A method, system and device for optimizing design of flexible net parameters for rock burst tunnel

Abstract

The present invention discloses an optimization design method, system and equipment for flexible net parameters for rock burst tunnels, which relates to the technical field of tunnel protection, and includes the following steps: collecting tunnel size parameters and surrounding rock physical and mechanical parameters of rock burst tunnels; performing numerical simulation of rock burst in unprotected tunnels; performing numerical simulation of rockfall impact test of flexible nets; establishing a sample library of rock burst energy levels corresponding to flexible nets; establishing and training a BP neural network; running the neural network to obtain preliminary values ​​of flexible net parameters; performing numerical simulation of rock burst in flexible net-protected tunnels, and performing quantitative evaluation of protection effects to determine final flexible net parameters. The present invention establishes a preliminary selection model for flexible net parameters through BP neural networks and genetic algorithms, and determines flexible net parameters through the established quantitative evaluation model, thereby reducing construction costs while ensuring the tunnel rock burst protection effect.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel protection, and in particular to a method, system and equipment for optimizing design of parameters of a flexible net for a rock burst tunnel. Background Art

[0002] Rockburst is a common disaster in tunnels, especially in deep tunnels or those with high tectonic stress. When the high elastic strain energy accumulated in the rock mass is greater than the energy consumed by rock destruction, the strain energy accumulated in the rock mass in the air is suddenly and violently released, causing brittle fracture of the rock mass like an explosion, resulting in a large amount of rock collapse, and generating huge noise and air wave impact, which often causes serious damage to the excavation face, equipment damage and casualties. It has become a global problem in the field of rock underground engineering and rock mechanics.

[0003] Traditionally, anchor rod-metal mesh-shotcrete protection system is used, but the metal mesh protection system has the disadvantages of complicated construction, high labor consumption and high cost, which makes it difficult to meet the requirements of tunnel construction. In recent years, scholars have proposed to use flexible mesh protection made of polymer to replace traditional metal mesh, which can not only play a supporting role, but also play a role in intercepting rock bursts.

[0004] However, the characteristics of rockburst disasters are complex, and the traditional "experience-oriented" prevention and control design lacks a dynamic adjustment process, making it difficult to take into account the safety and economic requirements of tunnel construction. As a result, the flexible network cannot meet the requirements of tunnel construction due to the incompatibility of safety and economy. Summary of the invention

[0005] The purpose of the present invention is to provide a method, system and equipment for optimizing the design of flexible net parameters for rockburst tunnels in response to the above-mentioned deficiencies in the prior art, so as to solve the problem that the traditional "experience-oriented" prevention and control design in the prior art lacks a dynamic adjustment process, making it difficult to take into account the requirements of tunnel construction safety and economy, resulting in the incompatibility of safety and economy of the flexible net and the inability to meet the requirements of tunnel construction.

[0006] The present invention specifically provides the following technical solution: a method for optimizing the design of parameters of a flexible net for a rockburst tunnel, comprising the following steps:

[0007] Obtain the tunnel dimension parameters and surrounding rock physical and mechanical parameters of the rockburst tunnel;

[0008] Based on the tunnel size parameters and the physical and mechanical parameters of the surrounding rock, a tunnel numerical model under different parameters is established, and a rock burst numerical simulation test is carried out through the tunnel numerical model, and characteristic parameters of rock burst stones under different parameters are obtained according to the test results;

[0009] Acquire initial flexible net parameters, determine the sensitive factor value range of the initial flexible net parameters, and establish a numerical model of rock impact on the flexible net in combination with rock burst rock characteristic parameters;

[0010] A rockfall impact test of a flexible net is carried out through the numerical model of the rock impacting the flexible net, and a mapping relationship between the flexible net parameters and the ultimate energy absorption capacity and the failure mode of the flexible net under different energies is established according to the test results, and a mapping relationship between the interception capacity of the flexible net and the impact energy is obtained through the mapping relationship and the failure mode, and a sample library of rock burst tunnel parameters corresponding to the flexible net is established according to the mapping relationship between the interception capacity of the flexible net and the impact energy;

[0011] Inputting the rockburst tunnel parameters in the sample library into the BP neural network to obtain preliminary values ​​of the flexible network parameters in the BP neural network;

[0012] A numerical model of a flexible net-protected rockburst tunnel is established based on the preliminary values ​​and engineering geological survey data, and a numerical simulation test of a flexible net intercepting rockburst stones is carried out;

[0013] Based on the numerical simulation test results of the flexible net intercepting rock burst stones, the key parameters of the flexible net and stones after impact are obtained, and the rock burst interception stone effect parameters and the flexible net cost are obtained through the key parameters of the flexible net and stones after impact. The rock burst interception stone effect parameters and the flexible net cost are used to quantitatively evaluate the protective effect of the flexible net, and the final flexible net parameters are determined based on the quantitative evaluation results.

