TBM tunnel support parameter optimization method based on mechanical response prediction

Abstract

The invention discloses a TBM (Tunnel Boring Machine) tunnel support parameter optimization method based on mechanical response prediction, and relates to the technical field of tunnel construction, and the method is characterized in that a large number of mechanical response samples are generated by establishing finite element calculation models under different surrounding rock states and support parameter combinations; meanwhile, field measured data are collected for supplement and correction, a surrounding rock-support mapping relation model is established by utilizing a deep learning algorithm, and an optimal support parameter combination meeting safety requirements is intelligently selected according to the relation between specific surrounding rock conditions and support responses, so that accurate optimization of support design is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and more specifically, to a TBM tunnel support parameter optimization method based on mechanical response prediction. Background Art

[0002] In western my country, tunnel construction faces complex engineering geological environments and multiple unfavorable factors, such as high ground temperature, high ground stress, high altitude and high seismic intensity. These special conditions pose severe challenges to the design and construction of deep buried tunnels. The most significant problem is the complexity of the ground stress state and distribution, which makes it very easy for support failure and support waste to occur during the construction of the tunnel, affecting the safety and economy of tunnel construction. Therefore, how to optimize the support parameters to adapt to different surrounding rock conditions and ensure the safety and economy of tunnel construction has become a key issue that needs to be solved urgently.

[0003] At present, deep tunnel support design mainly relies on empirical methods, analogy methods and numerical simulation methods. Although empirical methods and analogy methods can provide references to a certain extent, they rely on empirical data from previous projects and cannot accurately reflect complex and changeable surrounding rock conditions, which can easily lead to conservative support design or excessive risks. Numerical simulation rules can predict the mechanical response during tunnel construction, but traditional numerical simulations are often aimed at a single working condition or simple surrounding rock conditions, and lack comprehensive research on the optimization of support parameters under a variety of complex geological conditions. In addition, these methods are usually time-consuming, require a lot of calculations and parameter adjustment processes, and it is difficult to quickly adjust the support scheme during construction, resulting in insufficient response speed and flexibility during field application.

[0004] The limitations of traditional support design are mainly reflected in the following aspects: First, the support design fails to fully consider the complexity and diversity of different surrounding rocks, resulting in insufficient universality and reliability of the support scheme; second, it is impossible to achieve rapid parameter optimization and adjustment, and it is difficult to adapt to the complex changes in geological conditions in actual construction; third, the existing methods often have a certain degree of conservative design, resulting in waste of support materials and increased construction costs, and failing to achieve a balance between economy and safety. Summary of the invention

[0005] The purpose of the present invention is to provide a TBM tunnel support parameter optimization method based on mechanical response prediction. The method generates a large number of mechanical response samples by establishing a finite element calculation model under different surrounding rock conditions and support parameter combinations, and collects field measured data for supplementation and correction. A surrounding rock-support mapping relationship model is established using a deep learning algorithm. According to the relationship between specific surrounding rock conditions and support response, the optimal support parameter combination that meets safety requirements is intelligently selected, thereby achieving accurate optimization of support design.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions: a method for optimizing TBM tunnel support parameters based on mechanical response prediction, the method comprising the following steps:

[0007] 1) Determine the mechanical characteristics of the surrounding rock: The mechanical characteristics of the surrounding rock include uniaxial compressive strength, Young's modulus, density, cohesion, internal friction angle, Poisson's ratio, joint spacing and burial depth;

[0008] 2) Forming a support parameter library: Combining the steel arch model and spacing, steel mesh diameter and spacing, steel bar row diameter and spacing, spray mix model and thickness, anchor model, length and spacing, lining thickness and other support parameters used at the construction site to form a support parameter library;

[0009] 3) Confirm the mechanical parameter values ​​characterizing the support performance of the TBM tunnel: combine the surrounding rock mechanical characteristics in step 1) with the support parameter library in step 2), conduct numerical simulation tests, and select the steel arch axial force, steel arch bending moment, steel arch displacement, anchor axial force, lining bending moment, lining displacement and other mechanical parameter values ​​characterizing the support performance of the TBM tunnel at 5 measuring points based on discrete element model calculation;

[0010] 4) Collecting the actual surrounding rock mechanical characteristics and support parameter samples on site, and forming a large data sample library of surrounding rock-support mechanical response together with the mechanical parameter values ​​of the support properties monitored in step 3);

[0011] 5) Construct the surrounding rock-support mapping model framework and normalize the surrounding rock mechanical characteristics and its mechanical response using formula (1):

[0012]

[0013] In the formula, max(x) and min(x) are the maximum and minimum values ​​of the protective gear, and x′ is the normalized value. At the same time, the support parameters are discretized and encoded.

