Fire-fighting internet-of-things dynamic management and control platform based on virtual reality

Through virtual reality technology, the construction of a dynamic control platform for fire protection IoT has been solved, and the real-time problems of fire monitoring and prediction in fire protection technology have been achieved, accurate prediction and efficient prevention and control of fire protection situations have been achieved, and the allocation and response capabilities of fire protection resources have been improved.

CN118976217APending Publication Date: 2024-11-19SHANGHAI LINBO CONSTR ENG CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410894194.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing fire protection technology lacks real-time performance in fire monitoring and prediction, resulting in insufficient prevention and control accuracy, and the inability to effectively identify key prevention and control areas, affecting the fire protection effect.

Method used

Adopt a fire protection IoT dynamic management and control platform based on virtual reality, real-time real-time through modules such as the construction of three-dimensional fire protection scene models, extraction of key prevention and control areas, fire equipment module layout, regional environmental data acquisition, fire analysis and whole-region fire trend prediction. Monitor and predict, generate emergency response plans.

Benefits of technology

It improves the effectiveness and accuracy of fire prevention and control, can predict fire situations in advance, and ensures efficient allocation and precise response of fire protection resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118976217A_ABST
    Figure CN118976217A_ABST
Patent Text Reader

Abstract

The invention discloses a fire-fighting Internet of Things dynamic management and control platform based on virtual reality, and relates to the technical field of fire-fighting control, and the platform comprises the steps: obtaining target region information, constructing a three-dimensional fire-fighting scene model, collecting scene space features, extracting a plurality of key prevention and control regions, and setting a plurality of edge analysis nodes for the plurality of key prevention and control regions, fire-fighting equipment module deployment and control are carried out; performing real-time environment monitoring to obtain a plurality of regional environment data sequences; and carrying out local fire behavior prediction and local fire behavior grade evaluation, obtaining a plurality of fire behavior analysis results, obtaining a global fire behavior trend prediction result in combination with the three-dimensional fire-fighting scene model, generating an emergency processing scheme, and carrying out fire behavior processing. The technical problems that in the prior art, the prevention and control accuracy is insufficient, and fire monitoring and prediction are lack of real-time performance are solved, and the technical effects that fire-fighting fire preposed prediction is carried out based on the virtual reality technology, and the effectiveness and accuracy of fire prevention and control are improved are achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of fire control technology, and in particular to a fire protection Internet of Things dynamic management and control platform based on virtual reality. Background Art

[0002] With the development of society and the acceleration of urbanization, the importance of fire safety has become increasingly prominent. Traditional fire control methods often have many limitations. In terms of understanding the fire situation in the target area, it may mainly rely on manual inspections and some simple monitoring equipment, and it is impossible to accurately identify key prevention and control areas, which in turn affects the effectiveness of prevention and control. In terms of fire monitoring, data collection is not real-time enough.

[0003] Existing technologies have the problem of insufficient prevention and control accuracy and lack of real-time technical issues in fire monitoring and prediction. Summary of the invention

[0004] This application provides a fire protection Internet of Things dynamic management and control platform based on virtual reality, which is used to solve the technical problems of insufficient prevention and control accuracy in the existing technology and lack of real-time performance in fire monitoring and prediction.

[0005] In view of the above problems, this application provides a fire protection Internet of Things dynamic management and control platform based on virtual reality.

[0006] This application provides a fire protection Internet of Things dynamic management and control platform based on virtual reality, which includes:

[0007] A three-dimensional fire scene model construction module, which is used to obtain target area information and construct a three-dimensional fire scene model based on virtual reality technology; a key control area extraction module, which is used to collect scene space features according to the three-dimensional fire scene model, and extract multiple key control areas according to the scene space features, and the multiple key control areas are provided with control level identification and location identification; a fire equipment module control module, which is used to set multiple edge analysis nodes for multiple key control areas, and control fire equipment modules based on the Internet of Things technology; a regional environment data sequence acquisition module, which is used to construct a regional sensor network a fire situation analysis result acquisition module, the fire situation analysis result acquisition module is used to receive the multiple regional environmental data sequences according to the multiple edge analysis nodes, perform local fire situation prediction and local fire situation level assessment, and obtain multiple fire situation analysis results; a global fire situation trend prediction result acquisition module, the global fire situation trend prediction result acquisition module is used to perform comprehensive fire situation trend prediction through the multiple fire situation analysis results in combination with the three-dimensional fire fighting scene model, and obtain the global fire situation trend prediction result; an emergency handling plan generation module, the emergency handling plan generation module is used to generate an emergency handling plan based on the global fire situation trend prediction result, and call the fire fighting equipment module to handle the fire situation.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] A three-dimensional fire scene model construction module is used to construct a three-dimensional fire scene model; a key prevention and control area extraction module is used to collect scene space features according to the three-dimensional fire scene model, and extract multiple key prevention and control areas according to the scene space features, and the multiple key prevention and control areas are provided with prevention and control level identification and location identification; a fire equipment module deployment module is used to set multiple edge analysis nodes for multiple key prevention and control areas, and to deploy fire equipment modules based on the Internet of Things technology; a regional environmental data sequence acquisition module is used to build a regional sensor network, perform real-time environmental monitoring, and obtain multiple regional environmental data sequences; a fire analysis result acquisition module is used to receive the multiple regional environmental data sequences according to the multiple edge analysis nodes, perform local fire prediction and local fire level assessment, and obtain multiple fire analysis results; a global fire trend prediction result acquisition module is used to perform comprehensive fire trend prediction based on the multiple fire analysis results and the three-dimensional fire scene model, and obtain global fire trend prediction results; an emergency treatment plan generation module is used to generate an emergency treatment plan based on the global fire trend prediction results, and call the fire equipment module to handle the fire. The technical effect of conducting pre-emptive prediction of fire situations based on virtual reality technology and improving the effectiveness and accuracy of fire prevention and control has been achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of the structure of a fire protection Internet of Things dynamic management and control platform based on virtual reality provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the process of extracting multiple key prevention and control areas from the virtual reality-based fire protection Internet of Things dynamic management and control platform provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: three-dimensional fire scene model construction module 10, key prevention and control area extraction module 20, fire equipment module deployment module 30, regional environment data sequence acquisition module 40, fire situation analysis result acquisition module 50, global fire situation trend prediction result acquisition module 60, emergency treatment plan generation module 70. DETAILED DESCRIPTION

