Method, system, equipment and medium for predicting the uplift of segments during shield tunnel construction

Abstract

The present application provides a method, system, equipment and medium for predicting the floating amount of segments during shield tunnel construction, which belongs to the field of tunnel detection technology. The method includes: obtaining an exploration data set and a measured data set of a shield tunnel section; inputting the exploration data set into a shield tunnel mechanical model for solution to obtain relevant mechanical parameter values ​​of the shield tunnel section; determining the physical control equation for reflecting the deformation characteristics of the shield tunnel section based on the Timoshenko beam model and its relevant mechanical parameter values; training a neural network model based on the measured data set and the physical control equation to obtain a segment floating amount prediction model; obtaining the positions of multiple segments to be measured in the shield tunnel section and inputting them into the segment floating amount prediction model for analysis to obtain the predicted floating amounts of multiple segments to be measured. The present application can integrate the physical mechanism that conforms to tunnel construction into the neural network model to effectively constrain the prediction process, which is conducive to improving the reliability of the segment floating amount prediction results.

Description

Technical Field

[0001] The present application relates to the field of tunnel detection technology, and in particular to a method, system, equipment and medium for predicting the floating amount of segments during shield tunnel construction. Background Art

[0002] During shield tunnel construction, segment uplift is a common problem. It can lead to a series of subsequent problems, including tunnel axis deviation, segment misalignment or splay, and even water leakage, seriously impacting the long-term stability and service life of the tunnel. With the development of artificial intelligence (AI) technology, neural network-based prediction methods have been gradually applied to shield tunnel construction. However, these methods fail to effectively integrate the physical mechanisms of tunnel construction and struggle to fully simulate complex soil-structure interactions. Summary of the Invention

[0003] The main purpose of this application is to propose a method, system, equipment and medium for predicting the floating amount of pipe segments during shield tunnel construction, which can integrate the physical mechanisms that conform to tunnel construction into the neural network model to effectively constrain the prediction process, which is conducive to improving the reliability of the prediction results of the floating amount of pipe segments.

[0004] To achieve the above objectives, one aspect of the present application provides a method for predicting the floating amount of a segment during shield tunnel construction, the method comprising:

[0005] Acquire an exploration dataset and a measured dataset of a shield tunnel section, wherein the exploration dataset includes geological parameter values, material parameter values, and shield construction parameter values ​​of the shield tunnel section, and the measured dataset includes positions and measured uplift amounts of multiple measured segments within the shield tunnel section;

[0006] Inputting the exploration data set into a pre-built shield tunnel mechanical model for solving, thereby obtaining relevant mechanical parameter values ​​of the shield tunnel section;

[0007] Determining a physical control equation for reflecting deformation characteristics of the shield tunnel section based on the Timoshenko beam model and the relevant mechanical parameter values;

[0008] Training a pre-built neural network model based on the measured data set and the physical control equation to obtain a segment lift prediction model;

[0009] The positions of multiple segments to be measured in the shield tunnel section are obtained and input into the segment floating amount prediction model for analysis to obtain the predicted floating amounts of the multiple segments to be measured.

[0010] Furthermore, the shield tunnel mechanical model includes an equivalent shear stiffness model and an equivalent bending stiffness model of the shield tunnel segment, an equivalent stiffness coefficient model of the foundation of the soil surrounding the shield tunnel segment, and a buoyancy model acting on the longitudinal direction of the shield tunnel segment.

[0011] Furthermore, the mathematical expression of the buoyancy model acting on the longitudinal direction of the shield tunnel segment is:

[0012] F T =F s (t)+F d (t)-G s ,

[0013]

[0014] F w =πR 2 γ w ,

[0015]

[0016] F d0 =2PRsinθ,

[0017] G s =πR 2 γ s ;

[0018] Among them, F T is the buoyancy force acting on the segment longitudinally, F s (t) is the static buoyancy of the segment at time t, F d (t) is the dynamic buoyancy of the segment at time t, G s is the self-weight stress of the segment, F s0 is the static buoyancy of the synchronous grouting slurry on the segment when it is not solidified, t s is the initial setting time of slurry, k s is the slurry solidification influence coefficient, F w is the groundwater pressure at the location of the segment, R is the outer radius of the segment, γ w is the density of groundwater, α g is the arc of the synchronous grouting slurry wrapped around the segment, γ g is the density of the synchronous grouting slurry, F d0 is the initial dynamic buoyancy of the segment, t d is the dissipation time of dynamic grouting pressure, k d is the grouting pressure dissipation influence coefficient, P is the synchronous grouting pressure on the segment, θ is the angle between the boundary of the grouting slurry bubble distribution area and the vertical direction, γ s The weight of the pipe segment.

[0019] Furthermore, the neural network model is constructed using a fully connected feedforward neural network as its basic architecture.

