Tunnel reliability analysis method, system, equipment, medium and product

Abstract

The invention discloses a tunnel reliability analysis method, system and device, a medium and a product, and relates to the field of tunnel reliability analysis, and the method comprises the steps: building a tunnel model based on the investigation data of a tunnel; performing grid division on the tunnel model to obtain a plurality of units; determining coordinates of each unit; the plurality of units comprise lining structure units and rock-soil body units; based on the coordinates of each unit, a random field simulation method is adopted for multiple times, the rock-soil body material parameters of each unit are simulated for multiple times, and multiple random field samples are obtained; each random field sample comprises rock-soil body material parameters of all units; based on a plurality of random field samples, adopting the trained long-short term recurrent neural network to obtain a shear strain value of a lining structure unit in each random field sample; and analyzing the reliability of the tunnel based on the shear strain value of the lining structure unit in each random field sample. According to the invention, the accuracy and speed of tunnel reliability analysis are improved.

Description

Technical Field

[0001] The present application relates to the field of tunnel engineering reliability analysis, and in particular to a tunnel reliability analysis method, system, equipment, medium and product. Background Art

[0002] The safety of tunnel structure refers to the ability of the tunnel lining and surrounding rock system to remain stable and safe during the construction and operation of the tunnel. Under the influence of multiple factors such as ground stress, groundwater pressure and construction disturbance, the stress state of the tunnel lining structure will continue to change. When the bearing capacity of the structure is not enough to resist these external effects, the tunnel may become unstable, which will cause lining damage and threaten the operational safety of the tunnel.

[0003] Tunnel reliability analysis is one of the important topics in the field of underground engineering design. Especially with the expansion of the scale and complexity of tunnel projects, it is particularly important to quantitatively analyze the probability and failure area of ​​tunnel lining instability. Traditional tunnel reliability analysis methods mainly analyze the instability risk based on deformation values ​​(such as surface settlement, vault settlement, etc.). However, these methods usually cannot accurately capture the true damage state of the tunnel lining structure. On the other hand, the spatial variability of rock and soil materials has an important influence on the instability behavior of the tunnel lining. Traditional analysis methods often do not fully consider this variability, which makes the reliability analysis results have certain limitations.

[0004] With the development of neural network technology, combining machine learning models to analyze tunnel reliability has become an effective method. However, traditional neural networks have limitations when processing time-series related data, and it is difficult to capture the complex patterns of shear strain values ​​changing with time and space. Summary of the invention

[0005] The purpose of this application is to provide a tunnel reliability analysis method, system, equipment, medium and product, which can obtain the shear strain values ​​of lining structure units in multiple random field samples by using a trained neural network, thereby improving the accuracy and speed of tunnel reliability analysis.

[0006] To achieve the above objectives, this application provides the following solutions.

[0007] In a first aspect, the present application provides a tunnel reliability analysis method, including.

[0008] Based on the tunnel survey data, a tunnel model is established; the tunnel model is gridded to obtain multiple units; and the coordinates of each unit are determined; the tunnel survey data includes rock and soil material parameters and lining structure; the multiple units include lining structure units and rock and soil units.

[0009] Based on the coordinates of each unit, the random field simulation method is used multiple times to simulate the rock and soil material parameters of each unit multiple times to obtain multiple random field samples; each random field sample includes the rock and soil material parameters of all units.

[0010] Based on multiple random field samples, the shear strain value of the lining structure unit in each random field sample is obtained by using the trained long-short term recurrent neural network.

[0011] The reliability of the tunnel is analyzed based on the shear strain values ​​of the lining structural elements in each random field sample.

[0012] In a second aspect, the present application provides a tunnel reliability analysis system, including.

[0013] The unit coordinate determination module is used to establish a tunnel model based on the tunnel survey data; grid the tunnel model to obtain multiple units; and determine the coordinates of each unit; the tunnel survey data includes rock and soil material parameters and lining structure; the multiple units include lining structure units and rock and soil units.

[0014] The random field sample acquisition module is connected to the unit coordinate determination module and is used to simulate the rock and soil material parameters of each unit multiple times by using the random field simulation method based on the coordinates of each unit to obtain multiple random field samples; each random field sample includes the rock and soil material parameters of all units.