[0014] This application provides a fire protection Internet of Things dynamic management and control platform based on virtual reality, which is used to solve the technical problems of insufficient prevention and control accuracy in the existing technology and lack of real-time fire monitoring and prediction.

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] Embodiment 1

[0017] like Figure 1 As shown, the present application provides a fire protection Internet of Things dynamic management and control platform based on virtual reality, and the fire protection Internet of Things dynamic management and control platform based on virtual reality includes:

[0018] The three-dimensional fire scene model construction module 10 is used to obtain target area information and construct a three-dimensional fire scene model based on virtual reality technology.

[0019] Specifically, obtaining information about the target area is the basis of this step, which involves the use of a variety of technologies and means, such as using laser scanning equipment to accurately measure the spatial size and shape of the target area, obtaining geographic data, building distribution and other information about the area through the Geographic Information System (GIS), and collecting detailed information about the specific location and parameters of firefighting facilities in the area. Building a three-dimensional fire scene model based on virtual reality technology is to use the powerful modeling and rendering capabilities of virtual reality to convert the acquired target area information into a digital model, including the undulations of the terrain, the geometric shapes of the buildings, the direction of the roads, etc., which are all accurately constructed, which helps to be more targeted when planning firefighting strategies and accurately allocate resources according to the characteristics and risk levels of different areas.

[0020] The key prevention and control area extraction module 20 is used to collect scene space characteristics according to the three-dimensional fire scene model, and extract multiple key prevention and control areas according to the scene space characteristics, and the multiple key prevention and control areas are provided with prevention and control level identification and location identification.

[0021] Specifically, when conducting an in-depth analysis of the three-dimensional fire scene model, image recognition and data analysis software are used to capture every scene space feature detail contained in the model in an all-round way. For each area in the model, its geometry, area size, and connection relationship with the surrounding areas are carefully analyzed. At the same time, the layout of the building is studied in depth, including the height, structure, and spacing between buildings, which can reflect potential fire risk factors. Accurately measuring and evaluating the width, curvature, and connectivity of passages and corridors with other areas is crucial for accurate prevention and control and real-time monitoring and early warning of the target area. Based on the rich scene space feature data collected, those critical prevention and control areas are accurately extracted. For example, for a factory area, warehouses storing a large amount of hazardous chemicals and workshops with complex electrical equipment may be identified as key prevention and control areas. For a high-rise residential area, the commercial area on the ground floor, the evacuation passage, and the equipment room on the roof may be the focus of attention. Each key control area has a corresponding control level mark, which involves a detailed assessment of the fire hazards in the area, such as whether there are a large number of flammable materials in the area, whether there is a possibility of fire sources, etc. At the same time, the population density in the area, the casualties and property losses that may be caused after the fire occurs will be comprehensively considered. For some areas with extremely high fire risks and extremely serious consequences once a fire occurs, the highest control level mark will be given, such as red. For areas with relatively low risks, lower control levels may be given, such as yellow or green. The location mark of each key control area is determined by a precise coordinate system, which corresponds to the actual geographical location to ensure that these areas can be found accurately in reality. The location mark may include specific latitude and longitude coordinates, building names, or specific area numbers. For example, in a model of a large commercial complex, a key control area may be marked as the southeast corner area on the third floor of Building 5. Such a clear mark allows firefighters to quickly find the target location when they receive a mission.

[0022] The fire-fighting equipment module control module 30 is used to set up multiple edge analysis nodes for multiple key prevention and control areas, and to perform fire-fighting equipment module control based on the Internet of Things technology.