[0020] Furthermore, the pre-built neural network model is trained based on the measured data set and the physical control equation to obtain a segment floating amount prediction model, which includes:

[0021] Determine a final loss function based on the physical control equation and a preset loss function; wherein the preset loss function is used to measure the difference between the model prediction value and the true value;

[0022] The neural network model is trained according to the measured data set and the final loss function to obtain the segment floating amount prediction model.

[0023] Furthermore, determining the final loss function according to the physical control equation and the preset loss function includes:

[0024] The residual term of the physical control equation is added to the preset loss function in a weighted summation manner to form the final loss function.

[0025] Furthermore, the shield tunnel section includes a first shield tunnel section and a second shield tunnel section, the first shield tunnel section is in an unsolidified state of the synchronous grouting slurry, the second shield tunnel section is in a solidified state of the synchronous grouting slurry, and the measured density of the pipe segments in the first shield tunnel section is greater than the measured density of the pipe segments in the second shield tunnel section.

[0026] To achieve the above-mentioned objectives, another aspect of the present application provides a system for predicting the floating amount of segments during shield tunnel construction, the system comprising:

[0027] an acquisition module, configured to acquire an exploration dataset and a measured dataset of a shield tunnel section, wherein the exploration dataset includes geological parameter values, material parameter values, and shield construction parameter values ​​of the shield tunnel section, and the measured dataset includes the positions and measured uplift amounts of multiple measured segments within the shield tunnel section;

[0028] A solution module, configured to input the exploration data set into a pre-built shield tunnel mechanical model for solution to obtain relevant mechanical parameter values ​​of the shield tunnel section;

[0029] a determination module, configured to determine a physical control equation reflecting deformation characteristics of the shield tunnel section based on the Timoshenko beam model and the relevant mechanical parameter values;

[0030] A training module, configured to train a pre-built neural network model based on the measured data set and the physical control equation to obtain a segment lift prediction model;

[0031] The prediction module is used to obtain the positions of multiple segments to be measured in the shield tunnel section and input the segments' floating amount prediction model for analysis to obtain the predicted floating amounts of the multiple segments to be measured.

[0032] To achieve the above-mentioned purpose, another aspect of the present application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned method when executing the computer program.

[0033] To achieve the above-mentioned purpose, another aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned method when executed by a processor.

[0034] This application includes at least the following beneficial effects: by utilizing relevant exploration data of the shield tunnel section to conduct a combined analysis of the shield tunnel mechanical model and the Timoshenko beam model, a physical control equation that can reflect the deformation characteristics of the shield tunnel section is determined, and then the physical control equation is integrated into the neural network model for application. This can not only effectively constrain the model prediction process and make the model more consistent with the actual physical behavior of tunnel construction, but also improve the reliability of the prediction results of the pipe segment floating amount, thereby providing more scientific guidance for the shield tunnel construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a method for predicting the floating amount of a segment during shield tunnel construction provided by an embodiment of the present application;

[0036] Figure 2 This is a structural diagram of a system for predicting the floating amount of segments during shield tunnel construction provided by an embodiment of the present application;

[0037] Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of systems and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0039] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0040] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0042] Shield tunneling is widely used in the construction of urban subways and highway tunnels because it does not interfere with ground traffic and is less susceptible to environmental conditions. However, segment uplift is a common problem during shield tunneling. This can lead to a series of subsequent problems, including tunnel axis deviation, segment misalignment or splay, and even water leakage, seriously impacting the long-term stability and service life of the tunnel.

[0043] In the existing technology, the main methods for calculating the buoyancy of the pipe segments include analytical methods, numerical simulation methods, and machine learning methods. Analytical methods often exhibit insufficient computational accuracy when dealing with heterogeneous foundations, complex boundary conditions, or dynamically changing external environments during construction. Numerical simulation methods have problems such as extremely large computational workload and difficulty in ensuring convergence when simulating the shield tunnel construction process under heterogeneous foundations or complex boundary conditions. Although the neural network model constructed based on machine learning can effectively capture the complex relationships between data, it is a data-driven "black box" model. Without a clear physical background, its prediction results are difficult to reflect the inherent mechanism of pipe segment buoyancy. In other words, neural network-based prediction methods have gradually been applied to the field of shield tunnel construction, but these methods have failed to effectively integrate the physical mechanisms of tunnel construction and have difficulty in fully simulating complex soil-structure interactions.

[0044] In view of this, the embodiments of the present application provide a method, system, equipment and medium for predicting the floating amount of pipe segments during the construction period of a shield tunnel. The scheme combines the shield tunnel mechanical model and the Timoshenko beam model by utilizing relevant exploration data of the shield tunnel section to determine a physical control equation that can reflect the deformation characteristics of the shield tunnel section, and then integrates the physical control equation into the neural network model for application. This can not only effectively constrain the model prediction process and make the model more consistent with the actual physical behavior of tunnel construction, but also improve the reliability of the prediction results of the pipe segment floating amount, thereby providing more scientific guidance for the shield tunnel construction process.

