A numerical simulation method for evaluating the mechanical properties of submarine tunnels under earthquake action

Abstract

The present invention provides a numerical simulation evaluation method for the mechanical properties of an undersea tunnel under earthquake action, which relates to the field of undersea tunnel damage technology. The specific steps include: systematically collecting parameters such as the geometric dimensions and material properties of the tunnel; using finite element analysis to establish a three-dimensional geometric model to perform numerical simulations of static and dynamic responses; constructing static and dynamic test models, training them through expert-assessed bearing capacity labels to obtain more accurate static and dynamic bearing capacities; performing data processing on environmental factors such as soil strength, groundwater level, and temperature changes, generating correction coefficients to correct bearing capacity values; and generating comprehensive coefficients by calculating static and dynamic stability coefficients to evaluate the damage state of the undersea tunnel. The present invention provides a scientific basis for seismic design, accurately reflects the damage state of the tunnel under the most unfavorable earthquake motion, and comprehensively considers the influence of environmental factors on tunnel damage, significantly improving the accuracy and reliability of the evaluation.

Description

Technical Field

[0001] The invention relates to the technical field of submarine tunnel damage assessment, and in particular to a numerical simulation assessment method for mechanical properties of a submarine tunnel under earthquake action. Background Art

[0002] At present, the investment cost of undersea tunnels is large and the construction period is long. Once they are damaged by earthquakes, they will have a huge adverse impact on the regional economy and people's lives and property. Therefore, ensuring the earthquake-resistant safety of undersea tunnels, conducting real-time intelligent health monitoring during operation, and formulating corresponding emergency disaster reduction plans provide technical support for urban development and protect people's lives and property safety, which is of great significance.

[0003] In the existing technology, there is currently a lack of research on the most unfavorable seismic motion parameters under complex sea conditions, and there is a lack of effective assessment methods for the damage and destruction state of submarine immersed tube tunnels under the most unfavorable seismic motion. In terms of real-time seismic safety monitoring, the existing technology cannot timely and accurately reflect the damage state of the structure, affecting the timely identification and response to potential risks. The damage and destruction state is affected by a variety of complex factors, and the existing technology is difficult to fully consider the influence of these factors and their interactions on the damage and destruction state, resulting in increased uncertainty in the assessment results.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a numerical simulation evaluation method for the mechanical properties of an undersea tunnel under earthquake action, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A numerical simulation evaluation method for mechanical properties of a submarine tunnel under earthquake action, comprising the following specific steps:

[0008] S1. Collect the geometric dimensions, material properties, static load, dynamic load and environmental impact parameters of the tunnel, the geometric dimensions include tunnel diameter, tunnel length, tunnel wall thickness and shape, the material properties include elastic modulus, density, compressive strength and Poisson's ratio, and the environmental impact parameters include soil strength value, groundwater level height and temperature change;

[0009] S2. Using the geometric parameters and material properties of the tunnel, a three-dimensional geometric model is established in the finite element analysis, the collected static load is input into the model, and the response of the tunnel under the static load is obtained by numerical simulation method, including displacement, stress and strain. The collected dynamic load is input into the model, and the response of the tunnel under the earthquake is obtained by numerical simulation method, including maximum displacement, maximum stress and maximum strain;

[0010] S3. Construct a static test model of the tunnel, take the displacement, stress and strain of the tunnel under static load as input, and the corresponding static bearing capacity as label, and have the expert group evaluate the corresponding static bearing capacity, train the static test model of the tunnel, input the newly collected displacement, stress and strain of the tunnel under static load into the trained static test model, obtain the static bearing capacity, construct a dynamic test model of the tunnel, take the maximum displacement, maximum stress and maximum strain of the tunnel under dynamic load as input, and the corresponding dynamic bearing capacity as label, and have the expert group evaluate the corresponding dynamic bearing capacity, train the dynamic test model of the tunnel, input the newly collected maximum displacement, maximum stress and maximum strain of the tunnel under dynamic load into the trained dynamic test model, and obtain the dynamic bearing capacity;

