Fire emergency simulation method and system based on scene digital twinning

Abstract

The invention discloses a fire emergency simulation method and system based on scene digital twinning, and the method comprises the steps: obtaining topographic data, raster image data, vector data, oblique photography data, point cloud data and BIM data required by emergency scene simulation, and generating a three-dimensional model of an emergency scene through an unreal engine; setting fire information when a fire occurs, setting a fire spreading simulation model, a building collapse simulation model and a personnel behavior simulation model, and performing linkage with the three-dimensional model of the emergency scene so as to perform analog simulation on the fire condition occurring in the emergency scene; and various fire conditions are simulated by adjusting the fire information.

Description

Technical Field

[0001] The present invention belongs to the technical field of emergency scene simulation, and more specifically, relates to a fire emergency simulation method and system based on scene digital twin. Background Art

[0002] With the rapid development of modern society, various emergencies and emergency situations occur frequently, posing a serious threat to public safety and social stability. Traditional emergency scene simulation methods have problems such as low fidelity and poor interactivity, which are difficult to meet the needs of modern emergency management. Therefore, it is of great significance to develop a fire emergency simulation method based on scene digital twins. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a fire emergency simulation method based on scene digital twin, which is used for emergency scene simulation when a fire occurs, comprising:

[0004] Obtain terrain data, raster image data, vector data, oblique photography data, point cloud data, and BIM data required for emergency scenario simulation, and generate a 3D model of the emergency scenario through the Unreal Engine;

[0005] Set fire information when a fire occurs, and set up fire spread simulation models, building collapse simulation models and personnel behavior simulation models, and link them with the three-dimensional model of the emergency scene to simulate the fire situation in the emergency scene;

[0006] Various fire situations are simulated by adjusting the fire information.

[0007] Furthermore, the fire spread simulation model includes:

[0008]

[0009] Wherein, α is the first adjustment factor of fire spread, W(x, y, t) is the wind speed at position (x, y) at time t, T(x, y, t) is the temperature at position (x, y) at time t, β is the second adjustment factor of fire spread, F(x, y) is the fuel density at position (x, y), T0 is the critical combustion temperature, γ is the third adjustment factor of fire spread, σ is the fourth adjustment factor of fire spread, τ is the current time, δ is the fifth adjustment factor of fire spread, E c is the threshold of energy required for fire spread, A1 is the first adjustment factor of time, ω is the second adjustment factor of time, θ is the third adjustment factor of time, A2 is the fourth adjustment factor of time, is a standard normal distribution with mean 0 and variance 1.

[0010] Furthermore, the building collapse simulation model includes:

[0011]

[0012] Among them, P f (x, y, z, t) is the building collapse index at the building position (x, y, z) at time t, λ is the adjustment factor of building collapse simulation, S0(x, y, z) is the initial stress distribution at the building position (x, y, z), S(x, y, z, τ) is the stress distribution at the building position (x, y, z) at time t, G(x, y, z, τ) is the structural resistance at the building position (x, y, z) at time τ, τ f is the fatigue limit time of the building material, T(x, y, z, τ) is the temperature at the location (x, y, z) of the building at time τ, and T c The high temperature limit of building materials;

[0013] When the building collapse index exceeds a preset collapse threshold, the building collapses.

[0014] Furthermore, the personnel behavior simulation model includes:

[0015]

[0016] Among them, x i (t) is the position vector of the i-th person in the emergency scene at time t, κ is the adjustment factor of the person's behavior, V0 is the maximum value of heat in the emergency scene, σ′ is the diffusion speed of heat, and x s ′(t) is the distance between the ith person and the s′th fire source in the emergency scene at time t, η is the adjustment factor of the reaction time, τ r The reaction time for personnel to get away from the fire source.

[0017] Furthermore, the fitting of all adjustment factors and weights is completed through the gradient descent method.

[0018] Furthermore, it also includes: adding physical simulation through Unreal Engine, wherein the physical simulation includes constructing a rigid body, setting collision detection, adding physical effects and force simulation.

