite stratum tunnel support parameters.

[0094] It should be noted that the above explanations and descriptions of the embodiment of the method for predicting support parameters of a tunnel in composite strata are also applicable to the device for predicting support parameters of a tunnel in composite strata of this embodiment, and will not be repeated here.

[0095] According to the prediction device of composite stratum tunnel support parameters proposed in the embodiment of the present application, the three-dimensional numerical model calculation parameters can be obtained, the support parameters and the relationship between the tunnel and the stratum can be sampled and combined, and the three-dimensional numerical simulation calculation condition grouping can be obtained, and then the three-dimensional numerical model can be established to obtain the control effect of the surrounding rock deformation under each three-dimensional numerical simulation calculation condition, so as to determine the sensitivity of different support parameters to the control effect, and obtain the influence weight of different support parameters on the control effect, so as to establish a prediction model of the support parameters, adjust the three-dimensional numerical model calculation parameters, obtain the nonlinear prediction function of the support parameters, and predict and optimize the support parameters to obtain the support parameters that meet the preset conditions, so as to achieve accurate optimization and prediction of the support parameters, improve the accuracy of the tunnel structure safety assessment, and provide strong data-driven support for the decision-making of tunnel engineering under complex geological conditions. Thus, the problem in the related technology that due to the complex geological environment of the composite stratum, the formation parameter survey results may have errors, which may easily lead to unreasonable design of support parameters, and may cause the surrounding rock deformation to not converge, the support structure to be seriously damaged, the waste of resources, the loss of cost and other problems.

[0096] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0097] A memory 301 , a processor 302 , and a computer program stored in the memory 301 and executable on the processor 302 .

[0098] When the processor 302 executes the program, the method for predicting composite stratum tunnel support parameters provided in the above embodiment is implemented.

[0099] Furthermore, the electronic device further comprises:

[0100] The communication interface 303 is used for communication between the memory 301 and the processor 302 .

[0101] The memory 301 is used to store computer programs that can be run on the processor 302 .

[0102] The memory 301 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0103] If the memory 301, the processor 302 and the communication interface 303 are implemented independently, the communication interface 303, the memory 301 and the processor 302 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0104] Optionally, in a specific implementation, if the memory 301, the processor 302 and the communication interface 303 are integrated on a chip, the memory 301, the processor 302 and the communication interface 303 can communicate with each other through an internal interface.

[0105] The processor 302 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0106] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting composite stratum tunnel support parameters.

[0107] An embodiment of the present application also provides a computer program product, which can run computer instructions. When the computer instructions are executed by a processor, the above-mentioned method for predicting composite stratum tunnel support parameters is implemented.

[0108] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0109] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0110] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0112] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0115] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting support parameters of a tunnel in composite strata, characterized in that: The following steps are involved: Acquire three-dimensional numerical model calculation parameters, wherein the three-dimensional numerical model calculation parameters include at least one of tunnel structure design parameters, stratum parameters, construction methods, support parameters, tunnel-stratum relationship, and on-site surrounding rock deformation data; The support parameters and the relationship between the tunnel and the stratum are sampled and combined using a Latin hypercube sampling algorithm to obtain a three-dimensional numerical simulation calculation condition grouping; A three-dimensional numerical model is established based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation conditions, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition based on the three-dimensional numerical model; The control effect is analyzed using a Kriging model to determine the sensitivity of different support parameters to the control effect, and based on the sensitivity, the influence weights of the different support parameters on the control effect are obtained; Establishing a prediction model of composite stratum tunnel support parameters based on the three-dimensional numerical model calculation parameters and the control effect, and adjusting the three-dimensional numerical model calculation parameters according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters; The nonlinear prediction function and the NSGA-III algorithm are used to predict and optimize the composite stratum tunnel support parameters to obtain the composite stratum tunnel support parameters that meet preset conditions.

2. The method according to claim 1, characterized in that The establishing of the three-dimensional numerical model based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation conditions grouping comprises: Using ANSYS software, combining the tunnel structure design parameters and the three-dimensional numerical simulation calculation conditions to establish multiple three-dimensional numerical grid models; Importing the three-dimensional numerical grid model into finite difference software FLAC-3D, and using the command stream function in the FLAC-3D to set the three-dimensional numerical grid model as a Mohr-Coulomb constitutive model, to obtain a set three-dimensional numerical grid model; The three-dimensional numerical grid model after the setting is assigned a value in combination with the formation parameters, an initial geostress field is applied to the three-dimensional numerical grid model after the setting according to the actual tunnel burial depth and the formation parameters, and iterative calculation is performed until the three-dimensional numerical grid model after the setting reaches a preset initial geostress equilibrium state, and the iteration is terminated to obtain the three-dimensional numerical grid model after the initial geostress equilibrium.

3. The method according to claim 2, characterized in that The control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition is obtained based on the three-dimensional numerical model, including: Using an actual excavation method, numerical calculation is performed on the three-dimensional numerical grid model after the initial ground stress is balanced, so as to sequentially set the surrounding rock to be excavated as a Null model; Based on the Null model, the support structure is assigned values ​​according to preset support parameters until the three-dimensional numerical grid model after the initial ground stress balance reaches an elastic equilibrium state under the influence of excavation; Based on the elastic equilibrium state, the displacement and stress of key parts of the tunnel after excavation are monitored and counted to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition.