[0015] The shear strain value acquisition module is connected to the random field sample acquisition module and is used to obtain the shear strain value of the lining structure unit in each random field sample based on multiple random field samples using a trained long-short term recurrent neural network.

[0016] The tunnel reliability determination module is connected to the shear strain value acquisition module and is used to analyze the reliability of the tunnel based on the shear strain value of the lining structure unit in each random field sample.

[0017] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned tunnel reliability analysis method.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned tunnel reliability analysis method when executed by a processor.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the above-mentioned tunnel reliability analysis method when executed by a processor.

[0020] According to the specific embodiments provided in this application, this application has the following technical effects.

[0021] The present application provides a tunnel reliability analysis method, system, equipment, medium and product, which obtains multiple rock and soil material parameter random fields through the coordinates of each unit and multiple random field simulation methods; based on multiple rock and soil material parameter random fields, the trained long-term and short-term recurrent neural network is used to quickly and accurately obtain the shear strain value of the lining structure unit in each rock and soil material parameter random field; thereby accurately analyzing the tunnel reliability. The speed and accuracy of tunnel reliability analysis are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is an application environment diagram of a tunnel reliability analysis method in one embodiment of the present application.

[0024] Figure 2 A schematic diagram of a flow chart of a tunnel reliability analysis method provided in one embodiment of the present application.

[0025] Figure 3 A schematic diagram of functional modules of a tunnel reliability analysis system provided in one embodiment of the present application.

[0026] Figure 4 A schematic diagram of the LSTM neuron cell structure provided in one embodiment of the present application.

[0027] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0030] The tunnel reliability analysis method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the survey data of the tunnel to the server 104. After the server 104 receives the survey data of the tunnel, for the survey data of the tunnel to be processed, the server 104 establishes a tunnel model; meshes the tunnel model to obtain multiple units; and determines the coordinates of each unit; based on the coordinates of each unit, the random field simulation method is used multiple times to simulate the rock and soil material parameters of each unit multiple times to obtain multiple random field samples; based on the multiple random field samples, the trained long-term and short-term recurrent neural network is used to obtain the shear strain value of the lining structure unit in each random field sample; based on the shear strain value of the lining structure unit in each random field sample, the reliability of the tunnel is analyzed. The server 104 can feedback the obtained tunnel reliability to the terminal 102. In addition, in some embodiments, the tunnel reliability analysis method may also be implemented by the server 104 or the terminal 102 alone.

[0031] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0032] In an exemplary embodiment, Figure 2 As shown, a tunnel reliability analysis method is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 204.

[0033] Step 201, based on the survey data of the tunnel, a tunnel model is established; the tunnel model is meshed to obtain a plurality of units; and the coordinates of each unit are determined; the survey data of the tunnel includes rock and soil material parameters and lining structure; the plurality of units include lining structure units and rock and soil units.

[0034] Specifically, based on the survey data of the tunnel, finite difference software is used to establish a tunnel model. The survey data of the tunnel includes the statistical characteristics of the rock and soil material parameters, the lining structure, the tunnel geometry data, and the deformation data of the tunnel support and surrounding rock to establish the tunnel model. The user selects the grid density according to actual needs to obtain multiple units. This application uses the traversal function in the FISH language to write a program to export multiple unit center points of the tunnel model to obtain the coordinates of multiple unit center points.

[0035] The statistical characteristics of the rock and soil material parameters include the mean, standard deviation, autocorrelation function and autocorrelation distance of the rock and soil material. The tunnel geometry data includes the size and structural characteristics of the tunnel, which are used to establish the geometric model of the tunnel. The rock and soil material parameters (such as elastic modulus, cohesion, internal friction angle, etc.) are used to assign values ​​to the tunnel model and describe the spatial variability of the soil and surrounding rock; the deformation data of the tunnel support and surrounding rock, such as tunnel crown arch settlement, surface settlement, etc., are used to analyze the deformation response of the tunnel under different working conditions.

[0036] Step 202, based on the coordinates of each unit, the random field simulation method is used multiple times to simulate the rock and soil material parameters of each unit multiple times to obtain multiple random field samples; each random field sample includes the rock and soil material parameters of all units.