[0019] Furthermore, it also includes: the user interacts with the objects in the emergency scene through the input device, and uses collision detection and UI interactive elements to realize the emergency scene control.

[0020] The present invention also proposes a fire emergency simulation system based on scene digital twin, which is used for emergency scene simulation when a fire occurs, including:

[0021] The model generation module is used to obtain the terrain data, raster image data, vector data, oblique photography data, point cloud data and BIM data required for emergency scene simulation, and generate a three-dimensional model of the emergency scene through the Unreal Engine;

[0022] A model module is set up to set fire information when a fire occurs, and to set up a fire spread simulation model, a building collapse simulation model, and a personnel behavior simulation model, and to link them with the three-dimensional model of the emergency scene, so as to simulate the fire situation occurring in the emergency scene;

[0023] The simulation module is used to simulate various fire situations by adjusting the fire information.

[0024] Furthermore, the fire spread simulation model includes:

[0025]

[0026] Wherein, α is the first adjustment factor of fire spread, W(x, y, t) is the wind speed at position (x, y) at time t, T(x, y, t) is the temperature at position (x, y) at time t, β is the second adjustment factor of fire spread, F(x, y) is the fuel density at position (x, y), T0 is the critical combustion temperature, γ is the third adjustment factor of fire spread, σ is the fourth adjustment factor of fire spread, τ is the current time, δ is the fifth adjustment factor of fire spread, E c is the threshold of energy required for fire spread, A1 is the first adjustment factor of time, ω is the second adjustment factor of time, θ is the third adjustment factor of time, A2 is the fourth adjustment factor of time, is a standard normal distribution with mean 0 and variance 1.

[0027] Furthermore, the building collapse simulation model includes:

[0028]

[0029] Among them, P f (x, y, z, t) is the building collapse index at the building position (x, y, z) at time t, λ is the adjustment factor of building collapse simulation, S0(x, y, z) is the initial stress distribution at the building position (x, y, z), S(x, y, z, τ) is the stress distribution at the building position (x, y, z) at time τ, G(x, y, z, τ) is the structural resistance at the building position (x, y, z) at time τ, τ f is the fatigue limit time of the building material, T(x, y, z, τ) is the temperature at the location (x, y, z) of the building at time τ, and T c The high temperature limit of building materials;

[0030] When the building collapse index exceeds a preset collapse threshold, the building collapses.

[0031] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:

[0032] The present invention uses Unreal Engine as the core technology, combined with advanced graphics rendering, physical simulation and artificial intelligence technologies, to achieve realistic simulation and efficient simulation of emergency scenarios. Its advantages are:

[0033] (1) Highly realistic: Using Unreal Engine’s advanced graphics rendering technology, we can build highly realistic emergency scenarios, improving the authenticity and credibility of the simulation effects.

[0034] (2) Strong interactivity: Realize real-time interaction between users and simulation scenarios, improve user participation and operation experience, and enhance the flexibility and adaptability of emergency response.

[0035] (3) Intelligent simulation: Through the application of artificial intelligence systems, the behavior of emergency rescue personnel and disaster victims can be intelligently simulated to improve the accuracy of simulation.

[0036] (4) Data analysis and decision support: Through data analysis of simulation results, we can provide decision support for emergency management, optimize emergency plans, and improve the efficiency and quality of emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;

[0038] Figure 2 is a structural diagram of a system in Embodiment 2 of the present invention;

[0039] Figure 3 This is the overall process of emergency scenario simulation in Example 1 of the present invention;

[0040] Figure 4 This is a flowchart of the emergency scene base construction of Example 1 of the present invention;

[0041] Figure 5 is a physical simulation configuration flow chart of embodiment 1 of the present invention;

[0042] Figure 6 This is a flow chart for implementing the interactive function of Example 1 of the present invention. DETAILED DESCRIPTION

[0043] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0044] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0045] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0046] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0047] The display screen is used to display the user interface of each application.