4. The method according to claim 1, characterized in that: The expression of the Kriging model is: Among them, y(x) is the model response value, x is the function value of the unknown sample point, and f i (x) is the basis function of the function value x of the unknown sample point, P is the number of basis functions, β i is the corresponding regression coefficient, z(x) has a mean of 0 and a variance of σ 2 Gaussian random process.

5. The method according to claim 1, characterized in that The method of establishing a prediction model for composite stratum tunnel support parameters based on the three-dimensional numerical model calculation parameters and the control effect, and adjusting the three-dimensional numerical model calculation parameters according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function for the composite stratum tunnel support parameters includes: The three-dimensional numerical model calculation parameters are used as training data samples to input into the prediction model of the composite stratum tunnel support parameters to predict the control effect of the surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters; Calculate the control effect of surrounding rock deformation corresponding to the calculation parameters of the three-dimensional numerical model and the mean square error of the surrounding rock deformation data on site; When the mean square error is greater than or equal to a preset value, the calculation parameters of the three-dimensional numerical model are adjusted according to the influence weight until the mean square error is less than the preset value, so as to optimize the prediction model and obtain a nonlinear prediction function of the composite formation tunnel support parameters.

6. A device for predicting support parameters of a tunnel in a composite stratum, characterized in that: include: An acquisition module, used for acquiring three-dimensional numerical model calculation parameters, wherein the three-dimensional numerical model calculation parameters include at least one of tunnel structure design parameters, stratum parameters, construction methods, support parameters, tunnel-stratum relationship and on-site surrounding rock deformation data; A combination module, used for sampling and combining the support parameters and the relationship between the tunnel and the stratum by using a Latin hypercube sampling algorithm to obtain a three-dimensional numerical simulation calculation condition grouping; A construction module, used to establish a three-dimensional numerical model based on the tunnel structure design parameters and the three-dimensional numerical simulation calculation conditions, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition based on the three-dimensional numerical model; An analysis module, used for analyzing the control effect by using a Kriging model to determine the sensitivity of different support parameters to the control effect, and obtaining the influence weights of the different support parameters on the control effect based on the sensitivity; An adjustment module, used to establish a prediction model of composite stratum tunnel support parameters based on the three-dimensional numerical model calculation parameters and the control effect, and adjust the three-dimensional numerical model calculation parameters according to the influence weights to optimize the prediction model to obtain a nonlinear prediction function of the composite stratum tunnel support parameters; The prediction module is used to predict and optimize the composite stratum tunnel support parameters by using the nonlinear prediction function and the NSGA-III algorithm to obtain the composite stratum tunnel support parameters that meet the preset conditions.

7. The device according to claim 6, characterized in that The building blocks include: A construction unit is used to establish multiple three-dimensional numerical grid models by using ANSYS software in combination with the tunnel structure design parameters and the three-dimensional numerical simulation calculation conditions; A setting unit is used to import the three-dimensional numerical grid model into the finite difference software FLAC-3D, and use the command stream function in the FLAC-3D to set the three-dimensional numerical grid model as a Mohr-Coulomb constitutive model to obtain the set three-dimensional numerical grid model; The first assignment unit is used to assign values ​​to the set three-dimensional numerical grid model in combination with the formation parameters, apply an initial geostress field to the set three-dimensional numerical grid model according to the actual tunnel burial depth and the formation parameters, and iterate the calculation until the set three-dimensional numerical grid model reaches a preset initial geostress equilibrium state, and the iteration is terminated to obtain the three-dimensional numerical grid model after the initial geostress equilibrium.

8. The device according to claim 7, characterized in that The building blocks include: A first calculation unit is used to perform numerical calculation on the three-dimensional numerical grid model after the initial ground stress is balanced by using an actual excavation method, so as to sequentially set the surrounding rock to be excavated as a Null model; A second assignment unit is used to assign values ​​to the support structure based on the Null model and according to preset support parameters until the three-dimensional numerical grid model after the initial ground stress balance reaches an elastic equilibrium state under the influence of excavation; The statistical unit is used to monitor and count the displacement and stress of key parts of the tunnel after excavation based on the elastic equilibrium state, so as to obtain the control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation condition.

9. The device according to claim 6, characterized in that The expression of the Kriging model is: Among them, y(x) is the model response value, x is the function value of the unknown sample point, and f i (x) is the basis function of the function value x of the unknown sample point, P is the number of basis functions, β i is the corresponding regression coefficient, z(x) has a mean of 0 and a variance of σ 2 Gaussian random process.

10. The device according to claim 6, characterized in that The adjustment module comprises: A prediction unit, used to use the three-dimensional numerical model calculation parameters as training data samples to input into the prediction model of the composite stratum tunnel support parameters to predict the control effect of the surrounding rock deformation corresponding to the three-dimensional numerical model calculation parameters; A second calculation unit is used to calculate the control effect of surrounding rock deformation corresponding to the calculation parameters of the three-dimensional numerical model and the mean square error of the surrounding rock deformation data on site; The optimization unit is used to adjust the calculation parameters of the three-dimensional numerical model according to the influence weight when the mean square error is greater than or equal to the preset value until the mean square error is less than the preset value, so as to optimize the prediction model to obtain the nonlinear prediction function of the composite formation tunnel support parameters.

11. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting composite stratum tunnel support parameters as described in any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for predicting composite stratum tunnel support parameters as described in any one of claims 1 to 5.

13. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the method for predicting composite stratum tunnel support parameters as described in any one of claims 1-5.

Images