[0014] Perform a 1D causal convolution operation using formula (2):

[0015]

[0016] Where X = [x1, x2, ..., x T ] is the input sequence, Y=[y1,y2,…,y T ] is the output sequence, W=[w1,w2,…,w K ] is the convolution kernel weight, d is the dilation factor;

[0017] The Dropout operation is performed through formula (3):

[0018] Y dropout =Y cov ⊙d (3)

[0019] Where Y cov is the output of causal convolution, d is the cov Random mask matrices of the same size are used to perform pruning operations by multiplication;

[0020] The nonlinear transformation is achieved by using the ReLU activation function through formula (4):

[0021] Y ReLU =max(0,W·Y dropout +b) (4)

[0022] In the formula, W is the weight and b is the bias;

[0023] The data flow of the GRU layer is controlled by three gating mechanisms (reset gate, update gate, candidate activation), and the calculation formula of the update gate is:

[0024] z t =σ(W z x t +U z y t-1 +b z ) (5)

[0025] Where W z with U z is the weight matrix, b z is the bias term;

[0026] The calculation formula for the reset gate is:

[0027] r t =σ(W r x t +U r y t-1 +b r ) (6)

[0028] The calculation formula for candidate activation is:

[0029]

[0030] The final output is:

[0031]

[0032] 6) Combining the surrounding rock-support mechanical response big data sample library in step 4) with the surrounding rock-support mapping model framework formed in step 5), model training is performed to form a trained surrounding rock-support mapping model;

[0033] 7) For each surrounding rock condition encountered in actual construction, different support parameter combinations and their corresponding mechanical responses are used to calculate the safety score, efficiency score and economic score respectively. Different weights are selected for the three scores according to different situations, and the WOA optimization algorithm is used to realize the optimization process, and finally the parameter optimization adjustment is formed.

[0034] The present invention is further configured as follows: the WOA optimization is divided into three stages:

[0035] The motion trajectory equation in the initial stage is:

[0036]

[0037] Where: k is the number of iterations; Q k and Respectively represent the vectors from the starting point to the search agent position and the best position; D is the vector from the current search point to the current best individual; A and C are coefficient vectors that control the way the search point moves; ρ1 and ρ2 are set to be random numbers between 0 and 1; a is the convergence factor that decreases linearly from 2 to 0;

[0038] The motion trajectory equation in the local search phase is:

[0039]

[0040] Where: b is the logarithmic spiral constant, l is a random number between [-1,1];

[0041] The motion trajectory equation in the global search phase is:

[0042]

[0043] Where: represents a randomly selected position vector.

[0044] In summary, the present invention has the following beneficial effects:

[0045] 1. Strong pertinence: By analyzing the mechanical responses under different surrounding rock conditions, the present invention can tailor support schemes for specific geological conditions, greatly improving the rationality and pertinence of support design, and avoiding support failure or support waste in traditional designs.

[0046] 2. High efficiency: The process of generating a large number of samples using numerical calculations can greatly shorten the time of support design. At the same time, through the pre-built response database, the optimal support parameter combination can be quickly obtained, and the support design can be quickly iterated and optimized, which greatly improves the response speed of the construction site.

[0047] 3. Good economy: By optimizing the combination of support parameters, the present invention can significantly reduce the use of support materials, while avoiding excessive support design, reducing construction costs, and achieving the best balance between the economy and safety of support design.

[0048] 4. Intelligence and flexibility: The core of the present invention lies in the dynamic correlation between support parameters and surrounding rock conditions. The support scheme can be adjusted in real time according to on-site monitoring data to ensure the safety and stability of tunnel construction. In addition, the method has strong scalability and can be applied to different types of tunnel projects and a variety of complex geological environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the measuring points of the support structure in Example 1 of the present invention;

[0050] Figure 2 It is the surrounding rock-support mapping model framework in Example 1 of the present invention;

[0051] Figure 3 It is the support parameter optimization framework in embodiments 1 and 2 of the present invention;

[0052] Figure 4 This is the prediction effect of the mapping relationship model in Example 2 of the present invention. DETAILED DESCRIPTION

[0053] The following is combined with Figure 1-4 The present invention is described in further detail.

[0054] Example 1: A method for optimizing TBM tunnel support parameters based on mechanical response prediction, such as Figure 1-3 As shown, the following steps are included:

[0055] 1) Determine multiple surrounding rock mechanical characteristics including uniaxial compressive strength, Young's modulus, density, cohesion, internal friction angle, Poisson's ratio, joint spacing, burial depth, etc.

[0056] 2) Combining various support parameters such as steel arch model and spacing, steel mesh diameter and spacing, steel bar row diameter and spacing, spray mix model and thickness, anchor model, length and spacing, lining thickness, etc. used at the construction site to form a support parameter library.