[0048] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0049] Example 1

[0050] like Figure 1 As shown, an embodiment of the present invention provides a fire emergency simulation method based on scene digital twin, which is used for emergency scene simulation when a fire occurs, including:

[0051] Step 101, obtaining terrain data, raster image data, vector data, oblique photography data, point cloud data and BIM data required for emergency scene simulation, and generating a three-dimensional model of the emergency scene through Unreal Engine;

[0052] Specifically, Figure 3 As shown:

[0053] The method of the present invention can build a highly realistic emergency scene by developing a GIS plug-in that supports the UE game engine, improve emergency response capabilities, and provide an effective training platform for emergency rescue personnel. Specifically, it includes the following steps:

[0054] 1. Environment construction and preparation: First, you need to install and configure the Unreal Engine development environment, which includes the necessary software and tools. At the same time, prepare the required models, textures, sound effects and other resources according to the project requirements.

[0055] 1) Environment setup.

[0056] Install Unreal Engine, download the JsonLibrary and HttpLibrary plugins, and enable plugins such as PixelStreaming, Datasmith, and Webbrowser.

[0057] 2) Prepare data.

[0058] In order to simulate realistic three-dimensional scenes, data is the foundation for building emergency scenes. Before building emergency scenes, it is necessary to prepare various types of data, including terrain data (DEM) of fire scenes, raster image data (DOM), vector data (used to model forests and other plants), oblique photography data, point cloud data, BIM data, and two- and three-dimensional data required in building emergency scenes. Commonly used two- and three-dimensional data acquisition methods are mainly geographic surveying and mapping, remote sensing images, drone aerial photography, three-dimensional laser scanning, etc.

[0059] Taking the fire emergency simulation scenario as an example, it is necessary to prepare terrain data, image data, two-dimensional vector data, and oblique photography data of the simulation area.

[0060] 3) Model processing.

[0061] According to the acquired 2D and 3D data, it is converted into a 3D model. Different types of data are processed differently according to their own attribute information and application in the scene. For example, vector data such as forests require customized processing according to the height, width and other information in its attribute information, as well as whether it needs to be deformed, interactive, or single in the scene.

[0062] The specific processing principles are as follows: ① The terrain data DEM of the fire scene is converted into 3DTiles data or the terrain data is directly converted into a height map. The height map is usually a grayscale image, in which the grayscale value of each pixel represents the height of the corresponding terrain location (for example, when a forest fire occurs, the terrain data DEM of the fire scene can represent the terrain height trend of the fire scene). Black usually represents the lowest point, white represents the highest point, and the middle grayscale value represents the middle height. ② Raster image data is generally generated by map slicing tools or converted into 3DTiles data. ③ Vector data is generally generated by 3D modeling tools or automated tools to generate three-dimensional models and saved in FBX, OBJ and other formats. If the vector data does not participate in the interaction, collision, deformation and other operations in the scene, the model generated by the entire vector data can be saved as a whole or generated by the tool. ④ Oblique photography data is generally converted into 3DTiles data. ⑤ Point cloud data itself is mainly in PLY, LAS, PCD and other formats, which need to be converted into FBX, OBJ and other formats through modeling tools. ⑥ BIM data (for example, when a fire occurs, there are buildings in the fire scene that need to be modeled, so the buildings need to be modeled through BIM data). Since the model composition is more complex than that of an ordinary model, it is necessary to use a dedicated Datasmith plug-in to convert BIM data into the Datasmith format.

[0063] Taking the fire emergency simulation scene as an example, it is necessary to process the terrain data into 3DTiles data and the raster image into tile data. The terrain and raster data are superimposed to generate three-dimensional data with ups and downs. Through 3D modeling tools or semi-automatic tools, two-dimensional buildings and roads are generated into three-dimensional monomer models. The model format can be FBX or OBJ. If these buildings do not need to interact in the fire scene, they can be directly generated into 3DTiles format models.

[0064] 2. Scenario design: Carry out detailed scenario design based on the characteristics and needs of the emergency scenario, including planning of terrain layout, building distribution, transportation facilities, personnel flow, etc.

[0065] Taking the fire emergency simulation scenario as an example, the scenario design needs to include the boundaries of the flooded scene, terrain, buildings, vehicles, personnel layout, weather system, lighting system, initial perspective, etc.

