Variable diameter shield disturbance mixing test method and system

Abstract

The application belongs to the technical field of underground structure test, and provides a variable-diameter shield disturbance mixed test method and system, which comprises the following steps: obtaining a posterior probability distribution according to a parameter sample obtained from soil body parameters; obtaining boundary displacement data according to a Bayesian inference result based on a numerical substructure, performing numerical analysis on the boundary displacement data based on a data conversion system, and obtaining predicted force data; obtaining predicted response data according to the predicted force data based on a physical substructure; updating the numerical substructure according to the predicted response data based on the data conversion system, and determining a target balance force according to new feedback force based on the updated numerical substructure to drive the next stage until the interaction boundary between the numerical substructure and the physical substructure meets displacement coordination and force balance. The method disclosed by the application obtains the posterior probability distribution of the rock-soil body parameters through Bayesian inference, and improves the adaptability and prediction accuracy of the variable-diameter shield tunneling process to the construction disturbance evolution process.

Description

Technical Field

[0001] This invention relates to the field of underground structure testing technology, and in particular to a method and system for mixed testing of variable-diameter shield tunneling disturbance. Background Technology

[0002] The variable-diameter shield tunneling process will apply additional loads to the adjacent underground structure, which may cause damage or even destruction to the structure. Hybrid tests can not only study the interaction between different substructures at the system scale, but also study the structural damage and failure laws at the structural scale. However, the fidelity of the numerical substructure in the hybrid test is usually difficult to guarantee, which makes it difficult to guarantee the accuracy of the boundary loads input from the numerical substructure to the test substructure.

[0003] The related technologies introduced digital twin technology in the hybrid test, which updated the numerical model to make its simulation results match the measured data of the construction site in real time, thereby ensuring the fidelity of the numerical substructure. However, due to the uncertainty of the soil and rock mass at the construction site, the above method is not accurate in simulating the response of the multi-source measuring points at the construction site, making it difficult to assess the construction risks caused by the uncertainty. Summary of the Invention

[0004] This invention provides a method and system for hybrid testing of disturbances in variable-diameter shield tunneling machines, which addresses the shortcomings of existing hybrid testing methods that struggle to assess the uncertainties of soil and rock masses at construction sites, resulting in inaccurate simulation results for responses from multiple source measuring points at the construction site. The method described in this invention improves the adaptability and prediction accuracy of variable-diameter shield tunneling processes to the evolution of construction disturbances.

[0005] This invention provides a hybrid test method for disturbance of variable-diameter shield tunneling machines, applied to a hybrid test system. The hybrid test system includes a numerical substructure, a data conversion system, and a physical substructure. The numerical substructure is constructed based on a three-dimensional finite element model. The method includes:

[0006] At each stage of tunneling using a variable-diameter shield, Bayesian derivation is performed on the parameter samples to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein, the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method.

[0007] Based on the numerical substructure, boundary displacement data is obtained according to the Bayesian derivation results. The boundary displacement data is then numerically analyzed using a data conversion system to obtain predicted force data. Based on the physical substructure, the loading device is driven to apply an equivalent load on the boundary of the physical model according to the predicted force data to obtain predicted response data. The predicted response data includes force response data and displacement response data.

[0008] The data conversion system updates the numerical substructure based on the predicted response data; the data conversion system determines a new feedback force based on the force response data and the predicted force data, and determines a target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable-diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein, the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0009] According to the present invention, a method for hybrid disturbance testing of variable-diameter shield tunneling machines includes Bayesian derivation of parameter samples, which comprises:

[0010] Based on the surrogate model, Bayesian inference is performed on the parameter samples to obtain the posterior probability distribution of the soil parameters and the Bayesian inference results; wherein, the surrogate model is obtained by iteratively training the target neural network using sample soil parameters and sample response data as training sample pairs, combined with the target algorithm; wherein, the target algorithm includes a multivariate adaptive regression spline algorithm or a multinomial chaotic kriging algorithm.

[0011] According to the present invention, a mixed test method for disturbance of a variable-diameter shield tunneling machine is provided, wherein the posterior probability distribution is obtained through the following steps:

[0012] The parameter samples are processed based on the surrogate model to obtain response prediction data;

[0013] A likelihood function is constructed based on the predicted response data and the soil parameters monitored at the current stage.