[0057] 3) Combine the surrounding rock mechanical characteristics in step 1) with the support parameter library in step 2) to conduct numerical simulation tests. Based on the discrete element model calculation, select Figure 1 The values ​​of multiple mechanical parameters representing the support properties of TBM tunnels, such as steel arch axial force, steel arch bending moment, steel arch displacement, anchor axial force, lining bending moment, and lining displacement at the five measuring points are shown.

[0058] 4) Extensively collect the on-site surrounding rock mechanical characteristics, support parameter samples and the corresponding mechanical response parameter values ​​monitored in step 3), and together with the mechanical response samples in step 3), form a surrounding rock-support mechanical response big data sample library.

[0059] 5) Figure 2 The surrounding rock-support mapping model framework is constructed as shown in the figure, and the mechanical characteristics of the surrounding rock and its mechanical response are normalized by formula (1):

[0060]

[0061] In the formula, max(x) and min(x) are the maximum and minimum values ​​of the protective gear, and x′ is the normalized value. At the same time, the support parameters are discretized and encoded.

[0062] Perform a 1D causal convolution operation using formula (2):

[0063]

[0064] Where X = [x1, x2, ..., x T ] is the input sequence, Y=[y1,y2,...,y T ] is the output sequence, W=[w1,w2,...,w K ] is the convolution kernel weight, and d is the dilation factor.

[0065] The Dropout operation is performed through formula (3):

[0066] Y dropout =Y cov ⊙d (3)

[0067] Where Y cov is the output of causal convolution, d is the cov Random mask matrices of the same size are multiplied to achieve pruning operations.

[0068] The nonlinear transformation is achieved by using the ReLU activation function through formula (4):

[0069] Y ReLU =max(0,W·Y dropout +b) (4)

[0070] Where W is the weight and b is the bias.

[0071] The data flow of the GRU layer is controlled by three gating mechanisms (reset gate, update gate, candidate activation), and the calculation formula of the update gate is:

[0072] z t =σ(W z x t+U z y t-1 +b z ) (5)

[0073] Where W z with U z is the weight matrix, b z is the bias term.

[0074] The calculation formula for the reset gate is:

[0075] r t =σ(W r x t +U r y t-1 +b r ) (6)

[0076] The calculation formula for candidate activation is:

[0077]

[0078] The final output is:

[0079]

[0080] 6) Combining the surrounding rock-support mechanical response big data sample library in step 4) with the surrounding rock-support mapping model framework formed in step 5), model training is performed to form a trained surrounding rock-support mapping model.

[0081] 7) For each surrounding rock condition encountered in actual construction, different support parameter combinations and their corresponding mechanical responses are used to calculate the safety score, efficiency score and economic score respectively. Different weights are selected for the three scores according to different situations, and the WOA optimization algorithm is used to realize the optimization process, and finally the parameter optimization adjustment is formed. The overall implementation framework is as follows: Figure 3 shown.

[0082] WOA optimization is divided into three stages:

[0083] The motion trajectory equation in the initial stage is:

[0084]

[0085] Where: k is the number of iterations; Q k and They represent the vectors from the starting point to the search agent position and the optimal position respectively; D is the vector from the current search point to the current best individual; A and C are coefficient vectors that control the way the search point moves; ρ1 and ρ2 are set to random numbers between 0 and 1; a is the convergence factor that decreases linearly from 2 to 0.

[0086] The motion trajectory equation in the local search phase is:

[0087]

[0088] Where: b is the logarithmic spiral constant, l is a random number between [-1,1].

[0089] The motion trajectory equation in the global search phase is:

[0090]

[0091] Where: represents a randomly selected position vector.

[0092] Example 2: Taking a railway tunnel as an example to demonstrate the implementation path of the present invention

[0093] (1) Young's modulus, specific gravity, cohesion, internal friction angle and Poisson's ratio are selected as indicators to characterize the mechanical properties of surrounding rock, which are represented by 8 cases as shown in Table 1.

[0094] Table 1 Schematic diagram of surrounding rock mechanical indicators

[0095]

[0096]

[0097] (2) Select different burial depth conditions and on-site support parameters shown in Table 2, and carry out numerical calculations in combination with the eight surrounding rock conditions shown in Table 1. A total of 8*8*9*8*6*4*4*9=3,981,312 working conditions are calculated, and the numerical calculations are carried out according to Figure 1 The five monitoring points shown record the mechanical response values ​​of the support structure, including steel arch axial force, steel arch bending moment, steel arch displacement, anchor axial force, lining bending moment, lining displacement, etc.

[0098] Table 2 Support parameter combination

[0099]

[0100] (3) Based on the surrounding rock-support mechanical response big data sample library formed in step (2), Figure 2 The surrounding rock-support mapping model framework is shown in the figure to carry out surrounding rock-support mapping model training and establish its mapping relationship model. Figure 4 This is the prediction effect diagram of the corresponding mapping relationship model.

