Simulation training optimization method for building fire

Abstract

The invention discloses a building fire simulation training optimization method, and relates to the data processing related technical field, and the method comprises the steps: collecting building structure data and building surrounding environment data of a target building; building a three-dimensional building simulation model based on computer analog simulation; based on historical fire records of similar buildings of the target building, extracting temperature distribution time sequence data, smoke time sequence data, fire point position data and fire source types; simulating N fire scenes in the three-dimensional building simulation model based on parametric simulation; enabling the training participants to carry out real-time interaction and operation based on virtual reality, and obtaining a behavior data set; and performing feedback optimization of fire simulation training based on an analysis result. The technical problem that the fire response efficiency and effect are insufficient due to the fact that the existing building fire simulation training is incomplete in information acquisition and difficult to truly simulate and restore a complex fire scene is solved, and the technical effect of improving the building fire simulation training efficiency and effect is achieved.

Description

Technical Field

[0001] The present application relates to data processing technology-related fields, and specifically to a simulation training optimization method for building fires. Background Art

[0002] With the acceleration of urbanization, complex buildings such as high-rise buildings and large commercial complexes have sprung up like mushrooms after a rain, bringing great convenience to urban prosperity and people's lives. However, the complexity and density of people in these buildings have also brought unprecedented fire safety challenges. Once a fire occurs, how to quickly and effectively evacuate people, control the spread of fire, and protect people's lives and property has become an important issue that needs to be solved urgently. Traditional building fire simulation training has also gradually exposed some problems. The complexity and authenticity of the simulation scenes are limited, and it is difficult to fully restore the complexity and variability of real fires. Participants in simulation training are usually limited to the fire brigade, lacking effective coordination with other emergency departments and the public. The result analysis and optimization methods of simulation training are relatively single, and it is difficult to adapt to the ever-changing fire situation.

[0003] Therefore, at the current stage, there are technical problems in the technologies related to building fire simulation training, such as incomplete information acquisition and difficulty in realistically simulating and restoring complex fire scenes, which leads to insufficient efficiency and effectiveness in fire response. Summary of the invention

[0004] This application provides a method for optimizing simulation training for building fires, and adopts technical means such as constructing three-dimensional simulation models and parametric simulation to solve the technical problems existing in existing building fire simulation training, such as incomplete information acquisition and difficulty in realistically simulating and restoring complex fire scenes, resulting in insufficient efficiency and effectiveness in fire response, thereby achieving the technical effect of improving the efficiency and effectiveness of building fire simulation training.

[0005] The present application provides a method for optimizing simulation training of building fires, the method comprising: collecting building structure data and building surrounding environment data of a target building by using a deployed sensor array, the sensor array comprising a plurality of sensors inside and outside the target building; constructing a three-dimensional building simulation model based on computer simulation according to the building structure data and the building surrounding environment data; extracting a plurality of temperature distribution time series data, a plurality of smoke time series data, a plurality of fire starting point location data, and a plurality of fire source types based on historical fire records of similar buildings of the target building; simulating N fire scenes in the three-dimensional building simulation model based on parameterized simulation using the plurality of temperature distribution time series data, the plurality of smoke time series data, the plurality of fire starting point location data, and the plurality of fire source types, wherein N is a positive integer greater than or equal to 1; setting training participants in the simulated target building fire scene, enabling the training participants to interact and operate in real time based on virtual reality, collecting the behavior data of the training participants in the simulation training, and obtaining a behavior data set; analyzing the behavior data set, and performing feedback optimization of the fire simulation training based on the analysis result.

[0006] In a possible implementation, the deployed sensor array is used to collect the building structure data and the building surrounding environment data of the target building, and the following processing is performed: the building surrounding environment data is acquired based on remote sensing technology; point cloud data of the surface of the target building is acquired by a laser scanner, and the internal image of the target building is acquired by a surveillance camera inside the target building; the internal image is processed to acquire the internal structure data of the target building; and the point cloud data and the internal structure data are integrated to form the building structure data.