[0011] S4. Perform data processing and correlation analysis on the collected soil strength values, groundwater level height and temperature change to generate a first correction coefficient for correcting the static bearing capacity value and a second correction coefficient for correcting the dynamic bearing capacity value;

[0012] S5. Process the static bearing capacity of the tunnel and the corresponding static load to obtain a static stability coefficient, process the dynamic bearing capacity of the tunnel and the corresponding dynamic load to obtain a dynamic stability coefficient, process the first correction coefficient and the static stability coefficient to generate a corrected static stability coefficient, process the second correction coefficient and the dynamic stability coefficient to generate a corrected dynamic stability coefficient;

[0013] S6. Perform data processing on the corrected static stability coefficient and the dynamic stability coefficient to generate a comprehensive coefficient, and evaluate the damage of the undersea tunnel according to the numerical range of the comprehensive coefficient.

[0014] Furthermore, using the geometric parameters and material properties of the tunnel, a three-dimensional geometric model is established in the finite element analysis, the collected static load is input into the model, and the response of the tunnel under the static load is obtained using the numerical simulation method. The specific process is as follows:

[0015] A three-dimensional tunnel geometry model is established based on the collected tunnel geometry dimensions. Finite element analysis software is used for modeling. The material properties of the tunnel are input into the model, the constitutive relationship of the material is set, and a static load is applied to the model.

[0016] The calculation formula for static load is as follows:

[0017] ;

[0018] in: is the static load, is the self-weight load, is the water pressure; the tunnel's deadweight load is applied by calculating the tunnel's deadweight:

[0019] ;

[0020] in: is the density of the material, is the acceleration due to gravity, is the volume of the tunnel;

[0021] The water pressure is calculated by the following formula:

[0022] ;

[0023] in: is the density of water, For water depth, is the cross-sectional area of ​​water located above the tunnel;

[0024] The tunnel bottom is set as a fixed boundary and the surrounding soil is set as an elastic boundary;

[0025] In the finite element software, set the analysis type to static analysis and input the self-weight load and water pressure;

[0026] Perform the solution to calculate the tunnel's response to static loads;

[0027] Set up multiple monitoring points to obtain the displacement data of each node in the model, and use the average value as the displacement of the tunnel;

[0028] Extract stress distribution, obtain stress at multiple monitoring points, and use the average value as the stress of the tunnel;

[0029] The strain distribution is extracted, the strains of multiple monitoring points are obtained, and their average is used as the strain of the tunnel.

[0030] Furthermore, the collected dynamic loads are input into the model, and the response of the tunnel under earthquake action is obtained using numerical simulation methods. The specific process is as follows:

[0031] Apply dynamic load to the model. The calculation formula of dynamic load is as follows:

[0032] ;

[0033] in, is the dynamic load of the tunnel, is the volume of the tunnel, is the peak acceleration;

[0034] After applying dynamic loads, run a dynamic response analysis to extract the maximum displacement of the monitoring points , maximum stress and maximum strain ;

[0035] The peak acceleration is calculated as follows:

[0036] ;

[0037] in, is the magnitude, is the epicenter distance, , , All are coefficients.

[0038] Furthermore, the static test model and the dynamic test model both adopt a convolutional neural network model, and the convolutional neural network model is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer all have at least two neurons, and all use ReLU as an activation function.

[0039] Furthermore, the collected soil strength values, groundwater level height and temperature change are subjected to data processing and correlation analysis to generate a first correction coefficient for correcting the static bearing capacity value, based on the following formula:

[0040] ;

[0041] in, is the first correction coefficient, is the soil strength value, is the groundwater level, is the temperature change, is the influence coefficient of groundwater level change on static bearing capacity, is the influence coefficient of temperature change on static bearing capacity, , .

[0042] Furthermore, the collected soil strength values, groundwater level height and temperature change are subjected to data processing and correlation analysis to generate a second correction coefficient for correcting the dynamic bearing capacity value, based on the following formula:

[0043] ;

[0044] in, is the second correction coefficient, is the influence coefficient of soil strength on dynamic bearing capacity, is the influence coefficient of groundwater level on dynamic bearing capacity, is the influence coefficient of temperature change on dynamic bearing capacity, , .