[0014] Preferably, the tunnel dimension parameters and surrounding rock physical and mechanical parameters of the rock burst tunnel are obtained, wherein the tunnel dimension parameters include the tunnel diameter R and the tunnel burial depth H, and the surrounding rock physical and mechanical parameters include the density , Cohesion , internal friction angle , elastic modulus , Poisson's ratio and ground stress .

[0015] Preferably, the initial flexible net parameters are obtained, the sensitive factor value range of the initial flexible net parameters is determined, and a numerical model of the rock impact on the flexible net is established in combination with the characteristic parameters of the rock burst rocks, wherein the characteristic parameters of the rock burst rocks include the rock size , Number of rocks ejected by rockburst and the kinetic energy of the projectile The initial flexible mesh parameters include density , elastic modulus and Poisson's ratio , the sensitive factors include the tensile strength of the flexible web strips , Node Strength , Strip width and mesh side length .

[0016] Preferably, the rockburst tunnel parameters in the sample library are input into the BP neural network to obtain the preliminary values ​​of the flexible network parameters in the BP neural network, specifically:

[0017] The rockburst tunnel parameters are input into the input layer of the BP neural network, processed through neuron connection weights and output to the output layer to obtain the preliminary values ​​of the flexible network parameters; the specific expression is:

[0018] .

[0019] in, is the input signal representing the rockburst tunnel parameters, is the synaptic weight of the neuron, n is the number of neurons in the input layer, is the bias, is the activation function, It is the output signal of the flexible network parameters. , is the number of neurons.

[0020] Preferably, after obtaining the preliminary values ​​of the flexible network parameters in the BP neural network, the following steps are also included:

[0021] The output results of the BP neural network are compared with the test samples and the error is analyzed. If the error does not meet the requirements, it is back-propagated to the input layer through the neuron connection, and the connection weights are corrected through the neurons. The connection weights are continuously corrected until the error meets the requirements.

[0022] Preferably, the BP neural network output result is compared with the test sample and the error is analyzed. If the error does not meet the requirement, it is back-propagated to the input layer through the neuron connection, and the connection weight is corrected through the neuron, and the connection weight is continuously corrected until the error meets the requirement, including the following steps:

[0023] Get the input of the hidden layer of the BP neural network , the specific expression is:

[0024] .

[0025] in The input layer node To the hidden layer nodes The weight of is the input signal of rockburst tunnel parameters;

[0026] Through the BP neural network hidden layer to the BP neural network hidden layer input Processing to obtain the output of the hidden layer of the BP neural network , the specific expression is:

[0027] .

[0028] in, is the activation function, is the hidden layer node The threshold value of

[0029] The output of the hidden layer of the BP neural network Input-output layer, output , the specific expression is:

[0030] .

[0031] in, is the hidden layer node To the output layer node The weight of is the hidden layer node The output, Output layer node The threshold value, Output layer node The actual output value of

[0032] The output error is obtained by the difference between the expected output and the actual output value of the BP neural network. , the specific expression is:

[0033] .

[0034] in, Output layer node The expected output value of is the number of nodes in the output layer;

[0035] By adjusting the weights and thresholds of the BP neural network, the optimal actual output value is obtained, and the optimal output error is obtained through the optimal actual output value. ; The adjusted weights and thresholds are as follows:

[0036] .

[0037] The optimal output error Get the global error. The specific expression is:

[0038] .

[0039] in, is the learning rate, is the gradient value of the output layer neuron, is the gradient value of the hidden layer neuron, is the adjusted hidden layer node To the output layer node The weight of The adjusted input layer node To the hidden layer nodes The weight of is the adjusted output layer node The threshold value, is the adjusted hidden layer node The threshold value.

[0040] Preferably, the method of obtaining rock burst interception stone effect parameters and flexible net cost through key parameters of the flexible net and stones after impact comprises the following steps:

[0041] Get interception ratio including rockburst , Flexible net energy absorption ratio The rockburst interception stone effect parameter of the quartz crystal is:

[0042] .

[0043] .

[0044] in, is the number of rocks ejected by rockburst; The number of escaped stones; Kinetic energy for projectile rocks; To escape the kinetic energy of the stone;

[0045] Get Flex Net Cost , the specific expression is:

[0046] .

[0047] in, is the price coefficient of the flexible mesh, is the number of flexible nets required.

[0048] Preferably, the rock burst interception stone effect parameter and the flexible net cost are used to quantitatively evaluate the protective effect of the flexible net, and the specific expression is:

[0049] Flexible net protection effect = .

[0050] Optimal protection effect = .

[0051] in, It means that under the condition of a certain stone interception ratio, the flexible net has the greatest energy absorption and the lowest cost.