[0037] This application uses matlab to perform random field simulation. Specifically, the autocorrelation function is used to calculate the autocorrelation between soil parameters at any two different lining structure units in the random field area.

[0038] .

[0039] in, is the autocorrelation between the parameters of the rock mass at two different units, For random field The coordinates of the center point of each unit, For random field The coordinates of the center point of each unit, is the covariance function, is the variance function.

[0040] Step 203, based on multiple random field samples, using the trained long-short term recurrent neural network, obtain the shear strain value of the lining structure unit in each random field sample.

[0041] Step 204 , analyzing the reliability of the tunnel based on the shear strain values ​​of the lining structure units in each random field sample.

[0042] In another exemplary embodiment of the present application, before step 202, it also includes: based on the statistical characteristics of the rock and soil material parameters, assuming the instability mode of the lining structure of the tunnel model, and defining shear strain penetration failure as the criterion for tunnel instability. The statistical characteristics of the rock and soil material parameters provide a basis for the instability mode of the lining structure of the tunnel model by describing the strength, stiffness and spatial variability of the material. Statistical characteristic data help determine which areas of the lining structure may become unstable, and the mode of instability (such as local instability or uniform instability). Shear strain penetration failure is based on the deformation behavior of the rock and soil, and is used as a criterion for analyzing the instability of the lining structure. When the shear strain value exceeds the critical value, it is regarded as the instability of the lining structure.

[0043] In another exemplary embodiment of the present application, step 203 is replaced by the following steps 301 to 302.

[0044] Step 301, based on multiple random field training samples, finite difference software is used to assign values ​​to the tunnel model multiple times to obtain the shear strain value of the lining structure unit in each random field training sample.

[0045] Step 302: training the long short-term recurrent neural network based on a plurality of random field training samples and the shear strain value of the lining structure unit in each random field training sample to obtain a trained long short-term recurrent neural network.

[0046] Specifically, 500 different random field training samples were generated through multiple random field simulations. Multiple monitoring points were set in the key areas of the lining structure of the tunnel model, and matrices were created to record the shear strain values ​​of each sample at different times and different spatial locations. These matrix data will be used as input for the long-term and short-term recurrent neural network.

[0047] The shear strain data is trained using the long-term and short-term recurrent neural network. The weights of the long-term and short-term recurrent neural network are adjusted by the backpropagation through time (BPTT) algorithm to ensure that the long-term and short-term recurrent neural network can effectively learn the change pattern of the shear strain value in time and space. The training set and the validation set are used to evaluate the prediction accuracy of the model. Based on the trained long-term and short-term recurrent neural network, the shear strain value of the newly generated random field samples is predicted, and the shear strain results at each time point and spatial position are output.

[0048] Specifically, the present application uses the finite difference method (FLAC3D) to calculate the shear strain value of the tunnel structure, and makes an instability determination based on the limit strain theory. The limit shear strain is usually calculated using the following formula.

[0049] .

[0050] in, is the first elastic limit principal strain, is the third elastic limit principal strain, is the ultimate shear strain of the material.

[0051] In another exemplary embodiment of the present application, the above step 204 is replaced by the following steps 401 to 402.

[0052] Step 401: When the shear strain values ​​of the lining structure units in any random field sample are greater than the ultimate strain value, the tunnel is determined to be unstable. The ultimate strain value is 1.06‰.

[0053] Step 402, analyzing the reliability of the tunnel based on the number of tunnel instability occurrences in a plurality of random field samples.

[0054] In another exemplary embodiment of the present application, step 402 specifically includes: using the Monte Carlo method to calculate the failure probability based on the number of tunnel instability in multiple random field samples, and analyzing the reliability of the tunnel based on the failure probability. The expression of the Monte Carlo method is as follows.

[0055] .

[0056] in, represents the probability of engineering failure, is the number of tunnel instability in multiple random field samples, For all random field samples, For the A random field sample, is the limit state function of geotechnical engineering, is the limit state function of geotechnical engineering of the jth random field sample, is an indicator function. When its current value is 1, it means The random field sample is invalid. When its current value is 0, it means that The random field samples did not fail.