[0014] The posterior probability distribution is calculated based on the prior probability distribution and the likelihood function.

[0015] According to the present invention, a method for hybrid disturbance testing of variable-diameter shield tunneling machines is provided, wherein the predicted force data obtained by numerically analyzing the boundary displacement data based on a data conversion system includes:

[0016] Based on the data conversion system, the soil-structure numerical model is invoked according to the boundary displacement data;

[0017] Numerical analysis is performed based on the soil-structure numerical model, using the boundary displacement data as the boundary displacement load, to obtain the predicted force data.

[0018] According to the present invention, a method for hybrid testing of variable-diameter shield tunneling perturbations includes updating the numerical substructure based on the predicted response data using the data conversion system, comprising:

[0019] Based on the data conversion system, the high-fidelity constitutive parameters and stiffness of the numerical substructure are updated according to the predicted response data to obtain the updated numerical substructure.

[0020] According to the present invention, a mixed test method for disturbance of a variable diameter shield tunnel is provided, wherein the soil parameters include at least one of the soil elastic modulus, cohesion and internal friction angle.

[0021] The present invention also provides a variable-diameter shield tunneling perturbation hybrid test system, comprising:

[0022] The Bayesian derivation module is used to perform Bayesian derivation on parameter samples at each stage of tunneling using a variable-diameter shield, to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein, the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method.

[0023] The analysis and loading module is used to obtain boundary displacement data based on the Bayesian derivation results according to the numerical substructure, perform numerical analysis on the boundary displacement data based on the data conversion system to obtain predicted force data, and drive the loading device to apply equivalent loads on the boundaries of the physical model based on the predicted force data according to the physical substructure to obtain predicted response data; wherein, the predicted response data includes force response data and displacement response data; the numerical substructure is constructed based on a three-dimensional finite element model;

[0024] An update module is used to update the numerical substructure based on the predicted response data using the data conversion system; determine a new feedback force based on the force response data and the predicted force data using the data conversion system; and determine a target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable-diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0025] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the variable-diameter shield tunneling disturbance hybrid test method as described above.

[0026] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the variable-diameter shield tunneling disturbance hybrid test method as described above.

[0027] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the variable-diameter shield tunneling disturbance hybrid test method as described above.

[0028] The present invention provides a method and system for hybrid testing of variable-diameter shield tunneling disturbances. By performing Bayesian derivation on parameter samples, the posterior probability distribution of soil parameters and the Bayesian derivation results are obtained. Based on the numerical substructure, boundary displacement data is acquired according to the Bayesian derivation results. A data conversion system performs numerical analysis on the boundary displacement data to obtain predicted force data. Based on the physical substructure, the loading device applies equivalent loads to the boundaries of the physical model according to the predicted force data, obtaining predicted response data. The data conversion system updates the numerical substructure based on the predicted response data. Based on the data conversion system, a new feedback force is determined based on the force response data and predicted force data. Based on the updated numerical substructure, a target equilibrium force is determined based on the new feedback force to drive the next stage until the boundary satisfies displacement coordination and force balance. This process obtains the posterior probability distribution of soil parameters through Bayesian inference, achieving a synergistic improvement in uncertainty quantification and multi-source response fitting, thereby enhancing the adaptability and prediction accuracy of the variable-diameter shield tunneling process to the evolution of construction disturbances. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0030] Figure 1 This is a flowchart illustrating the variable-diameter shield tunneling disturbance hybrid test method provided by the present invention.

[0031] Figure 2 This is a schematic diagram of the structure of the variable diameter shield tunneling disturbance hybrid test system provided by the present invention.

[0032] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0034] The following is combined Figures 1-2 The present invention describes the variable-diameter shield tunneling disturbance hybrid test method and system.

[0035] Figure 1 This is a flowchart illustrating the variable-diameter shield tunneling disturbance hybrid test method provided by the present invention, as shown below. Figure 1 As shown, this method is applied to a hybrid experimental system, which includes a numerical substructure, a data conversion system, and a physical substructure. The numerical substructure is constructed based on a three-dimensional finite element model and includes the following steps:

[0036] Step 110: At each stage of tunneling using a variable diameter shield, Bayesian derivation is performed on the parameter samples to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein, the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method.