[0045] Furthermore, the static bearing capacity of the tunnel and the corresponding static load are processed to obtain the static stability coefficient, and the dynamic bearing capacity of the tunnel and the corresponding dynamic load are processed to obtain the dynamic stability coefficient, according to the following formula:

[0046] ;

[0047] ;

[0048] in, is the static stability coefficient, is the static bearing capacity of the tunnel, is the static load of the tunnel, is the dynamic stability coefficient, is the dynamic bearing capacity of the tunnel.

[0049] Furthermore, the first correction coefficient and the static stability coefficient are processed to generate a corrected static stability coefficient, and the second correction coefficient and the dynamic stability coefficient are processed to generate a corrected dynamic stability coefficient, according to the following formula:

[0050] ;

[0051] ;

[0052] in, is the modified static stability coefficient, is the corrected dynamic stability coefficient.

[0053] Furthermore, the modified static stability coefficient and dynamic stability coefficient are processed to generate a comprehensive coefficient. According to the numerical range of the comprehensive coefficient, the damage of the submarine tunnel is evaluated. The specific process is as follows:

[0054] ;

[0055] in, is the comprehensive coefficient;

[0056] when , it indicates that the tunnel is seriously damaged and needs to be inspected and evaluated immediately to confirm the nature and extent of the damage and ensure safety;

[0057] when , it indicates that the tunnel structure is safe, has no obvious damage, can withstand the current load, and continue to be used normally.

[0058] Due to the modified static stability factor , reflecting the bearing capacity of the tunnel under static load, and the modified dynamic stability coefficient , reflecting the bearing capacity of the tunnel under dynamic load;

[0059] Therefore, the comprehensive coefficient Directly reflects the tunnel's carrying capacity, low A value of The value indicates that the structure is intact.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention can conduct in-depth research on the most unfavorable seismic motion under complex sea conditions by systematically collecting and analyzing seismic motion parameters, fill the gap in the prior art in this field, and provide a scientific basis for the seismic design of submarine immersed tube tunnels; by establishing static and dynamic test models, combined with the bearing capacity labels evaluated by experts, the numerical simulation method is used to obtain the response of the tunnel under static load and the response under dynamic load, so that the collected data can accurately reflect the damage state of the tunnel under the most unfavorable seismic motion; by processing data and performing correlation analysis on environmental factors such as soil strength, groundwater level, and temperature changes, a first correction coefficient for correcting the static bearing capacity value and a second correction coefficient for correcting the dynamic bearing capacity value are generated, and the first correction coefficient and the second correction coefficient are used to correct the static stability coefficient and the dynamic stability coefficient respectively, and the influence of these factors and their interactions on the damage state of the tunnel is fully considered. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0063] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0064] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0065] Example:

[0066] See also Figure 1 , the present invention provides a technical solution:

[0067] A numerical simulation evaluation method for mechanical properties of a submarine tunnel under earthquake action, comprising the following specific steps:

[0068] S1. Collect the geometric dimensions, material properties, static load, dynamic load and environmental impact parameters of the tunnel, the geometric dimensions include tunnel diameter, tunnel length, tunnel wall thickness and shape, the material properties include elastic modulus, density, compressive strength and Poisson's ratio, the static load is provided by the deadweight load of the tunnel and the water pressure, the dynamic load is provided by the mass and peak acceleration of the tunnel, and the environmental impact parameters include soil strength value, groundwater level height and temperature change;

[0069] S2. Using the geometric parameters and material properties of the tunnel, a three-dimensional geometric model is established in the finite element analysis, the collected static load is input into the model, and the response of the tunnel under the static load is obtained by numerical simulation method, including displacement, stress and strain. The collected dynamic load is input into the model, and the response of the tunnel under the earthquake is obtained by numerical simulation method, including maximum displacement, maximum stress and maximum strain;