[0057] This application uses random fields to simulate the spatial variability of rock and soil materials, combines the ultimate strain theory with the time series processing capabilities of long-term and short-term recurrent neural networks, predicts the instability of tunnel lining structures, and uses this model to evaluate the reliability of tunnel structures. Long-term and short-term recurrent neural networks can fully learn the spatiotemporal variation patterns of shear strain data, improve the accuracy and reliability of instability prediction, and have important engineering application value.

[0058] Based on the same inventive concept, Figure 3 As shown, the embodiment of the present application also provides a tunnel reliability analysis system. The tunnel reliability analysis method described above is applied, and includes the following modules.

[0059] The unit coordinate determination module 501 is used to establish a tunnel model based on the tunnel survey data; grid the tunnel model to obtain multiple units; and determine the coordinates of each unit; the tunnel survey data includes rock and soil material parameters and lining structure; the multiple units include lining structure units and rock and soil units.

[0060] The random field sample acquisition module 502 is connected to the unit coordinate determination module 501, and is used to simulate the rock and soil material parameters of each unit multiple times by using the random field simulation method based on the coordinates of each unit to obtain multiple random field samples; each random field sample includes the rock and soil material parameters of all units.

[0061] The shear strain value acquisition module 503 is connected to the random field sample acquisition module 502 and is used to obtain the shear strain value of the lining structure unit in each random field sample based on multiple random field samples using a trained long-short term recurrent neural network.

[0062] The tunnel reliability determination module 504 is connected to the shear strain value acquisition module 503 and is used to analyze the reliability of the tunnel based on the shear strain value of the lining structure unit in each random field sample.

[0063] In another exemplary embodiment of the present application, the preferred solution is as follows.

[0064] The material parameters of the rock and soil mass include elastic modulus, cohesion, and internal friction angle. The material parameters of the rock and soil mass are normalized. The normalized sample matrix X is obtained. Due to the diversity of data features, the features of the data set have different value ranges. Therefore, before using the data, the data needs to be normalized and converted into dimensionless scalars so that different features have the same measurement scale. At the same time, the adverse effects caused by erroneous data can be eliminated, which is convenient for subsequent model training and prediction.

[0065] As a step in data preprocessing, normalization transforms the interval of multi-feature monitoring time series data into [0,1], so as to better adapt to the training of deep learning models and accelerate convergence. When the evaluation criteria of sample data are different, it is necessary to dimensionalize them. Normalization can eliminate the impact of the dimension on the evaluation results and make different indicators comparable.

[0066] After the above normalization process, each feature data sequence is converted into the same measurement scale, and all data sequences are mapped to [0,1] to facilitate subsequent model calculations.

[0067] The normalized sample matrix X is divided into training set, validation set and test set according to the number of rows, where 70% of the data is used as training set data, 10% of the data is used as validation set data, and 20% of the data is used as test set data. In machine learning, training set, validation set and test set are three important parts of the data set, which are used to train, evaluate and test the performance of machine learning models.

[0068] The training set is a dataset used by machine learning models for training and learning, and is used to train the model's parameters. The validation set is a dataset used to evaluate the model's performance, and is used to adjust the model's parameters during the training process, improve the model's performance, and avoid overfitting or underfitting the model. The test set is a dataset used to evaluate the final performance of the model, which does not overlap with the training set and validation set, and is used to determine whether the model is accurate. Generally, the training set accounts for a larger proportion, usually 60%-80% of the total dataset, while the validation set or test set accounts for a smaller proportion, usually 10%-20% of the total dataset.

[0069] The training set, validation set, and test set matrices are divided into three three-dimensional tensors x_train, x_val, and x_test as input tensors of the neural network model, respectively, with dimensions: batch size, time step, and number of feature channels. These three dimensions are the input dimensions of the long-term and short-term recurrent neural network. The data is divided into these three dimensions to facilitate input into the neural network for training. In some embodiments, the batch size is set according to the size of the computer video memory used to train the neural network model, which is generally 32. The time step can be customized to the best setting, such as using a time step of 10. The number of feature channels is consistent with the number of features of the normalized sample matrix X of the multi-feature monitoring time series data. For example, if there are five data features, the number of feature channels is 5. The training data unit x_train after data processing is in the form of Tensor[32,10,5].