[0037] In this step, during the initial stage of tunneling by the variable-diameter shield, the prior probability distribution of the soil parameters can be pre-set experimentally.

[0038] For example, by conducting preliminary experiments based on geological surveys, engineering experience, and analogical analysis, prior probability distributions of multiple key soil parameters can be constructed to characterize the initial understanding of strata characteristics.

[0039] Specifically, before the mixed test is carried out, based on the constructed prior distribution of soil parameters, the soil parameters monitored in the real environment are sampled using the Markov Lemont Carlo (MCMC) sampling method to generate corresponding parameter samples.

[0040] In this step, during the non-initial stage of the variable diameter shield tunneling, the prior probability distribution of the soil parameters can be the posterior probability distribution obtained by Bayesian derivation of the soil parameters in the previous stage; that is, it continuously iterates at different stages of construction, using the posterior probability distribution of the previous stage as the prior probability distribution of the next stage, and continuously incorporating new monitoring data to improve the stability of parameter identification and the reliability of prediction results.

[0041] In this embodiment, the soil parameters include at least one of the soil elastic modulus, cohesion, and internal friction angle.

[0042] In this embodiment, the correlation between soil parameters and predicted values ​​can be simulated by constructing a mathematical model or a neural network model. The residual between the predicted value and the actual construction site monitoring data can be determined through this correlation, thereby quantifying the credibility of the current parameter sample. Then, the prior probability distribution corresponding to the soil parameter and the credibility are combined to calculate the corresponding posterior probability distribution, and the Bayesian inference result corresponding to the soil parameter is output as the input of the numerical sub-model in the current stage of the hybrid experiment.

[0043] Step 120: Based on the numerical substructure, obtain boundary displacement data according to the Bayesian derivation results; perform numerical analysis on the boundary displacement data based on the data conversion system to obtain predicted force data; based on the physical substructure, drive the loading device to apply equivalent loads on the boundary of the physical model according to the predicted force data to obtain predicted response data; wherein, the predicted response data includes force response data and displacement response data.

[0044] In this step, the numerical substructure uses a three-dimensional finite element model to describe the shield tunneling disturbance effect and the interaction between the strata and the structure in high fidelity. The physical substructure uses a large-scale physical model to accurately reproduce the local damage evolution mechanism such as shield segment cracking, joint opening, and bolt yielding. Both substructures use the OpenFresco-LabVIEW-servo loading platform to achieve boundary displacement coordination and force balance control, ensuring the consistency and reliability of the system response.

[0045] In this embodiment, the variable-diameter shield tunneling disturbance hybrid test requires multiple data iterations (each tunneling stage is one iteration process), and each iteration process is divided into a forward data stream and a reverse data stream; wherein, the forward data stream includes the following process:

[0046] In this embodiment, an interaction boundary can be set between the numerical substructure and the physical substructure through a virtual interaction platform (such as OpenFresco); the Bayesian derivation results output in step 110 are input into the numerical substructure, which can describe the shield tunneling disturbance effect and the interaction between the strata and the structure with high fidelity based on the three-dimensional finite element model; and the predicted displacement of the interaction boundary (i.e., boundary displacement data) is read out using the OpenFresco platform.

[0047] In this embodiment, inputting boundary displacement data into the data conversion system for numerical analysis includes: calling the soil-structure numerical model based on the boundary displacement data using the data conversion system; performing numerical analysis based on the boundary displacement data as boundary displacement loads using the soil-structure numerical model to obtain predicted force data.

[0048] In this embodiment, the soil-structure model of the data conversion system accurately realizes the nonlinear mapping of "displacement → force", providing a scientific decision-making basis for millimeter-level displacement control and kilonewton-level load prediction for variable diameter shield tunneling projects.

[0049] In this embodiment, the edge predicted force data is set as the boundary condition as the loading condition of the physical substructure, and the loading device is driven to apply an equivalent load on the boundary of the preset physical model in the physical substructure. By measuring the mechanical response of the soil and structure (corresponding to the interaction force between soil and structure), the corresponding response data and displacement response data are obtained.