[0070] S3. Construct a static test model of the tunnel, take the displacement, stress and strain of the tunnel under static load as input, and the corresponding static bearing capacity as label, and have the expert group evaluate the corresponding static bearing capacity, train the static test model of the tunnel, input the newly collected displacement, stress and strain of the tunnel under static load into the trained static test model, obtain the static bearing capacity, construct a dynamic test model of the tunnel, take the maximum displacement, maximum stress and maximum strain of the tunnel under dynamic load as input, and the corresponding dynamic bearing capacity as label, and have the expert group evaluate the corresponding dynamic bearing capacity, train the dynamic test model of the tunnel, input the newly collected maximum displacement, maximum stress and maximum strain of the tunnel under dynamic load into the trained dynamic test model, and obtain the dynamic bearing capacity;

[0071] S4. Perform data processing and correlation analysis on the collected soil strength values, groundwater level height and temperature change to generate a first correction coefficient for correcting the static bearing capacity value and a second correction coefficient for correcting the dynamic bearing capacity value;

[0072] S5. Process the static bearing capacity of the tunnel and the corresponding static load to obtain a static stability coefficient, process the dynamic bearing capacity of the tunnel and the corresponding dynamic load to obtain a dynamic stability coefficient, process the first correction coefficient and the static stability coefficient to generate a corrected static stability coefficient, process the second correction coefficient and the dynamic stability coefficient to generate a corrected dynamic stability coefficient;

[0073] S6. Perform data processing on the corrected static stability coefficient and the dynamic stability coefficient to generate a comprehensive coefficient, and evaluate the damage of the undersea tunnel according to the numerical range of the comprehensive coefficient.

[0074] On the basis of the above embodiment, a three-dimensional geometric model is established in the finite element analysis using the geometric parameters and material properties of the tunnel, the collected static load is input into the model, and the response of the tunnel under the static load is obtained using the numerical simulation method, including displacement, stress and strain. The specific process is as follows:

[0075] A three-dimensional tunnel geometry model is established based on the collected tunnel geometry dimensions (tunnel diameter, length, wall thickness, shape), and the finite element analysis software is used for modeling. The material properties of the tunnel (elastic modulus, compressive strength, Poisson's ratio) are input into the model, the constitutive relationship of the material is set, and a static load is applied to the model.

[0076] The calculation formula for static load is as follows:

[0077] ;

[0078] in: is the static load, is the self-weight load, For water pressure;

[0079] The tunnel's deadweight load is applied by calculating the tunnel's deadweight:

[0080] ;

[0081] in: is the density of the material, is the acceleration due to gravity, is the volume of the tunnel;

[0082] The water pressure is calculated by the following formula:

[0083] ;

[0084] in: is the density of water, For water depth, is the cross-sectional area of ​​water located above the tunnel;

[0085] The tunnel bottom is set as a fixed boundary, and the surrounding soil is set as an elastic boundary, allowing a certain amount of displacement;

[0086] In the finite element software, set the analysis type to static analysis and input the self-weight load and water pressure;

[0087] Perform the solution to calculate the tunnel's response to static loads;

[0088] Set up multiple monitoring points to obtain the displacement data of each node in the model, and use the average value as the displacement of the tunnel;

[0089] Extract stress distribution, obtain stress at multiple monitoring points, and use the average value as the stress of the tunnel;

[0090] The strain distribution is extracted, the strains of multiple monitoring points are obtained, and their average is used as the strain of the tunnel.

[0091] On the basis of the above embodiment, the collected dynamic load is input into the model, and the response of the tunnel under the earthquake is obtained by numerical simulation method. The specific process is as follows:

[0092] Apply dynamic load to the model. The calculation formula of dynamic load is as follows:

[0093] ;

[0094] in, is the dynamic load of the tunnel, is the volume of the tunnel, is the peak acceleration;

[0095] After applying dynamic loads, run a dynamic response analysis to extract the maximum displacement of the monitoring points , maximum stress and maximum strain ;

[0096] The peak acceleration is calculated as follows:

[0097] ;

[0098] in, is the magnitude, is the epicenter distance, , , All are coefficients.