[0023] Specifically, for the extracted key control areas, multiple edge analysis nodes are set according to their specific characteristics and needs. These edge analysis nodes are distributed in key locations of each key control area, and can collect and analyze various types of information about the surrounding environment in real time. Each edge analysis node is equipped with advanced sensors and data processing modules, which can accurately monitor key parameters such as temperature, humidity, and smoke concentration. At the same time, with the help of Internet of Things technology, comprehensive fire equipment module deployment work is carried out. Through the connection of the Internet of Things, various types of fire equipment, such as fire extinguishers, fire hydrants, automatic sprinkler systems, etc., are closely associated with edge analysis nodes. Each fire equipment is given a unique identity and location information to ensure that it can be quickly located and called when needed. In the deployment process, the specific conditions of each key control area are fully considered. For example, in areas with high fire risks and dense personnel, the number and types of fire equipment will be increased to ensure that there are sufficient resources available in emergency situations. For some special areas, such as places where valuables or precision instruments are stored, special fire extinguishing equipment, such as gas fire extinguishing systems, are equipped to avoid damage to items caused by traditional fire extinguishing methods. Through the real-time communication function of the Internet of Things, the edge analysis node can promptly transmit the collected information to the fire monitoring center. Once the monitoring data of a key prevention and control area is abnormal, such as a sharp rise in temperature or the smoke concentration reaches the warning value, the system will immediately issue an alarm. The fire monitoring center can make decisions quickly based on this information and mobilize the corresponding fire-fighting equipment to respond, thereby achieving precise prevention and control, real-time monitoring and early warning, and efficient allocation of fire-fighting resources.

[0024] The regional environment data sequence acquisition module 40 is used to construct a regional sensor network, perform real-time environmental monitoring, and acquire multiple regional environment data sequences.

[0025] Specifically, a comprehensive and efficient regional sensor network is built. This network consists of many sensor nodes distributed in different regions. These sensor nodes cover a variety of types, such as temperature sensors, humidity sensors, smoke sensors, gas sensors, etc., which comprehensively monitor all aspects of the environment and ensure that the sensor network can cover every key area that needs to be monitored, whether it is an open field or a complex building interior space. Start real-time environmental monitoring. The sensor nodes continuously collect various environmental data in the area, including real-time temperature changes, humidity fluctuations, smoke concentration levels, and possible harmful gas content. Each sensor node collects data at a very high frequency to ensure that it can capture subtle changes in the environment and instantaneous abnormalities. Over time, these continuously collected data form multiple regional environmental data sequences, which record in detail the environmental status of each area at different time points. It provides a solid foundation and strong support for subsequent environmental analysis, risk warning and decision-making.

[0026] The fire analysis result acquisition module 50 is used to receive the multiple regional environmental data sequences according to the multiple edge analysis nodes, perform local fire prediction and local fire level assessment, and obtain multiple fire analysis results.

[0027] Specifically, each edge analysis node, as a key node for receiving regional environmental data sequences, maintains a high degree of sensitivity and accuracy. When multiple regional environmental data sequences are transmitted to the edge analysis nodes, they use built-in advanced algorithms and models (such as neural network models, vector machine algorithms, etc.) to start in-depth analysis and processing. For example, the neural network model learns key features and patterns from a large amount of historical environmental data and known fire cases. When receiving a new regional environmental data sequence, the neural network can quickly identify the features related to potential fires and make predictions based on this. At the same time, when evaluating the local fire level, multiple key factors will be fully considered, such as the extent to which the temperature exceeds the safety threshold, the time required for the smoke concentration to reach a specific dangerous level, and the degree of abnormality of other environmental parameters. The local fire level assessment is based on the prediction and further evaluates the severity of the possible fire. It will comprehensively consider multiple factors, such as the specific value of the temperature, the level of smoke concentration, and the degree of abnormality of other relevant environmental indicators. Based on these comprehensive considerations, the fire is divided into different levels, such as mild, moderate, severe, etc. This will allow for a more accurate understanding of the extent of potential fire hazards. Eventually, multiple fire analysis results will be obtained, and each edge analysis node will produce a specific analysis result for the area it is responsible for, including a prediction of whether there is a fire and a corresponding fire level assessment. These multiple fire analysis results can be summarized to fully understand the specific fire conditions in different areas within the entire monitoring range, providing an important basis for subsequent decision-making and response measures.

[0028] The module 60 for obtaining the global fire situation trend prediction result is used to perform a comprehensive fire situation trend prediction based on the multiple fire situation analysis results in combination with the three-dimensional fire fighting scene model to obtain the global fire situation trend prediction result.

[0029] Specifically, multiple fire analysis results are local analysis conclusions from different edge analysis nodes on their respective areas, and contain key information about the possibility and level of fire in each area. Combined with the three-dimensional fire scene model, this three-dimensional fire scene model is a highly refined restoration of the actual monitoring area, including detailed information such as the three-dimensional structure, internal layout, channel direction, and specific location of fire-fighting facilities of all buildings. To closely combine multiple fire analysis results with this model is to accurately place the fire situation in each area to the corresponding spatial position of the model. For example, in the model, you can clearly see which areas are marked as having a higher risk of fire, and the spatial relationship between these areas and surrounding buildings, channels, etc. Next, a comprehensive fire trend prediction is carried out to determine the possible development direction and speed of the fire based on the fire analysis results of each area. For example, if the temperature in an area continues to rise rapidly and the smoke concentration increases sharply, combined with the wind direction and building structure around it, it can be inferred that the fire may spread in a specific direction. Considering the distribution of channels and fire-fighting facilities in the three-dimensional fire scene model, these factors are evaluated to hinder or promote the spread of fire. For example, if there are facilities such as fire hydrants on the path where the fire may spread, it can be estimated that the development of the fire can be delayed to a certain extent; but if the passage is narrow or blocked, it may accelerate the spread of the fire. The final result of the global fire trend forecast will cover the future development of the fire in the entire monitoring area, including the area where the fire may occur, the intensity of the fire, and the key areas that may be affected. It is not just a simple summary of the fire analysis results of each individual area, but through in-depth analysis, a comprehensive and accurate forecast of the overall trend of the fire in the entire area is obtained, which can accurately control the fire situation in the entire area and improve the accuracy of prevention and control.