[0050] The reverse data stream for the variable-diameter shield tunneling disturbance hybrid test provided in this embodiment includes the following process:

[0051] Step 130: Update the numerical substructure based on the predicted response data using the data conversion system; determine the new feedback force based on the force response data and predicted force data using the data conversion system, and determine the target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein, the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0052] In this step, the physical substructure sends the predicted response data to the data conversion system. The data conversion system calls the parameter evaluation and back analysis module by comparing the force response data (measured value) and the predicted force data (predicted value). This module is used to identify the stress model or material physical properties of the soil and structure, update the physical properties of the soil-structure numerical model (i.e., the numerical substructure), recalculate the equivalent feedback force, and send it back to the numerical substructure.

[0053] In this embodiment, the physical properties include at least one of high-fidelity constitutive parameters and stiffness properties.

[0054] For example, updating the numerical substructure based on the predicted response data using the data conversion system includes: updating the high-fidelity constitutive parameters and stiffness of the numerical substructure based on the predicted response data using the data conversion system to obtain the updated numerical substructure; in this embodiment, real-time inversion is used to achieve true constitutive updating and stiffness updating, thereby improving the accuracy of data simulation of the numerical substructure.

[0055] In this embodiment, the numerical subsystem introduces a new unbalanced force based on the updated feedback force. The unbalanced force is the difference between the predicted force and the feedback force, driving a new round of iteration (i.e., the next stage of tunneling using a variable-diameter shield). After multiple rounds of iteration, the unbalanced force approaches zero (or the unbalanced force is lower than the preset tolerance). That is, the interaction boundary between the physical substructure and the numerical substructure simultaneously satisfies the displacement coordination and force balance conditions, achieving iterative convergence.

[0056] It should be noted that the posterior probability distribution of the current stage is used as the prior probability distribution of the next stage. A set of parameter samples is generated using the MCMC sampling method and input into the efficient surrogate model to quickly obtain the corresponding predicted values. The residuals between the predicted values ​​and the actual construction site monitoring data are calculated, and then the likelihood function is constructed using the residuals. Finally, Bayes' theorem is used to combine the prior distribution of this stage with the likelihood function to obtain the posterior probability distribution and Bayesian derivation results of the next stage. The target unbalanced force and the Bayesian derivation results of the next stage are then input into the numerical substructure to obtain the corresponding boundary displacement data for subsequent experimental processes. This process is repeated until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance, thus completing the tunneling test of the variable diameter shield.

[0057] As can be seen from the above embodiments, after each round of Bayesian update, a hybrid test is carried out for the entire tunneling process based on the latest parameters. The hybrid test outputs information on stratum deformation, structural response and damage evolution. As the soil parameters are iteratively updated and the test is gradually carried out, combined with the posterior distribution uncertainty quantification results, the test prediction accuracy is gradually improved, which can provide real-time risk warning, parameter control and construction method optimization decision support for the construction process.

[0058] The variable-diameter shield tunneling disturbance hybrid test method provided in this invention obtains the posterior probability distribution of soil parameters and the Bayesian derivation results by performing Bayesian derivation on parameter samples. Based on the numerical substructure, boundary displacement data is obtained according to the Bayesian derivation results. Based on the data conversion system, numerical analysis is performed on the boundary displacement data to obtain predicted force data. Based on the physical substructure, the loading device is driven to apply equivalent loads on the boundary of the physical model according to the predicted force data to obtain predicted response data. Based on the data conversion system, the numerical substructure is updated according to the predicted response data. Based on the data conversion system, a new feedback force is determined according to the force response data and predicted force data. Based on the updated numerical substructure, the target equilibrium force is determined according to the new feedback force to drive the next stage until the boundary satisfies displacement coordination and force balance. This process obtains the posterior probability distribution of soil parameters through Bayesian inference, achieving a synergistic improvement in uncertainty quantification and multi-source response fitting, thereby improving the adaptability and prediction accuracy of the variable-diameter shield tunneling process to the evolution of construction disturbances.

[0059] In some embodiments, Bayesian derivation of parameter samples includes: performing Bayesian derivation of parameter samples based on a surrogate model to obtain the posterior probability distribution of soil parameters and the Bayesian derivation result; wherein the surrogate model is obtained by iteratively training a target neural network using sample soil parameters and sample response data as training sample pairs and combined with a target algorithm; wherein the target algorithm includes a multivariate adaptive regression spline algorithm or a multinomial chaotic kriging algorithm.

