Method, device, product and medium for realizing fire deduction in fire-fighting digital twin

Abstract

The application provides a fire disaster deduction implementation method, device, product and medium in a fire-fighting digital twin, which combines digital twin technology and fire disaster dynamic deduction technology to obtain a space-time evolution process of a fire disaster, thereby effectively improving fire emergency response efficiency, enhancing the accuracy and flexibility of the fire-fighting digital twin, and providing more scientific, intuitive and efficient support for modern building fire safety management.

Description

Technical Field

[0001] This application relates to the field of digital twin technology, specifically to a method for implementing fire simulation in fire protection digital twins, computer equipment and computer program products, and computer-readable storage media. Background Technology

[0002] With the rapid development of digital twin technology, it has been applied in many fields, such as building fire protection and fire emergency response. Digital twin technology has been applied to the field of building fire protection and fire emergency response to realize fire protection digital twins, in order to simulate situations such as fire spread and thus provide support for emergency decision-making.

[0003] Fire simulation, as an important component of fire protection digital twins, generates data describing the spatiotemporal evolution of fires by simulating the occurrence and spread of fires. However, existing fire simulations suffer from a deficiency in their implementation: the constructed fire protection digital twin scenario does not match the resulting dynamic fire simulation, and the simulation cannot be deeply integrated with the fire protection digital twin scenario. Summary of the Invention

[0004] One objective of this application is to ensure that the constructed fire protection digital twin scenario can be accurately matched with the obtained fire dynamic simulation, and to realize the implementation method, computer equipment and computer program products, and computer-readable storage media in the fire protection digital twin that achieves deep integration of fire dynamic simulation and fire protection digital twin scenario.

[0005] According to one aspect of the embodiments of this application, a method for implementing fire simulation in fire protection digital twins is disclosed, the method comprising:

[0006] Acquire scene resource packages and key simulation parameters for fire protection digital twin scenarios, wherein the scene resource packages are scene data containing parameterized 3D models;

[0007] The scene resource package is converted from the model elements corresponding to the parametric 3D model into fire dynamics simulation units;

[0008] Instances of simulation models are generated by fusing simulation units and key simulation parameters into a simulation model template.

[0009] Fire dynamic simulation is generated using the simulation model instance, and the simulation scheme data is used to dynamically display the spatiotemporal evolution of fire in the fire protection digital twin scenario.

[0010] According to one aspect of the embodiments of this application, a computer device is disclosed, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0011] According to one aspect of the embodiments of this application, a computer program product is disclosed, including a computer program that, when executed by a processor, implements the steps of the method as described above.

[0012] According to one aspect of the embodiments of this application, a computer-readable storage medium is disclosed having a computer program stored thereon that, when executed by a processor, implements the steps of the method as described above.

[0013] This application embodiment acquires a scene resource package and key simulation data for a given fire protection digital twin scenario. The scene resource package includes scene data of a parametric 3D model. Then, the scene resource package is converted into fire dynamics simulation units corresponding to the model elements of the parametric 3D model. Fire dynamics simulation units corresponding to each model element on the parametric 3D model are obtained. The fire dynamics simulation units and key simulation parameters are fused with the simulation model template to generate simulation model instances. This allows for deep integration of the constructed fire protection digital twin scenario with fire dynamic simulation. That is, simulation scheme data is generated by performing fire dynamic simulation through simulation model instances. The simulation scheme data is used to dynamically display the spatiotemporal evolution of the fire in the fire protection digital twin scenario, ensuring that the constructed fire protection digital twin scenario can accurately match the obtained fire dynamic simulation.

[0014] This application embodiment combines fire protection digital twins with fire simulation technology to obtain the spatiotemporal evolution of a fire, thereby effectively improving the efficiency of fire emergency response, enhancing the accuracy and flexibility of fire protection digital twins, and providing more scientific, intuitive and efficient support for fire safety management in modern buildings.

[0015] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0016] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0017] The above and other objectives, features and advantages of this application will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart illustrating a method for implementing fire simulation in a fire protection digital twin, according to an exemplary embodiment.

[0019] Figure 2 It is based on Figure 1 The corresponding embodiment shows a flowchart describing the steps of acquiring scene resource packages and key simulation parameters for a fire protection digital twin scenario.

[0020] Figure 3 It is based on Figure 1 The flowchart described in the corresponding embodiment describes the steps of converting model elements corresponding to the parameterized 3D model of the scene resource package into fire dynamics simulation units.

[0021] Figure 4 This is a flowchart of a method for implementing fire simulation in a fire digital twin according to another exemplary embodiment of this application.

[0022] Figure 5 This is a flowchart of a method for implementing fire simulation in a fire digital twin according to another exemplary embodiment of this application.

[0023] Figure 6 This is a flowchart illustrating a method for implementing fire simulation in a fire digital twin according to another embodiment of this application.

[0024] Figure 7 A flowchart illustrating a fire dynamics simulation unit obtained from CAD drawings is shown in one embodiment.

[0025] Figure 8 It shows Figure 7 A schematic diagram of the entire process of fire simulation using the FDS model in the corresponding embodiment.

[0026] Figure 9 It shows Figure 8 A schematic diagram illustrating the execution process of fire dynamic simulation and real-time calculation in a corresponding embodiment.

[0027] Figure 10 This is a schematic diagram of a fire protection digital twin scenario according to one embodiment.

[0028] Figure 11 It is based on Figure 10 A schematic diagram of the interface for dynamic display of fire spatiotemporal simulation shown in the corresponding embodiment. Detailed Implementation

[0029] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided to make the description of this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The drawings are merely illustrative of this application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0030] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more exemplary embodiments. Numerous specific details are provided in the following description to give a full understanding of exemplary embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced with one or more of the specific details omitted, or other methods, components, steps, etc., can be employed. In other instances, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0031] Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0032] This application embodiment realizes the matching and fusion of fire protection digital twins to dynamic fire simulations, and can implement dynamic flood simulations adapted to its model and attributes for the built fire protection digital twin scenario, forming an efficient, flexible and intelligent fire emergency response system, which will greatly shorten the response time and avoid human delays and operational errors.

[0033] Therefore, the fire dynamic simulation that can be implemented in the embodiments of this application can be applied to all fire protection digital twin scenarios, and can simulate the entire process of fire spatiotemporal evolution for the required fire protection digital twin scenarios.

[0034] See Figure 1 , Figure 1 This is a flowchart illustrating a method for implementing fire simulation in a fire protection digital twin, according to an exemplary embodiment.