[0030] The emergency treatment plan generation module 70 is used to generate an emergency treatment plan based on the global fire trend prediction result and call the fire fighting equipment module to handle the fire.

[0031] Specifically, based on the understanding of the global fire trend forecast results, a comprehensive emergency response plan is quickly formulated. This plan includes many aspects, such as determining the deployment location of firefighting forces, planning the routes of firefighting vehicles, clarifying the firefighting strategies in different areas (whether it is direct firefighting or controlling the spread of fire, etc.), and arranging the order and path of personnel evacuation. The plan will be as detailed and comprehensive as possible to cope with various possible situations. After generating the emergency response plan, the corresponding firefighting equipment modules are called according to the requirements of the plan. These firefighting equipment modules include various types of fire trucks, such as fire-fighting fire trucks, ladder fire trucks, high-spray fire trucks, etc., and may also include other related equipment, such as firefighting robots, smoke exhaust equipment, etc. Through precise calling and coordination, these equipment can be quickly put into fire handling to ensure that the calling of firefighting equipment modules is highly matched with the actual fire situation needs.

[0032] In one possible implementation, Figure 2 As shown, the key control area extraction module 20 is also used for:

[0033] The three-dimensional fire scene model is embedded with real-time scene information, and scene space feature collection is performed based on the real-time scene information. The scene space features include but are not limited to functional zoning information, local area location information, and local area connectivity information.

[0034] Based on the functional zoning information, multiple initial regional prevention and control levels are determined.

[0035] Based on the local area location information and the local area connectivity information, an adjacent area impact assessment is performed to generate a plurality of area impact coefficients.

[0036] The multiple initial regional prevention and control levels are corrected using the multiple regional impact coefficients to obtain multiple local regional prevention and control levels.

[0037] Arrange the local areas in order according to their prevention and control levels, and extract multiple key prevention and control areas.

[0038] Specifically, by embedding real-time scene information into the three-dimensional fire scene model, the dynamic changes of various elements in the fire scene can be reflected in real time. For example, the layout of buildings, the smoothness of passages, the location of fire-fighting facilities, etc., to collect scene space features. The functional zoning information can clarify the purpose of each area, such as office area, storage area, etc., which helps to understand the fire risk characteristics of different areas; local area location information can accurately determine the specific location of each area in the overall scene, which is very important for planning fire action routes and determining key areas of concern; local area connectivity information reveals the connection relationship between various areas, such as which areas are directly connected, which is of great significance for the prediction of fire spread and the formulation of prevention and control strategies.

[0039] The initial regional control level is determined based on the functional zoning information. For example, the storage area where flammable items are stored is set to a higher control level because once a fire occurs, it may spread rapidly and cause greater harm; while the control level of the general office area may be relatively low. In this way, preliminary resource allocation planning can be carried out according to the potential risk level of different areas, so that a targeted response can be made quickly in the event of a fire.

[0040] The impact of adjacent areas is evaluated based on the location information and connectivity information of local areas. For example, if there are two adjacent areas with a larger fire in one area, the impact on the other area can be evaluated based on the connectivity between them, thereby generating a corresponding regional impact coefficient. This coefficient can quantify the mutual impact between adjacent areas and help better predict the possible development direction and impact range of the fire.

[0041] The initial regional control level is corrected through the regional impact coefficient to make the control level more in line with the actual situation. For example, the initial control level of a certain area is low, but due to the greater influence of its adjacent areas, its control level will be improved after correction, thus obtaining a more accurate local area control level. This can more finely adjust resource allocation and response strategies to ensure that the most reasonable decision can be made when facing complex fire situations.

[0042] By arranging the prevention and control levels of multiple local areas in order, it is clear which areas have the highest prevention and control levels, which are second, etc. The extracted key prevention and control areas are the areas that need to be focused on and given priority, such as dispatching firefighting forces to key prevention and control areas for monitoring and prevention, or giving priority to firefighting and rescue operations in these areas when a fire occurs, so as to minimize the losses and harm caused by the fire.

[0043] In a possible implementation, the fire equipment module control module 30 is further used for:

[0044] Based on the multiple key prevention and control areas, the corresponding multiple prevention and control area function types and multiple local area prevention and control levels are extracted respectively.

[0045] According to the functional types of the multiple prevention and control areas and the prevention and control levels of the multiple local areas, an edge computing power assessment is performed to determine the computing power of multiple edge nodes.

[0046] Based on the computing power of multiple edge nodes, configure multiple edge analysis nodes.

[0047] Specifically, for each key control area, its specific purpose needs to be analyzed in detail to clarify which control area function type it belongs to, such as an area for storing flammable materials or an area with dense personnel. At the same time, the local area control level of the key control area previously determined is accurately extracted to provide basic data for subsequent analysis and decision-making. For example, a key control area is determined to be a storage area (control area function type), and its local area control level is advanced.

[0048] According to the different functional types of the prevention and control areas and the local area prevention and control levels, various factors are comprehensively considered to evaluate the required edge computing power. Areas with complex functional types and high prevention and control levels often require more powerful edge computing power to support their monitoring, analysis and response needs. Through in-depth analysis and calculation of these factors, the computing power required for each edge node is accurately determined. For example, the storage area may need to monitor a large amount of item status and environmental data in real time, so it requires higher edge computing power; while ordinary areas with lower prevention and control levels may require relatively less computing power.