[0060] In this embodiment, an efficient proxy model is established through the following steps:

[0061] (1) Perform Latin hypercube sampling on the soil parameter set to generate sample soil parameters.

[0062] In this embodiment, data cleaning or normalization preprocessing operations can be performed on the parameter samples to reduce the impact of outliers and improve the quality of the parameter samples.

[0063] (2) Based on the preset finite element model, the response data is calculated according to the parameter sample to obtain the corresponding sample response data, and the sample soil parameters form a training sample pair.

[0064] (3) Use multivariate adaptive regression spline (MARS) and multinomial chaotic kriging (PCK) algorithms to iteratively train convolutional neural networks or Transformer models. Under the condition of satisfying the iteration, a surrogate model is obtained, which has the ability to quickly predict parameter-response relationship.

[0065] The variable-diameter shield tunneling disturbance hybrid test method provided in this invention uses sample soil parameters and sample response data as training sample pairs, and combines the target algorithm to iteratively train the target neural network to obtain a surrogate model for Bayesian inference of parameter samples, thereby obtaining the posterior probability distribution of soil parameters and Bayesian inference results. It can achieve efficient prediction of soil sample prediction and response through Bayesian inference driven by the surrogate model, and at the same time improve the efficiency of hybrid test.

[0066] In some embodiments, the posterior probability distribution is obtained through the following steps: processing parameter samples based on a surrogate model to obtain response prediction data; constructing a likelihood function based on the response prediction data and the soil parameters monitored in the current stage; and calculating the posterior probability distribution based on the prior probability distribution and the likelihood function.

[0067] In this embodiment, before the mixed test is carried out, a set of parameter samples is generated based on the constructed prior distribution of soil parameters using the Markov Lemont Carlo (MCMC) sampling method. These samples are then input into the efficient surrogate model to quickly obtain the corresponding response prediction data. The residuals between the predicted values ​​and the actual construction site monitoring data are calculated. By assuming that the residuals follow a Gaussian distribution, a likelihood function is constructed to quantify the credibility of the current parameter samples.

[0068] In this embodiment, the likelihood function L ( x This can be expressed by the following formula:

[0069] ;

[0070] in, i The data observation points are numbered. These are monitoring values ​​from the construction site. These are model predictions. It is the error variance; using Bayes' theorem, the prior distribution is combined with the likelihood function to obtain the posterior distribution of the parameter, which reflects the correction result of the current stage data on the parameter.

[0071] The variable-diameter shield tunneling disturbance hybrid test method provided in this invention processes parameter samples through a surrogate model to obtain response prediction data; constructs a likelihood function based on the response prediction data and the soil parameters monitored at the current stage; calculates the posterior probability distribution based on the prior probability distribution and the likelihood function; and establishes a hybrid test technology system for response identification and rolling optimization throughout the entire construction process by organically combining the hybrid test process with Bayesian inference, significantly improving the scientificity and reliability of risk control and response prediction in the variable-diameter shield tunneling process.

[0072] The variable diameter shield tunneling machine disturbance hybrid test system provided by the present invention will be described below. The variable diameter shield tunneling machine disturbance hybrid test system described below can be referred to in correspondence with the variable diameter shield tunneling machine disturbance hybrid test method described above.

[0073] Figure 2 This is a schematic diagram of the variable-diameter shield tunneling disturbance hybrid test system provided by the present invention, as shown below. Figure 2 As shown, the variable-diameter shield tunneling disturbance hybrid test system includes: a Bayesian derivation module 210, an analysis and loading module 220, and an update module 230.

[0074] The Bayesian derivation module 210 is used to perform Bayesian derivation on parameter samples at each stage of tunneling using a variable-diameter shield to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein, the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method.

[0075] The analysis and loading module 220 is used to obtain boundary displacement data based on the Bayesian derivation results of the numerical substructure, perform numerical analysis on the boundary displacement data based on the data conversion system to obtain predicted force data, and drive the loading device to apply equivalent loads on the boundary of the physical model based on the predicted force data of the physical substructure to obtain predicted response data. The predicted response data includes force response data and displacement response data. The numerical substructure is constructed based on a three-dimensional finite element model.