[0101] (4) Basis Figure 3The support parameter optimization framework shown in the figure sets the safety score weight, efficiency score weight, and economic score weight as 0.5, 0.3, and 0.2, respectively, and sets the optimization framework to finally form the TBM tunnel support parameter optimization method. When the burial depth is 1000m, the deformation model is 4350MPa and the weight is 25kN / m 3 The recommended support parameters for the surrounding rock with cohesion of 1.809MPa, internal friction angle of 28.8° and Poisson's ratio of 0.26 are as follows: shotcrete thickness of 10cm, anchor length of 3.5m, anchor spacing of 1.2*1m, anchor range of semicircle of 180°, steel mesh arch of 90°φ8,20*20, steel arch frame of HW100 and spacing of 1.8m.

[0102] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A TBM tunnel support parameter optimization method based on mechanical response prediction, characterized by: The method comprises the following steps: 1) Determine the mechanical characteristics of the surrounding rock: The mechanical characteristics of the surrounding rock include uniaxial compressive strength, Young's modulus, density, cohesion, internal friction angle, Poisson's ratio, joint spacing and burial depth; 2) Forming a support parameter library: Combining the steel arch model and spacing, steel mesh diameter and spacing, steel bar row diameter and spacing, spray mix model and thickness, anchor model, length and spacing, lining thickness and other support parameters used at the construction site to form a support parameter library; 3) Confirm the mechanical parameter values ​​characterizing the support performance of the TBM tunnel: combine the surrounding rock mechanical characteristics in step 1) with the support parameter library in step 2), conduct numerical simulation tests, and select the steel arch axial force, steel arch bending moment, steel arch displacement, anchor axial force, lining bending moment, lining displacement and other mechanical parameter values ​​characterizing the support performance of the TBM tunnel at 5 measuring points based on discrete element model calculation; 4) Collecting the actual surrounding rock mechanical characteristics and support parameter samples on site, and forming a large data sample library of surrounding rock-support mechanical response together with the mechanical parameter values ​​of the support properties monitored in step 3); 5) Construct the surrounding rock-support mapping model framework and normalize the surrounding rock mechanical characteristics and its mechanical response using formula (1): In the formula, max(x) and min(x) are the maximum and minimum values ​​of the protective gear, and x′ is the normalized value. At the same time, the support parameters are discretized and encoded. Perform a 1D causal convolution operation using formula (2): Where X = [x1, x2, …, x T ] is the input sequence, Y=[y1,y2,…,y T ] is the output sequence, W=[w1,w2,...,w K ] is the convolution kernel weight, d is the dilation factor; The Dropout operation is performed through formula (3): AND dropout =And cov ⊙d (3) Where Y cov is the output of causal convolution, d is the cov Random mask matrices of the same size are used to perform pruning operations by multiplication; The nonlinear transformation is achieved by using the ReLU activation function through formula (4): Y ReLU =max(0,W·Y dropout +b) (4) In the formula, W is the weight and b is the bias; The data flow of the GRU layer is controlled by three gating mechanisms (reset gate, update gate, candidate activation), and the calculation formula of the update gate is: z t =σ(W z x t +U z y t-1 +b z ) (5) Where W z with U z is the weight matrix, b z is the bias term; The calculation formula for the reset gate is: r t =σ(W r x t +U r y t-1 +b r ) (6) The calculation formula for candidate activation is: The final output is: 6) Combining the surrounding rock-support mechanical response big data sample library in step 4) with the surrounding rock-support mapping model framework formed in step 5), model training is performed to form a trained surrounding rock-support mapping model; 7) For each surrounding rock condition encountered in actual construction, different support parameter combinations and their corresponding mechanical responses are used to calculate the safety score, efficiency score and economic score respectively. Different weights are selected for the three scores according to different situations, and the WOA optimization algorithm is used to realize the optimization process, and finally the parameter optimization adjustment is formed.

2. The method for optimizing TBM tunnel support parameters based on mechanical response prediction according to claim 1 is characterized in that: The WOA optimization is divided into three stages: The motion trajectory equation in the initial stage is: Where: k is the number of iterations; Q k and Respectively represent the vectors from the starting point to the search agent position and the best position; D is the vector from the current search point to the current best individual; A and C are coefficient vectors that control the way the search point moves; ρ1 and ρ2 are set to be random numbers between 0 and 1; a is the convergence factor that decreases linearly from 2 to 0; The motion trajectory equation in the local search phase is: Where: b is the logarithmic spiral constant, l is a random number between [-1,1]; The motion trajectory equation in the global search phase is: Where: represents a randomly selected position vector.

Images