[0099] in, , , It is the coefficient obtained through regression analysis of historical earthquake data. The specific process is as follows:

[0100] Assumptions and and The relationship between is linear;

[0101] The coefficients are estimated by minimizing the sum of squared residuals between observed and predicted values. , , ;

[0102] Calculate the standard error and p-value of each coefficient to assess its significance;

[0103] Determine the goodness of fit of the model to evaluate the overall performance of the model;

[0104] Use part of the data for model fitting and another part for validation to reduce overfitting;

[0105] Analyze the residuals from the model predictions to ensure that they are normally distributed and have no systematic biases;

[0106] Once the model parameters are determined, they can be used to predict the peak acceleration at a specific location. .

[0107] On the basis of the above embodiments, the static test model and the dynamic test model both adopt a convolutional neural network model, and the convolutional neural network model is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer all have at least two neurons, and all use ReLU as an activation function.

[0108] In this embodiment, for the static test model, the input features of the deep neural network of the multilayer perceptron include: displacement, stress and strain of the tunnel, three features;

[0109] For the dynamic test model, the input features of the deep neural network of the multilayer perceptron include three features: maximum displacement, maximum stress and maximum strain of the tunnel.

[0110] The structure of a deep neural network with a multilayer perceptron is:

[0111] Input layer: receives input of 3 features;

[0112] The first hidden layer has 128 neurons and uses ReLU as the activation function.

[0113] The second hidden layer has 256 neurons and also uses the ReLU activation function.

[0114] The third hidden layer has 128 neurons and uses the ReLU activation function.

[0115] Output layer: has a single neuron, either static or dynamic capacity.

[0116] The process of training a static test model is as follows:

[0117] Based on the historical displacement, stress and strain of the tunnel, the expert group will assess the corresponding static bearing capacity;

[0118] The displacement, stress and strain of the tunnel are used as input, and the corresponding static bearing capacity is used as the output label for training. The mean square error is used as the loss function. When the mean square error is When the range is within the range, the training of the static test model of the tunnel is completed.

[0119] The process of training the dynamic test model is as follows:

[0120] Based on the historical maximum displacement, maximum stress and maximum strain of the tunnel, the expert group will assess the corresponding dynamic bearing capacity;

[0121] The maximum displacement, maximum stress and maximum strain of the tunnel are used as input, and the corresponding dynamic bearing capacity is used as the output label for training. The mean square error is used as the loss function. When the mean square error is When within the range, the training of the dynamic test model of the tunnel is completed.

[0122] On the basis of the above embodiment, the collected soil strength values, groundwater level height and temperature change are subjected to data processing and correlation analysis to generate a first correction coefficient for correcting the static bearing capacity value, based on the following formula:

[0123] ;

[0124] in, is the first correction coefficient, is the soil strength value, is the groundwater level, is the temperature change, is the influence coefficient of groundwater level change on static bearing capacity, is the influence coefficient of temperature change on static bearing capacity.

[0125] First, soil strength Typically exhibits a nonlinear response to groundwater level changes, using an exponential function This nonlinear effect can be better captured, reflecting the change in soil strength as the water level rises or falls. rapid changes.

[0126] Second, the formula converts soil strength and groundwater level , Temperature change The influence relationship between them is regarded as an independent multiplication form, emphasizing the independent effect of each factor on the bearing capacity. is the basic strength, and and The effects of modify this base value.

[0127] Third, use The form of can approximately express the effect of temperature change on bearing capacity. Usually, the effect of temperature on soil properties can be approximately linearized within a range.

[0128] In summary, the functional relationship among soil strength value, groundwater level, temperature change and the first correction coefficient can be expressed through the above functional form.

[0129] Under saturated conditions, changes in groundwater levels directly affect effective stress. Rising water levels will increase pore water pressure, significantly reduce effective stress, and thus have a greater impact on soil strength. Sensitive soils such as clay can have large strength changes under wet conditions, especially when the water level changes. The absolute value of will be larger.

[0130] Temperature changes usually affect soil strength indirectly, through changes in soil moisture content, dryness, and physical and chemical properties. Therefore, while temperature changes will also affect strength, their effect may be smaller than the direct effect of water levels.

[0131] Many empirical studies in soil mechanics have shown that changes in groundwater levels often have a more significant effect on bearing capacity. Some studies have shown that rising groundwater levels can lead to a reduction in bearing capacity of 20%-50% or more, while the effect of temperature changes is usually in the range of 5%-15%.