[0066] 3. Resource import and editing: Import the designed scene resources into Unreal Engine and use the tools provided by the engine to edit and adjust them. This includes adjusting materials, setting lighting, adding shadows, etc. to make the scene more realistic.

[0067] By developing a GIS plug-in that supports the UE game engine, we can import real-world geospatial data into the Unreal Engine to achieve a realistic earth scene display. It has powerful geospatial data processing capabilities. It supports the import of geospatial data in various formats, including terrain data, vector data, satellite images, etc. Data can be directly imported through this plug-in without complex data processing operations, thus saving development time and effort.

[0068] Importing and editing resources is to build emergency scenes in Unreal Engine. Scene building is a comprehensive process involving multiple aspects and steps, such as Figure 4 The detailed steps are as follows:

[0069] ①Create basic terrain.

[0070] Terrain is crucial in emergency scenarios. Whether it is fire spread, buildings, or personnel behavior, the terrain must be accurate. Otherwise, a small mistake will lead to a huge error, which will have a huge impact on the emergency simulation results. Currently, terrain can be created in the following two ways.

[0071] Use Unreal Engine's Terrain tool to create a basic terrain. In Unreal Engine's Terrain tool, create a new Terrain object and select the height map as the height data source for the terrain. Then adjust various parameters of the terrain as needed, such as size, height range, etc. You can also apply different materials and textures to enhance the visual effects of the terrain.

[0072] You can also create terrain by using 3D tiles data generated by terrain, and by developing a GIS plug-in that supports the UE game engine to load local or online 3D tiles data to create terrain. Ground textures can also be created by loading image raster data as terrain textures.

[0073] ②Add lighting weather system.

[0074] After the terrain is created, add the weather and lighting system blueprint objects to the scene to simulate weather and lighting changes.

[0075] The lighting system mainly creates an Actor-based BP_Sun blueprint class, and adds exponential height fog components, post-processing components, sky light components, volumetric cloud components, directional light components, static mesh components, arrow components, sky atmosphere components, billboard components, and Niagara particle system components to the blueprint class.

[0076] The weather system mainly creates the Actor-based BP_Weather blueprint class, and adds Niagara particle system components, directional light components, post-processing components, audio components, and scene components to the blueprint class.

[0077] After adding weather and lighting blueprint objects to the scene, you can set the year, month, day, time, northern and southern hemispheres, and time zones to display the actual sunlight effect. At the same time, the weather system can also simulate sunny, cloudy, light rain, moderate rain, heavy rain, light snow, moderate snow, university, blizzard, haze, sandstorm and other weather conditions. You can also set wind speed, cloud cover and other parameters to adjust the weather system according to actual conditions.

[0078] ③Place the three-dimensional model.

[0079] After the terrain is created, you need to add three-dimensional models to the scene, including physical models of real scenes such as buildings, roads, trees, rivers, vehicles, pedestrians, street lights, etc.

[0080] In the Unreal Engine's content browser, select the "Import" function, then find the 3D model file and import it into the content browser. Then select and place 3D objects such as models and characters from the content browser into the scene. And adjust the position, rotation, and scale of the object to make the model coincide with the actual position in the terrain.

[0081] 3D Tiles data and tile data can be loaded into the scene by developing a GIS plug-in that supports the UE game engine. Datasmith data can be loaded into the scene through the Datasmith plug-in of the Unreal Engine.

[0082] ④Add camera and set scene configuration.

[0083] Create a Pawn-based blueprint class BP_Camera, add BP_Camera to the scene, set the position, rotation, and scale of the camera, and adjust various camera properties such as field of view (FOV), near clipping plane, and far clipping plane according to scene requirements to obtain the desired visual effect.

[0084] Depending on the size of the scene, set the world scene range and world partition as well as parameters such as exposure, visibility unit size, and maximum distance field distance.