[0045] The embodiment of the present application provides a method for predicting the floating amount of segments during the construction period of a shield tunnel, which relates to the field of tunnel detection technology and can be applied to a terminal, a server, or software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the above-mentioned method for predicting the floating amount of segments during the construction period of a shield tunnel, etc., but is not limited to the above forms.

[0046] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0047] Figure 1 This is an optional flow chart of a method for predicting the floating amount of a segment during shield tunnel construction provided by an embodiment of the present application. Figure 1The method may include, but is not limited to, steps S101 to S105:

[0048] Step S101: Acquire an exploration dataset and a measured dataset of a shield tunnel section;

[0049] Step S102: inputting the exploration data set into a pre-built shield tunnel mechanical model for solving, thereby obtaining relevant mechanical parameter values ​​of the shield tunnel section;

[0050] Step S103: determining a physical control equation for reflecting the deformation characteristics of the shield tunnel section based on the Timoshenko beam model and the relevant mechanical parameter values;

[0051] Step S104: training a pre-built neural network model based on the measured data set and the physical control equation to obtain a segment lift prediction model;

[0052] Step S105 , obtaining positions of multiple segments to be measured in the shield tunnel section and inputting them into the segment lift prediction model for analysis to obtain predicted lifts of the multiple segments to be measured.

[0053] Steps S101 to S105 shown in the embodiment of the present application integrate physical mechanisms consistent with tunnel construction into the neural network model to effectively constrain the prediction process, which is conducive to improving the reliability of the prediction results of the pipe segment floating amount.

[0054] In step S101 of some embodiments, the exploration data set of the shield tunnel section mainly records all parameter values ​​required to be applied when solving the shield tunnel mechanical model, specifically including the material parameter values, geological parameter values ​​and shield construction parameter values ​​used in the shield tunnel section. The material parameter values ​​used are key factors in determining the overall stress state of the shield tunnel. The materials used include segments, bolts, etc. The geological parameter values ​​have an important influence on the stability and buoyancy characteristics of the tunnel structure during shield construction. The shield construction parameter values ​​have important reference value for the deformation behavior of the segments and the calculation of the buoyancy amount.

[0055] In step S101 of some embodiments, the measured data set of the shield tunnel section specifically includes the positions and measured buoyancy of multiple measured segments in the shield tunnel section. The measured buoyancy of the measured segments can be obtained by manual on-site measurement using a total station and a ruler. The position of the measured segment is a one-dimensional position and can be represented by an X-coordinate value. The X-coordinate axis takes the position of the shield tail as the origin and is set along the longitudinal axis of the shield tunnel. Generally, a configuration point is arranged within the entire range of each segment. The position and measured buoyancy of each measured segment in the shield tunnel section can be understood as the position and measured buoyancy of the configuration point arranged on the measured segment.

[0056] The shield tunnel section mainly includes the first shield tunnel section in the unsolidified state of the synchronous grouting slurry (hereinafter referred to as the unsolidified slurry section) and the second shield tunnel section in the solidified state of the synchronous grouting slurry (hereinafter referred to as the solidified slurry section). The unsolidified slurry section is the tunnel section from the shield tail to the initial setting position of the grouting slurry, and the solidified slurry section is the tunnel section after the initial setting position of the grouting slurry. Considering that the buoyancy force on the segments falling in the unsolidified slurry section changes dramatically, the corresponding displacement and deformation are relatively complex, while the deformation of the segments falling in the solidified slurry section is relatively stable, in order to improve the model training accuracy and prediction reliability, the measurement density of the segments in the unsolidified slurry section should be greater than the measurement density of the segments in the solidified slurry section. For example, it is required to measure the buoyancy of each ring of segments falling in the unsolidified slurry section, but the buoyancy of all segments falling in the solidified slurry section is measured every five rings.

[0057] In step S102 of some embodiments, the shield tunnel mechanical model specifically includes an equivalent stiffness coefficient model of the foundation of the soil surrounding the shield tunnel segment, an equivalent bending stiffness model of the shield tunnel segment, an equivalent shear stiffness model of the shield tunnel segment, and a buoyancy model acting in the longitudinal direction of the shield tunnel segment. The equivalent bending stiffness model of the shield tunnel segment and the equivalent shear stiffness model of the shield tunnel segment are important representations of the mechanical behavior of the shield tunnel. The above-mentioned models are explained as follows:

[0058] (1) The equivalent shear stiffness model of the shield tunnel segment can be expressed using the following mathematical expression:

[0059]

[0060] In the formula, (k f GA) eq is the equivalent shear stiffness of the segment, ξ is the equivalent shear stiffness correction factor, l s is the width of a single ring segment, l b is the length of the bolt, n is the number of longitudinal connecting bolts between segments, k fb is the Timoshenko shear coefficient of the bolt, G b is the shear stiffness of the bolt, A b is the cross-sectional area of ​​the bolt, k fs is the Timoshenko shear coefficient of the segment ring, G s is the shear stiffness of the segment ring, A s is the cross-sectional area of ​​the segment ring, and the parameter l s 、l b , n, k fb , G b 、A b 、k fs , Gs and A s Pertains to the parameter values ​​of the material used.