[0049] According to the determined computing power of multiple edge nodes, the corresponding edge analysis nodes are reasonably configured to ensure that each edge analysis node has sufficient computing power to handle the tasks of the key prevention and control areas it is responsible for, including deploying appropriate hardware equipment or adjusting the allocation of virtual resources. For example, the edge nodes corresponding to the storage area are configured with high-performance processors and sufficient memory to meet their requirements for edge computing power, so that data analysis and real-time monitoring can be carried out efficiently, and potential fire safety hazards can be discovered and responded to in a timely manner.

[0050] In a possible implementation, the fire equipment module control module 30 is further used for:

[0051] Based on the functional types of the multiple control areas and the local area control levels, firefighting equipment is selected to determine the equipment type set and equipment quantity set.

[0052] Obtain key prevention and control locations in multiple local areas, and determine the installation location information of fire-fighting equipment.

[0053] Based on the equipment type set, equipment quantity set and fire equipment installation location information, fire equipment modules are deployed and controlled, and communication connections are established with the multiple edge analysis nodes.

[0054] Specifically, when selecting fire-fighting equipment, the functional types of multiple prevention and control areas need to be fully considered. For example, for production areas, large fire extinguishers that can deal with industrial fires, such as dry powder fire extinguishers, may be needed; while office areas are more suitable for small, lightweight and easy-to-operate fire extinguishers. At the same time, the local area prevention and control level also plays a key role. Areas with high prevention and control levels, such as places where important materials are stored or where there are high risks, need to be equipped with advanced automatic fire extinguishing systems, intelligent fire detectors, etc. Based on these factors, select the type of equipment suitable for each area, such as the type of fire extinguisher, the type of fire extinguishing system, etc., to form an equipment type set, and then determine the specific number of each type of equipment based on the size of the area, the degree of potential fire risk, etc., to form an equipment quantity set.

[0055] Conduct in-depth surveys and analyses of local areas, and identify key prevention and control locations with high potential fire risks and serious consequences once a fire occurs, through research on regional layout, facility distribution, and personnel activity patterns. These locations include warehouse corners where a large number of flammable materials are stored, areas where electrical equipment is concentrated and the load is large, and key nodes of evacuation passages where there are dense personnel. After determining these key prevention and control locations, start planning their installation locations based on the functional characteristics and effective coverage of different fire-fighting equipment. For example, fire extinguishers should be placed near key prevention and control locations for easy access to ensure that they can be quickly obtained and used in an emergency. At the same time, it is also necessary to comprehensively consider factors such as the feasibility of installation, the convenience of maintenance, and the coordination with other facilities. It is necessary to weigh and select from multiple alternative locations to find the most suitable installation location, and finally form detailed and accurate fire-fighting equipment installation location information to provide clear guidance and basis for subsequent fire-fighting equipment installation work, so as to maximize the effectiveness of fire-fighting equipment.

[0056] After having a clear set of equipment types, equipment quantity sets, and fire equipment installation location information, start the specific fire equipment module deployment work. According to the equipment type, the corresponding fire equipment such as fire extinguishers, fire hydrants, fire alarms, etc. are accurately placed in the predetermined installation location. In the deployment process, attention should be paid to the installation quality and stability of the equipment to ensure that it can work normally under various environmental conditions. At the same time, these fire equipment modules should establish reliable communication connections with multiple edge analysis nodes. Through various communication technologies and line laying, information can be exchanged between fire equipment and edge analysis nodes in real time. Edge analysis nodes can obtain the status information of fire equipment at any time, such as whether a fire extinguisher has been moved, whether a fire alarm has detected an abnormality, etc. Once there is any abnormal situation or potential risk, the edge analysis node can respond quickly, issue an alarm in time, or take corresponding control measures.

[0057] In a possible implementation, the fire situation analysis result acquisition module 50 is further used to:

[0058] The multiple edge analysis nodes respectively include corresponding fire situation prediction units and fire situation assessment units.

[0059] Based on historical fire records, fire characteristic data sequences are extracted, fire development curves are drawn to perform fire trend analysis, and supervised training is performed in combination with corresponding disaster environment characteristic sequences to obtain the fire prediction unit.

[0060] The historical fire development trend and historical fire impact data are obtained, and the fire assessment unit is obtained through training.

[0061] According to the fire situation prediction unit and the fire situation assessment unit, analysis is performed in combination with the multiple regional environmental data sequences to obtain multiple fire situation analysis results.

[0062] Specifically, corresponding fire prediction units and fire assessment units are set in multiple edge analysis nodes. These units are key components for accurate analysis and assessment of fire conditions. The fire prediction unit is mainly responsible for estimating and speculating on possible future fires, while the fire assessment unit focuses on comprehensive analysis and evaluation of fires that have occurred or are occurring, in order to determine their degree of harm, development trend, and other aspects.