[0085] Taking the fire emergency simulation scene as an example, the terrain and grid data prepared at the beginning are loaded into the scene to generate an undulating data base, and the terrain position, rotation and other parameters are adjusted. After the base is built, the weather and lighting system is added, and the weather and lighting parameters in the scene are set according to the real-world location, time and weather. Then, the other previously generated 3D models are added to the scene in turn, and the positions are adjusted to align with the terrain and grid. Finally, the camera is added and the initial position of the camera is set. At the same time, according to the size of the scene, parameters such as whether the scene is large, whether the world partition is required, and the scene exposure are set.

[0086] Step 102, setting fire information when a fire occurs, and setting a fire spread simulation model, a building collapse simulation model, and a personnel behavior simulation model, and linking them with a three-dimensional model of an emergency scene, so as to simulate the fire situation occurring in the emergency scene;

[0087] Specifically, the fire spread simulation model includes:

[0088]

[0089] Wherein, α is the first adjustment factor of fire spread, W(x, y, t) is the wind speed at position (x, y) at time t, T(x, y, t) is the temperature at position (x, y) at time t, β is the second adjustment factor of fire spread, F(x, y) is the fuel density at position (x, y), T0 is the critical combustion temperature, γ is the third adjustment factor of fire spread, σ is the fourth adjustment factor of fire spread, τ is the current time, δ is the fifth adjustment factor of fire spread, E c is the threshold of energy required for fire spread, A1 is the first adjustment factor of time, ω is the second adjustment factor of time, θ is the third adjustment factor of time, A2 is the fourth adjustment factor of time, is a standard normal distribution with mean 0 and variance 1.

[0090] Specifically, the building collapse simulation model includes:

[0091]

[0092] Among them, P f (x, y, z, t) is the building collapse index at the building position (x, y, z) at time t, λ is the adjustment factor of building collapse simulation, S0(x, y, z) is the initial stress distribution at the building position (x, y, z), S(x, y, z, τ) is the stress distribution at the building position (x, y, z) at time τ, G(x, y, z, τ) is the structural resistance at the building position (x, y, z) at time τ, τ f is the fatigue limit time of the building material, T(x, y, z, τ) is the temperature at the location (x, y, z) of the building at time τ, and T c The high temperature limit of building materials;

[0093] When the building collapse index exceeds a preset collapse threshold, the building collapses.

[0094] Specifically, the personnel behavior simulation model includes:

[0095]

[0096] Among them, xi (t) is the position vector of the i-th person in the emergency scene at time t, k is the adjustment factor of the person's behavior, V0 is the maximum value of heat in the emergency scene, σ′ is the diffusion speed of heat, and x s ′(t) is the distance between the ith person and the s′th fire source in the emergency scene at time t, η is the adjustment factor of the reaction time, τ r The reaction time for personnel to get away from the fire source.

[0097] Specifically, the fitting of all adjustment factors and weights is completed through the gradient descent method.

[0098] Step 103, simulating various fire situations by adjusting the fire information.

[0099] Specifically, it also includes: adding physical simulation through the Unreal Engine, wherein the physical simulation includes constructing a rigid body, setting collision detection, adding physical effects and force simulation.

[0100] Specifically, it also includes: the user interacts with objects in the emergency scene through input devices, and uses collision detection and UI interactive elements to achieve emergency scene control.

[0101] 4. Through the physics engine of Unreal Engine, physical phenomena in emergency scenarios, such as fire spread and building collapse, are simulated. At the same time, fire spread simulation models, building collapse simulation models and personnel behavior simulation models are used to simulate the spread of fire, building collapse, and the behavior of emergency rescue personnel and disaster victims, including actions, decisions and interactions. These simulations can enhance the authenticity and complexity of simulations and improve the accuracy and efficiency of emergency response, such as Figure 5 shown.

[0102] Physical configuration:

[0103] ① Create a physical world environment. Open the physical settings in the project and configure the global physical parameters, such as setting the gravity direction and strength, friction merging mode, maximum angular velocity, fluid friction, etc.

[0104] ② Set physical properties. For the 3D model added to the scene, set the physical properties, including defining the object's mass, inertia, collision shape, etc.

[0105] ③Configure collision detection. For entity models that may collide, you need to set collision parameters, including collision presets, collision layer priorities, and filtering rules.