[0061] (2) The equivalent bending stiffness model of the shield tunnel segment can be expressed using the following mathematical expression:

[0062]

[0063] Where, (EI) eq is the equivalent bending stiffness of the segment, E s is the elastic modulus of the segment ring, I s is the moment of inertia of the segment ring, ζ is the equivalent coefficient of elastic bending stiffness within the scope of the tunnel annular joint, λ is the relative coefficient of the annular joint influence length, and the parameter E s and I s Pertains to the parameter values ​​of the material used.

[0064] (3) When the shield tunnel segment falls into the slurry solidification section, the equivalent stiffness coefficient model of the soil surrounding the shield tunnel segment can be expressed by the following mathematical expression:

[0065]

[0066] When the shield tunnel segment falls on the unsolidified section of the slurry, the equivalent stiffness coefficient model of the soil surrounding the shield tunnel segment can be expressed by the following mathematical expression:

[0067]

[0068] Where k is the equivalent stiffness coefficient of the soil around the segment, E f is the elastic modulus of the soil around the segment, η h is a coefficient that takes into account the influence of the buried depth of the shield tunnel on the foundation stiffness, D is the outer diameter of the segment, μ is the Poisson's ratio of the soil around the segment, h is the buried depth of the tunnel, η f is the foundation equivalent stiffness reduction factor, and parameter E f , μ and h are geological parameter values, and parameter D is the parameter value of the material used.

[0069] It should be noted that synchronous grouting is a key process in shield construction, and the grouting process has a significant impact on the stiffness characteristics of the foundation. Specifically, the initial setting time, grouting pressure, and slurry distribution of the synchronous grouting slurry all affect the equivalent stiffness coefficient of the foundation. A longer initial setting time for the synchronous grouting slurry will result in lower foundation stiffness, thereby increasing the risk of tunnel segments floating. In addition, the depth of the tunnel is also a significant factor affecting the stiffness of the foundation. The greater the tunnel depth, the stronger the foundation's constraint on the tunnel, and the correspondingly larger equivalent stiffness coefficient, effectively suppressing the tunnel's floating phenomenon.

[0070] (4) Regarding the buoyancy model acting on the longitudinal direction of the shield tunnel segment, the gravity effect of the shield machine, trolley and other equipment is ignored and can be expressed by the following mathematical expression:

[0071] F T =F s (t)+F d (t)-G s ,

[0072]

[0073] F w =πR 2 γ w ,

[0074]

[0075] F d0 =2PRsinθ,

[0076] G s =πR 2 γ s ;

[0077] Where, F T is the buoyancy force acting on the segment longitudinally, F s (t) is the static buoyancy of the segment at time t, which is determined by the groundwater pressure and the mechanical properties of the grouting during the initial setting process when the synchronous grouting slurry has not yet completely solidified. d (t) is the dynamic buoyancy of the segment at time t, which is determined by the grouting pressure, slurry distribution and tunnel construction status. G s is the self-weight stress of the segment, F s0 is the static buoyancy of the synchronous grouting slurry on the segment when it is not solidified, t s is the initial setting time of slurry, k s is the slurry solidification influence coefficient, F w is the groundwater pressure at the location of the segment, R is the outer radius of the segment, and R = D / 2, γ w is the density of groundwater, α g is the arc of the synchronous grouting slurry wrapped around the segment, γ g is the density of the synchronous grouting slurry, F d0 is the initial dynamic buoyancy of the segment, t d is the dissipation time of dynamic grouting pressure, k d is the grouting pressure dissipation influence coefficient, P is the synchronous grouting pressure on the segment, θ is the angle between the boundary of the grouting slurry bubble distribution area and the vertical direction, γ sis the weight of the segment, and parameter t s 、k s , α g , γ g , t d 、k d , P and θ are shield construction parameter values, parameter γ w Belong to the geological parameter values, parameters R and γ s Pertains to the parameter values ​​of the material used.

[0078] In the above step S102, after the exploration data set of the shield tunnel section is input into the shield tunnel mechanical model for solution, the output relevant mechanical parameter values ​​of the shield tunnel section include at least the equivalent shear stiffness value of the segment, the equivalent bending stiffness value of the segment, the equivalent stiffness coefficient value of the foundation of the soil around the segment, and the buoyancy force on the longitudinal direction of the segment.