[0052] The present invention provides an optimization design system for flexible net parameters for rock burst tunnels, comprising:

[0053] A data acquisition module, used to obtain tunnel size parameters and surrounding rock physical and mechanical parameters of the rock burst tunnel;

[0054] A simulation test module is used to establish a tunnel numerical model under different parameters based on the tunnel size parameters and the physical and mechanical parameters of the surrounding rock, and to carry out a rock burst numerical simulation test through the tunnel numerical model, and to obtain the characteristic parameters of the rock burst stones under different parameters according to the test results;

[0055] A numerical model building module is used to obtain initial flexible net parameters, determine the sensitive factor value range of the initial flexible net parameters, and establish a numerical model of rock impact on the flexible net in combination with rock burst rock characteristic parameters;

[0056] An impact test module is used to carry out a rockfall impact test on a flexible net through a numerical model of the rock impacting the flexible net, establish a mapping relationship between the flexible net parameters and the ultimate energy absorption capacity, and the failure mode of the flexible net under different energies according to the test results, and obtain a mapping relationship between the flexible net interception capacity and the impact energy through the mapping relationship and the failure mode, and establish a sample library of flexible net corresponding rock burst tunnel parameters according to the mapping relationship between the flexible net interception capacity and the impact energy;

[0057] An initial value acquisition module, used to input the rockburst tunnel parameters in the sample library into the BP neural network to obtain the initial values ​​of the flexible network parameters in the BP neural network;

[0058] A flexible net interception module is used to establish a numerical model of a flexible net-protected rockburst tunnel according to the preliminary values ​​and the engineering geological survey data of the rockburst tunnel, and to carry out a numerical simulation test of the flexible net intercepting rockburst stones;

[0059] The optimization module is used to obtain the key parameters of the flexible net and the stone after the impact based on the numerical simulation test results of the flexible net intercepting rock burst stones, obtain the rock burst interception stone effect parameters and the flexible net cost through the key parameters of the flexible net and the stone after the impact, use the rock burst interception stone effect parameters and the flexible net cost to quantitatively evaluate the protective effect of the flexible net, and determine the final flexible net parameters based on the quantitative evaluation results.

[0060] The present invention provides a computer device, comprising a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the above-mentioned method for optimizing the parameters of a flexible net for a rockburst tunnel.

[0061] Compared with the prior art, the present invention has the following significant advantages:

[0062] The present invention establishes a mapping relationship between tunnel parameters and flexible net parameters through numerical simulation of rock burst and flexible net rockfall impact tests, establishes a flexible net parameter preliminary selection model based on BP neural network and genetic algorithm, establishes a protection effect quantitative evaluation model by combining the interception ratio of rock burst stones, the flexible net energy absorption ratio and the flexible net cost, dynamically adjusts the flexible net parameters, realizes further determination of the flexible net parameters, and reduces the construction cost under the premise of ensuring the tunnel rock burst protection effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flow chart of a method for optimizing design of parameters of a flexible net for a rockburst tunnel provided by the present invention;

[0064] Figure 2 A schematic diagram of numerical simulation of rock burst in an unprotected tunnel in an embodiment provided by the present invention;

[0065] Figure 3 A schematic diagram of numerical simulation of rockfall impact test of a flexible net in an embodiment provided by the present invention;

[0066] Figure 4 A schematic diagram of numerical simulation of rock burst in a flexible net protection tunnel provided in an embodiment of the present invention;

[0067] Figure 5 This is a schematic diagram of the quantitative evaluation of the protective effect of the flexible net in the embodiment provided by the present invention. DETAILED DESCRIPTION

[0068] The following is a clear and complete description of the technical solutions of the embodiments of the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0069] The purpose of the present invention is to provide a method, system and equipment for optimizing the design of parameters of a flexible net for a rock burst tunnel, so as to reduce the construction cost while ensuring the rock burst protection effect of the tunnel.

[0070] like Figure 1 As shown, the present invention proposes a method for optimizing the design of flexible mesh parameters for rock burst tunnels to solve the problems of the prior art, which specifically includes the following steps:

[0071] Step S1: Collect rockburst tunnel data to obtain tunnel dimension parameters and surrounding rock physical and mechanical parameters of the rockburst tunnel.

[0072] S1 is specifically:

[0073] Obtain the tunnel dimension parameters of the rockburst tunnel, including the hole diameter R and the tunnel burial depth H, as well as the physical and mechanical parameters of the surrounding rock, including the density , Cohesion , internal friction angle , elastic modulus , Poisson's ratio and ground stress The density of the rock is Measured by wax seal method, cohesion , internal friction angle The elastic modulus is measured by triaxial compression test. , Poisson's ratio The ground stress is measured by uniaxial compression test. Measured by field tests.

[0074] Step S2: Based on the tunnel size parameters and the physical and mechanical parameters of the surrounding rock, a tunnel numerical model under different parameters is established, and a (unprotected) rockburst numerical simulation test is carried out through the tunnel numerical model. The characteristic parameters of rockburst stones under different parameters are obtained according to the test results.

[0075] S2 is specifically:

[0076] Examples of tunnel parameters for rockburst numerical simulation tests are shown in Table 1. Rockburst numerical simulation tests were carried out in GDEM. Figure 2 shown.