[0007] In a possible implementation, a three-dimensional building simulation model is constructed based on computer simulation according to the building structure data and the building surrounding environment data, and the following processing is performed: based on the building structure data, a three-dimensional geometric model of the target building is established using three-dimensional modeling software; the building surrounding environment data is mapped onto the three-dimensional geometric model; and the three-dimensional building simulation model is obtained by fusion.

[0008] In a possible implementation, the fusion acquires the three-dimensional building simulation model and further performs the following processing: acquires real-time data of the target building, the real-time data including internal real-time data and external real-time data; extracts target building features according to the internal real-time data and the external real-time data; and updates the three-dimensional building simulation model based on the target building features to obtain an updated three-dimensional building simulation model.

[0009] In a possible implementation, based on historical fire records of similar buildings to the target building, multiple temperature distribution time series data, multiple smoke time series data, and multiple fire point location data are extracted, and the following processing is also performed: the historical fire records of similar buildings to the target building are screened out from a historical fire record database; based on the historical fire records, multiple temperature monitoring data and multiple smoke monitoring data at preset time intervals at different locations of the target building are extracted, each of the historical fire records corresponds to M fire point locations, where M is a positive integer; the multiple temperature monitoring data and the multiple smoke monitoring data are sorted to obtain the multiple temperature distribution time series data and the multiple smoke time series data, respectively.

[0010] In a possible implementation, the multiple temperature distribution time series data, the multiple smoke time series data, the multiple fire point location data, and the multiple fire source types are used to simulate N fire scenes in the three-dimensional building simulation model based on parametric simulation, wherein N is a positive integer greater than or equal to 1, and the following processing is also performed: analysis is performed based on the multiple temperature distribution time series data and the multiple smoke time series data to obtain fire analysis results; based on the fire analysis results, the size of the fire and the speed of fire spread are evaluated; and the location of the fire point, the type of fire source, the size of the fire and the speed of fire spread are used as fire scene setting parameters.

[0011] In a possible implementation, based on parametric simulation, N fire scenes are simulated in the three-dimensional building simulation model, and the following processing is also performed: based on parametric simulation, N fire scenes are simulated in the three-dimensional building simulation model; the N simulated fire scenes are run, multiple real-time temperature data and multiple smoke data are observed and recorded, and corresponding real-time temperature change distribution and real-time smoke change distribution are established.

[0012] In a possible implementation, the behavior data set is analyzed, and feedback optimization of the fire simulation training is performed based on the analysis results. The following processing is also performed: feedback data for each training participant is generated based on the behavior data set; a simulation training optimization plan is generated based on the feedback data, and the simulation training optimization plan includes adjusting the fire scene and updating the fire scene setting parameters; and feedback optimization of the fire simulation training is performed based on the simulation training optimization plan.

[0013] The present application proposes a method for optimizing simulation training of building fires, which uses a deployed sensor array to collect building structure data and building surrounding environment data of a target building, wherein the sensor array includes multiple sensors inside and outside the target building; a three-dimensional building simulation model is constructed based on computer simulation according to the building structure data and the building surrounding environment data; based on historical fire records of similar buildings of the target building, multiple temperature distribution time series data, multiple smoke time series data, multiple fire starting point location data, and multiple fire source types are extracted; and based on the multiple temperature distribution time series data, the multiple smoke time series data, the multiple fire starting point location data, and the multiple fire source types, the three-dimensional building simulation model is constructed based on the computer simulation according to the building structure data and the building surrounding environment data. Parametric simulation, simulating N fire scenes in the three-dimensional building simulation model, where N is a positive integer greater than or equal to 1; setting training participants in the simulated target building fire scene, enabling the training participants to interact and operate in real time based on virtual reality, collecting the behavioral data of the training participants in the simulation training, and obtaining a behavioral data set; analyzing the behavioral data set, and performing feedback optimization of the fire simulation training based on the analysis results, thereby solving the technical problems existing in the existing building fire simulation training, such as incomplete information acquisition, difficulty in realistically simulating and restoring complex fire scenes, and insufficient efficiency and effectiveness of fire response, thereby achieving the technical effect of improving the efficiency and effectiveness of building fire simulation training. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of a flow chart of a simulation training optimization method for building fires provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the process of constructing a three-dimensional building simulation model in a simulation training optimization method for building fires provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a method for optimizing simulation training of building fires, such as Figure 1 As shown, the method includes:

[0021] Step S100, using the deployed sensor array to collect the building structure data and building surrounding environment data of the target building, the sensor array includes multiple sensors inside and outside the target building. The deployed sensor array is used to collect the building structure data and building surrounding environment data of the target building. The sensor array is a sensor network composed of multiple sensors, which are carefully arranged inside and outside the target building to collect various data related to the building structure and environment. Specifically, the sensors inside the target building include monitoring cameras, environmental monitoring sensors and electrical safety monitoring sensors. The monitoring camera can monitor multiple images inside the target building; the environmental monitoring sensor includes a temperature sensor, a humidity sensor, a gas concentration sensor (such as a smoke detector), etc.; the electrical safety monitoring sensor is used to monitor the safety status of the electrical system, such as a current monitor, a voltage monitor, an arc detector, etc.; the sensors outside the target building include monitoring cameras and laser scanners to monitor and obtain the surrounding environment data of the target building. These sensors are connected to the central control system by wire or wireless means, and the collected data are transmitted to the data processing center in real time for analysis and processing. By analyzing these data, the structural health status, environmental status and changes in the external environment of the building can be understood in real time.

[0022] In a possible implementation, step S100 further includes step S110, obtaining the data of the surrounding environment of the building based on remote sensing technology. Various information data of the surrounding environment of the building are obtained by using remote sensing technology (such as satellite remote sensing, aerial remote sensing, etc.). It also includes step S120, obtaining point cloud data of the surface of the target building by using a laser scanner, and obtaining the internal image of the target building by using a surveillance camera inside the target building. Using a laser scanner to obtain point cloud data on the surface of a target building, and using a surveillance camera inside the target building to obtain an image of the interior of the target building are two different but complementary data acquisition methods for obtaining detailed three-dimensional information and internal conditions of a building. Specifically, a laser scanner emits a laser beam and receives the signal reflected back, thereby measuring the three-dimensional coordinate information on the surface of the building. The laser scanner can quickly scan the entire building and obtain a large amount of point cloud data, which can accurately represent the shape, size and surface features of the building; by installing a surveillance camera inside the building, the image inside the building is captured and transmitted in real time, which intuitively reflects the layout, facilities, personnel activities, etc. inside the building. The surveillance camera can be installed at key locations of the building, such as corridors, rooms, staircases, etc., so as to fully understand the situation inside the building. It also includes step S130, processing based on the internal image to obtain the internal structure data of the target building. It also includes step S140, integrating the point cloud data and the internal structure data to form the building structure data. By converting point cloud data into a 3D mesh model and then overlaying or mapping the internal structure data (such as images or videos) with the 3D mesh model, the external shape and internal structure information of the building can be integrated to form a complete building structure data.

[0023] Step S200, constructing a three-dimensional building simulation model based on computer simulation according to the building structure data and the building surrounding environment data. Constructing a three-dimensional building simulation model based on the building structure data and the building surrounding environment data using computer simulation technology specifically refers to integrating the collected building structure data (such as the position, size, material, etc. of beams, columns, floor slabs, etc.) and building surrounding environment data (such as terrain, vegetation, roads, meteorological conditions, etc.) into a three-dimensional virtual environment through specific software and algorithms, thereby creating a highly realistic building simulation model.

[0024] In one possible implementation, Figure 2As shown, step S200 further includes step S210, based on the building structure data, using three-dimensional modeling software to establish a three-dimensional geometric model of the target building. Through professional three-dimensional modeling software, the integrated building structure data is converted into a visual three-dimensional stereo model. It also includes step S220, mapping the building surrounding environment data on the three-dimensional geometric model. The collected building surrounding environment data (such as topography, vegetation coverage, water distribution, land use, traffic roads, meteorological climate, etc.) are combined with the established three-dimensional geometric model to present these environmental data in a visual way in the three-dimensional model. It also includes step S230, fusing to obtain the three-dimensional building simulation model. The mapped building surrounding environment data is fused with the three-dimensional geometric model and the building structure data to obtain a three-dimensional building simulation model.

