Fire-fighting strategy optimization method and platform combined with dynamic environment data
By combining dynamic environmental data with fire protection strategy optimization methods, and utilizing fire monitoring modules for acquisition and fire simulation analysis, the problem of the lack of dynamic adaptability in fire protection strategies has been solved. This has enabled real-time optimization and intelligent alerts for fire protection strategies, thereby improving fire protection efficiency.
Patent Information
- Application Number
- CN202411462757.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-19
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing firefighting strategies lack dynamic adaptability and are unable to cope with complex and ever-changing fire scene environments and monitoring equipment malfunctions, resulting in low rescue efficiency and waste of resources.
By combining dynamic environmental data, fire monitoring modules acquire data, failure scenario characteristics are analyzed, failure monitoring components are identified, and fire simulation analysis is performed to generate visualized fire simulation results, enabling real-time optimization and intelligent alerts for fire protection strategies.
It enables real-time optimization of fire protection strategies, improves the effectiveness and relevance of the strategies, and ensures the rational allocation and efficient utilization of fire protection resources.
Smart Images

Figure CN118966487A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a firefighting strategy optimization method and platform combining dynamic environmental data. Background Art
[0002] With the acceleration of urbanization and the increase in the density of various types of buildings, fire safety has become an important link in urban management that cannot be ignored. Traditional firefighting strategies mainly rely on fixed plans and manual judgment, which are difficult to cope with the complex and changeable fire scene environment and possible failures of monitoring equipment. Especially in areas such as large commercial complexes, high-rise buildings and industrial parks, due to the complex building structure, dense population and high mobility, once a fire occurs, its spread speed and degree of harm are often difficult to predict and control. However, most of the existing firefighting systems are still at the level of static plans and simple data collection, lacking dynamic analysis of environmental data and real-time monitoring of the status of monitoring modules. This results in the firefighting strategy may not be able to adapt to changes on the scene in time when a fire occurs, resulting in low rescue efficiency and waste of resources. Summary of the invention
[0003] The present application provides a firefighting strategy optimization method and platform combined with dynamic environmental data, which solves the technical problem in the prior art that firefighting strategies lack dynamic adaptability and are not well matched with actual conditions.
[0004] In view of the above problems, an embodiment of the present application provides a fire protection strategy optimization method and platform combined with dynamic environmental data.
[0005] A first aspect of an embodiment of the present application provides a fire strategy optimization method combined with dynamic environment data, the method comprising: Acquire multiple fire monitoring modules in a predetermined area, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks; perform block fire condition analysis under monitoring failure for the multiple fire monitoring modules respectively, and generate multiple failure scenario features corresponding to the multiple monitoring blocks; when a fire warning is triggered in the predetermined area, obtain multiple block monitoring data time series of the multiple fire monitoring modules in real time; identify failure monitoring components based on the multiple block monitoring data time series, and generate a first failure monitoring component and a first failure time; perform fire triggering simulation analysis under dynamic environment loading using the multiple failure scenario features, the first failure monitoring component, and the first failure time, and establish a fire visualization simulation result for the predetermined area; perform matching analysis of the current fire strategy through the fire visualization simulation result, and if the fire matching degree is less than a preset matching degree threshold, generate a strategy optimization reminder message and send it to the fire dispatch center.
[0006] A second aspect of the embodiments of the present application provides a fire strategy optimization platform combined with dynamic environment data, the platform comprising: A monitoring module acquisition module, the monitoring module acquisition module is used to acquire multiple fire monitoring modules in a predetermined area, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks; a fire condition analysis module, the fire condition analysis module is used to perform block fire condition analysis under monitoring failure for the multiple fire monitoring modules respectively, and generate multiple failure scenario features corresponding to the multiple monitoring blocks; a data acquisition module, the data acquisition module is used to acquire multiple block monitoring data time series of the multiple fire monitoring modules in real time when the predetermined area triggers a fire warning; a failure component identification module, the failure component identification module is used to identify the failure monitoring component based on the multiple block monitoring data time series, and generate a first failure monitoring component and a first failure time; a simulation analysis module, the simulation analysis module is used to use the multiple failure scenario features, the first failure monitoring component and the first failure time to perform fire triggering simulation analysis under dynamic environment loading, and establish a fire visualization simulation result for the predetermined area; a matching analysis module, the matching analysis module is used to perform matching analysis of the current fire strategy through the fire visualization simulation result, and if the fire matching degree is less than the preset matching degree threshold, a strategy optimization reminder message is generated and sent to the fire dispatch center.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, multiple fire monitoring modules in a predetermined area are obtained, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks. Then, the block fire analysis under monitoring failure is performed for the multiple fire monitoring modules respectively, and multiple failure scenario features corresponding to the multiple monitoring blocks are generated. When the predetermined area triggers a fire warning, the multiple block monitoring data time series of the multiple fire monitoring modules are obtained in real time. Further, the failure monitoring component is identified based on the multiple block monitoring data time series, and the first failure monitoring component and the first failure time are generated. Then, the fire triggering simulation analysis under dynamic environment loading is performed using multiple failure scenario features, the first failure monitoring component and the first failure time, and the fire visualization simulation result of the predetermined area is established. Finally, the matching analysis of the current fire strategy is performed through the fire visualization simulation result. If the fire matching degree is less than the preset matching degree threshold, the strategy optimization reminder information is generated and sent to the fire dispatch center. The technical problem that the fire strategy lacks dynamic adaptability in the prior art and does not match the actual situation is solved. The fire triggering simulation analysis under dynamic environment loading realizes the real-time optimization and intelligent reminder of the fire strategy, and achieves the technical effect of improving the effectiveness and pertinence of the fire strategy. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] 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.