[0070] Build a long short-term recurrent neural network. The long short-term recurrent neural network (LSTM) is a variant of the recurrent neural network (RNN) commonly used to process sequence data. It can effectively solve long sequence problems and is used to solve problems such as gradient disappearance and gradient explosion. For the structure of LSTM neuron cells, see Figure 4 .

[0071] Figure 4 middle, represents the input of the current time step (t), represents the hidden state at the current time step (t), represents the Sigmoid function, tanh represents the tangent function, which maps the input value to the range between -1 and 1, and X represents the element-by-element multiplication operation.

[0072] In LSTM, there are three gates: forget gate, input gate and output gate. The gating mechanism in the LSTM structure can better control the flow of information and effectively avoid the interference of irrelevant information and the problem of gradient disappearance. In addition, LSTM also has cell state and hidden state. The workflow of LSTM is as follows.

[0073] (1) At each time step, the values ​​of the forget gate, input gate, and output gate are calculated based on the hidden state of the previous time step and the input of the current time step.

[0074] (2) Use the forget gate to determine the information that has been forgotten from the cell state. The formula is as follows.

[0075] .

[0076] in, is the output of the forget gate, is the weight matrix of the forget gate, is the bias term of the forget gate, is the hidden state of the previous time step and the input of the current time step.

[0077] (3) Using the input gate and the new candidate value, the cell state is updated to add the new information to the cell state; the sigmoid layer determines which values ​​will be updated, and the tanh layer creates a new candidate value vector. The formula used is as follows.

[0078] .

[0079] .

[0080] in, is the output of the input gate, is the candidate memory cell state, is the weight matrix of the input gate, is the weight matrix of the candidate memory cell state, is the bias term of the input gate, is the bias term of the candidate memory cell state.

[0081] (4) Use the output gate to determine the information extracted from the cell state and generate the hidden state of the current time step. The output gate determines which information to output, and the output value is scaled by the tanh function.

[0082] .

[0083] .

[0084] in, is the output of the sigmoid function of the output gate, is the updated memory cell state, is the final hidden state output.

[0085] (5) The cell state and hidden state are passed to the next layer of LSTM in the next time step or used to generate the final output.

[0086] After preprocessing the multi-feature data, the LSTM model is used for training. The training set data is used to apply the back propagation algorithm for model training. The back propagation algorithm is referred to as the BP algorithm. It is a learning algorithm suitable for multi-layer neural networks. It is based on the gradient descent method. Its information processing ability comes from the multiple combinations of simple nonlinear functions, so it has a strong function reproduction ability.

[0087] Continuously adjust the model parameters to reduce the loss function. The loss function is used to measure the deviation between the model's predicted value and the true value. Generally, the smaller the better. In this step, the model parameters need to be adjusted to continuously reduce the loss function.

[0088] The Adam optimizer and appropriate learning rate are used to optimize the model. The Adam optimizer is an adaptive optimization algorithm that can adjust the learning rate based on historical gradient information. In actual use, the learning rate can be adjusted according to the data scale and data complexity, and the optimal range is generally [0.0001, 0.01].

[0089] Monitor the model performance indicators, loss function and accuracy, and use the validation set to evaluate the model performance to avoid overfitting. The model performance is measured by the mean square error SME and the coefficient of determination R2 value. The model is trained multiple times to obtain the optimal value of SME and the coefficient of determination R2. The loss function is an operation function used to measure the difference between the predicted value and the true value of the model. It is a non-negative real-valued function. The smaller the loss function, the better the robustness of the model. In the process of parameter adjustment, the model is solved and evaluated by minimizing the loss function. The accuracy of the model refers to the number of all correctly predicted samples in the model / the total number of observed samples for a given test set. In the process of parameter adjustment, the accuracy of the model should be continuously improved as much as possible.

[0090] Through the above steps, the LSTM neural network model can be obtained. When the loss function value on the validation set reaches the lowest point, the model parameters are saved to obtain the optimal model. Through the execution of the above steps, the optimal prediction model is obtained for subsequent reliability analysis.