[0106] ④ Set rigid bodies and constraints. If necessary, set the model object to a rigid body, because a rigid body is an object that follows physical laws (such as Newton's laws of motion). You can set the rigid body's mass, moment of inertia and other properties to affect its behavior in the physical world. At the same time, you can add constraints to the model object to control its movement or create more complex physical interactions.

[0107] ⑤ Add forces and effects. In order to simulate physical phenomena in the real world, you can apply forces (such as gravity, wind, thrust, etc.) to objects. In addition, you can also add physical effects such as damping, friction, etc. to enhance the realism of the simulation.

[0108] ⑥ Adjust physical simulation parameters. Unreal Engine provides a variety of physical simulation parameters for users to adjust to optimize performance or improve simulation accuracy. These parameters include simulation step size, number of iterations, etc.

[0109] ⑦Testing and debugging. After completing the configuration of the physical world, you need to test and debug. By running the game and observing the behavior of the objects, you can check whether the physical interaction is as expected and make necessary adjustments.

[0110] 5. Interactive function realization: realize the interactive function between users and simulation scenes, allowing users to operate, control and observe during the simulation process. By setting interactive rules and interfaces, users can adjust simulation parameters, control simulation characters, and obtain simulation results and data in real time.

[0111] The specific steps of the interactive function are as follows: Figure 6 As shown:

[0112] 1) Input device integration. First, integrate the user's input devices (such as keyboard, mouse, handle, touch screen, etc.) into the Unreal Engine. The Unreal Engine provides a rich input processing mechanism that allows reading user input events such as key presses, clicks, drags, etc. At the same time, using the Unreal Engine's input system, you can also create custom input bindings to map specific input events to actions in the game logic.

[0113] 2) Collision detection and processing. After the objects in the simulation scene are configured with the correct collision body and rigid body properties, by writing the collision event processing logic, specific actions are performed or events are triggered when the user collides with the objects in the scene.

[0114] 3) Interactive interface and UI. By using the UI system of Unreal Engine, design and implement various interactive elements such as buttons, sliders, menus, etc. Associate these UI elements with the game logic so that users can perform corresponding actions when interacting with them.

[0115] 4) Physical simulation and response. Since emergency scenarios involve physical simulation, the implemented interaction logic must be coordinated with the physical system.

[0116] 5) Animation and visual feedback. Visual feedback is an important way to enhance the interactive experience. When users interact with objects in the scene, use animation and visual effects to convey the results and status of the operation.

[0117] 6) Audio feedback. Audio feedback is also an important interactive element in weather simulation and other aspects, which is used to simulate real emergency scene effects.

[0118] 7) Testing and debugging. After implementing the interactive functions, conduct sufficient testing and debugging to ensure that the interactive logic works properly in various situations and fix any problems found.

[0119] 6. Simulation drills and testing: After the simulation scenario is built, simulation drills and testing are carried out. This includes simulating various emergency situations, observing the system's response and performance, and making adjustments and optimizations based on the test results.

[0120] 7. Performance optimization: Based on the test results, optimize the performance of the scene to ensure smooth operation during the simulation without any problems such as lag or delay.

[0121] 8. Data analysis and evaluation: Perform data analysis and evaluation on the simulation results to extract key information about emergency response, such as response time, resource allocation, etc. By analyzing these data, the effectiveness and feasibility of the emergency plan can be evaluated, providing decision support for emergency management.

[0122] 9. Results presentation and feedback: Finally, the simulation results are presented to relevant personnel in a visual way, and their feedback and suggestions are collected to further improve and optimize the simulation method.

