Highway tunnel digital twin emergency evacuation method and system

Abstract

The invention provides a digital twin emergency evacuation method and system for a highway tunnel. The method comprises the steps that S1, multi-source fire data of multiple positions in the tunnel are collected at fixed time intervals; s2, constructing a temperature field model, and calculating the thermal strain of each position based on the multi-source fire data; s3, constructing a structural field model, generating local stress of each position according to the thermal strain, then correcting temperature field model parameters by using the local stress, and then repeating the steps S2 to S3 until the local stress does not change any more; s4, constructing a smoke flow field model, calculating the fire source power of each position according to the multi-source fire data, and calculating the smoke flow diffusion rate of each position by using the smoke flow field model according to the fire source power; and S5, generating an optimal personnel evacuation scheme according to the smoke flow diffusion rate and the local stress of each position. According to the method, the problems that in the prior art, prediction of the fire development situation by using a static model is inaccurate, and accurate support cannot be provided for emergency decision making are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency response in highway tunnels, and in particular to a digital twin emergency evacuation method and system for highway tunnels. Background Art

[0002] Traditional highway tunnel emergency evacuation simulation systems are primarily used to simulate emergency response processes for emergencies such as fires and traffic accidents. These systems typically rely on static 3D models and pre-configured emergency plans to help managers develop evacuation plans, optimize emergency resource allocation, and improve tunnel operation safety.

[0003] However, traditional highway tunnel emergency simulation systems rely on three-dimensional models of highway tunnels with fixed parameters. These models are usually static and cannot update model parameters in real time when a fire occurs. As a result, the simulation results are disconnected from the actual disaster situation and cannot reflect the dynamic multi-physics field coupling effects in emergencies such as fires in real time. This leads to inaccurate predictions of smoke spread and an inability to provide accurate support for emergency decision-making. Therefore, the response plan is dynamically adjusted according to the actual situation at the accident site, which greatly reduces the applicability and effectiveness of the plan. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention provides a digital twin emergency evacuation method and system for highway tunnels, which solves the problem in the existing technology that the use of static models to predict the spread of fire in a fire is inaccurate and cannot provide accurate support for emergency decision-making.

[0005] According to an embodiment of the present invention, a highway tunnel digital twin emergency evacuation method includes:

[0006] S1: Collect multi-source fire data at multiple locations in the tunnel at fixed time intervals;

[0007] S2: Construct a temperature field model and calculate the thermal strain at each location based on multi-source fire data;

[0008] S3: Build a structural field model and generate local stress at each location based on thermal strain. Then use the local stress to correct the temperature field model parameters. Then repeat steps S2-S3 until the local stress no longer changes.

[0009] S4: Construct a smoke flow field model, calculate the fire source power at each location based on the multi-source fire data, and use the smoke flow field model to calculate the smoke diffusion rate at each location based on the fire source power;

[0010] S5: Generate an optimal evacuation plan based on the smoke diffusion rate and local stress at each location, and then perform emergency evacuation according to the optimal evacuation plan.

[0011] Preferably, the multi-source fire data includes the current temperature, concrete elastic modulus, carbon dioxide concentration, smoke concentration, fire source type and convection coefficient of each location.

[0012] Preferably, the method of constructing a temperature field model and calculating the thermal strain at each location based on multi-source fire data includes:

[0013] Calculate the temperature difference between the current temperature of multiple points at the current location and the temperature collected at the previous moment, and obtain a discrete temperature field based on the temperature difference;

[0014] Construct a temperature field model and calculate the equivalent thermal conductivity based on the current temperature;

[0015] The discrete temperature field, equivalent thermal conductivity and local stress at the previous moment are imported into the temperature field model, and the temperature field model is solved using the finite volume method to obtain the thermal strain corresponding to the current position.

[0016] Preferably, the formula of the temperature field model is as follows:

[0017]

[0018] The structural field model is as follows:

[0019] σ struct =E·ε thernal

[0020] Where T is the current temperature, t is the time, ε thernal is the thermal strain, T0 is the initial temperature (293K), E is the elastic modulus of concrete, k is the equivalent thermal conductivity, β is the thermal-mechanical coupling coefficient, α c is the coefficient of thermal expansion.

[0021] Preferably, the boundary conditions of the temperature field include the fire source boundary temperature and the wall boundary temperature. The fire source boundary temperature is directly determined according to the fire source type, and the wall boundary temperature is determined according to the convection coefficient, current temperature and discrete temperature field at the current position.