[0079] In step S103 of some embodiments, in order to more accurately study the deformation characteristics of the floating section of the shield tunnel, it is preferred to use a Timoshenko beam model based on a Winkel foundation to construct the physical control equation. The Timoshenko beam model can simultaneously consider shear deformation characteristics and bending deformation characteristics. The specific expression of the physical control equation constructed in combination with the relevant mechanical parameter values ​​of the shield tunnel section is as follows:

[0080]

[0081] Where x is the position of the segment, w is the floating amount of the segment, is the pitch angle of the segment.

[0082] After determining the physical control equation, the boundary conditions required to solve the physical control equation should also be set. Since the shield tunnel section can be regarded as a Timoshenko beam on the Winkel foundation, the boundary conditions can be regarded as the boundary conditions at both ends of the beam. The end away from the shield tail of the shield machine can be regarded as a fixed end because the synchronous grouting slurry is completely solidified. At the end connected to the shield tail of the shield machine, the buoyancy and pitch angle of the segment can be considered to be controlled by the posture of the shield machine. The posture of the shield machine includes the vertical deviation and pitch angle of the shield tail. The boundary conditions can be expressed by the following mathematical expression:

[0083]

[0084] Where w 1,x＝0 is the buoyancy of the segment at one end connected to the shield tail of the shield machine. is the pitch angle of the segment at the end connected to the shield tail of the shield machine, w 2,x＝∞ is the buoyancy of the segment at the end away from the shield tail of the shield machine. is the pitch angle of the segment at the end away from the shield tail of the shield machine, dv is the vertical deviation of the shield tail, P v is the pitch angle of the shield tail.

[0085] In step S104 of some embodiments, the neural network model adopted is constructed based on the existing fully connected feedforward neural network (FCNN) as the basic architecture. The fully connected feedforward neural network contains 6 hidden layers, each hidden layer consists of 256 neurons, and the Tanh function is used as the activation function in the network, thereby enhancing the complexity and expression ability of the model, so that the model can better capture the nonlinear deformation characteristics of the shield tunnel segments after training.

[0086] In some embodiments, the above step S104 may include but is not limited to steps S201 to S202:

[0087] Step S201: Determine a final loss function based on the preset loss function originally required by the neural network model and the physical control equation.

[0088] In this step, it is preferred to introduce the residual term of the physical control equation into the preset loss function in a weighted summation manner to form the final loss function, which can be expressed by the following mathematical expression:

[0089] LOSS total =α1LOSS PDE +α2LOSS data ;

[0090] Where, LOSS total is the final loss function, LOSS PDE is the residual term of the physical control equation, α1 is the term about LOSS PDE Weight, LOSS data is the preset loss function, α2 is about LOSS data The weight of .

[0091] Among them, the preset loss function mainly measures the difference between the model prediction value and the true value, and one of the mean square error loss function, mean absolute error loss function, cross entropy loss function, etc. can be preferably used; the residual term of the physical control equation mainly measures whether the model prediction value satisfies the physical control equation. It is preferred to calculate the first to fourth order derivatives of the model prediction value through the automatic differentiation method, and then substitute these derivative results into the physical control equation. For the first equation contained in the physical control equation, the difference between the left and right values ​​of the first equation is calculated and used as the first residual. For the second equation contained in the physical control equation, it is judged whether the left side value of the second equation meets the boundary conditions required to solve the physical control equation. If it meets the boundary conditions, the second residual is set to zero. If it does not meet the boundary conditions, the difference between the left side value of the second equation and the corresponding threshold is calculated and used as the second residual. Finally, the sum of the first residual and the second residual is taken as the residual term value of the physical control equation. The final loss function, which is jointly determined by the residual term of the physical control equation and the preset loss function, can ensure that the prediction results output by the model when it relies on the final loss function for training are consistent with the laws of physics and basically match the measured data.

[0092] Step S202: training the neural network model based on the final loss function and the measured data set of the shield tunnel section to obtain a segment lift prediction model.

[0093] In this step, the training method of the neural network model includes: inputting the measured data set of the shield tunnel section into the neural network model; training the neural network model by forward propagation, and using the final loss function to calculate the loss value of the neural network model; then, based on the loss value of the neural network model, using the back propagation algorithm and combining the Adam optimizer to optimize the weights and biases of the neural network model; by iteratively executing the above model training and parameter optimization process until the neural network model reaches a convergence state, that is, the rate of change of the final loss function is less than the preset rate of change threshold, or the current number of iterations reaches the preset maximum number of iterations, a segment floating amount prediction model can be obtained.

[0094] By using the final loss function and the measured data set of the shield tunnel section to train the neural network model, it can be ensured that the final segment buoyancy prediction model can efficiently describe the stress and deformation behavior of the Timoshenko beam on the Winkel foundation while meeting the accuracy requirements, thereby achieving reliable and accurate prediction of the shield tunnel segment buoyancy.