[0035] The method for implementing fire simulation in fire protection digital twins provided in this application includes:

[0036] Step S110: Obtain the scene resource package and key simulation parameters of the fire protection digital twin scene. The scene resource package is scene data containing a parametric 3D model.

[0037] Step S120: Convert the model elements corresponding to the parametric 3D model of the scene resource package into fire dynamics simulation units;

[0038] Step S130: Generate a simulation model instance by fusing the fire dynamics simulation unit and the key simulation parameters simulation template;

[0039] Step S140: Fire dynamic simulation is generated by pushing model instances to generate simulation scheme data. The simulation scheme data is used to dynamically display the spatiotemporal evolution of fire in the fire digital twin scenario.

[0040] These steps are explained in detail below.

[0041] First, it should be noted that the fire simulation in this application embodiment is a simulation of the spatiotemporal evolution of the fire at a future time when the fire occurs. Thus, the fire simulation realized in the fire digital twin through this application embodiment can clearly identify which stage of the fire is about to occur, thereby enabling a prepared and rapid response.

[0042] The fire simulation in fire protection digital twin is the execution process of dynamically simulating the fire in the constructed fire protection digital twin scenario. The simulation data obtained from the dynamic fire simulation will also be integrated and projected into the fire protection digital twin scenario, rather than being limited to single parameter simulation. Whether at the level of dynamic fire simulation or at the level of presenting the simulation situation, it is deeply matched and integrated with the fire protection digital twin scenario, which can greatly improve the accuracy and reliability of fire simulation.

[0043] In other words, the fire dynamic simulation is implemented by embedding a fire twin scenario. The fire twin scenario can vary depending on the fire protection zone and time point for which the fire dynamic simulation is to be performed.

[0044] For example, a fire twin scenario corresponds to at least one fire compartment or a combination of two or more fire compartments. Thus, dynamic fire simulations can be performed on the fire twin scenario based on a set time point for the actual corresponding fire compartment, so that the dynamic fire simulation can be accurately matched with the fire compartment, i.e., the fire twin scenario.

[0045] Based on the actual fire protection needs of the fire compartments, the corresponding fire protection digital twin scenarios will be dynamically built. That is, twins will be constructed for each fire compartment. On the one hand, the association between each twin and the physical entities related to the fire compartment will be implemented, as well as the association between each twin and the physical entities related to fire protection. The twin will also be adapted to the associated physical entities and define its own events and / or business processes. The constructed twins will be added to the fire protection digital twin scenario corresponding to the fire compartment. In this way, the operation driven by physical entities can be obtained, and the operation of other associated twins will be coordinated with its own operation, thereby achieving the operation of the fire protection digital twin.

[0046] Each twin operating in the fire protection digital twin scenario can be directed to different Internet of Things (IoT) devices, such as fire protection equipment like fire trucks, water tankers, and fire hydrants, as well as the buildings containing fire compartments and the physical entities distributed within them. This ensures that the fire protection digital twin scenario, which forms the basis for fire simulations, is designed to meet the actual needs of the real-world scenario, thereby guaranteeing full coverage of the real-world scenario and improving the reliability of fire emergency response.

[0047] To further explain, the execution of fire simulations can be quickly switched to the corresponding fire protection digital twin scenario based on the different fire protection zones to be simulated and their changes, and then the fire simulation can be carried out on the switched fire protection digital twin scenario.

[0048] Therefore, in the execution of step S110, for the fire protection zone that needs to be simulated, the scene resource package and key simulation parameters of its fire protection digital twin scene are obtained. On the one hand, the scene resource package is used to obtain the fire protection digital twin scene, and on the other hand, the simulation is carried out in this fire protection digital twin scene according to the obtained key simulation parameters.

[0049] Each fire protection digital twin scenario has its corresponding scenario resource package. During the fire protection digital twin fire simulation, simply importing the scenario resource package is enough to run and simulate the corresponding fire protection digital twin scenario, which greatly reduces the threshold for fire simulation and improves convenience.

[0050] To further explain, the scene resource package of a fire protection digital twin scenario carries scene data containing a parametric 3D model. In other words, the scene resource package is a digital description of the geometric properties and other attributes of this parametric 3D twin. For example, these other attributes include, but are not limited to, material properties.

[0051] Parametric 3D models are derived from parametric modeling. In scene resource packages, they exist as functions—functions corresponding to points, lines, and surfaces—and can be used to represent the constructed parametric 3D model. The model support provided by the parametric 3D models of each twin in a fire protection digital twin scenario allows subsequent dynamic fire simulations and front-end displays to precisely target specific surfaces or lines, rather than affecting the entire model. This significantly enhances accuracy. The parametric 3D models enable more detailed and precise operation and simulation of the twins, resulting in a more detailed and accurate understanding of fire evolution.

[0052] For example, a fire-fighting digital twin scenario used for simulation and front-end display will be used to present the operation of the twin corresponding to the spontaneously combusting vehicle at an intersection. In the current implementation, the model of each vehicle is built based on images, the business processes and events created, the front-end display, and even the fire simulation are all applied to the vehicle as a whole.

[0053] The geometric attributes obtained through parametric modeling are added to the twin in the fire protection digital twin scenario. This twin can correspond to the vehicle as a whole, as well as each part within the vehicle, such as tires and bearings. Each part can then have its own sub-twin, enabling the creation of its own business processes and events. Real-time data and other twins drive the operation, achieving precise response in the fire protection digital twin scenario and facilitating further implementation. Existing models are mostly image-based, such as models constructed from various static images, dynamic images, or even video streams. These models lack the precision to points, lines, and surfaces, and therefore cannot provide the necessary responses or fire simulations. Consequently, the responses and fire simulations they can perform are limited to the overall model corresponding to a single physical entity, and cannot address the individual parts of that model.

[0054] Fire protection digital twin scenarios mostly focus on large-scale buildings and their internal structures. Therefore, the parametric 3D model carried by the twin in a fire protection digital twin scenario is geared towards the building and its internal structure. Thus, in an exemplary embodiment, a scene resource package containing a parametric 3D model is included. The parametric modeling is an execution process that generates a parametric 3D model from drawings carrying building information. After completing the parametric modeling of the building, its internal structure, and even fire-related physical entities, the model data in the converted parametric 3D model can be used to obtain the scene resource package of the fire protection digital twin scenario.