[0123] Example 2

[0124] like Figure 2 As shown, an embodiment of the present invention further provides a fire emergency simulation system based on scene digital twins, which is used for simulating emergency scenes when a fire occurs, including:

[0125] The model generation module is used to obtain the terrain data, raster image data, vector data, oblique photography data, point cloud data and BIM data required for emergency scene simulation, and generate a three-dimensional model of the emergency scene through the Unreal Engine;

[0126] A model module is set up to set fire information when a fire occurs, and to set up a fire spread simulation model, a building collapse simulation model, and a personnel behavior simulation model, and to link them with the three-dimensional model of the emergency scene, so as to simulate the fire situation occurring in the emergency scene;

[0127] Specifically, the fire spread simulation model includes:

[0128]

[0129] Wherein, α is the first adjustment factor of fire spread, W(x, y, t) is the wind speed at position (x, y) at time t, T(x, y, t) is the temperature at position (x, y) at time t, β is the second adjustment factor of fire spread, F(x, y) is the fuel density at position (x, y), T0 is the critical combustion temperature, γ is the third adjustment factor of fire spread, σ is the fourth adjustment factor of fire spread, τ is the current time, δ is the fifth adjustment factor of fire spread, E c is the threshold of energy required for fire spread, A1 is the first adjustment factor of time, ω is the second adjustment factor of time, θ is the third adjustment factor of time, A2 is the fourth adjustment factor of time, is a standard normal distribution with mean 0 and variance 1.

[0130] Specifically, the building collapse simulation model includes:

[0131]

[0132] Among them, P f (x, y, z, t) is the building collapse index at the building position (x, y, z) at time t, λ is the adjustment factor of building collapse simulation, S0(x, y, z) is the initial stress distribution at the building position (x, y, z), S(x, y, z, τ) is the stress distribution at the building position (x, y, z) at time τ, G(x, y, z, τ) is the structural resistance at the building position (x, y, z) at time τ, τ f is the fatigue limit time of the building material, T(x, y, z, τ) is the temperature at the location (x, y, z) of the building at time τ, and T c The high temperature limit of building materials;

[0133] When the building collapse index exceeds a preset collapse threshold, the building collapses.

[0134] Specifically, the personnel behavior simulation model includes:

[0135]

[0136] Among them, x i (t) is the position vector of the i-th person in the emergency scene at time t, κ is the adjustment factor of the person's behavior, V0 is the maximum value of heat in the emergency scene, σ′ is the diffusion speed of heat, and x s′(t) is the distance between the ith person and the s′th fire source in the emergency scene at time t, η is the adjustment factor of the reaction time, τ r The reaction time for personnel to get away from the fire source.

[0137] Specifically, the fitting of all adjustment factors and weights is completed through the gradient descent method.

[0138] The simulation module is used to simulate various fire situations by adjusting the fire information.

[0139] Specifically, it also includes: adding physical simulation through the Unreal Engine, wherein the physical simulation includes constructing a rigid body, setting collision detection, adding physical effects and force simulation.

[0140] Specifically, it also includes: the user interacts with objects in the emergency scene through input devices, and uses collision detection and UI interactive elements to achieve emergency scene control.

[0141] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0142] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0144] 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, that is, they 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.

[0145] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0146] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0147] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A fire emergency simulation method based on scene digital twin, used for emergency scene simulation when a fire occurs, characterized in that: include: Obtain terrain data, raster image data, vector data, oblique photography data, point cloud data, and BIM data required for emergency scenario simulation, and generate a 3D model of the emergency scenario through the Unreal Engine; Set fire information when a fire occurs, and set up fire spread simulation models, building collapse simulation models and personnel behavior simulation models, and link them with the three-dimensional model of the emergency scene to simulate the fire situation in the emergency scene; Various fire situations are simulated by adjusting the fire information.

2. A fire emergency simulation method based on scene digital twin according to claim 1, characterized in that: The fire spread simulation model includes: Wherein, α is the first adjustment factor of fire spread, W(x, y, t) is the wind speed at position (x, y) at time t, T(x, y, t) is the temperature at position (x, y) at time t, β is the second adjustment factor of fire spread, F(x, y) is the fuel density at position (x, y), T0 is the critical combustion temperature, γ is the third adjustment factor of fire spread, σ is the fourth adjustment factor of fire spread, τ is the current time, δ is the fifth adjustment factor of fire spread, E c is the threshold of energy required for fire spread, A1 is the first adjustment factor of time, ω is the second adjustment factor of time, θ is the third adjustment factor of time, A2 is the fourth adjustment factor of time, is a standard normal distribution with mean 0 and variance 1.