[0132] Therefore, the influence coefficient of groundwater level change on static bearing capacity is Greater than the effect of temperature change on static bearing capacity ,Right now , without the influence of other parameters, .

[0133] On the basis of the above embodiment, the collected soil strength values, groundwater level height and temperature change are subjected to data processing and correlation analysis to generate a second correction coefficient for correcting the dynamic bearing capacity value, according to the following formula:

[0134] ;

[0135] in, is the second correction coefficient, is the influence coefficient of soil strength on dynamic bearing capacity, is the influence coefficient of groundwater level on dynamic bearing capacity, is the influence coefficient of temperature change on dynamic bearing capacity.

[0136] First, As the direct influence of soil strength on dynamic bearing capacity, the linear form is adopted because soil strength is usually positively correlated with bearing capacity, through the coefficient , the effect of soil strength on dynamic bearing capacity can be quantified, which is convenient for analysis and calculation.

[0137] Second, use and The effects of groundwater level and temperature are dealt with separately. Changes in groundwater level often produce significant nonlinear effects, especially under saturated conditions, so an exponential form is used to capture this effect. Temperature changes fluctuate periodically, and a sine function can be used to express its effect on bearing capacity within a certain range.

[0138] Third, the formula , and The influence coefficient can be adjusted according to different soil types and environmental conditions, making the model more applicable in different situations. By optimizing these parameters, the dynamic bearing capacity of the soil under specific conditions can be more accurately reflected.

[0139] In summary, the functional relationship among soil strength value, groundwater level, temperature change and the second correction coefficient can be expressed through the above functional form.

[0140] Since soil strength directly determines the soil's bearing capacity, stronger soil can support greater loads. It is usually larger because soil strength is one of the main factors affecting dynamic bearing capacity.

[0141] The groundwater level affects the effective stress by changing the pore water pressure. Although the effect of water level changes on effective stress can be significant, this effect is indirect. It may also be larger, but is usually not as large as the soil strength obvious.

[0142] Most soil mechanics studies have shown that soil strength is an important determinant of bearing capacity, usually in dynamic bearing capacity models. The absolute value of For example, in actual tests, changes in soil strength often directly lead to significant changes in bearing capacity, while the impact of water level on bearing capacity often requires a certain threshold to become apparent.

[0143] In soil mechanics research, the effect of temperature on soil strength is often considered a secondary effect rather than a primary factor. For example, temperature changes may affect bearing capacity in certain seasons or under extreme conditions, but under most common conditions, they are not as significant as the effects of soil strength and groundwater level. Usually smaller.

[0144] Therefore, the influence coefficient of soil strength on dynamic bearing capacity is Greater than the influence coefficient of groundwater level on dynamic bearing capacity , the influence coefficient of groundwater level on dynamic bearing capacity Greater than the influence coefficient of temperature change on dynamic bearing capacity ,Right now , without the influence of other parameters, .

[0145] On the basis of the above embodiment, the static bearing capacity of the tunnel and the corresponding static load are processed to obtain the static stability coefficient, and the dynamic bearing capacity of the tunnel and the corresponding maximum dynamic load are processed to obtain the dynamic stability coefficient, according to the following formula:

[0146] ;

[0147] ;

[0148] in, is the static stability coefficient, is the static bearing capacity of the tunnel, is the static load of the tunnel, is the dynamic stability coefficient, is the dynamic bearing capacity of the tunnel.

[0149] On the basis of the above embodiment, the first correction coefficient and the static stability coefficient are processed to generate a corrected static stability coefficient, and the second correction coefficient and the dynamic stability coefficient are processed to generate a corrected dynamic stability coefficient, according to the following formula:

[0150] ;

[0151] ;

[0152] in, is the modified static stability coefficient, is the corrected dynamic stability coefficient.

[0153] On the basis of the above embodiment, the modified static stability coefficient and dynamic stability coefficient are processed to generate a comprehensive coefficient. According to the numerical range of the comprehensive coefficient, the damage of the submarine tunnel is evaluated. The specific process is as follows:

[0154] ;

[0155] in, is the comprehensive coefficient.