[0076] The update module 230 is used to update the numerical substructure based on the predicted response data using the data conversion system; to determine the new feedback force based on the force response data and predicted force data using the data conversion system; and to determine the target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein, the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0077] The variable-diameter shield tunneling disturbance hybrid test system provided in this invention obtains the posterior probability distribution of soil parameters and the Bayesian derivation results by performing Bayesian derivation on parameter samples. Based on the numerical substructure, boundary displacement data is obtained according to the Bayesian derivation results. Based on the data conversion system, numerical analysis is performed on the boundary displacement data to obtain predicted force data. Based on the physical substructure, the loading device is driven to apply equivalent loads on the boundary of the physical model according to the predicted force data to obtain predicted response data. Based on the data conversion system, the numerical substructure is updated according to the predicted response data. Based on the data conversion system, a new feedback force is determined according to the force response data and predicted force data. Based on the updated numerical substructure, the target equilibrium force is determined according to the new feedback force to drive the next stage until the boundary satisfies displacement coordination and force balance. This process obtains the posterior probability distribution of soil parameters through Bayesian inference, achieving a synergistic improvement in uncertainty quantification and multi-source response fitting, thereby improving the adaptability and prediction accuracy of the variable-diameter shield tunneling process to the evolution of construction disturbances.

[0078] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a hybrid test method for variable-diameter shield tunneling disturbance. This method is applied to a hybrid test system, which includes a numerical substructure, a data conversion system, and a physical substructure. The numerical substructure is constructed based on a three-dimensional finite element model and includes: performing Bayesian derivation on parameter samples at each stage of tunneling using a variable-diameter shield to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method; obtaining boundary displacement data based on the Bayesian derivation results using the numerical substructure; and performing numerical analysis on the boundary displacement data using the data conversion system to obtain... The process involves obtaining predicted force data; applying equivalent loads to the boundaries of the physical model using a loading device driven by the physical substructure based on the predicted force data to obtain predicted response data; wherein the predicted response data includes force response data and displacement response data; updating the numerical substructure based on the predicted response data using a data conversion system; determining a new feedback force based on the force response data and predicted force data using the data conversion system, and determining the target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable-diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0079] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the variable-diameter shield tunneling disturbance hybrid test method provided by the above methods. This method is applied to a hybrid test system, which includes a numerical substructure, a data conversion system, and a physical substructure. The numerical substructure is constructed based on a three-dimensional finite element model and includes: performing Bayesian derivation on parameter samples at each stage of tunneling using a variable-diameter shield to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method; and based on the numerical substructure, the Bayesian derivation results are obtained... If boundary displacement data is obtained, numerical analysis is performed on the boundary displacement data based on the data conversion system to obtain predicted force data. Based on the physical substructure, the loading device is driven to apply equivalent loads on the boundary of the physical model according to the predicted force data to obtain predicted response data. The predicted response data includes force response data and displacement response data. The numerical substructure is updated based on the predicted response data based on the data conversion system. Based on the force response data and predicted force data, the new feedback force is determined based on the data conversion system, and the target equilibrium force is determined based on the updated numerical substructure and the new feedback force to drive the next stage of variable diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance. The prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0081] Furthermore, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, this computer program performs the variable-diameter shield tunneling disturbance hybrid test method provided by the methods described above. This method is applied to a hybrid test system, which includes a numerical substructure, a data conversion system, and a physical substructure. The numerical substructure is constructed based on a three-dimensional finite element model and includes: performing Bayesian derivation on parameter samples at each stage of tunneling using a variable-diameter shield to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method; obtaining boundary displacement data based on the Bayesian derivation results using the numerical substructure; and performing data conversion based on the data conversion... The system performs numerical analysis on the boundary displacement data to obtain predicted force data. Based on the physical substructure, the loading device applies equivalent loads to the boundary of the physical model according to the predicted force data, obtaining predicted response data. The predicted response data includes force response data and displacement response data. The data conversion system updates the numerical substructure based on the predicted response data. Based on the data conversion system, a new feedback force is determined based on the force response data and predicted force data. Based on the updated numerical substructure, the target equilibrium force is determined based on the new feedback force to drive the next stage of variable diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance. The prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