[0063] Comprehensively collect historical fire records and preprocess these data, including data cleaning, denoising and format conversion, to ensure data accuracy and consistency. Extract key fire characteristics from preprocessed historical fire data, such as fire occurrence time, scale, fire source type, etc. These characteristics will be used for subsequent fire trend analysis and prediction. Draw fire development curves based on the extracted fire characteristic data. These curves can show the development trend of fire over time and help analysts understand the evolution of fire. At the same time, obtain environmental feature sequences corresponding to fires, such as temperature, humidity, wind speed and other information. These environmental features may have an impact on the development and spread of fires. Combine the fire development curve with the disaster environment feature sequence, use the neural network algorithm to let the fire prediction unit learn the relationship between them, and improve the accuracy and reliability of the fire prediction unit by continuously adjusting and optimizing the model parameters. Use the validation set to evaluate the trained fire prediction unit, and further optimize the model based on the evaluation results to improve its performance and generalization ability. After multiple iterations and optimizations, a fire prediction unit that can accurately predict future fire trends is finally obtained. The unit can predict and analyze possible future fires based on input real-time data and environmental information.

[0064] Collect a large amount of historical fire data, including information such as the time, location, scale, and fire fighting of the fire. This data can come from multiple channels such as fire departments, insurance companies, and scientific research institutions. Then, we clean and preprocess this data to remove noise and outliers, and convert it into a format suitable for machine learning algorithms. Select a neural network algorithm to train the fire assessment model. During the training process, we divide the historical fire data into a training set and a test set, use the training set to train the model, and use the test set to evaluate the performance of the model. During the training process, continuously adjust and optimize the parameters of the algorithm or model to improve its ability to fit historical data and prediction accuracy. After a large amount of data training and repeated optimization and adjustment, we finally successfully trained a fire assessment unit that can effectively assess the fire situation.

[0065] Multiple regional environmental data sequences are input into the fire prediction unit and the fire assessment unit. These regional environmental data sequences contain various information such as meteorological data (temperature, humidity, wind speed, etc.), geographical features (topography, altitude, etc.), vegetation coverage, building distribution and materials of each region. The fire prediction unit will predict and infer the possibility and trend of future fires in each region based on these environmental data and the patterns and laws it has learned. It will output the probability prediction value of fires in each region in different time periods, or give an analysis of key factors that may cause fires. At the same time, the fire assessment unit will comprehensively evaluate the potential impact of fires in each region based on the input environmental data and its own evaluation capabilities, including analyzing the possible spread speed, scope, degree of damage to buildings and infrastructure, and impact on the ecological environment once a fire occurs under specific environmental conditions. Then, the prediction results of the fire prediction unit and the evaluation results of the fire assessment unit are comprehensively analyzed and closely combined with the specific regional environmental data sequences to obtain multiple detailed fire analysis results. For example, for a certain area, the following analysis results may be obtained: the probability of a fire occurring in the next week is medium, and if it occurs, the fire may spread quickly and may cause moderate damage to some surrounding buildings.

[0066] In a possible implementation, the global fire situation trend prediction result acquisition module 60 is further used to:

[0067] Based on the plurality of fire condition analysis results, a plurality of local fire condition prediction results and a plurality of local fire condition assessment levels are extracted.

[0068] The local area location information and local area connectivity information of the three-dimensional fire scene model are obtained, and the fire spread simulation analysis is performed in combination with the multiple local fire prediction results and multiple local fire assessment levels to obtain the global fire trend prediction results.

[0069] Specifically, the multiple fire analysis results obtained are carefully disassembled and analyzed, and the specific fire prediction results for each local area are extracted from these results, such as the specific probability value or possibility description of a fire occurring in a local area. At the same time, the fire assessment level corresponding to each local area is also determined, such as high, medium, and low levels. These levels reflect the assessment of the severity of the fire in the local area, the degree of potential harm, etc.

[0070] The local area location information of the three-dimensional fire scene model is obtained, which includes the specific coordinates, orientation and other information of each local area in the entire scene, so that the relative position relationship of each local area can be accurately known. At the same time, the local area connectivity information is obtained, which can be road connection conditions, spatial channel conditions, etc., indicating the mutual accessibility and correlation between local areas. Then, these location and connectivity information are combined with the multiple local fire prediction results and local fire assessment levels extracted previously. Using the cellular automaton algorithm, the entire scene is divided into cells, each cell represents a local area, and its initial state is set according to the extracted local fire prediction results and assessment levels. For example, the cells that have caught fire are marked as a specific state, and the cells that are not on fire but have a higher risk are marked as another state. According to the rules of the cellular automaton, the burning cells may spread the fire to the adjacent cells at each time step. The probability and conditions of the spread are set based on the actual situation, such as taking into account factors such as distance, wind direction, and building obstruction. At the same time, combined with the local area connectivity information, it is determined whether the propagation path between cells is unobstructed. As time goes by, the state of the cells is constantly updated to simulate the spread of the fire in the entire scene. After such simulation analysis, a global fire trend prediction result is finally obtained. This result comprehensively describes the possible fire development trend in the entire area after considering various factors, including which areas may be affected first, the possible direction and speed of the fire spread, and which areas may face greater risks in the future. This provides an important basis for firefighting decision-making and resource allocation.

[0071] In a possible implementation, the global fire situation trend prediction result acquisition module 60 is further used to:

[0072] Based on the multiple local fire prediction results, multiple fire development trends in multiple local areas are extracted.

[0073] The regional risk levels are ranked based on the multiple fire development trends and combined with multiple local fire assessment levels, and multiple high-risk areas are extracted.

[0074] For the multiple high-risk areas, spatial flow analysis is performed in combination with the local area location information and the local area connectivity information to determine the central impact area.

[0075] Based on the central impact area, fire spread simulation analysis is performed in combination with the multiple high-risk areas to obtain global fire trend prediction results.