[0077] Obtain the size of rockburst blocks under different tunnel parameters , Number of rocks ejected by rockburst and the kinetic energy of the projectile , establish the mapping relationship between tunnel parameters and rock burst impact energy.

[0078] Table 1 Examples of tunnel parameters for rockburst numerical simulation test

[0079]

[0080] The model uses a two-dimensional network topology of triangular units. To avoid excessive calculation, a rockburst area is artificially set on the left wall of the tunnel in the model to reduce the size of the triangular mesh. The mesh size of the rockburst area and surrounding units and interfaces is 0.1m, and the mesh size of the rest of the area is 0.5m.

[0081] The calculation does not consider the influence of gravity. The Mohr-Coulomb constitutive model is used for rock. In the initial stress calculation, the contact surface is set as a linear elastic model, and the strength and stiffness of the contact surface are automatically selected from the unit.

[0082] The simulation of rockburst first constrains the normal direction of the rectangular area on the side wall of the model, applies consistent ground stress loads in three directions, and calculates until stability. Then, the normal constraints on all sides are released, and non-reflecting boundaries are applied locally on the top, bottom, left and right sides of one side of the model, and the boundary of the middle one-third of the right side of the rectangular area is converted into a free surface.

[0083] Examples of the obtained rockburst stone characteristic parameters are shown in Table 2:

[0084] Table 2 Examples of characteristic parameters of rocks in rockburst numerical simulation

[0085]

[0086] Step S3: Acquire initial flexible net parameters, determine the sensitive factor value range of the initial flexible net parameters, and establish a numerical model of rock impact on the flexible net in combination with rock burst rock characteristic parameters.

[0087] The initial flexible net parameters are the mechanical parameters of the flexible net.

[0088] S3 is specifically:

[0089] Obtaining the density of flexible mesh through indoor tests , elastic modulus and Poisson's ratio . Select the tensile strength of the flexible web strips , Node Strength , Strip width and mesh side length As sensitive factors for parameter optimization, examples of determining the values ​​of sensitive factors are shown in Table 3.

[0090] Table 3 Examples of values ​​for sensitive factors

[0091]

[0092] Step S4: Conduct a rockfall impact test (numerical simulation) of the flexible net through a numerical model of rock impacting the flexible net, establish a mapping relationship between the flexible net parameters and the ultimate energy absorption capacity, and the failure mode of the flexible net under different energies based on the test results, and obtain a mapping relationship between the flexible net interception capacity and the impact energy through the mapping relationship and the failure mode, and establish a sample library of rockburst tunnel parameters corresponding to the flexible net based on the mapping relationship between the flexible net interception capacity and the impact energy. The rockburst tunnel parameter here is the rockburst energy level.

[0093] S4 is specifically:

[0094] The size of rocks under different rockburst levels , Number of rocks ejected by rockburst and the kinetic energy of the projectile .like Figure 3As shown in the figure, a numerical model of rocks with different parameters impacting the flexible net is established, and the rockfall impact test of the flexible net is carried out in LS-DYNA. The mapping relationship between the flexible net parameters and the ultimate energy absorption capacity is established, as well as its failure mode under different energy impacts.

[0095] The flexible net model uses hexahedral elements, and the mesh is encrypted for the node part. Keyword settings are performed in LS-PREPOST, including material model, contact settings, boundary conditions and solution settings. Keyword solutions are performed in LS-RUN to obtain the damage of the rock impact flexible net, such as Figure 2 shown.

[0096] An example of the mapping relationship between the flexible network parameters and the tunnel parameters is shown in Table 4.

[0097] Table 4 Example of mapping relationship between flexible network parameters and tunnel parameters

[0098]

[0099] The flexible network parameters include density , elastic modulus and Poisson's ratio , sensitive factors include the tensile strength of the flexible web strips , Node Strength , Strip width and mesh side length .

[0100] Step S5: Input the rockburst tunnel parameters in the sample library into the BP neural network to obtain preliminary values ​​of the flexible network parameters in the BP neural network.

[0101] S5 is as follows:

[0102] The rockburst tunnel parameters are selected as the input layer input parameters, the flexible network parameters are selected as the output layer output parameters, and the training learning samples are used to adjust the bias of the network until the neural network model is good. That is:

[0103] The rockburst tunnel parameters are input into the input layer of the BP neural network, processed through neuron connection weights and output to the output layer to obtain the preliminary values ​​of the flexible network parameters; the specific expression is:

[0104] .

[0105] in, is the input signal representing the rockburst tunnel parameters, is the synaptic weight of the neuron, n is the number of neurons in the input layer, is the bias, is the activation function, It is the output signal of the flexible network parameters. , is the number of neurons.

[0106] The process of constructing the BP neural network, sample training, optimizing the neural network parameters based on the genetic algorithm, and running the neural network to obtain the preliminary values ​​of the flexible network parameters is as follows:

[0107] (1) Sample design. The rockburst tunnel data samples used as training and test samples were determined by researching literature and field data. 80 groups of samples were selected as learning samples and 20 groups as test samples.