[0022] Preferably, when the local stress exceeds a critical value, the critical value is used as the local stress and the temperature field model parameters are corrected, while the boundary conditions of the smoke field model are updated.

[0023] Preferably, the optimal personnel evacuation plan includes an evacuation route and fan control instructions;

[0024] Methods for generating optimal evacuation plans based on smoke diffusion rate and local stress at each location include:

[0025] Fit the smoke diffusion path according to the smoke diffusion rate at each location;

[0026] Based on the smoke diffusion path, temperature changes, and local stress at each location, the LSTM model is used to predict the fire spread path, and a path planning algorithm is used to generate an evacuation route.

[0027] Generate fan control instructions based on the smoke diffusion path.

[0028] On the other hand, according to an embodiment of the present invention, a highway tunnel digital twin emergency evacuation system is also provided. The system uses the above-mentioned highway tunnel digital twin emergency evacuation method, including:

[0029] A collection module, the collection module is used to collect multi-source fire data at multiple locations in the tunnel;

[0030] A model building module, wherein the model building module is used to build a temperature field model, a structural stress model and a smoke flow field model;

[0031] a deduction module, the deduction module being configured to calculate the thermal strain at each location based on the multi-source fire data using a temperature field model, generate local stress at each location based on the thermal strain, and then use the local stress to correct the temperature field model parameters; and calculate the fire source power at each location based on the multi-source fire data, and calculate the smoke diffusion rate at each location based on the fire source power using a smoke flow field model;

[0032] A decision module is used to generate an optimal personnel evacuation plan based on the smoke diffusion rate and local stress at each location, and then perform emergency evacuation according to the optimal personnel evacuation plan.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention dynamically corrects the parameters of the temperature field model and the structural field model through thermodynamic coupling between the temperature field model and the structural field model, so that they can accurately simulate the temperature and structural changes in the highway tunnel. The smoke flow field model is then used to dynamically calculate the smoke diffusion rate, providing accurate support for personnel emergency evacuation decisions. The fire development trend is then predicted based on the smoke diffusion rate, temperature and local stress, and the optimal personnel evacuation strategy and electromechanical facility linkage control instructions are generated. The digital twin model formed by multiple coupling models is used to correct the parameters between the coupling models, and data is collected at a fixed time to generate the corresponding tunnel personnel evacuation plan, providing a highly timely and safe emergency response strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a highway tunnel emergency evacuation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The technical solutions of the present invention are further described below with reference to the accompanying drawings and embodiments.

[0037] like Figure 1 As shown, an embodiment of the present invention proposes a highway tunnel digital twin emergency evacuation method, including:

[0038] S1: Collect multi-source fire data at multiple locations in the tunnel at fixed time intervals (e.g., once every second) to improve data timeliness;

[0039] The multi-source fire data includes the current temperature, concrete elastic modulus, carbon dioxide concentration, smoke concentration, fire source type, and convection coefficient at each location.

[0040] The current temperature, carbon dioxide concentration, and smoke concentration can be measured using the corresponding sensors. The concrete elastic modulus is a fixed property of the concrete wall of the highway tunnel, generally 32GPa. The fire source type is captured by the camera and then the image recognition model is used to identify the fire source type, such as gasoline burning, cardboard burning, etc. The convection coefficient is the convection coefficient of natural air convection, 25W / (m 2 K),

[0041] S2: Construct a temperature field model and calculate the thermal strain at each location based on multi-source fire data;

[0042] S3: Build a structural field model and generate local stress at each location based on thermal strain. Then use the local stress to correct the temperature field model parameters. Then repeat steps S2-S3 until the local stress no longer changes.

[0043] First, calculate the temperature difference between the current temperature of multiple points at the current location and the temperature collected at the previous moment, and obtain the discrete temperature field T according to the temperature difference. n , where n is the discrete point number;

[0044] Then, a temperature field model is constructed. The distribution of the temperature field is described by an improved heat conduction equation, and the reverse feedback term of the structural stress field is introduced:

[0045]

[0046] Where: k is the equivalent thermal conductivity, which changes with temperature: k = k0 (1 + αT), k0 is the thermal conductivity at room temperature (1.8 W / (m·K) for concrete), α is the temperature coefficient, which is 4.7×10 -4 K -1 , β is the thermomechanical coupling coefficient, which represents the reverse feedback strength of the structural stress on the temperature field. It is calibrated by the thermomechanical coupling experiment, β = 0.67 (95% confidence interval [0.67, 0.71]), T0 is the initial temperature (293K), T is the current temperature, and t is the time.