[0055] In other words, for the fire protection digital twin scenario that needs to be built, a parametric 3D model can be generated with one click based on the drawings that carry building information. This enables the rapid and convenient construction of fire protection digital twin scenarios for any real-world environment, further lowering the threshold for fire protection digital twin applications and achieving fire simulations, and making it highly user-friendly.

[0056] See Figure 2 , Figure 2 It is based on Figure 1 The corresponding embodiment shows a flowchart describing the steps of acquiring scene resource packages and key simulation parameters for a fire protection digital twin scenario.

[0057] The step S110 of obtaining the scene resource package and key simulation parameters of the fire protection digital twin scene provided in this application embodiment includes:

[0058] Step S111: Generate a parametric 3D model from the drawings carrying architectural information;

[0059] Step S112: Convert the model data in the parametric 3D model to obtain the scene resource package of the fire protection digital twin scene.

[0060] The following is a detailed explanation of these two steps.

[0061] The process involves acquiring drawings covering the area to be simulated in a fire simulation, and directly generating a parametric 3D model from these drawings—that is, performing rapid and automatic modeling based on the drawings. For example, step S111 may include: first, parsing the drawings; then, searching for continuous walls based on a geometric data composite spatial index structure; and finally, providing a data foundation for modeling through continuous wall search and identification, obtaining wall and window data—obtained from the identification of the drawings. This process yields a large amount of complete architectural information scattered throughout the drawings without manual intervention. Finally, based on this complete architectural information, i.e., the wall and window data, wall construction and the creation of doors and windows on the walls are performed to obtain a parametric 3D model. This efficient and accurate automatic conversion from drawings to a parametric 3D model is achieved without human intervention.

[0062] Specifically, a geometric data composite spatial index structure is constructed for the drawing elements carrying architectural information. The drawing generates a parametric 3D model based on the architectural information it carries. A list of wall lines to be searched, formed by element identifiers belonging to wall lines in the drawing, is used to search for continuous walls within the geometric data composite spatial index structure, obtaining the wall lines constituting the continuous walls and the blocks of objects placed on the continuous walls. Based on the wall lines constituting the continuous walls and the blocks of objects placed on the continuous walls, the physical entities corresponding to the continuous walls on the drawing, and the distribution of objects placed on the physical entities, are obtained. The wall, door, and window data of the drawing are obtained by identifying the physical entities and the objects placed on them. Walls and doors and windows on the walls are created using the wall, door, and window data, resulting in a parametric 3D model.

[0063] Drawings depict the walls and other elements within a building in a two-dimensional format, including doors and windows. A series of drawings is used to represent the building as a whole. These drawings contain a wealth of information related to the building's design, construction, and function, including not only geometry and spatial layout but also materials, construction methods, spatial functions, dimensions, and other architectural details.

[0064] Further categorization involves the architectural information carried by the drawings, including wall information, door and window information, etc. Based on this architectural information, the affiliation information of each element on the drawing is determined, and then the elements belonging to the wall lines on the drawing are identified from this affiliation information.

[0065] Since the drawings contain architectural information, the geometric data of each wall line can be obtained from the wall information in the architectural information. Similarly, the geometric data belonging to doors and / or windows can be obtained from the door and window information in the architectural information. This eliminates the need for manual operation and greatly reduces or even eliminates human intervention.

[0066] For drawings, such as the aforementioned two-dimensional drawings, architectural information is scattered across the drawings, requiring analysis to extract this information. Specifically, the extracted architectural information includes the geometric data of the elements distributed across the drawing, as well as the attribution information of these elements; that is, extracting the elements and even their attributes.

[0067] The extraction of graphic elements during the analysis of drawings will extract all geometric data from the drawings. This geometric data is used to represent the building's walls, doors, windows, and other components. Furthermore, the distribution of each graphic element on the drawing can be obtained through the geometric data, such as the geometric data indicating the two-dimensional geometric range and key point positions of the graphic element.

[0068] The layer information contained in the architectural information in the drawings, such as "Walls", "Doors", "Windows", etc., as layer information, identifies the category to which the graphic elements belong. For example, the graphic elements on this layer belong to wall lines, doors, windows, etc.

[0069] Based on this, by performing drawing analysis, we can obtain the geometric data and attribution information of the elements distributed on the drawing.

[0070] In another embodiment, the drawings may not be standardized, and the graphic elements distributed on the drawings may not be completely classified into the corresponding layers. For example, a graphic element of a certain wall line may not be set on the wall line layer in the drawing, but on another layer. In this case, it is necessary to extract the graphic element attributes during the drawing parsing process, rather than relying solely on the layer information contained in the building information to obtain the graphic element's affiliation information.

[0071] Specifically, the extraction of primitive attributes involves extracting the semantic information of primitives, and then determining the type of primitive and obtaining its attribution information based on the semantic information.

[0072] The semantic information includes information such as annotations, line types, dimensions, and materials. This information is added to the drawing parsing process to assist in obtaining the attribution information of graphic elements based on layer information, thereby ensuring the accuracy and comprehensiveness of the attribution information obtained for graphic elements and avoiding the occurrence of incorrect or even missing attribution information.

[0073] After obtaining the geometric data and attribution information of the graphic elements from the drawings, a geometric data composite spatial index structure can be constructed to store the geometric data of the graphic elements. Based on the obtained attribution information, a list of wall lines to be searched can be generated for the graphic elements from the drawings. Only then can an efficient search be performed in the geometric data composite spatial index structure based on the list of wall lines to be searched.

[0074] Based on the characteristics of drawings, a composite spatial index structure for geometric data is constructed to adapt to the geometric data contained in the drawings. This composite spatial index structure provides structured storage for the geometric data of the parsed primitives and enables efficient searching of the parsed geometric data.

[0075] It should be clearly stated that a geometric data composite spatial index structure should be constructed for each drawing to achieve automatic and rapid modeling. In other words, each drawing can correspond to a geometric data composite spatial index structure to ensure the orderly storage and efficient searching of the drawing's data, thereby enabling rapid modeling of the drawing.

[0076] For example, the geometric data composite spatial index structure is tree-like, containing several nodes, through which geometric data is stored. That is, the geometric data composite spatial index structure is used to insert geometric data into nodes using primitive identifiers as indexes. In an exemplary embodiment, the geometric data composite spatial index structure includes two spatial index structures; in other words, the two spatial index structures are adapted to the two-dimensional geometric extent and key point location information corresponding to the primitives in the geometric data.