[0076] Specifically, based on the multiple local fire prediction results previously determined, the specific conditions of each local area are analyzed. For example, the fire in a certain local area may show a trend of rapid spread over time, while the fire in another local area may be relatively stable but continue to burn, etc., and the different fire development trends of multiple local areas are extracted.

[0077] These fire development trends are combined with the corresponding local fire assessment levels. Based on factors such as the speed of fire development and severity, as well as the potential degree of harm reflected by the assessment level, a comprehensive analysis of each local area is conducted, and these areas are ranked according to the level of risk. This will enable us to clearly extract those local areas with higher risks, which may be the areas that need the most priority attention and response.

[0078] For the multiple high-risk areas extracted, spatial flow analysis is performed by combining the local area location information and the local area connectivity information, taking into account factors such as air flow, personnel flow, and possible fire transmission paths, to determine which area among these high-risk areas is in a relatively central position and has a greater impact on the surrounding areas, that is, it is determined as the central impact area.

[0079] Taking the central impact area as the core, combined with the previously identified multiple high-risk areas, the cellular automation algorithm is used again to conduct a more detailed fire spread simulation analysis, considering the radiation and driving effect of the central impact area on other high-risk areas and surrounding areas, and calculating the possible spread and evolution of the fire between these areas through the simulation algorithm, and finally obtaining a more accurate and comprehensive global fire trend prediction result. This result can clearly show the possible development trend of the fire in the entire area, the key affected areas, and the key locations that need special attention.

[0080] In a possible implementation, the global fire situation trend prediction result acquisition module 60 is further used to:

[0081] The central influence area is taken as a first diffusion center, and a first diffusion coefficient is configured.

[0082] The remaining high-risk areas except the central impact area are used as auxiliary diffusion points, and multi-level diffusion coefficients are configured according to the regional risk level.

[0083] Based on the first diffusion coefficient and the multi-level diffusion coefficient, a fire spread simulation is performed in the three-dimensional fire scene model to obtain a global fire trend prediction result.

[0084] Specifically, the central impact area is explicitly set as the first diffusion center, which means that it is regarded as the key source or core area of ​​fire spread, and a specific first diffusion coefficient is assigned to it. This coefficient is used to quantify the key characteristics of the speed, intensity or possibility of the fire spreading outward from the central impact area. It reflects the activity and potential diffusion capacity of the fire in the central area.

[0085] Other high-risk areas except the central impact area are regarded as auxiliary diffusion points. Although these areas are not the main sources of diffusion, their existence and risk level also have an important impact on the overall fire spread. According to the regional risk level, a multi-level diffusion coefficient is configured for each auxiliary diffusion point. The auxiliary diffusion point with a higher risk level may have a relatively larger diffusion coefficient, which means that it has a greater potential impact on the surrounding areas; and the auxiliary diffusion point with a lower risk level has a correspondingly smaller diffusion coefficient.

[0086] Based on the first diffusion coefficient and the multi-level diffusion coefficient, the fire spread simulation is carried out in the three-dimensional fire scene model. During the simulation process, factors such as heat conduction, smoke diffusion, fire spread, building structure and obstacles need to be considered. According to these coefficients, the specific situation of the fire spreading outward from the first diffusion center and each auxiliary diffusion point is calculated. Taking into account the interaction between them, the propagation path and various influencing factors, a comprehensive and accurate global fire trend prediction result is finally obtained. This result can clearly show the possible spread range of the fire in the entire area, the key affected areas, and the fire change trend in different time periods. It provides strong data support and basis for fire decision-making and response strategies, and reasonably arranges the placement of fire resources and predicts the possible development direction of the fire.

[0087] In summary, the embodiments of the present application have at least the following technical effects:

[0088] This application provides a fire protection Internet of Things dynamic management and control platform based on virtual reality, a three-dimensional fire protection scene model construction module, which constructs a three-dimensional fire protection scene model; a key control area extraction module, which collects scene space features according to the three-dimensional fire protection scene model; a fire protection equipment module control module, which sets multiple edge analysis nodes for multiple key control areas, and controls fire protection equipment modules; a regional environmental data sequence acquisition module, which builds a regional sensor network, performs real-time environmental monitoring, and obtains multiple regional environmental data sequences; a fire analysis result acquisition module, which performs local fire prediction and local fire level assessment according to the multiple edge analysis nodes, and obtains multiple fire analysis results; a global fire trend prediction result acquisition module, which performs comprehensive fire trend prediction through the multiple fire analysis results, and obtains global fire trend prediction results; an emergency treatment plan generation module, which generates an emergency treatment plan based on the global fire trend prediction results, and calls the fire protection equipment module to handle the fire. The technical effect of pre-prediction of fire conditions based on virtual reality technology and improving the effectiveness and accuracy of fire prevention and control is achieved.