[0108] (2) Sample standardization. Normalization is used to compress all data into the range of [0, 1]. The specific implementation steps are as follows:

[0109] ① The data is dimensionless, and the calculation formula is: .

[0110] in, is the original data; is the average of the original data; is the original data after dimensionless conversion; is the standard deviation of the original data.

[0111] ② Compress the data to between [0, 1], and the calculation formula is: .

[0112] in, and are the maximum and minimum values ​​after dimensionlessness respectively; It is dimensionless and compressed data.

[0113] (3) Determine the number of network layers. A single hidden layer neural network is selected, that is, the neural network structure is a three-layer structure consisting of an input layer, a hidden layer, and an output layer.

[0114] (4) Determine the number of neurons in each layer. The input layer parameters of the network include five components: tunnel depth, cross-section diameter (circular), horizontal ground stress, vertical ground stress, and uniaxial compressive strength of surrounding rock, that is, the input layer has five neurons. The output layer parameters include four components: flexible net strip tensile strength, strip width, node strength, and mesh side length, that is, the output layer has four neurons. Method for determining the number of neurons in the hidden layer:

[0115] .

[0116] in, n is the number of neurons in the input layer, lis the number of neurons in the hidden layer. So the number of neurons is selected as 11, and it is adjusted around 11 according to the network performance during the training process.

[0117] (5) Select an activation function. Common activation functions include Sigmoid function, Tanh function and ReLU function. Considering the applicability of the three functions comprehensively, Sigmoid function is selected.

[0118] (6) Run the neural network. Suppose the neural network input is The actual output value is , the expected output is The number of node input layers is , the number of hidden layers is , the number of nodes in the output layer is .

[0119] After obtaining the preliminary values ​​of the flexible network parameters in the BP neural network, the following steps are also included:

[0120] Compare the output of the BP neural network with the test sample and analyze the error. If the error does not meet the requirements, it will be back-propagated to the input layer through the neuron connection, and the connection weights will be corrected through the neurons, and the connection weights will be continuously corrected until the error meets the requirements. Specifically:

[0121] ① Get the input of the hidden layer of the BP neural network , the specific expression is:

[0122] .

[0123] in, The input layer node To the hidden layer nodes The weight of is the input signal of rockburst tunnel parameters.

[0124] ②Through the BP neural network hidden layer, the input to the BP neural network hidden layer Processing to obtain the output of the hidden layer of the BP neural network , the specific expression is:

[0125] .

[0126] in, is the activation function, is the hidden layer node The threshold value.

[0127] ③Through the output of the hidden layer of the BP neural network Input-output layer, output , the specific expression is:

[0128] .

[0129] in, is the activation function, is the hidden layer node To the output layer node The weight of is the hidden layer node The output, Output layer node The threshold value, Output layer node The actual output value.

[0130] ④ Obtain the output error through the difference between the expected output and the actual output value of the BP neural network , the specific expression is:

[0131] .

[0132] in, Output layer node The expected output value of is the number of nodes in the output layer.

[0133] By adjusting the weights and thresholds of the BP neural network, the optimal actual output value is obtained, and the optimal output error is obtained through the optimal actual output value. ; The adjusted weights and thresholds are as follows:

[0134] ⑤Weight and threshold adjustment:

[0135] .

[0136] in, is the learning rate, is the gradient value of the output layer neuron, is the gradient value of the hidden layer neuron, is the adjusted hidden layer node To the output layer node The weight of The adjusted input layer node To the hidden layer nodes The weight of is the adjusted output layer node The threshold value, is the adjusted hidden layer node The threshold value.

[0137] ⑥Through the optimal output error Get the global error. The specific expression is:

[0138] .

[0139] Repeat ②~⑥ until the error is less than the set value.

[0140] Optimize neural network parameters based on genetic algorithm: Use the fitness function of genetic algorithm to calculate and select weights and thresholds with smaller errors to optimize neural network parameters. Input the tunnel parameters that need to be optimized for flexible network parameters, and obtain the preliminary values ​​of flexible network parameters through model calculation.

[0141] Step S6: A numerical model of a flexible net protecting a rockburst tunnel is established based on the preliminary values ​​and the engineering geological survey data of the rockburst tunnel, and a numerical simulation test of a flexible net intercepting rockburst stones is carried out in LS-DYNA, such as Figure 4 shown.

[0142] Step S7: Based on the numerical simulation test results of the flexible net intercepting rock burst stones, the key parameters of the flexible net and stones after the impact are obtained, and the rock burst interception stone effect parameters and the flexible net cost are obtained through the key parameters of the flexible net and stones after the impact. The rock burst interception stone effect parameters and the flexible net cost are used to quantitatively evaluate the protective effect of the flexible net, and the final flexible net parameters are determined based on the quantitative evaluation results.