[0095] The following further illustrates the solution provided in the embodiment of the present application with reference to specific application examples, including the following:

[0096] Step 1: Obtain exploration data sets and measured data sets of the shield tunnel section;

[0097] The exploration data set of this shield tunnel section specifically includes: the width of the single ring segment l s is 1.8m, the length of the bolt l b is 0.4m, the number of longitudinal connecting bolts between segments n is 19, and the shear stiffness of the bolts G b 7.94×10 4 MPa, shear stiffness of the segment ring G s 1.46×10 4 MPa, cross-sectional area of ​​the bolt A b 7.065×10 -4 m 2 , the cross-sectional area of ​​the segment ring A s 10.5504m 2 , Timoshenko shear coefficient k of the bolt fb The Timoshenko shear coefficient k of the segment ring is 0.9. fs is 0.5, the equivalent shear stiffness correction factor ξ is 0.45; the elastic modulus E of the segment ring s 3.5×10 4 MPa, moment of inertia of the segment ring I s 93.3128m 4 The equivalent coefficient of elastic bending stiffness in the tunnel annular joint is ζ, which is 0.0213, and the relative coefficient of the annular joint influence length is λ, which is 1. The elastic modulus of the soil around the segment is E f The pressure is 33 MPa, the outer diameter D of the segment is 8.8 m, the Poisson's ratio μ of the soil around the segment is 0.3, the buried depth h of the tunnel is 20 m, and the coefficient η considering the influence of the buried depth of the shield tunnel on the foundation stiffness is h is 1.2588, and the foundation equivalent stiffness reduction factor η f is 0.5; initial setting time of slurry t s is 6h, the slurry solidification influence coefficient k s is 2, the outer radius R of the segment is 4.4m, and the arc α of the synchronous grouting slurry wrapped around the segment g is 2π, the density of the synchronous grouting slurry γ g 20kN / m 3 , dissipation time of dynamic grouting pressure t d For 6h, the grouting pressure dissipation influence coefficient k d is 1, the synchronous grouting pressure P on the segment is 350kPa, the angle θ between the boundary of the grouting slurry bubble distribution area and the vertical direction is π / 2, and the segment weight γ s 25kN / m 3 , the density of groundwater γ w 10kN / m3 In addition, it is preferred to set the vertical deviation d of the shield tail v and the pitch angle P of the shield tail v All are zero.

[0098] The measured dataset for this shield tunnel section specifically includes the positions and measured uplift of multiple measured segments within the shield tunnel section. The shield tunnel section is 99 meters long, meaning the position of each segment within it ranges from (0m to 99m). This shield tunnel section primarily consists of an unset slurry section and a set slurry section. Measurements show that the length of the unset slurry section is 14.4 meters, and the length of the set slurry section is 84.6 meters. The position of each segment within the unset slurry section is smaller than the position of each segment within the set slurry section. Since the segment length is 1.8 meters, the unset slurry section contains 8 segments, and the set slurry section contains 47 segments. The 55 segments within this shield tunnel section are numbered starting with the segment closest to the shield tail.

[0099] Step 2: The pre-built shield tunnel mechanical model includes the foundation equivalent stiffness coefficient model of the soil around the shield tunnel segment, the equivalent bending stiffness model of the shield tunnel segment, the equivalent shear stiffness model of the shield tunnel segment, and the buoyancy model acting on the longitudinal direction of the shield tunnel segment. The exploration data set of the shield tunnel segment is input into each of the above models for solution to obtain the relevant mechanical parameter values ​​of the shield tunnel segment, including the equivalent shear stiffness (k f GA) eq , Equivalent bending stiffness of the segment (EI) eq , the equivalent stiffness coefficient k of the soil around the segment and the buoyancy F acting on the segment in the longitudinal direction T .

[0100] Step three, the relevant mechanical parameter values ​​of the shield tunnel section and the Timoshenko beam model are integrated and analyzed to determine the physical control equation, which mainly reflects the deformation characteristics of the shield tunnel section.

[0101] Step 4: A neural network model is constructed using a fully connected feedforward neural network as the basic architecture. The neural network model is trained using the physical control equation and the measured data set of the shield tunnel section to obtain a segment floating amount prediction model.

[0102] Step 5: Obtain the positions of multiple segments to be measured in the shield tunnel section and input them into the finally trained segment buoyancy prediction model for analysis to obtain the predicted buoyancy of the multiple segments to be measured.