[0082] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for hybrid disturbance testing of variable-diameter shield tunnels, characterized in that, Applied to a hybrid experimental system, the hybrid experimental system comprising a numerical substructure, a data conversion system, and a physical substructure, wherein the numerical substructure is constructed based on a three-dimensional finite element model, the method includes: At each stage of tunneling using a variable-diameter shield, Bayesian derivation is performed on the parameter samples to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein, the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method. The Bayesian derivation of the parameter samples includes: Based on the surrogate model, Bayesian inference is performed on the parameter samples to obtain the posterior probability distribution of the soil parameters and the Bayesian inference results; wherein, the surrogate model is obtained by iteratively training the target neural network using sample soil parameters and sample response data as training sample pairs, combined with the target algorithm; wherein, the target algorithm includes a multivariate adaptive regression spline algorithm or a multinomial chaotic kriging algorithm. Based on the numerical substructure, boundary displacement data is obtained according to the Bayesian derivation results. The boundary displacement data is then numerically analyzed using a data conversion system to obtain predicted force data. Based on the physical substructure, the loading device is driven to apply an equivalent load on the boundary of the physical model according to the predicted force data to obtain predicted response data. The predicted response data includes force response data and displacement response data. The data conversion system updates the numerical substructure based on the predicted response data; the data conversion system determines a new feedback force based on the force response data and the predicted force data, and determines a target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable-diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein, the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage; The step of updating the numerical substructure based on the predicted response data using the data transformation system includes: Based on the data conversion system, the high-fidelity constitutive parameters and stiffness of the numerical substructure are updated according to the predicted response data to obtain the updated numerical substructure; The high-fidelity constitutive parameters and stiffness are updated through real-time inversion.

2. The variable-diameter shield tunneling disturbance hybrid test method according to claim 1, characterized in that, The posterior probability distribution is obtained through the following steps: The parameter samples are processed based on the surrogate model to obtain response prediction data; A likelihood function is constructed based on the predicted response data and the soil parameters monitored at the current stage. The posterior probability distribution is calculated based on the prior probability distribution and the likelihood function.

3. The variable-diameter shield tunneling disturbance hybrid test method according to claim 1, characterized in that, The numerical analysis of the boundary displacement data based on the data conversion system to obtain the predicted force data includes: Based on the data conversion system, the soil-structure numerical model is invoked according to the boundary displacement data; Numerical analysis is performed based on the soil-structure numerical model, using the boundary displacement data as the boundary displacement load, to obtain the predicted force data.

4. The variable-diameter shield tunneling disturbance hybrid test method according to claim 1, characterized in that, The soil parameters include at least one of the following: soil elastic modulus, cohesion, and internal friction angle.

5. A variable-diameter shield tunneling machine disturbance hybrid test system, employing the variable-diameter shield tunneling machine disturbance hybrid test method as described in claim 1, characterized in that, include: The Bayesian derivation module is used to perform Bayesian derivation on parameter samples at each stage of tunneling using a variable-diameter shield, to obtain the posterior probability distribution of soil parameters and the Bayesian derivation results; wherein, the parameter samples are obtained based on the prior distribution of soil parameters and the MCMC sampling method. The analysis and loading module is used to obtain boundary displacement data based on the Bayesian derivation results according to the numerical substructure, perform numerical analysis on the boundary displacement data based on the data conversion system to obtain predicted force data, and drive the loading device to apply equivalent loads on the boundaries of the physical model based on the predicted force data according to the physical substructure to obtain predicted response data; wherein, the predicted response data includes force response data and displacement response data; the numerical substructure is constructed based on a three-dimensional finite element model; An update module is used to update the numerical substructure based on the predicted response data using the data conversion system; determine a new feedback force based on the force response data and the predicted force data using the data conversion system; and determine a target equilibrium force based on the updated numerical substructure and the new feedback force to drive the next stage of variable-diameter shield tunneling until the interaction boundary between the numerical substructure and the physical substructure satisfies displacement coordination and force balance; wherein the prior probability distribution corresponding to the next stage is the posterior probability distribution of the current stage.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the variable-diameter shield tunneling disturbance hybrid test method as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the variable-diameter shield tunneling disturbance hybrid test method as described in any one of claims 1 to 4.

Images