[0143] S7 is specifically:

[0144] Using the interception ratio of rockburst , Flexible net energy absorption ratio and flexible mesh cost M A quantitative evaluation formula for the protective effect of flexible nets is established, and the rock burst protection level and construction cost are divided into "low level, low cost"; "low level, medium cost"; "low level, high cost"; "medium level, low cost"; "medium level, medium cost"; "medium level, high cost"; "high level, low cost"; "high level, medium cost"; and "high level, high cost".

[0145] Interception ratio of rockburst , Flexible net energy absorption ratio :

[0146] .

[0147] .

[0148] in, is the number of rocks ejected by rockburst; The number of escaped stones; Kinetic energy for projectile rocks; To escape the kinetic energy of the stone.

[0149] Flexible mesh cost , the specific expression is:

[0150] .

[0151] in, is the price coefficient of the flexible mesh, is the number of flexible nets required.

[0152] Quantitative evaluation formula:

[0153] Flexible net protection effect = .

[0154] Optimal protection effect = .

[0155] in, It means that when the rock interception ratio is constant, the flexible net has the highest energy absorption and the lowest cost. , Flexible net energy absorption ratio and flexible mesh cost M The calculation results are shown in Table 5:

[0156] In the case of a certain rockburst interception ratio ( Figure 5 In the case of interception ratio of 70%), the protection effect is divided into 9 categories according to the energy absorption ratio and cost of the flexible net: "low energy absorption, low cost"; "low energy absorption, medium cost", such as P1 and P10; "low energy absorption, high cost", such as P7; "medium energy absorption, low cost", such as P5 and P6; "medium energy absorption, medium cost", such as P2, P3 and P8; "medium energy absorption, high cost", such as P9; "high energy absorption, low cost", such as P4; "high energy absorption, medium cost"; "high energy absorption, high cost", such as Figure 5 shown.

[0157] Determine the final flexible net parameters: Combined with the quantitative evaluation results of the flexible net, reduce costs while ensuring the stone interception ratio, and determine the final flexible net parameters.

[0158] Table 5 Interception ratio of rockburst , Flexible net energy absorption ratio and flexible mesh cost M Calculation result example

[0159]

[0160] The quantitative evaluation formula needs to be used according to the actual engineering needs. Some tunnels with low ground stress are unlikely to have rock bursts, and may not need flexible nets to intercept high-kinetic energy rocks. They are only part of the support system. At this time, the main consideration is the construction cost. Some tunnels with high ground stress have a high probability of rock bursts and impact energy. It is necessary to adopt high-strength flexible net parameters to protect the safety of construction personnel and equipment in the tunnel. At this time, the main consideration is the prevention and control effect of rock bursts.

[0161] In summary, the present invention establishes the mapping relationship between tunnel parameters and flexible net parameters through numerical simulation of rock burst and flexible net rockfall impact test, establishes a preliminary selection model of flexible net parameters based on BP neural network and genetic algorithm, and combines the interception ratio of rock burst and rock fragments to establish a mapping relationship between tunnel parameters and flexible net parameters. , Flexible net energy absorption ratio and flexible mesh cost M A quantitative evaluation model for protection effect is established, and the parameters of the flexible net are further determined to reduce the construction cost while ensuring the tunnel rock burst protection effect.

[0162] Based on the above method, the present invention provides an optimization design system for flexible net parameters for rockburst tunnels, including: a data acquisition module, a simulation test module, a numerical model construction module, an impact test module, an initial value acquisition module, a flexible net interception module and an optimization module.

[0163] Among them, the data acquisition module is used to collect rockburst tunnel data, and obtain the tunnel size parameters and surrounding rock physical and mechanical parameters of the rockburst tunnel; the simulation test module is used to establish a tunnel numerical model under different parameters based on the tunnel size parameters and the surrounding rock physical and mechanical parameters, and carry out rockburst numerical simulation tests through the tunnel numerical model, and obtain the characteristic parameters of rockburst stones under different parameters according to the test results; the numerical model construction module is used to obtain the initial flexible net parameters, determine the sensitive factor value range of the initial flexible net parameters, and establish a numerical model of stone impacting the flexible net in combination with the characteristic parameters of rockburst stones; the impact test module is used to carry out a flexible net rockfall impact test through the numerical model of stone impacting the flexible net, and establish a mapping relationship between the flexible net parameters and the ultimate energy absorption capacity according to the test results, as well as the failure mode of the flexible net under different energies, and obtain the flexible net barrier through the mapping relationship and failure mode. The mapping relationship between the interception capacity and the impact energy of the flexible net is established, and a sample library of the rockburst tunnel parameters corresponding to the flexible net is established according to the mapping relationship between the interception capacity and the impact energy of the flexible net; the initial value acquisition module is used to input the rockburst tunnel parameters in the sample library into the BP neural network to obtain the preliminary values ​​of the flexible net parameters in the BP neural network; the flexible net interception module is used to establish a numerical model of the rockburst tunnel protected by the flexible net according to the preliminary values ​​and the engineering geological survey data of the rockburst tunnel, and to carry out numerical simulation tests on the flexible net intercepting rockburst stones; the optimization module is used to obtain the key parameters of the flexible net and the stone after the impact based on the numerical simulation test results of the flexible net intercepting rockburst stones, and obtain the rockburst interception stone effect parameters and the flexible net cost through the key parameters of the flexible net and the stone after the impact, and use the rockburst interception stone effect parameters and the flexible net cost to quantitatively evaluate the protection effect of the flexible net, and determine the final flexible net parameters based on the quantitative evaluation results.