[0025] In a possible implementation, step S230 further includes step S231, obtaining real-time data of the target building, wherein the real-time data includes internal real-time data and external real-time data. It also includes step S232, extracting target building features according to the internal real-time data and the external real-time data. By analyzing the real-time data streams from the inside and outside of the target building, key features or attributes related to the building are identified and extracted, which may include video images captured by surveillance cameras, environmental parameters collected by sensors (such as temperature, humidity, light, air quality, etc.), personnel activity data, equipment operation status, etc. The purpose of extracting target building features is to provide useful information support for subsequent updating of the three-dimensional model. It also includes step S233, updating the three-dimensional building simulation model based on the target building features to obtain an updated three-dimensional building simulation model. Using the key features or attributes extracted from the real-time data inside and outside the target building, the existing three-dimensional building simulation model is modified, adjusted or enhanced to make it more accurately reflect the actual state or changes of the target building.

[0026] Step S300, based on the historical fire records of similar buildings of the target building, extract multiple temperature distribution time series data, multiple smoke time series data, multiple fire point location data, and multiple fire source types. Temperature distribution time series data refers to the temperature data of various areas inside or outside the building (such as floors, rooms, corridors, etc.) at different time points (usually intervals of seconds, minutes or hours) when a fire occurs, reflecting the speed and direction of fire spread, as well as the intensity of the fire; smoke time series data records the changes in smoke concentration over time in various areas inside or outside the building when a fire occurs, reflecting the speed and range of smoke diffusion; fire point location data refers to the specific location of the fire, including floor, room number, specific coordinates, etc., which is an important basis for fire investigation and cause analysis, and is also key information for fire simulation and prevention and control. Extracting fire point location data helps determine the scope and severity of the fire; multiple fire source types refer to the source types that cause fires, such as electrical fires, gas leaks, arson, etc. Extracting data on multiple fire source types can help analyze the fire risks that the target building may face and formulate corresponding fire prevention and control strategies and plans. By analyzing the fire source types in historical fire records, we can understand the common fire source types and their characteristics in similar buildings, and provide targeted suggestions for fire prevention and control of target buildings.

[0027] In a possible implementation, step S300 further includes step S310, screening out the historical fire records of similar buildings of the target building from the historical fire record database. Through specific search and screening conditions, historical fire records of other buildings similar to the target building in terms of type, structure, use, geographical location, etc. are searched in the historical fire record database. It also includes step S320, extracting multiple temperature monitoring data and multiple smoke monitoring data of preset time intervals at different locations of the target building according to the historical fire records, each of the historical fire records corresponds to M fire starting point locations, where M is a positive integer. The preset time interval refers to the interval time for recording temperature and smoke data during the fire, such as every minute, every five minutes, etc. The preset time interval can be determined according to the severity of the fire and the performance of the monitoring equipment. The temperature monitoring data and the smoke monitoring data are important bases for evaluating the development of the fire and judging the fire risk; each historical fire record may correspond to one or more fire starting point locations; the M fire starting point locations indicate that in the historical fire records, each record may correspond to a different number of fire starting point locations, and different fires may occur at different locations due to different reasons and conditions, so the number of fire starting points may be different. The method further includes step S330 of sorting the plurality of temperature monitoring data and the plurality of smoke monitoring data to obtain the plurality of temperature distribution time series data and the plurality of smoke time series data respectively. The collected temperature monitoring data and smoke monitoring data are sorted according to their timestamps or recording order to form two independent time series data sets, namely, temperature distribution time series data and smoke time series data.