[0103] A method for predicting the floating amount of segments during shield tunnel construction proposed in an embodiment of the present application combines and analyzes the shield tunnel mechanical model and the Timoshenko beam model using relevant exploration data of the shield tunnel section to determine a physical control equation that can reflect the deformation characteristics of the shield tunnel section. The physical control equation is then incorporated into the neural network model for application. This method can not only effectively constrain the model prediction process and make the model more consistent with the actual physical behavior of tunnel construction, but also improve the reliability of the segment floating amount prediction results, thereby providing more scientific guidance for the shield tunnel construction process.

[0104] See also Figure 2 The present application also provides a system for predicting the floating amount of segments during shield tunnel construction, which can implement the above-mentioned method for predicting the floating amount of segments during shield tunnel construction. The system includes:

[0105] An acquisition module 301 is used to acquire an exploration data set and a measured data set of a shield tunnel section;

[0106] The exploration data set of the shield tunnel section specifically includes the material parameter values, geological parameter values, and shield construction parameter values ​​of the shield tunnel section, and the measured data set of the shield tunnel section specifically includes the positions and measured uplift amounts of multiple measured segments within the shield tunnel section;

[0107] A solution module 302 is used to input the exploration data set of the shield tunnel section into a pre-built shield tunnel mechanical model for solution to obtain relevant mechanical parameter values ​​of the shield tunnel section;

[0108] A determination module 303 is configured to determine a physical control equation based on relevant mechanical parameter values ​​of the shield tunnel segment and the Timoshenko beam model, which mainly reflects the deformation characteristics of the shield tunnel segment;

[0109] A training module 304 is configured to train a pre-built neural network model based on the physical governing equations and a measured data set of the shield tunnel section to obtain a segment lift prediction model;

[0110] The prediction module 305 is used to obtain the positions of multiple segments to be measured in the shield tunnel section and input them into the segment floating amount prediction model for analysis to obtain the predicted floating amounts of the multiple segments to be measured.

[0111] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0112] The present application also provides an electronic device comprising a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program, implements the aforementioned method for predicting the uplift of segments during shield tunnel construction. The electronic device can be any smart terminal, including a tablet computer and an in-vehicle computer.

[0113] It can be understood that the contents of the above method embodiments are applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0114] See also Figure 3 , Figure 3 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0115] The processor 401 may be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0116] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented through software or firmware, the relevant program code is stored in the memory 402 and is called by the processor 401 to execute the technical solutions provided by the embodiments of the present application.

[0117] Input / output interface 403, used to implement information input and output;

[0118] Communication interface 404, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0119] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0120] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via a bus 405 .

[0121] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for predicting the floating amount of pipe segments during the construction period of a shield tunnel.

[0122] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiment, the functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0123] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0124] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0125] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0126] The system embodiment described above is merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0127] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0128] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0129] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the above units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0131] The units described above as separate components may or may not be physically separate, and 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 these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0134] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A method for predicting the floating amount of a segment during shield tunnel construction, characterized in that: The method comprises: Acquire an exploration dataset and a measured dataset of a shield tunnel section, wherein the exploration dataset includes geological parameter values, material parameter values, and shield construction parameter values ​​of the shield tunnel section, and the measured dataset includes positions and measured uplift amounts of multiple measured segments within the shield tunnel section; Inputting the exploration data set into a pre-built shield tunnel mechanical model for solving, thereby obtaining relevant mechanical parameter values ​​of the shield tunnel section; Determining a physical control equation for reflecting deformation characteristics of the shield tunnel section based on the Timoshenko beam model and the relevant mechanical parameter values; Training a pre-built neural network model based on the measured data set and the physical control equation to obtain a segment lift prediction model; Obtaining positions of a plurality of segments to be measured in the shield tunnel section and inputting the positions into the segment lift prediction model for analysis to obtain predicted lifts of the plurality of segments to be measured; The relevant mechanical parameter values ​​include the equivalent shear stiffness value of the segment, the equivalent bending stiffness value of the segment, the equivalent stiffness coefficient value of the foundation of the soil surrounding the segment, and the buoyancy force acting on the segment in the longitudinal direction. The specific expression of the physical control equation is as follows: Where, is the equivalent bending stiffness of the segment, is the buoyancy of the segment, is the position of the segment, is the equivalent stiffness coefficient of the soil around the segment, is the outer radius of the segment, is the equivalent shear stiffness of the segment, is the buoyancy force acting on the segment longitudinally, is the pitch angle of the segment; The boundary conditions required to solve the physical control equations are expressed using the following mathematical expressions: Where, is the buoyancy of the segment at one end connected to the shield tail of the shield machine. is the pitch angle of the segment at one end connected to the shield tail of the shield machine. is the buoyancy of the segment at the end away from the shield tail of the shield machine. It is the pitch angle of the segment at the end away from the shield tail of the shield machine. The posture of the shield machine includes the vertical deviation and pitch angle of the shield tail. is the vertical deviation of the shield tail, is the pitch angle of the shield tail.