[0164] The present invention also provides a computer device, including a memory and a processor. The memory stores a program. When the program is executed by the processor, the processor executes the steps of a method for optimizing the parameters of a flexible net for a rockburst tunnel.

[0165] According to the disclosed embodiments, a computing device may communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth communications, etc.), or with any device (e.g., routers, modems, etc.) that enables a computing device to communicate with one or more other computing devices.

[0166] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0167] The present invention uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for optimizing the parameters of a flexible mesh for a rockburst tunnel, characterized in that: The steps include: Obtain the tunnel dimension parameters and surrounding rock physical and mechanical parameters of the rockburst tunnel; Based on the tunnel size parameters and the physical and mechanical parameters of the surrounding rock, a tunnel numerical model under different parameters is established, and a rock burst numerical simulation test is carried out through the tunnel numerical model, and characteristic parameters of rock burst stones under different parameters are obtained according to the test results; Acquire initial flexible net parameters, determine the sensitive factor value range of the initial flexible net parameters, and establish a numerical model of rock impact on the flexible net in combination with rock burst rock characteristic parameters; A rockfall impact test of a flexible net is carried out through the numerical model of the rock impacting the flexible net, and a mapping relationship between the flexible net parameters and the ultimate energy absorption capacity and the failure mode of the flexible net under different energies is established according to the test results, and a mapping relationship between the interception capacity of the flexible net and the impact energy is obtained through the mapping relationship and the failure mode, and a sample library of rock burst tunnel parameters corresponding to the flexible net is established according to the mapping relationship between the interception capacity of the flexible net and the impact energy; Inputting the rockburst tunnel parameters in the sample library into the BP neural network to obtain preliminary values ​​of the flexible network parameters in the BP neural network; According to the preliminary values ​​and the engineering geological survey data of the rockburst tunnel, a numerical model of a flexible net protecting a rockburst tunnel is established, and a numerical simulation test of a flexible net intercepting rockburst stones is carried out; Based on the numerical simulation test results of the flexible net intercepting rock burst stones, the key parameters of the flexible net and stones after impact are obtained, and the rock burst interception stone effect parameters and the flexible net cost are obtained through the key parameters of the flexible net and stones after impact. The rock burst interception stone effect parameters and the flexible net cost are used to quantitatively evaluate the protective effect of the flexible net, and the final flexible net parameters are determined based on the quantitative evaluation results.

2. The method for optimizing the parameters of a flexible mesh for a rockburst tunnel according to claim 1, characterized in that: The tunnel dimension parameters and surrounding rock physical and mechanical parameters of the rock burst tunnel are obtained, wherein the tunnel dimension parameters include the tunnel diameter R and the tunnel burial depth H, and the surrounding rock physical and mechanical parameters include the density , Cohesion , internal friction angle , elastic modulus , Poisson's ratio and ground stress .

3. The method for optimizing the parameters of a flexible mesh for a rockburst tunnel according to claim 1, characterized in that: The initial flexible net parameters are obtained, the sensitive factor value range of the initial flexible net parameters is determined, and a numerical model of the rock impacting the flexible net is established in combination with the characteristic parameters of the rock bursting rocks, wherein the characteristic parameters of the rock bursting rocks include the rock size , Number of rocks ejected by rock burst and the kinetic energy of the projectile The initial flexible mesh parameters include density , elastic modulus and Poisson's ratio , the sensitive factors include the tensile strength of the flexible web strips , Node Strength , Strip width and mesh side length .

4. The method for optimizing the parameters of a flexible mesh for a rockburst tunnel according to claim 1, characterized in that: The rockburst tunnel parameters in the sample library are input into the BP neural network to obtain the preliminary values ​​of the flexible network parameters in the BP neural network, specifically: The rockburst tunnel parameters are input into the input layer of the BP neural network, processed through neuron connection weights and output to the output layer to obtain the preliminary values ​​of the flexible network parameters; the specific expression is: ； in, is the input signal representing the rockburst tunnel parameters, is the synaptic weight of the neuron, n is the number of neurons in the input layer, is the bias, is the activation function, It is the output signal of the flexible network parameters. , is the number of neurons.

5. The method for optimizing the parameters of a flexible net for a rockburst tunnel according to claim 4, characterized in that: After obtaining the preliminary values ​​of the flexible network parameters in the BP neural network, the following steps are also included: The output results of the BP neural network are compared with the test samples and the error is analyzed. If the error does not meet the requirements, it is back-propagated to the input layer through the neuron connection, and the connection weights are corrected through the neurons. The connection weights are continuously corrected until the error meets the requirements.