[0077] As mentioned earlier, the geometric data of primitives includes two-dimensional geometric extents and key point location information. Correspondingly, the geometric data composite spatial index structure includes two spatial index structures: R-tree and KD-tree. By inserting two-dimensional geometric extents into nodes of the R-tree using primitive identifiers as indexes, and since the R-tree supports hierarchical storage of rectangular regions, and the two-dimensional geometric extents are mostly defined as rectangular regions, efficient querying and searching of geometric data in drawings can be achieved with the support of the R-tree.

[0078] Furthermore, by inserting key point location information into nodes of the KD tree using primitive identifiers as indexes, the query and search of key point location information can be achieved using the KD tree, which is suitable for two-dimensional spatial data.

[0079] In summary, by adapting to the characteristics of various types of data in geometric data, two spatial index structures are constructed as a composite spatial index structure for geometric data. This adapts to the drawings and achieves orderly data storage while also ensuring the efficiency of subsequent queries and searches.

[0080] To further explain, the two-dimensional geometric extent defined by a primitive can be obtained by calculating its bounding box. This bounding box is the smallest rectangular bounding box of the primitive in two-dimensional space; specifically, it can be an axis-aligned bounding box. Thus, the smallest matrix bounding box of the primitive in two-dimensional space serves as the two-dimensional geometric extent defined by that primitive. This bounding box is then inserted into the R-tree using the primitive identifier as an index. Each primitive's two-dimensional geometric extent and its identifier form a node in the R-tree, achieving hierarchical storage of geometric data in the drawing and efficiently supporting query and search operations.

[0081] It should be understood that the two-dimensional geometric range of the primitives obtained through drawing analysis can be straight lines, arcs, polylines, splines, etc. Under the influence of the two-dimensional geometric range, the spatial relationship between primitives can be quickly determined. Furthermore, combined with the R-tree, which is suitable for data storage and searching of this type of two-dimensional geometric range, the storage itself is optimized, and the data search performance of the modeling process is also enhanced, thereby improving timeliness while ensuring lightweight modeling.

[0082] The geometric data composite spatial index structure referred to is not about the composite nature of the geometric data, but rather about adapting two spatial index structures to the characteristics of the geometric data itself to achieve fast query and search of primitives.

[0083] The key point location information of graphic elements, along with the two-dimensional geometric range, is part of the geometric data obtained from the analytical drawing. However, under the influence of the composite spatial index structure of geometric data, optimal processing of the geometric data is achieved by applying their respective characteristics. For example, the key point location information of graphic elements can exist in the form of point coordinates. For instance, for graphic elements such as lines, arcs, polylines, and splines, it can be the coordinates of the starting point and the ending point corresponding to the graphic element.

[0084] The KD-tree is constructed based on point coordinates. For all primitives, their point coordinates are extracted from the geometric data as the key point location information of that primitive, such as the start and end point coordinates mentioned above. These coordinates are then inserted into the KD-tree along with the primitive identifier. In drawings, primitives are obtained by decomposing blocks. Therefore, the process of parsing drawings essentially includes decomposing the blocks in the drawing, obtaining the decomposed primitives and their key point location information, and then constructing the corresponding spatial index structure.

[0085] In geometric data, both key point location information and two-dimensional geometric range are representations and descriptions of the corresponding primitives. The two-dimensional geometric range spatially defines the primitives, while key point location information represents the key points of the primitives, such as the starting and ending point coordinates mentioned earlier. Therefore, analyzing drawings to obtain two-dimensional geometric information, key point location information, and even attribution information all represent and describe the corresponding primitives from various dimensions, which will greatly improve the accuracy of subsequent model construction.

[0086] The R-tree and KD-tree spatial indexing structures work together to store geometric data for primitives in drawings. This significantly improves the efficiency of geometric data retrieval and search in subsequent Building Information Modeling (BIM) and automated modeling, enhances the accuracy of spatial relationship judgment, and is applicable to batch modeling of large-scale drawings.

[0087] After generating a parametric 3D model from the fire simulation based on the drawings, the model data in the parametric 3D model is converted to obtain a scene resource package for the fire digital twin scene.

[0088] As mentioned earlier, a parametric 3D model is a digital representation of a building or other related physical entity. It contains information about the building and all its components. A scene resource package is obtained by transforming the model data in the parametric 3D model.

[0089] For example, the created parametric 3D model, which includes elements such as rooms, floors, walls, equipment, stairs, ventilation systems, and fire extinguishing equipment, is exported to obtain model data. The resulting model data contains the geometric attributes and other attribute data of the scene. The model data is then converted into a scene resource package suitable for digital twin simulation applications.

[0090] In addition, it should be clear that the obtained real-time data can be updated in the scene resource package, and then used to update the fire simulation digital twin scene.

[0091] In step S110, in addition to acquiring the scene resource package of the fire protection digital twin scenario, key simulation parameters will also be acquired. For example, key simulation parameters include simulation time, heat release efficiency, ignition point, and sprinkler status information, which will not be listed one by one here.

[0092] Key simulation parameters are the core factors influencing the development of a fire and form the basis for driving the simulation process and calculating the fire's trajectory. For example, key simulation parameters include parameters related to the environment, physics, building layout and facilities, occupant distribution within the building, and evacuation strategies.

[0093] As the scene resource package and key simulation parameters are obtained in step S110, the scene resource package is converted into fire dynamics simulation units by the corresponding model elements of the parameterized three-dimensional model in step S120, so as to obtain the corresponding fire dynamics simulation model for the model elements distributed on the parameterized three-dimensional model.

[0094] In step S120, the model element refers to the digital representation in a parametric 3D model used to describe physical entities, such as buildings and their components. A model element is the basic building block of a parametric 3D model, and each model element contains geometric attributes as well as other related attributes, such as material, structural properties, and function.

[0095] For example, doors, windows, roofs, stairs, railings, and fire-fighting equipment are all model elements distributed in the parametric 3D model.

[0096] In summary, model elements are derived directly from the geometric properties and other attributes of the parametric 3D models in the scene resource package.

[0097] Fire dynamics simulation units, also known as FDS (Fire Dynamics Simulator) model elements, are the basic building blocks of fire dynamics simulation models. Fire dynamics simulation units, obtained by transforming model elements from parametric 3D models, inherit from the model elements and describe various attributes such as the physical environment and geometric structure.