[0047] In addition, the boundary conditions of the temperature field model are as follows:

[0048] Fire source boundary temperature: This paper takes the gasoline combustion flame temperature as an example, T fire =1473K.

[0049] Wall boundary temperature:

[0050] Finally, the finite volume method is used to solve the temperature field model to obtain the thermal strain ε corresponding to the current position thernal .

[0051] The structural field model is as follows:

[0052] σ struct =E·ε thernal

[0053] σ struct For local stress, when the temperature field model is used for the first time, the local stress calculated last time is used, and then the structural field model is used to update it to obtain new local stress. The temperature field model uses the new local stress to recalculate the thermal strain, and steps S2-S3 are repeated until the local stress no longer changes.

[0054] When the local stress exceeds the critical value (0.3 MPa), the location is marked as "structural failure", and the critical value is used as the local stress and the temperature field model parameters are corrected.

[0055] The temperature at each location can be calculated based on the temperature field, and the fire in the highway tunnel can be graded by combining the temperatures at various locations:

[0056] Level I: local small fire (temperature <200℃); Level II: medium-scale fire (200℃≤temperature<500℃); Level III: large-scale fire (500℃≤temperature<800℃); Level IV: extreme fire (temperature ≥800℃).

[0057] S4: Construct a smoke flow field model, calculate the fire source power at each location based on the multi-source fire data, and use the smoke flow field model to calculate the smoke diffusion rate at each location based on the fire source power;

[0058] The smoke flow field model uses a modified turbulence model:

[0059]

[0060] Where Q is the smoke diffusion rate, is the diffusion coefficient, γ is the temperature gradient influence factor, is the temperature gradient, ▽ 2Q is the Laplace operator of smoke concentration, which represents the second-order spatial derivative of smoke concentration and describes the diffusion process of smoke (diffusion from high concentration to low concentration area).

[0061] Enhanced heat release: The greater the fire source power, the more intense the combustion reaction, and the heat released increases linearly; Thermal buoyancy effect: The density of high-temperature flue gas is lower than that of air, which generates strong thermal buoyancy, driving the flue gas to rise and diffuse rapidly; Enhanced turbulence: High-power fire sources cause local airflow speeds to increase and turbulence intensity, further accelerating the mixing and diffusion of flue gas. Therefore, the nonlinear superposition of thermal buoyancy and turbulence causes the smoke diffusion rate to increase exponentially with the fire source power.

[0062] Therefore, the above formula can be simplified to:

[0063] Q=Q0·e ηP

[0064] Among them, Q0 is the initial smoke concentration, η is the calibration coefficient, which is generally taken as 0.05, and P is the fire source power, which can be reversed according to the carbon dioxide concentration.

[0065] When the local stress exceeds the critical value (0.3 MPa), the location is marked as "structural failure", indicating that the wall at that location has collapsed. Therefore, the boundary conditions of the smoke field model need to be modified. If the local stress does not exceed the critical value, the boundary conditions are not modified.

[0066] S5: Generate an optimal evacuation plan based on the smoke diffusion rate and local stress at each location, and then perform emergency evacuation according to the optimal evacuation plan.

[0067] Based on the smoke diffusion rate at each location, the smoke diffusion path in the highway tunnel can be fitted. The temperature change at each location can be calculated based on the temperature field model to determine the fire level of the highway tunnel. At the same time, based on the local stress, it can be determined which areas have collapsed and are inaccessible. In this way, the safe area in the highway tunnel can be determined. The LSTM model is then used to predict the fire spread path, and the path planning algorithm is used to generate a safer evacuation path to guide the affected people to evacuate. In this way, the digital twin model formed by multiple coupled models is used to correct the parameters between the coupled models, and data is collected at a fixed time to generate the corresponding emergency evacuation plan, providing a timely and safe emergency response strategy.

[0068] In addition, according to the smoke diffusion path, the fans in the highway tunnel are turned on at the same time. For example, if P is increased from level II (20MW) to level III (50MW), the system calculates Q = Q0·e 0.05×50 ≈12.2Q0, automatically increase the fan power to 80% to suppress smoke diffusion, thereby creating more safety areas.

[0069] On the other hand, an embodiment of the present invention further provides a highway tunnel digital twin emergency evacuation system, which uses the above-mentioned highway tunnel digital twin emergency evacuation method, including:

[0070] A collection module, which is used to collect multi-source fire data at multiple locations in the tunnel;

[0071] Model building module, the model building module is used to build temperature field model, structural stress model and smoke flow field model;

[0072] A deduction module is used to calculate the thermal strain at each location based on multi-source fire data using a temperature field model, generate local stress at each location based on the thermal strain, and then use the local stress to correct the temperature field model parameters. The module also calculates the fire source power at each location based on the multi-source fire data and calculates the smoke diffusion rate at each location based on the fire source power using a smoke flow field model.