[0156] when , it indicates that the tunnel is seriously damaged and needs to be inspected and evaluated immediately to confirm the nature and extent of the damage and ensure safety;

[0157] when , it indicates that the tunnel structure is safe, has no obvious damage, can withstand the current load, and can continue to be used normally.

[0158] In engineering, It is usually a benchmark value, indicating that the bearing capacity of the structure can just meet the existing load requirements. It means that the modified static and dynamic stability factors of the tunnel are just sufficient to support the current usage and are at a critical point.

[0159] Due to the modified static stability factor , reflecting the bearing capacity of the tunnel under static load, and the modified dynamic stability coefficient , reflects the bearing capacity of the tunnel under dynamic load. Therefore, the comprehensive coefficient Directly reflects the bearing capacity of the tunnel, weak bearing capacity (lower Values) mean that there is damage to the structure, such as cracks and settlement, while strong bearing capacity (higher value) indicates that the structure is intact.

[0160] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0161] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0163] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A numerical simulation evaluation method for mechanical properties of a submarine tunnel under earthquake action, characterized in that: The specific steps include: S1. Collect the geometric dimensions, material properties, static load, dynamic load and environmental impact parameters of the tunnel, the geometric dimensions include tunnel diameter, tunnel length, tunnel wall thickness and shape, the material properties include elastic modulus, density, compressive strength and Poisson's ratio, and the environmental impact parameters include soil strength value, groundwater level height and temperature change; S2. Using the geometric parameters and material properties of the tunnel, a three-dimensional geometric model is established in the finite element analysis, the collected static load is input into the model, and the response of the tunnel under the static load is obtained by numerical simulation method, including displacement, stress and strain. The collected dynamic load is input into the model, and the response of the tunnel under the earthquake is obtained by numerical simulation method, including maximum displacement, maximum stress and maximum strain; S3. Construct a static test model of the tunnel, take the displacement, stress and strain of the tunnel under static load as input, and the corresponding static bearing capacity as label, and have the expert group evaluate the corresponding static bearing capacity, train the static test model of the tunnel, input the newly collected displacement, stress and strain of the tunnel under static load into the trained static test model, obtain the static bearing capacity, construct a dynamic test model of the tunnel, take the maximum displacement, maximum stress and maximum strain of the tunnel under dynamic load as input, and the corresponding dynamic bearing capacity as label, and have the expert group evaluate the corresponding dynamic bearing capacity, train the dynamic test model of the tunnel, input the newly collected maximum displacement, maximum stress and maximum strain of the tunnel under dynamic load into the trained dynamic test model, and obtain the dynamic bearing capacity; S4. Perform data processing and correlation analysis on the collected soil strength values, groundwater level height and temperature change to generate a first correction coefficient for correcting the static bearing capacity value and a second correction coefficient for correcting the dynamic bearing capacity value; S5. Process the static bearing capacity of the tunnel and the corresponding static load to obtain a static stability coefficient, process the dynamic bearing capacity of the tunnel and the corresponding dynamic load to obtain a dynamic stability coefficient, process the first correction coefficient and the static stability coefficient to generate a corrected static stability coefficient, process the second correction coefficient and the dynamic stability coefficient to generate a corrected dynamic stability coefficient; S6. Perform data processing on the corrected static stability coefficient and the dynamic stability coefficient to generate a comprehensive coefficient, and evaluate the damage of the undersea tunnel according to the numerical range of the comprehensive coefficient.

2. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 1 is characterized by: Using the geometric parameters and material properties of the tunnel, a three-dimensional geometric model is established in the finite element analysis. The collected static load is input into the model, and the response of the tunnel under the static load is obtained using the numerical simulation method. The specific process is as follows: A three-dimensional tunnel geometry model is established based on the collected tunnel geometry dimensions. Finite element analysis software is used for modeling. The material properties of the tunnel are input into the model, the constitutive relationship of the material is set, and a static load is applied to the model. The calculation formula for static load is as follows: ； in: is the static load, is the self-weight load, For water pressure; The tunnel's deadweight load is applied by calculating the tunnel's deadweight: ； in: is the density of the material, is the acceleration due to gravity, is the volume of the tunnel; The water pressure is calculated by the following formula: ； in: is the density of water, For water depth, is the cross-sectional area of ​​water located above the tunnel; The tunnel bottom is set as a fixed boundary and the surrounding soil is set as an elastic boundary; In the finite element software, set the analysis type to static analysis and input the self-weight load and water pressure; Perform the solution to calculate the tunnel's response to static loads; Set up multiple monitoring points to obtain the displacement data of each node in the model, and use the average value as the displacement of the tunnel; Extract stress distribution, obtain stress at multiple monitoring points, and use the average value as the stress of the tunnel; The strain distribution is extracted, the strains of multiple monitoring points are obtained, and their average is used as the strain of the tunnel.

3. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 2 is characterized by: The collected dynamic loads are input into the model, and the numerical simulation method is used to obtain the response of the tunnel under earthquake action. The specific process is as follows: Apply dynamic load to the model. The calculation formula of dynamic load is as follows: ； in, is the dynamic load of the tunnel, is the volume of the tunnel, is the peak acceleration; after applying the dynamic load, run the dynamic response analysis and extract the maximum displacement of the monitoring point , maximum stress and maximum strain ; The peak acceleration is calculated as follows: ； in, is the magnitude, is the epicenter distance, , , All are coefficients.

4. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 3 is characterized by: The static test model and the dynamic test model both adopt a convolutional neural network model, and the convolutional neural network model is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer all have at least two neurons, and all use ReLU as an activation function.

5. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 4 is characterized by: The collected soil strength values, groundwater level height and temperature change are processed and correlated to generate the first correction coefficient for correcting the static bearing capacity value. The formula is as follows: ； in, is the first correction coefficient, is the soil strength value, is the groundwater level, is the temperature change, is the influence coefficient of groundwater level change on static bearing capacity, is the influence coefficient of temperature change on static bearing capacity, , .

6. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 5 is characterized by: The collected soil strength values, groundwater level and temperature changes are processed and correlated to generate a second correction factor for correcting the dynamic bearing capacity value. The formula is as follows: ； in, is the second correction coefficient, is the influence coefficient of soil strength on dynamic bearing capacity, is the influence coefficient of groundwater level on dynamic bearing capacity, is the influence coefficient of temperature change on dynamic bearing capacity, , .

7. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 6 is characterized by: The static bearing capacity and the corresponding static load of the tunnel are processed to obtain the static stability coefficient, and the dynamic bearing capacity and the corresponding dynamic load of the tunnel are processed to obtain the dynamic stability coefficient. The formula is as follows: ； ； in, is the static stability coefficient, is the static bearing capacity of the tunnel, is the dynamic stability coefficient, is the dynamic bearing capacity of the tunnel.

8. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 7 is characterized by: The first correction coefficient and the static stability coefficient are processed to generate a corrected static stability coefficient, and the second correction coefficient and the dynamic stability coefficient are processed to generate a corrected dynamic stability coefficient, according to the following formula: ； ； in, is the modified static stability coefficient, is the corrected dynamic stability coefficient.

9. The method for numerical simulation and evaluation of mechanical properties of submarine tunnels under earthquake action according to claim 8 is characterized by: The modified static stability coefficient and dynamic stability coefficient are processed to generate a comprehensive coefficient. According to the numerical range of the comprehensive coefficient, the damage of the submarine tunnel is evaluated. The specific process is as follows: ； in, is the comprehensive coefficient; when , it indicates that the tunnel is seriously damaged and needs to be inspected and evaluated immediately to confirm the nature and extent of the damage and ensure safety; when , it indicates that the tunnel structure is safe, has no obvious damage, can withstand the current load, and continue to be used normally; Corrected static stability factor , reflecting the bearing capacity of the tunnel under static load, and the modified dynamic stability coefficient , reflecting the bearing capacity of the tunnel under dynamic load; Therefore, the comprehensive coefficient Directly reflects the bearing capacity of the tunnel, low A value of The value indicates that the structure is intact.

Images