[0098] By converting model elements into fire dynamics simulation units, the fire dynamics simulation model for fire dynamics simulation is obtained by converting the parametric 3D model. This ensures that the fire dynamics simulation is accurately matched and deeply integrated with the corresponding real-world scenario and the fire protection digital twin scenario. The fire dynamics simulation can be adapted to real-world fire scenarios, thus enhancing the accuracy of the simulation.

[0099] The conversion of model elements into fire dynamics simulation units includes meshing, attribute mapping, and the final fusion process.

[0100] For example, please also see Figure 3 , Figure 3 It is based on Figure 1 The flowchart described in the corresponding embodiment describes the steps of converting model elements corresponding to the parameterized 3D model of the scene resource package into fire dynamics simulation units.

[0101] The conversion step S120 of the parameterized 3D model of the scene resource package into a fire dynamics inference unit provided in this embodiment includes:

[0102] Step S121: Perform meshing processing on all model elements in the scene resource package that correspond to the parametric 3D model to obtain the corresponding mesh structure;

[0103] Step S122: Map the attribute data of the model elements to the fire simulation parameters of the grid structure;

[0104] Step S123: Integrate fire simulation parameters and grid structure to obtain fire dynamics simulation units.

[0105] This step will be explained in detail below.

[0106] In step S121, the scene data is parsed, and the model elements corresponding to the parametric 3D model in the scene resource package are converted into a mesh structure, that is, each model element is divided into meshes to obtain a mesh structure.

[0107] Specifically, similar to the parametric 3D model, the attribute data of model elements includes geometric and non-geometric attributes. For example, geometric attributes include the distribution elements of the building, namely the location, shape, and size of walls, floors, ceilings, doors, and windows. Non-geometric attributes include semantic information, spatial layout information, and equipment information. Semantic information includes the function, material type, and physical properties of each element. Spatial layout information includes the division of rooms and their adjacent relationships, such as rooms connected by corridors and the relationship between upper and lower floors. Equipment information includes the location and functional description of specific fire-fighting equipment such as ventilation systems, fire source locations, and smoke exhaust vents.

[0108] By parsing scene data, geometric and other attributes of each model element are extracted, and the extracted geometric attributes are then geometrically simplified. This simplification process removes minor details irrelevant to the fire's evolution, such as decorative details, retaining only the core building structure, such as walls, floors, and windows. It also optimizes accuracy by dividing the simplified geometry into meshes according to a set mesh density to obtain the mesh structure of each model element.

[0109] Furthermore, the execution of step S121 may also include a coordinate system transformation process, that is, performing a coordinate system transformation on the obtained mesh structure to ensure that it can be adapted to the subsequent execution process and to ensure the consistency of the coordinate system and the corresponding unit.

[0110] In step S122, the model elements are transformed into a mesh structure, and the non-geometric properties of these model elements are mapped to input parameters for fire simulation, i.e., fire simulation parameters. For example, for each of the aforementioned non-geometric properties, such as mapping the material type to the fire simulation parameters of the mesh structure, the location of the fire-fighting equipment indicated by the equipment information is mapped to its position in the mesh structure, and then used as fire simulation parameters.

[0111] At this point, the processing of geometric and non-geometric attributes on the model elements can be completed. The resulting mesh structure, which maps the fire simulation parameters, can be fused with the fire simulation parameters and the mesh structure through step S123 to obtain the fire dynamics simulation unit corresponding to the model element.

[0112] Therefore, the conversion of model elements into fire dynamics simulation units avoids the time wasted in manual modeling and reduces the risk of human input errors. It enables large-scale and complex fire simulations to be performed under the action of fire dynamics simulation units of various model elements, ensuring the reliability of fire simulations.

[0113] With the execution of step S120, a basic unit for fire dynamic simulation is obtained, namely the fire dynamics simulation unit. Since the fire dynamics simulation unit integrates the attributes of the model elements corresponding to the physical entities, the simulation model instance generated in step S130 under the control of the fire dynamics simulation unit is consistent with the real scene and the constructed fire digital twin scene, and is no longer limited to simulation through parameterized control of key simulation parameters, which greatly improves the accuracy of the spatiotemporal evolution process obtained by spatial simulation.

[0114] In the execution of step S130, the simulation model instance is obtained by instantiating the model used for dynamic fire simulation. The simulation model instance provides a virtual environment adapted to the fire digital twin scenario for the simulation analysis, thereby laying the foundation for the dynamic fire simulation in step S140 with the support of the accurate construction of the fire digital twin scenario and the simulation model instance.

[0115] Fire dynamics simulation units and key simulation parameters will serve as key components of the constructed fire environment. After the fire dynamics simulation units and key simulation parameters are integrated into the simulation model template, a simulation model instance is generated.

[0116] For example, the fire dynamics simulation unit can be used to simulate fire spread, smoke diffusion, heat conduction, fire effects, etc. Correspondingly, the fire dynamics simulation unit includes physical and behavioral models. On the one hand, it is constructed based on the attributes provided by the model elements. On the other hand, it will also construct the physical and behavioral models contained based on the dimensions to be simulated. For example, the included models include fire source model, smoke diffusion model, heat transfer and temperature field model, and personnel evacuation and behavior model, which will not be listed one by one here.

[0117] Key simulation parameters are the core factors influencing the fire development process and are the foundation for driving the simulation process and calculating the fire development trend. After obtaining the key simulation parameters and fire dynamics simulation units through steps S110 and S120 respectively, simulation model instances can be created from the simulation model template.

[0118] The simulation model template contains several fire dynamics simulation units and parameter configurations. The simulation model template defines how to combine each fire dynamics simulation unit to simulate fire events and behaviors, providing structured input data for the fire dynamics simulation in step S140.

[0119] For example, the execution process of step S130 includes: instantiating a predefined simulation model template, integrating fire dynamics simulation units and key simulation parameters to generate a simulation model instance, wherein the simulation model template is a framework containing fire dynamics simulation units and parameter configurations.

[0120] After generating the simulation model instance, the simulation model instance can be run through step S140 to perform fire dynamic simulation and generate simulation scheme data.

[0121] Understandably, simulation model instances provide standardized data for dynamic fire simulations, and are grounded in specific scenarios, thereby obtaining simulation scheme data oriented towards time and space.

[0122] In step S140, it should be understood that the simulation model instance maps to a specific fire protection digital twin scenario. For the specific fire protection digital twin scenario mapped, the simulation model instance is run so that each fire dynamics simulation unit integrated in the simulation model instance can perform simulation of its respective simulation dimension, which is also the fire description dimension, thereby obtaining simulation scheme data containing each fire description dimension.