3. A fire emergency simulation method based on scene digital twin as claimed in claim 2, characterized in that: The building collapse simulation model comprises: Among them, P f (x, y, z, t) is the building collapse index at the building position (x, y, z) at time t, λ is the adjustment factor of building collapse simulation, S0(x, y, z) is the initial stress distribution at the building position (x, y, z), S(x, y, z, τ) is the stress distribution at the building position (x, y, z) at time τ, G(x, y, z, τ) is the structural resistance at the building position (x, y, z) at time τ, τ f is the fatigue limit time of the building material, T(x, y, z, τ) is the temperature at the location (x, y, z) of the building at time τ, and T c The high temperature limit of building materials; When the building collapse index exceeds a preset collapse threshold, the building collapses.

4. A fire emergency simulation method based on scene digital twin as claimed in claim 3, characterized in that: The personnel behavior simulation model includes: Among them, x i (t) is the position vector of the i-th person in the emergency scene at time t, κ is the adjustment factor of the person's behavior, V0 is the maximum value of heat in the emergency scene, σ′ is the diffusion speed of heat, and x s′ (t) is the distance between the ith person and the s′th fire source in the emergency scene at time t, η is the adjustment factor of the reaction time, τ r The reaction time for personnel to get away from the fire source.

5. A fire emergency simulation method based on scene digital twin as claimed in claim 4, characterized in that: The fitting of all adjustment factors and weights is completed through the gradient descent method.

6. A fire emergency simulation method based on scene digital twin according to claim 1, characterized in that: Also includes: Add physics simulation through Unreal Engine, which includes building rigid bodies, setting up collision detection, adding physical effects and force simulation.

7. A fire emergency simulation method based on scene digital twin according to claim 1, characterized in that: Also includes: Users interact with objects in the emergency scene through input devices and use collision detection and UI interactive elements to control the emergency scene.

8. A fire emergency simulation system based on scene digital twin, used for emergency scene simulation when a fire occurs, characterized in that: include: The model generation module is used to obtain the terrain data, raster image data, vector data, oblique photography data, point cloud data and BIM data required for emergency scene simulation, and generate a three-dimensional model of the emergency scene through the Unreal Engine; A model module is set up to set fire information when a fire occurs, and to set up a fire spread simulation model, a building collapse simulation model, and a personnel behavior simulation model, and to link them with the three-dimensional model of the emergency scene, so as to simulate the fire situation occurring in the emergency scene; The simulation module is used to simulate various fire situations by adjusting the fire information.

9. A fire emergency simulation system based on scene digital twins as claimed in claim 8, characterized in that: The fire spread simulation model includes: Wherein, α is the first adjustment factor of fire spread, W(x, y, t) is the wind speed at position (x, y) at time t, T(x, y, t) is the temperature at position (x, y) at time t, β is the second adjustment factor of fire spread, F(x, y) is the fuel density at position (x, y), T0 is the critical combustion temperature, γ is the third adjustment factor of fire spread, σ is the fourth adjustment factor of fire spread, τ is the current time, δ is the fifth adjustment factor of fire spread, E c is the threshold of energy required for fire spread, A1 is the first adjustment factor of time, ω is the second adjustment factor of time, θ is the third adjustment factor of time, A2 is the fourth adjustment factor of time, is a standard normal distribution with mean 0 and variance 1.

10. A fire emergency simulation system based on scene digital twins as claimed in claim 9, characterized in that: The building collapse simulation model comprises: Among them, P f (x, y, z, t) is the building collapse index at the building position (x, y, z) at time t, λ is the adjustment factor of building collapse simulation, S0(x, y, z) is the initial stress distribution at the building position (x, y, z), S(x, y, z, τ) is the stress distribution at the building position (x, y, Z) at time τ, G(x, y, z, τ) is the structural resistance at the building position (x, y, z) at time τ, τ f is the fatigue limit time of the building material, T(x, y, z, τ) is the temperature at the location (x, y, z) of the building at time τ, and T c The high temperature limit of building materials; When the building collapse index exceeds a preset collapse threshold, the building collapses.

Images