[0028] Step S400, using the multiple temperature distribution time series data, the multiple smoke time series data, the multiple fire point location data, and the multiple fire source types, based on parametric simulation, simulate N fire scenes in the three-dimensional building simulation model, where N is a positive integer greater than or equal to 1. Using multiple temperature distribution time series data, multiple smoke time series data, multiple fire point location data and multiple fire source types, N fire scenes are simulated in the three-dimensional building simulation model based on parametric simulation. Specifically, according to the extracted data, the parameters of the fire simulation are set. These parameters may include fire source type, fire source location, fire size, burning rate, spread speed, temperature distribution, smoke concentration, etc. The constructed three-dimensional building simulation model is used as a basis, and the set fire parameters are applied to the three-dimensional building simulation model to simulate the fire. According to the number of fire scenes N that need to be simulated, the above parameter setting and simulation steps are repeated to generate N different fire scenes, each scene has different fire source location, fire source type, fire size and other parameters. The dynamic processes such as temperature distribution, smoke diffusion, and fire spread in each fire scene are observed and recorded. The simulation results are deeply analyzed to understand the key information such as fire characteristics, spread trends, and evacuation paths in different fire scenes. Based on actual data, a variety of possible fire scenes are simulated in the three-dimensional building simulation model to provide strong support and guidance for fire prevention and control and emergency rescue.

[0029] In a possible implementation, step S400 further includes step S410, analyzing the multiple temperature distribution time series data and the multiple smoke time series data to obtain fire analysis results. Using data analysis technology and methods, these time series data are deeply processed and interpreted to extract key information and patterns related to the occurrence, development and impact of the fire, so as to obtain a comprehensive analysis and evaluation result of the fire. It also includes step S420, evaluating the size of the fire and the speed of fire spread according to the fire analysis results. The severity and development trend of the fire are quantitatively or qualitatively evaluated by using key information and patterns extracted from multiple temperature distribution time series data and multiple smoke time series data. The size of the fire can usually be measured by factors such as the height of the flame, the intensity of thermal radiation, the type and quantity of the burning material, etc. For example, the size and distribution of the high temperature area can reflect the concentration and intensity of the fire; the fire spread speed refers to the expansion speed of the fire in time and space. By analyzing the temperature distribution time series data and smoke time series data in the fire analysis results, the spread of the fire at different time points can be understood. For example, by observing the changes in the temperature distribution map, the spread direction and speed of the fire can be determined; and the smoke diffusion map can reflect the diffusion range and speed of the smoke, thereby indirectly inferring the spread of the fire. It also includes step S430, using the location of the fire point, the type of the fire source, the size of the fire and the fire spread speed as fire scene setting parameters. Different fire starting point locations will affect the fire spread path, firefighters' rescue path, and evacuation strategies; the choice of fire source type will directly affect the characteristics and spread speed of the fire. For example, a fire caused by liquid fuel leakage may have a faster spread speed and a larger fire; the size of the fire determines the destructive power of the fire and its impact on the surrounding environment. In simulation training, different sizes of fire can be set as needed to test the firefighters' ability to respond to different fires; the fire spread speed is affected by many factors, such as the nature, quantity, and ventilation conditions of combustibles. In simulation training, by setting different fire spread speeds, different types of fire scenes can be simulated, such as fast-spreading fires and slow-spreading fires, so that firefighters can conduct targeted training and response. By setting these parameters reasonably, a realistic and effective fire simulation scene can be created to help firefighters improve their ability and level in responding to fires.

[0030] In a possible implementation, step S400 further includes step S440, simulating N fire scenes in the three-dimensional building simulation model based on parametric simulation. Using parametric modeling technology, in the established three-dimensional building simulation model, by setting and adjusting different parameters and conditions, N different fire scenes are simulated. The parametric simulation software will simulate the occurrence, development and spread of the fire through calculation and analysis according to the set parameters and conditions, including the spread of flames, the diffusion of smoke, the change of temperature, etc. Through simulation, a three-dimensional fire scene visualization effect can be generated, so that users can intuitively understand the propagation path, impact range and potential risks of the fire in the building. It also includes step S450, running the simulated N fire scenes, observing and recording multiple real-time temperature data and multiple smoke data, and establishing corresponding real-time temperature change distribution and real-time smoke change distribution. In the three-dimensional building simulation model, N fire scenes previously set up through parametric simulation are run in sequence, and multiple temperature data and smoke data in the fire scenes are collected and recorded in real time, reflecting the development of the fire at different time points and different spatial locations. Based on the collected real-time temperature data and smoke data, real-time temperature change distribution maps and smoke change distribution maps are generated and displayed, so as to intuitively understand the temperature change law and heat spread trend of the fire and the diffusion of the smoke generated by the fire in the building or surrounding space.