[0091] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for the reliability of the tunnel. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a tunnel reliability analysis method is implemented.

[0092] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0093] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned tunnel reliability analysis method is implemented.

[0094] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned tunnel reliability analysis method is implemented.

[0095] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0096] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0097] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0098] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, 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 this application.

Claims

1. A tunnel reliability analysis method, characterized in that: The tunnel reliability analysis method comprises: Based on the survey data of the tunnel, a tunnel model is established; the tunnel model is meshed to obtain a plurality of units; and the coordinates of each unit are determined; the survey data of the tunnel includes rock and soil material parameters and lining structure; the plurality of units include lining structure units and rock and soil units; Based on the coordinates of each unit, the random field simulation method is used multiple times to simulate the material parameters of the rock and soil mass of each unit multiple times to obtain multiple random field samples; each random field sample includes the material parameters of the rock and soil mass of all units; Based on multiple random field samples, the shear strain value of the lining structure unit in each random field sample is obtained by using the trained long-short term recurrent neural network. The reliability of the tunnel is analyzed based on the shear strain values ​​of the lining structural elements in each random field sample.

2. The tunnel reliability analysis method according to claim 1, characterized in that: The tunnel reliability analysis method further includes: training the long-short term recurrent neural network to obtain a trained long-short term recurrent neural network; the training process of the long-short term recurrent neural network includes: Based on multiple random field training samples, finite difference software is used to assign values ​​to the tunnel model multiple times to obtain the shear strain value of the lining structure unit in each random field training sample; The long-short-term recurrent neural network is trained based on a plurality of random field training samples and the shear strain value of the lining structure unit in each random field training sample to obtain a trained long-short-term recurrent neural network.

3. The tunnel reliability analysis method according to claim 1, characterized in that: Based on the shear strain values ​​of the lining structural units in each random field sample, the reliability of the tunnel is analyzed, including: When the shear strain values ​​of the lining structure units in any random field sample are greater than the ultimate strain value, the tunnel is judged to be unstable; The reliability of the tunnel is analyzed based on the number of tunnel instability events in multiple random field samples.

4. The tunnel reliability analysis method according to claim 3, characterized in that: The ultimate strain value is 1.06‰.

5. The tunnel reliability analysis method according to claim 3, characterized in that: The reliability of the tunnel is analyzed based on the number of tunnel instability events in multiple random field samples, including: Based on the number of tunnel instability occurrences in multiple random field samples, the failure probability is calculated using the Monte Carlo method, and based on the failure probability, the reliability of the tunnel is analyzed.

6. The tunnel reliability analysis method according to claim 5, characterized in that: The expression of the Monte Carlo method is: ； in, represents the probability of engineering failure, is the number of tunnel instability in multiple random field samples, For all random field samples, For the A random field sample, is the limit state function of geotechnical engineering, is the limit state function of geotechnical engineering of the jth random field sample, is an indicator function. When its current value is 1, it means The random field sample is invalid. When its current value is 0, it means that The random field samples did not fail.

7. A tunnel reliability analysis system, using the tunnel reliability analysis method according to any one of claims 1 to 6, characterized in that: The tunnel reliability analysis system comprises: The unit coordinate determination module is used to establish a tunnel model based on the tunnel survey data; mesh the tunnel model to obtain multiple units; and determine the coordinates of each unit; the tunnel survey data includes rock and soil material parameters and lining structure; the multiple units include lining structure units and rock and soil units; A random field sample acquisition module is connected to the unit coordinate determination module and is used to simulate the rock and soil material parameters of each unit multiple times by using a random field simulation method based on the coordinates of each unit to obtain multiple random field samples; each random field sample includes the rock and soil material parameters of all units; A shear strain value acquisition module is connected to the random field sample acquisition module and is used to obtain the shear strain value of the lining structure unit in each random field sample based on multiple random field samples by using a trained long-short term recurrent neural network; The tunnel reliability determination module is connected to the shear strain value acquisition module and is used to analyze the reliability of the tunnel based on the shear strain value of the lining structure unit in each random field sample.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the tunnel reliability analysis method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the tunnel reliability analysis method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the tunnel reliability analysis method according to any one of claims 1 to 6 is implemented.

Images