2. The method for predicting the floating amount of segments during shield tunnel construction according to claim 1, characterized in that: The shield tunnel mechanical model includes an equivalent shear stiffness model and an equivalent bending stiffness model of the shield tunnel segment, an equivalent stiffness coefficient model of the foundation of the soil surrounding the shield tunnel segment, and a buoyancy model acting on the longitudinal direction of the shield tunnel segment.

3. The method for predicting the floating amount of segments during shield tunnel construction according to claim 2, characterized in that: The mathematical expression of the buoyancy model acting on the longitudinal direction of the shield tunnel segment is: in, For The static buoyancy of the segment at the moment For The dynamic buoyancy of the lower segment at this moment, is the self-weight stress of the segment, The static buoyancy generated by the synchronous grouting slurry on the segment when it is not solidified. is the initial setting time of the slurry, is the slurry solidification influence coefficient, is the groundwater pressure at the location of the segment, is the density of groundwater, The curvature of the segment wrapped by the synchronous grouting slurry, is the density of the synchronous grouting slurry, is the initial dynamic buoyancy of the segment, is the dissipation time of dynamic grouting pressure, is the grouting pressure dissipation influence coefficient, is the synchronous grouting pressure on the segment, is the angle between the boundary of the grouting slurry bubble distribution area and the vertical direction, The weight of the pipe segment.

4. The method for predicting the floating amount of segments during shield tunnel construction according to claim 1, characterized in that: The neural network model is constructed using a fully connected feedforward neural network as the basic architecture.

5. The method for predicting the floating amount of segments during shield tunnel construction according to claim 1, characterized in that: The pre-built neural network model is trained based on the measured data set and the physical control equation to obtain a segment floating amount prediction model, including: Determine a final loss function based on the physical control equation and a preset loss function; wherein the preset loss function is used to measure the difference between the model prediction value and the true value; The neural network model is trained according to the measured data set and the final loss function to obtain the segment floating amount prediction model.

6. The method for predicting the floating amount of segments during shield tunnel construction according to claim 5, characterized in that: Determining the final loss function according to the physical control equation and the preset loss function includes: The residual term of the physical control equation is added to the preset loss function in a weighted summation manner to form the final loss function.

7. The method for predicting the floating amount of segments during shield tunnel construction according to claim 1, characterized in that: The shield tunnel section includes a first shield tunnel section and a second shield tunnel section. The first shield tunnel section is in an unsolidified state of the synchronous grouting slurry, and the second shield tunnel section is in a solidified state of the synchronous grouting slurry. The measured density of the pipe segments in the first shield tunnel section is greater than the measured density of the pipe segments in the second shield tunnel section.

8. A system for predicting the floating amount of segments during shield tunnel construction, characterized in that: The system comprises: an acquisition module, configured to acquire an exploration dataset and a measured dataset of a shield tunnel section, wherein the exploration dataset includes geological parameter values, material parameter values, and shield construction parameter values ​​of the shield tunnel section, and the measured dataset includes the positions and measured uplift amounts of multiple measured segments within the shield tunnel section; A solution module, configured to input the exploration data set into a pre-built shield tunnel mechanical model for solution to obtain relevant mechanical parameter values ​​of the shield tunnel section; a determination module, configured to determine a physical control equation reflecting deformation characteristics of the shield tunnel section based on the Timoshenko beam model and the relevant mechanical parameter values; A training module, configured to train a pre-built neural network model based on the measured data set and the physical control equation to obtain a segment lift prediction model; A prediction module is used to obtain the positions of multiple segments to be measured in the shield tunnel section and input them into the segment floating amount prediction model for analysis to obtain the predicted floating amounts of the multiple segments to be measured; The relevant mechanical parameter values ​​include the equivalent shear stiffness value of the segment, the equivalent bending stiffness value of the segment, the equivalent stiffness coefficient value of the foundation of the soil surrounding the segment, and the buoyancy force acting on the segment in the longitudinal direction. The specific expression of the physical control equation is as follows: Where, is the equivalent bending stiffness of the segment, is the buoyancy of the segment, is the position of the segment, is the equivalent stiffness coefficient of the soil around the segment, is the outer radius of the segment, is the equivalent shear stiffness of the segment, is the buoyancy force acting on the segment longitudinally, is the pitch angle of the segment; The boundary conditions required to solve the physical control equations are expressed using the following mathematical expressions: Where, is the buoyancy of the segment at one end connected to the shield tail of the shield machine. is the pitch angle of the segment at one end connected to the shield tail of the shield machine. is the buoyancy of the segment at the end away from the shield tail of the shield machine, It is the pitch angle of the segment at the end away from the shield tail of the shield machine. The posture of the shield machine includes the vertical deviation and pitch angle of the shield tail. is the vertical deviation of the shield tail, is the pitch angle of the shield tail.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images