6. The method for optimizing the parameters of a flexible net for a rockburst tunnel according to claim 5, characterized in that: The BP neural network output result is compared with the test sample and the error is analyzed. If the error does not meet the requirement, it is back-propagated to the input layer through the neuron connection, and the connection weight is corrected through the neuron. The connection weight is continuously corrected until the error meets the requirement, including the following steps: Get the input of the hidden layer of the BP neural network , the specific expression is: ； in, The input layer node To the hidden layer nodes The weight of is the input signal of rockburst tunnel parameters; Through the BP neural network hidden layer to the BP neural network hidden layer input Processing to obtain the output of the hidden layer of the BP neural network , the specific expression is: ； in, is the activation function, is the hidden layer node The threshold value of The output of the hidden layer of the BP neural network Input-output layer, output , the specific expression is: ； in, is the hidden layer node To the output layer node The weight of is the hidden layer node The output, Output layer node The threshold value, Output layer node The actual output value of The output error is obtained by the difference between the expected output and the actual output value of the BP neural network. , the specific expression is: ； in, Output layer node The expected output value of is the number of nodes in the output layer; By adjusting the weights and thresholds of the BP neural network, the optimal actual output value is obtained, and the optimal output error is obtained through the optimal actual output value. ; The adjusted weights and thresholds are as follows: ； The optimal output error Get the global error. The specific expression is: ； in, is the learning rate, is the gradient value of the output layer neuron, is the gradient value of the hidden layer neuron, is the adjusted hidden layer node To the output layer node The weight of The adjusted input layer node To the hidden layer nodes The weight of is the adjusted output layer node The threshold value, is the adjusted hidden layer node The threshold value.

7. The method for optimizing the parameters of a flexible mesh for a rockburst tunnel according to claim 1, characterized in that: The method of obtaining rock burst interception stone effect parameters and flexible net cost through key parameters of the flexible net and stones after impact includes the following steps: Get interception ratio including rockburst , Flexible net energy absorption ratio The rockburst interception stone effect parameter is: ； ； in, is the number of rocks ejected by rockburst; The number of escaped stones; Kinetic energy for projectile rocks; To escape the kinetic energy of the stone; Get Flex Net Cost , the specific expression is: ； in, is the price coefficient of the flexible mesh, is the number of flexible nets required.

8. A method for optimizing the parameters of a flexible net for a rockburst tunnel according to claim 7, characterized in that: The rock burst interception stone effect parameter and the flexible net cost are used to quantitatively evaluate the protective effect of the flexible net, and the specific expression is: Flexible net protection effect = ; Optimal protection effect = ; in, It means that under the condition of a certain stone interception ratio, the flexible net has the greatest energy absorption and the lowest cost.

9. An optimization design system for flexible mesh parameters for rock burst tunnels, characterized in that: include: A data acquisition module, used to obtain tunnel size parameters and surrounding rock physical and mechanical parameters of the rock burst tunnel; A simulation test module is used to establish a tunnel numerical model under different parameters based on the tunnel size parameters and the physical and mechanical parameters of the surrounding rock, and to carry out a rock burst numerical simulation test through the tunnel numerical model, and to obtain the characteristic parameters of the rock burst stones under different parameters according to the test results; A numerical model building module is used to obtain initial flexible net parameters, determine the sensitive factor value range of the initial flexible net parameters, and establish a numerical model of rock impact on the flexible net in combination with rock burst rock characteristic parameters; An impact test module is used to carry out a rockfall impact test on a flexible net through a numerical model of the rock impacting the flexible net, establish a mapping relationship between the flexible net parameters and the ultimate energy absorption capacity, and the failure mode of the flexible net under different energies according to the test results, and obtain a mapping relationship between the flexible net interception capacity and the impact energy through the mapping relationship and the failure mode, and establish a sample library of flexible net corresponding rock burst tunnel parameters according to the mapping relationship between the flexible net interception capacity and the impact energy; An initial value acquisition module, used to input the rockburst tunnel parameters in the sample library into the BP neural network to obtain the initial values ​​of the flexible network parameters in the BP neural network; A flexible net interception module is used to establish a numerical model of a flexible net-protected rockburst tunnel according to the preliminary values ​​and the engineering geological survey data of the rockburst tunnel, and to carry out a numerical simulation test of the flexible net intercepting rockburst stones; The optimization module is used to obtain the key parameters of the flexible net and the stone after the impact based on the numerical simulation test results of the flexible net intercepting rock burst stones, obtain the rock burst interception stone effect parameters and the flexible net cost through the key parameters of the flexible net and the stone after the impact, use the rock burst interception stone effect parameters and the flexible net cost to quantitatively evaluate the protective effect of the flexible net, and determine the final flexible net parameters based on the quantitative evaluation results.

10. A computer device, characterized in that: It comprises a memory and a processor, wherein a program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of a method for optimizing the parameters of a flexible net for a rockburst tunnel as claimed in any one of claims 1 to 8.

Images