[0031] Step S500, setting training participants in a simulated target building fire scene, enabling the training participants to interact and operate in real time based on virtual reality, collecting the behavior data of the training participants in the simulation training, and obtaining a behavior data set. Using virtual reality (VR) technology, a highly realistic virtual environment is created for the target building fire scene, and training participants are set in the virtual environment. These participants can be simulated firefighters, emergency personnel or the public. Each participant is assigned a specific role and task, such as evacuating the crowd, finding the source of the fire, and extinguishing the fire. Through VR equipment (such as head-mounted displays, handles, etc.), the training participants can interact and operate with the virtual environment in real time. They can move, observe, select and use virtual tools and equipment to complete their respective tasks. During the simulation training process, the behavior data of the training participants is collected in real time, which may include the movement trajectory, operation records, response time, decision-making process, etc. of the participants. The collected behavior data is sorted, cleaned and annotated to construct a complete behavior data set. This data set will contain the behavior data of multiple training participants in multiple fire scenes, as well as related tags and metadata.

[0032] Step S600, analyze the behavior data set, and perform feedback optimization of fire simulation training based on the analysis results. Perform in-depth analysis on the collected behavior data set to understand the behavior performance of the training participants in the simulated fire scene, including analyzing the decision-making process, reaction time, operation correctness, collaboration ability and other aspects of the participants. According to the analysis results, formulate targeted feedback and optimization strategies, which may include providing additional training materials, increasing the difficulty and complexity of simulation training, improving the environment and equipment of simulation training, optimizing the training process and task settings, etc. Apply the formulated feedback and optimization strategies to the actual fire simulation training, provide direct feedback and guidance to the training participants, and adjust the parameters and settings of the simulation training. After implementing feedback and optimization, continuously monitor the behavior performance of the training participants, collect new behavior data sets, evaluate the effect of feedback optimization through comparative analysis, and further adjust and optimize the strategies as needed to form an iterative and cyclic feedback optimization mechanism to continuously improve the effect and quality of fire simulation training.

[0033] In a possible implementation, step S600 further includes step S610, analyzing based on the behavior data set to generate feedback data for each training participant. By deeply processing and analyzing the collected user behavior data set, key information and behavior patterns related to the training participants are extracted, and personalized feedback data for each training participant is generated based on this information and pattern. It also includes step S620, generating a simulation training optimization plan based on the feedback data, and the simulation training optimization plan includes adjusting the fire scene and updating the fire scene setting parameters. According to the actual performance and feedback of the participants, the fire scene and its setting parameters in the simulation training are adjusted and optimized to improve the effectiveness and pertinence of the training, including adding new fire scenes to cover more emergency situations and operating environments; modifying the design of existing scenes to make them closer to the actual situation; adjusting the complexity and difficulty of the scene to meet the needs of different participants, etc.; updating the scene setting parameters according to the feedback data, which may include the location of the fire source, the size of the fire, the type and quantity of combustibles, ventilation conditions, environmental conditions (such as temperature, humidity, wind speed, etc.), etc. By adjusting these parameters, the simulation results can be closer to the actual situation and the effectiveness of the simulation training can be improved. The method further includes step S630, wherein the fire simulation training is feedback optimized based on the simulation training optimization scheme. According to the collected feedback data from the training participants, the original fire simulation training content and settings are targetedly improved and adjusted to improve the efficiency and effect of the building fire simulation training.