[0123] The simulation data includes detailed information on various fire description dimensions, such as the dynamic development of the fire, the spatial distribution of smoke and temperature, and equipment response. This provides strong support for fire safety design, emergency response plans, and optimization of personnel evacuation routes, and provides a reliable basis for fire case management.

[0124] The resulting simulation data is essentially a fusion of time series data from various fire description dimensions. Based on the corresponding fire description dimension, the simulation data includes the evolution status in both time and space dimensions, so as to present the fire evolution status in both time and space.

[0125] Therefore, by way of example, another exemplary embodiment of this application provides a method for implementing fire simulation in fire digital twins, which further includes:

[0126] The time series data is segmented and extracted to obtain time slice data corresponding to a time point and spatial slice data corresponding to a fire compartment. The time slice data and spatial slice data describe the spatiotemporal evolution of the fire in the fire protection digital twin scenario mapped by the specified fire compartment at the specified time point.

[0127] The data generated by fire dynamic simulation is time series data, which contains the fire status of each time point and each fire compartment during the fire process. In order to effectively utilize the obtained data, the time series data will be sliced ​​to obtain time slice data and spatial slice data.

[0128] Time-slice data is data extracted from each fire description dimension based on a point in time, while spatial-slice data is data sliced ​​into different fire compartments based on the spatial division of the fire digital twin scenario. For example, the fire status of each floor, room, or specific area in each fire description dimension.

[0129] The obtained time slice data and spatial slice data will be used to display the spatiotemporal evolution of fire at a specified time point and in a specified fire compartment.

[0130] Furthermore, the obtained time slice data and spatial slice data will be compressed. The compressed time slice data and spatial slice data will then be used to update the spatiotemporal evolution status of the fire digital twin scenario at a specific point in time, thereby avoiding the problem of a large amount of data output from fire simulation, improving processing efficiency and reducing storage requirements.

[0131] For further information, please refer to [link / reference]. Figure 4 , Figure 4 This is a flowchart of a method for implementing fire simulation in a fire digital twin according to another exemplary embodiment of this application.

[0132] In another exemplary embodiment of this application, the method for implementing fire simulation in fire digital twins further includes:

[0133] Step S210: Load and render the fire protection digital twin scene corresponding to the specified fire compartment, and perform front-end display of the parameterized 3D model corresponding to each twin in the fire protection digital twin scene;

[0134] Step S220: Obtain the time slice data corresponding to the current time point and the spatial slice data corresponding to the specified fire compartment;

[0135] Step S230: Integrate the time slice data and spatial slice data into the fire protection digital twin scene displayed on the front end.

[0136] This step will be explained in detail below.

[0137] Select a fire compartment to load and render the fire protection digital twin scene of the selected fire compartment, and realize the front-end display of the parametric 3D model corresponding to each twin in the fire protection digital twin scene.

[0138] In other words, the parametric 3D model, as the geometric attributes of each twin, will be distributed throughout the rendered fire protection digital twin scene.

[0139] For the rendered fire protection digital twin scene, time slice data and spatial slice data are obtained according to the current time point and the corresponding fire protection zone. These data can then be integrated and projected onto the fire protection digital twin scene, so as to intuitively and accurately present the spatiotemporal evolution of the fire in the fire protection digital twin scene that reconstructs the real fire scene, thereby enhancing the accuracy and adaptability of the display of the spatiotemporal evolution of the fire.

[0140] Furthermore, the rendered digital twin scenario for fire protection also includes a pre-configured timeline for the dynamic display of the fire's spatiotemporal evolution. For more information, please refer to [link / reference needed]. Figure 5 In one exemplary embodiment, the method for implementing fire simulation in fire digital twins provided in this application further includes:

[0141] Step S310: Locate the time point to which the pointer in the running timeline has flowed. This time point corresponds to the node configured on the timeline and is located in the time slice corresponding to that node. The pointer can be dragged on the timeline.

[0142] Step S320: Obtain time slice data and spatial slice data based on the time point and the fire protection zone mapped by the fire protection digital twin scene.

[0143] Step S330: Update the time slice data and spatial slice data to the currently rendered fire protection digital twin scene. The update includes the integration of time slice data and spatial slice data into the fire protection digital twin scene, as well as the dynamic update of the parametric 3D model in the fire protection digital twin scene.

[0144] This step will be explained in detail below.

[0145] First, it should be noted that the embodiments of this application configure a timeline with several nodes distributed along it, and each node is configured with a corresponding twin. The distribution of nodes on the timeline has a default configuration so that it can run even without more real-time data before the timeline is implemented, and provides an initial response and evolution implementation.

[0146] As the timeline runs, the default configured nodes can be changed to adapt to the key stages mapped in the simulated firefighting evolution; no specific limitation is made here. Running the timeline refers to starting execution at any point in time, not just at a node. For example, when the pointer advances to a timeline point, it triggers a simulation start operation, at which point the timeline will run in response to the simulation start operation.

[0147] It should be further explained that the current triggered timeline operation, as well as the dynamic response and evolution of the ongoing fire protection digital twin scenario, are all oriented towards a fire protection digital twin scenario, such as a fire compartment, or a fire protection digital twin scenario constructed from the fire scene formed by several fire compartments, and can switch to the timeline of the scenario as the scenario changes.

[0148] The configuration of the twin on the pre-configured timeline and the nodes distributed on the timeline enables the operation of the fire protection digital twin scenario to be driven by the timeline and the real-time data input. This achieves automatic response and evolution across stages, while also adapting to the real fire environment to improve the flexibility and adaptability of emergency response, ensuring that it can cope with complex and sudden fire situations.

[0149] In one exemplary embodiment, nodes distributed along the timeline are configured to run twins and fire simulation data for their corresponding time slices. This fire simulation data is used to dynamically display the fire-fighting evolution.

[0150] In other words, the nodes distributed on the timeline are the starting points of a time slice. When the timeline pointer moves to a node, it means that the fire is about to enter a certain stage. The time point where the node is located is the starting time of this stage, and the time range corresponding to this stage is the time slice corresponding to the node.

[0151] Therefore, the fire simulation will be divided into several slices under the action of the time axis. Then, the slice data under each slice, namely the time slice data corresponding to the time slice and the spatial slice data of the fire compartment to which it belongs, will be used for dynamic display of the time-based fire evolution of each node.