[0089] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0091] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A fire protection IoT dynamic management and control platform based on virtual reality, characterized by: The fire protection Internet of Things dynamic management and control platform based on virtual reality includes: A three-dimensional fire scene model construction module, wherein the three-dimensional fire scene model construction module is used to obtain target area information and construct a three-dimensional fire scene model based on virtual reality technology; A key prevention and control area extraction module, the key prevention and control area extraction module is used to collect scene space features according to the three-dimensional fire scene model, and extract multiple key prevention and control areas according to the scene space features, the multiple key prevention and control areas are marked with prevention and control level identifiers and location identifiers; A fire-fighting equipment module control module, which is used to set up multiple edge analysis nodes for multiple key prevention and control areas, and to control fire-fighting equipment modules based on the Internet of Things technology; A regional environmental data sequence acquisition module, which is used to build a regional sensor network, perform real-time environmental monitoring, and acquire multiple regional environmental data sequences; A fire situation analysis result acquisition module, the fire situation analysis result acquisition module is used to receive the multiple regional environment data sequences according to the multiple edge analysis nodes, perform local fire situation prediction and local fire situation level assessment, and obtain multiple fire situation analysis results; A module for obtaining a global fire situation trend prediction result, wherein the module is used to perform a comprehensive fire situation trend prediction based on the multiple fire situation analysis results and the three-dimensional fire fighting scene model to obtain a global fire situation trend prediction result; The emergency treatment plan generation module is used to generate an emergency treatment plan based on the global fire trend prediction result and call the fire fighting equipment module to handle the fire.

2. The fire protection Internet of Things dynamic management and control platform based on virtual reality as claimed in claim 1 is characterized in that: The key control area extraction module is also used to: The three-dimensional fire scene model is embedded with real-time scene information, and scene space feature collection is performed based on the real-time scene information. The scene space features include but are not limited to functional zoning information, local area location information, and local area connectivity information; Based on the functional zoning information, determining multiple initial regional prevention and control levels; According to the local area location information and the local area connectivity information, an adjacent area impact assessment is performed to generate a plurality of area impact coefficients; The multiple initial regional prevention and control levels are modified by the multiple regional impact coefficients to obtain multiple local regional prevention and control levels; Arrange the local areas in order according to their prevention and control levels, and extract multiple key prevention and control areas.

3. The fire protection Internet of Things dynamic management and control platform based on virtual reality according to claim 1 is characterized in that: The fire equipment module control module is also used for: Based on the multiple key prevention and control areas, extracting the corresponding multiple prevention and control area function types and multiple local area prevention and control levels respectively; Perform edge computing power evaluation according to the multiple control area function types and the multiple local area control levels to determine the computing power of multiple edge nodes; Based on the computing power of multiple edge nodes, configure multiple edge analysis nodes.

4. The fire protection Internet of Things dynamic management and control platform based on virtual reality as claimed in claim 3 is characterized in that: The fire equipment module control module is also used for: Based on the functional types of the multiple control areas and the local area control levels, firefighting equipment is selected to determine an equipment type set and an equipment quantity set; Obtain key prevention and control locations in multiple local areas, and thereby determine the installation location information of fire-fighting equipment; Based on the equipment type set, equipment quantity set and fire equipment installation location information, fire equipment modules are deployed and controlled, and communication connections are established with the multiple edge analysis nodes.

5. The fire protection Internet of Things dynamic management and control platform based on virtual reality according to claim 1 is characterized in that: The fire analysis result acquisition module is also used for: The plurality of edge analysis nodes respectively include corresponding fire prediction units and fire assessment units; Based on historical fire records, extract fire characteristic data sequences, draw fire development curves to analyze fire trends, and perform supervised training in combination with corresponding disaster environment characteristic sequences to obtain the fire prediction unit; Acquire historical fire development trends and historical fire impact data, and train the fire assessment unit; According to the fire situation prediction unit and the fire situation assessment unit, analysis is performed in combination with the multiple regional environmental data sequences to obtain multiple fire situation analysis results.

6. The fire protection Internet of Things dynamic management and control platform based on virtual reality as claimed in claim 2 is characterized in that: The global fire situation trend prediction result acquisition module is also used for: Based on the multiple fire situation analysis results, extract multiple local fire situation prediction results and multiple local fire situation assessment levels; The local area location information and local area connectivity information of the three-dimensional fire scene model are obtained, and the fire spread simulation analysis is performed in combination with the multiple local fire prediction results and multiple local fire assessment levels to obtain the global fire trend prediction results.

7. The fire protection Internet of Things dynamic management and control platform based on virtual reality according to claim 6 is characterized in that: The global fire situation trend prediction result acquisition module is also used for: Extracting multiple fire development trends in multiple local areas based on the multiple local fire prediction results; According to the multiple fire development trends and in combination with multiple local fire assessment levels, regional risk levels are ranked and multiple high-risk areas are extracted; For the multiple high-risk areas, spatial flow analysis is performed in combination with the local area location information and the local area connectivity information to determine the central impact area; Based on the central impact area, fire spread simulation analysis is performed in combination with the multiple high-risk areas to obtain global fire trend prediction results.

8. The fire protection Internet of Things dynamic management and control platform based on virtual reality according to claim 7 is characterized in that: The global fire situation trend prediction result acquisition module is also used for: Taking the central influence area as a first diffusion center and configuring a first diffusion coefficient; The remaining high-risk areas except the central impact area are used as auxiliary diffusion points, and multi-level diffusion coefficients are configured according to the regional risk level; Based on the first diffusion coefficient and the multi-level diffusion coefficient, a fire spread simulation is performed in the three-dimensional fire scene model to obtain a global fire trend prediction result.

Citation Information

Cited By

  • Fire-fighting linkage control device for petroleum and petrochemical engineering

    CN119607486A

  • Elevator machine room fireproof safety control system based on potassium ion aerosol fire extinguishing

    CN121588415A