[0034] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A simulation training optimization method for building fire, characterized in that: The method comprises: Collecting building structure data and building surrounding environment data of a target building using a deployed sensor array, wherein the sensor array includes a plurality of sensors inside and outside the target building; Constructing a three-dimensional building simulation model based on computer simulation according to the building structure data and the building surrounding environment data; Based on the historical fire records of similar buildings of the target building, multiple temperature distribution time series data, multiple smoke time series data, multiple fire point location data, and multiple fire source types are extracted; Using the multiple temperature distribution time series data, the multiple smoke time series data, the multiple fire point location data, and the multiple fire source types, based on parameterized simulation, simulate N fire scenes in the three-dimensional building simulation model, where N is a positive integer greater than or equal to 1; Setting training participants in a simulated target building fire scene, enabling the training participants to interact and operate in real time based on virtual reality, collecting behavioral data of the training participants in the simulation training, and obtaining a behavioral data set; The behavior data set is analyzed, and feedback optimization of the fire simulation training is performed based on the analysis results.

2. A building fire simulation training optimization method as claimed in claim 1, characterized in that: The method of collecting the building structure data and the building surrounding environment data of the target building by using the arranged sensor array comprises: Acquiring the surrounding environment data of the building based on remote sensing technology; Using a laser scanner to obtain point cloud data of the surface of the target building, and using a surveillance camera inside the target building to obtain an image inside the target building; Processing based on the internal image to obtain internal structure data of the target building; The building structure data is formed by integrating the point cloud data and the internal structure data.

3. A building fire simulation training optimization method as claimed in claim 1, characterized in that: According to the building structure data and the building surrounding environment data, a three-dimensional building simulation model is constructed based on computer simulation, the method comprising: Based on the building structure data, using three-dimensional modeling software, establish a three-dimensional geometric model of the target building; Mapping the building surrounding environment data on the three-dimensional geometric model; The three-dimensional building simulation model is obtained by fusion.

4. A simulation training optimization method for building fire according to claim 3, characterized in that: The method for fusing and acquiring the three-dimensional building simulation model includes: Acquiring real-time data of the target building, wherein the real-time data includes internal real-time data and external real-time data; Extracting target building features according to the internal real-time data and the external real-time data; Based on the target building features, the three-dimensional building simulation model is updated to obtain an updated three-dimensional building simulation model.

5. A building fire simulation training optimization method as claimed in claim 1, characterized in that: Based on the historical fire records of similar buildings of the target building, a plurality of temperature distribution time series data, a plurality of smoke time series data, and a plurality of fire point location data are extracted, and the method includes: Filtering out the historical fire records of similar buildings to the target building from a historical fire record database; Extracting a plurality of temperature monitoring data and a plurality of smoke monitoring data at preset time intervals at different locations of the target building according to the historical fire records, each of the historical fire records corresponding to M fire starting points, where M is a positive integer; The plurality of temperature monitoring data and the plurality of smoke monitoring data are sorted to obtain the plurality of temperature distribution time series data and the plurality of smoke time series data respectively.

6. A building fire simulation training optimization method as claimed in claim 1, characterized in that: Using the multiple temperature distribution time series data, the multiple smoke time series data, the multiple fire point location data, and the multiple fire source types, based on parameterized simulation, simulating N fire scenes in the three-dimensional building simulation model, wherein N is a positive integer greater than or equal to 1, the method includes: Performing analysis based on the multiple temperature distribution time series data and the multiple smoke time series data to obtain a fire analysis result; Based on the fire analysis results, assess the size of the fire and the speed of fire spread; The fire starting point location, the fire source type, the fire size and the fire spread speed are used as fire scene setting parameters.

7. A method for optimizing simulation training of building fire according to claim 6, characterized in that: Based on parametric simulation, N fire scenes are simulated in the three-dimensional building simulation model, and the method includes: Simulating N fire scenarios in the three-dimensional building simulation model based on parametric simulation; The N simulated fire scenes are run, a plurality of real-time temperature data and a plurality of smoke data are observed and recorded, and corresponding real-time temperature change distribution and real-time smoke change distribution are established.

8. A method for optimizing simulation training of building fire according to claim 1, characterized in that: The behavior data set is analyzed, and feedback optimization of fire simulation training is performed based on the analysis result, the method comprising: Analyze the behavioral data set to generate feedback data for each training participant; Generate a simulation training optimization plan based on the feedback data, wherein the simulation training optimization plan includes adjusting the fire scene and updating the fire scene setting parameters; Feedback optimization is performed on the fire simulation training based on the simulation training optimization scheme.

Images