[0152] Furthermore, it adapts to the current stage, configuring and running the corresponding twin based on the node and its corresponding time slice. The operation of the twin will realize the operation of the fire protection digital twin scenario in its time slice. In other words, the twins running in the fire protection digital twin scenario include the main twin and other twins, and there are associations between the other twins and the main twin to achieve mutual collaboration between the twins.

[0153] The time-slice data and spatial-slice data will be projected onto the fire protection digital twin scene that is running the twin, and the operation of the twin will also be controlled by the dynamic updates of the time-slice data and spatial-slice data.

[0154] For example, several nodes distributed along the timeline correspond to past, present, and future times, respectively. Therefore, the twin's operations at each time point will be based on real-time data input at that time and fire simulation data, and will adaptively run through events and / or business processes defined by the twin itself, achieving precise front-end display based on its geometric attributes.

[0155] Among them, the twin operation oriented towards the past time is a reproduction of historical situations, and the extrapolation made is a reverse extrapolation; the twin operation based on the present time is a precise feedback of the current fire situation; the twin operation and extrapolation oriented towards the future time is a simulation and prediction of the fire evolution process, especially the fire evolution process.

[0156] Driven by the time axis, on the one hand, the defined events and / or business processes will be adaptively triggered by the operation of the twin under real-time data input, and the front-end will be visualized and dynamically displayed based on the geometric attributes carried by the twin, i.e., the parametric 3D model; on the other hand, the fire simulation data of the current time slice will be played in accordance with the flow of the pointer, so as to realize forward and reverse simulations in the past, present and future.

[0157] The operation of the timeline can be triggered when the simulation begins. At this time, the pointer on the timeline will flow according to the time flow and advance to a node. Once the pointer advances to a node, that node will be triggered.

[0158] Correspondingly, the timeline will also stop running in response to the end of the simulation, and will switch to another time point in response to the dragging operation of the pointer, so that the timeline can run again at that time point.

[0159] Thus, under the influence of the timeline, the dynamic response and evolution of the fire protection digital twin scenario can be interactively controlled, and it can be migrated and switched at any time as needed, greatly enhancing the flexibility of the operation of the fire protection digital twin scenario.

[0160] See Figure 6 , Figure 6 This is a flowchart illustrating a method for implementing fire simulation in a fire digital twin according to another embodiment of this application.

[0161] In one exemplary embodiment, the method for implementing fire simulation in fire digital twins provided in this application further includes:

[0162] Step S410: For the key observation points in the fire protection digital twin scenario, calculate the real-time observation values ​​mapped to the key observation points based on the time slice data and spatial slice data.

[0163] Step S420: Dynamically display the observed values ​​mapped by key observation points in the fire protection digital twin scenario.

[0164] The following is a detailed explanation of these two steps.

[0165] This process is based on the simulation scheme data. It extracts data slices from the time slices on the time axis, that is, it extracts the corresponding time slice data and spatial slice data to perform real-time calculation of the observation values ​​mapped to the key observation points.

[0166] The key observation points referred to are those in the fire scene that are representative and important for the evolution of the fire. For example, key observation points may be the fire source and its surrounding area, key points in the smoke diffusion path, and key points in the distribution of high-temperature areas and flammable materials. There is no limitation here, and they can be flexibly adjusted according to specific circumstances.

[0167] As the time pointer advances, the time slice data and spatial slice data corresponding to the current time point are rendered and projected onto the fire protection digital twin scene, dynamically displaying the spatial distribution changes of the observation values ​​mapped by key observation points.

[0168] This enables a dynamic display of the spatiotemporal evolution of fire simulation data, effectively enhancing fire emergency response capabilities.

[0169] In summary, driven by the timeline, and looking towards the future on the timeline, the timeline will be gradually advanced to complete the dynamic simulation and extrapolation of fires in all time slices, obtain all simulation scheme data covering the entire future time, so as to effectively support rapid response and early warning, optimize fire prevention and control decisions, and then adjust and update the current fire fighting and rescue efforts.

[0170] The following section will illustrate the implementation of the method described above using a specific application.

[0171] See Figure 7 , Figure 7 A flowchart illustrating a fire dynamics simulation unit obtained from CAD drawings is shown in one embodiment.

[0172] During this process, CAD drawings are automatically generated into 3D models of building walls, doors, windows, stairs, elevators, and various facilities through forward parametric modeling. In other words, based on this, various building elements are parametrically modeled for the real-world scenario required for fire simulation. For example, CAD elements (walls, columns, doors, windows, etc.) are picked up to automatically generate parametric 3D models, and CAD elements (location, size, and rotation) are picked up to automatically place the corresponding facilities, thus realizing the rapid construction of Building Information Modeling (BIM).

[0173] After obtaining the parametric 3D model, the model elements distributed on it are converted into fire dynamics simulation units, namely the FDS (Fire Dynamics Simulator) model, through the FdsConstructouPlugin (Fds construction plugin).

[0174] See further Figure 8 of, Figure 8 It shows Figure 7 A schematic diagram of the entire process of fire simulation using the FDS model in the corresponding embodiment.

[0175] The obtained FDS model and key simulation parameters, such as simulation time, heat release efficiency, ignition point and spraying, are fused into the FDS model template, i.e. the aforementioned simulation template, to instantiate the FDS model and obtain the simulation model instance, i.e., the FDS model instance.

[0176] It should be understood that the fusion process first requires determining whether an FDS model template exists. If no FDS model template exists, it needs to be created using FdsConstructouPlugin.

[0177] For the instantiated FDS model instance, a dynamic fire simulation will be performed for the specified fire compartment. Thus, the fire compartment referred to is the fire compartment corresponding to the fire protection digital twin scenario. The constructed parametric 3D model and the CAD drawings used to construct the parametric 3D model are all corresponding to this fire compartment.

[0178] Through dynamic fire simulation and analysis algorithms, simulation scheme data and corresponding observation values ​​can be obtained, such as burned area, zonal fire probability, and burnout time.

[0179] The derived simulation data, as well as the rendering data used to render the fire protection digital twin scene, are all obtained by data slicing to obtain slice data corresponding to time points and partitions, and then compressed and stored for front-end display.

[0180] It should be understood that the fire dynamic simulation is based on a computational process involving multi-dimensional variables and complex interactions. Interactive simulation is conducted by establishing relationships between various variables to obtain more accurate and comprehensive simulation data.