[0073] The decision module is used to generate the optimal personnel evacuation plan according to the smoke diffusion rate and local stress at each location, and then perform emergency evacuation according to the optimal personnel evacuation plan.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the purpose and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A digital twin emergency evacuation method for a highway tunnel, characterized by: include: S1: Collect multi-source fire data at multiple locations in the tunnel at fixed time intervals; S2: Construct a temperature field model and calculate the thermal strain at each location based on multi-source fire data; S3: Build a structural field model and generate local stress at each location based on thermal strain. Then use the local stress to correct the temperature field model parameters. Then repeat steps S2-S3 until the local stress no longer changes. S4: Construct a smoke flow field model, calculate the fire source power at each location based on the multi-source fire data, and use the smoke flow field model to calculate the smoke diffusion rate at each location based on the fire source power; S5: Generate an optimal evacuation plan based on the smoke diffusion rate and local stress at each location, and then perform emergency evacuation according to the optimal evacuation plan.

2. A highway tunnel digital twin emergency evacuation method according to claim 1, characterized in that: The multi-source fire data includes the current temperature, concrete elastic modulus, carbon dioxide concentration, smoke concentration, fire source type and convection coefficient of each location.

3. A highway tunnel digital twin emergency evacuation method according to claim 2, characterized in that: Methods for constructing a temperature field model and calculating thermal strain at each location based on multi-source fire data include: Calculate the temperature difference between the current temperature of multiple points at the current location and the temperature collected at the previous moment, and obtain a discrete temperature field based on the temperature difference; Construct a temperature field model and calculate the equivalent thermal conductivity based on the current temperature; The discrete temperature field, equivalent thermal conductivity and local stress at the previous moment are imported into the temperature field model, and the temperature field model is solved using the finite volume method to obtain the thermal strain corresponding to the current position.

4. A highway tunnel digital twin emergency evacuation method according to claim 3, characterized in that: The formula of the temperature field model is as follows: The structural field model is as follows: s struct =E·e thernal Where T is the current temperature, t is the time, ε thernal is the thermal strain, T0 is the initial temperature (293K), E is the elastic modulus of concrete, k is the equivalent thermal conductivity, β is the thermal-mechanical coupling coefficient, α c is the coefficient of thermal expansion.

5. A highway tunnel digital twin emergency evacuation method according to claim 4, characterized in that: The boundary conditions of the temperature field include the fire source boundary temperature and the wall boundary temperature. The fire source boundary temperature is directly determined according to the fire source type, and the wall boundary temperature is determined according to the convection coefficient, current temperature and discrete temperature field at the current position.

6. The highway tunnel digital twin emergency evacuation method according to claim 1, characterized in that: When the local stress exceeds the critical value, the critical value is used as the local stress and the temperature field model parameters are modified, and the boundary conditions of the smoke field model are updated at the same time.

7. The highway tunnel digital twin emergency evacuation method according to claim 1, characterized in that: The optimal personnel evacuation plan includes an evacuation route and fan control instructions; Methods for generating optimal evacuation plans based on smoke diffusion rate and local stress at each location include: Fit the smoke diffusion path according to the smoke diffusion rate at each location; Based on the smoke diffusion path, temperature changes, and local stress at each location, the LSTM model is used to predict the fire spread path, and a path planning algorithm is used to generate an evacuation route. Generate fan control instructions based on the smoke diffusion path.

8. A highway tunnel digital twin emergency evacuation system, characterized by: The system uses a highway tunnel digital twin emergency evacuation method according to any one of claims 1 to 7, comprising: A collection module, the collection module is used to collect multi-source fire data at multiple locations in the tunnel; A model building module, wherein the model building module is used to build a temperature field model, a structural stress model and a smoke flow field model; a deduction module, the deduction module being configured to calculate the thermal strain at each location based on the multi-source fire data using a temperature field model, generate local stress at each location based on the thermal strain, and then use the local stress to correct the temperature field model parameters; and calculate the fire source power at each location based on the multi-source fire data, and calculate the smoke diffusion rate at each location based on the fire source power using a smoke flow field model; A decision module is used to generate an optimal personnel evacuation plan based on the smoke diffusion rate and local stress at each location, and then perform emergency evacuation according to the optimal personnel evacuation plan.

Images