[0181] See Figure 9 Place, Figure 9 It shows Figure 8 A schematic diagram illustrating the execution process of fire dynamic simulation and real-time calculation in a corresponding embodiment.

[0182] During this process, dynamic fire simulations are performed on designated fire compartments, which are derived from areas drawn using CAD drawings.

[0183] If an FDS simulation has already been performed, i.e. a fire dynamic simulation performed for an FDS model instance, the obtained simulation scheme data can be used directly. If an FDS simulation has been performed before, a simulation should be created.

[0184] For the time series data of the obtained simulation scheme, on the one hand, data slicing and data compression are performed, and on the other hand, observations such as burnout time, burned area and fire probability are obtained through real-time operation. Thus, the spatiotemporal simulation status of fire corresponding to a point in time and fire compartment can be obtained.

[0185] To further illustrate, the obtained parametric 3D model is used to export its scene resource package. Then, using this scene resource package, the fire simulation digital twin scenario required for the fire simulation is imported into the constructed fire simulation system. For example... Figure 10 As shown, Figure 10 This is a schematic diagram of a fire protection digital twin scenario according to one embodiment.

[0186] At this point, key simulation parameters, such as time point, heat release efficiency, ignition point location, and spray status information, can be entered for multivariate simulation.

[0187] The obtained simulation data will be used to visually demonstrate the dynamic processes of fire spread, smoke diffusion, and temperature changes in the fire protection digital twin scenario through rendering. Figure 11 As shown, Figure 11 It is based on Figure 10 A schematic diagram of the interface for dynamic display of fire spatiotemporal simulation shown in the corresponding embodiment.

[0188] It achieves deep integration of fire simulation with building models, i.e. parametric 3D models, improving simulation accuracy and visualization effects, and ensuring the comprehensiveness and accuracy of fire safety analysis.

[0189] Therefore, the heat map data from different time frames, i.e. the data obtained from the simulation scheme, will intuitively show the temperature distribution, burned area and ignition probability of each area during the fire spread process, accurately predict the deepening of the fire in each fire protection zone, and the results obtained in real time will also be marked at the corresponding key observation points to provide quantitative basis for the fire spread process.

[0190] In one exemplary embodiment, this application also provides a computer device including a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the steps of the method as described above.

[0191] In one exemplary embodiment, this application also provides a computer program product including a computer program that, when executed by a processor, implements the steps of the method as described above.

[0192] In one exemplary embodiment, this application also provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method as described above.

[0193] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the method according to the embodiments of this application.

[0194] In an exemplary embodiment of this application, a computer program medium is also provided, on which computer-readable instructions are stored, which, when executed by a computer's processor, cause the computer to perform the methods described in the above method embodiments.

[0195] According to one embodiment of this application, a program product for implementing the methods in the above-described method embodiments is also provided. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of this invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0196] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0197] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0198] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0199] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0200] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0201] Furthermore, although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0202] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0203] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the appended claims.

Claims

1. A method for implementing fire simulation in fire protection digital twins, characterized in that, The method includes: Acquire scene resource packages and key simulation parameters for fire protection digital twin scenarios, wherein the scene resource packages are scene data containing parameterized 3D models; The scene resource package is converted from the model elements corresponding to the parametric 3D model into fire dynamics simulation units; Instances of simulation models are generated by fusing simulation units and key simulation parameters into a simulation model template. Fire dynamic simulation is performed using the simulation model instance to generate simulation scheme data, which is used to dynamically display the spatiotemporal evolution of fire in the fire protection digital twin scenario. The acquisition of the scene resource package and key simulation parameters for the fire protection digital twin scenario includes: Generate parametric 3D models from drawings containing architectural information; The model data in the parametric 3D model is converted to obtain a scene resource package for the fire protection digital twin scene; The steps for generating a parametric 3D model from drawings carrying architectural information include: constructing a geometric data composite spatial index structure for the drawings carrying architectural information; generating a parametric 3D model from the drawings based on the architectural information they carry; performing a continuous wall search in the geometric data composite spatial index structure based on the list of wall lines to be searched formed by the element identifiers belonging to the wall lines in the drawings; obtaining the wall lines that constitute the continuous walls and the blocks of objects set on the continuous walls; obtaining the physical entities corresponding to the continuous walls on the drawings, and the distribution of objects set on the physical entities, based on the wall lines that constitute the continuous walls and the blocks of objects set on the continuous walls; identifying the physical entities and the objects set on the physical entities to obtain the wall, door, and window data of the drawings; and creating walls and doors and windows on the walls using the wall, door, and window data to obtain a parametric 3D model. The steps of constructing a geometric data composite spatial index structure for drawing elements carrying architectural information include: obtaining the geometric data and attribution information of the elements distributed on the drawing by parsing the drawing; the geometric data of the elements includes two-dimensional geometric range and key point location information; the geometric data composite spatial index structure includes two spatial index structures, namely R-tree and KD-tree.

2. The method according to claim 1, characterized in that, The key simulation parameters include simulation time, heat release efficiency, ignition point, and spray status information.

3. The method according to claim 1, characterized in that, The conversion of the model elements corresponding to the parametric 3D model of the scene resource package into fire dynamics simulation units includes: All model elements in the scene resource package corresponding to the parametric 3D model are subjected to meshing to obtain the corresponding mesh structure; The attribute data of the model elements are mapped to the fire simulation parameters of the grid structure; The fire dynamics simulation unit is obtained by integrating the fire simulation parameters and the grid structure.

4. The method according to claim 1, characterized in that, The generation of simulation model instances by fusing simulation units and key simulation parameters into a simulation model template includes: A predefined simulation model template is instantiated by integrating fire dynamics simulation units and key simulation parameters to generate a simulation model instance. The simulation model template is a framework that includes fire dynamics simulation units and parameter configurations.

5. The method according to claim 1, characterized in that, The process of generating simulation scheme data through dynamic fire simulation using the simulation model instance includes: By using each fire dynamics simulation unit in the simulation model instance to simulate the key simulation parameters for their respective fire description dimensions, simulation scheme data is obtained. The simulation scheme data is time series data that integrates various fire description dimensions.

6. The method according to claim 5, characterized in that, The method further includes: The time series data is segmented and extracted to obtain time slice data corresponding to a time point and spatial slice data corresponding to a fire compartment. The time slice data and spatial slice data describe the spatiotemporal evolution of the fire in the fire protection digital twin scenario mapped by the specified fire compartment at the specified time point.

7. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-6.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1-6.

Images