[0009] Figure 1 A schematic diagram of a flow chart of a fire strategy optimization method combining dynamic environmental data provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a fire strategy optimization platform combined with dynamic environmental data provided in an embodiment of the present application.
[0010] Explanation of the reference numerals: monitoring module acquisition module 11 , fire condition analysis module 12 , data acquisition module 13 , failed component identification module 14 , simulation analysis module 15 , matching analysis module 16 . DETAILED DESCRIPTION
[0011] The embodiments of the present application provide a fire strategy optimization method and platform combined with dynamic environmental data, thereby solving the technical problem in the prior art that fire strategies lack dynamic adaptability and are not well matched with actual conditions.
[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0013] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.
[0014] Embodiment 1, as Figure 1 As shown, an embodiment of the present application provides a fire strategy optimization method combined with dynamic environment data, wherein the method includes: Acquire multiple fire monitoring modules in a predetermined area, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks.
[0015] In the predetermined area, multiple fire monitoring modules are deployed. These fire monitoring modules are distributed in different monitoring blocks. Each monitoring block represents a specific area in the predetermined area, with specific fire risks and monitoring requirements. Fire monitoring modules may include smoke detectors, temperature sensors, flame detectors and other equipment to monitor the fire risk in the block in real time.
[0016] A block fire condition analysis under monitoring failure is performed for each of the multiple fire monitoring modules to generate multiple failure scenario features corresponding to the multiple monitoring blocks.
[0017] For each fire monitoring module, fire simulation software is used to simulate the block fire conditions that may be caused by its failure state (such as equipment failure, false alarm or missed alarm), including key parameters such as the spread speed of the fire, the diffusion range of the smoke, and the temperature change trend. Based on the simulation results, the failure scenario characteristics of each monitoring block when the fire monitoring module fails are extracted. These characteristics may include the maximum spread range of the fire, the time when the smoke concentration reaches a dangerous level, and the area where the temperature exceeds the safety threshold.
[0018] Furthermore, the multiple fire monitoring modules are respectively subjected to block fire condition analysis under monitoring failure to generate multiple failure scenario features corresponding to the multiple monitoring blocks, including: Extract multiple first monitoring components included in the first fire monitoring module among the multiple fire monitoring modules; use the block characteristics of the first monitoring block corresponding to the first fire monitoring module as a constraint, perform failure fire scenario simulation on the multiple first monitoring components, and generate multiple failure fire scenario sets; extract fire characteristics from the multiple failure fire scenario sets, and generate multiple first failure scenario characteristics; establish a mapping relationship between the multiple first failure scenario characteristics and the multiple first monitoring components, and add them to the multiple failure scenario characteristics.
[0019] Specifically, multiple first monitoring components of the first fire monitoring module are extracted from multiple fire monitoring modules, and these first monitoring components are jointly responsible for monitoring the fire risk in a specific block (i.e., the first monitoring block); the block characteristics (such as building structure, material type, personnel distribution, etc.) of the first monitoring block corresponding to the first fire monitoring module are used as constraints, and fire simulation software is used to combine these constraints to simulate the failure fire scenario of the multiple monitoring components in the first monitoring module to generate multiple failure fire scenario sets, each scenario set represents a specific monitoring component failure situation and the fire changes caused by it; fire characteristics are extracted for each failure fire scenario set, which These features may include the spread speed of the fire, the diffusion range of the smoke, the temperature change trend, etc.; based on the results of the fire feature extraction, multiple first failure scenario features are generated, and each first failure scenario feature corresponds to a specific monitoring component failure and the fire characteristics caused by it; by establishing a mapping relationship between multiple first failure scenario features and multiple first monitoring components, each failure scenario feature can be traced back to the specific monitoring component failure; the generated multiple first failure scenario features and their mapping relationship with the monitoring components are added to the overall failure scenario feature library, forming a complete data set containing failure scenario features of multiple monitoring blocks.
[0020] Furthermore, taking the block characteristics of the first monitoring block corresponding to the first fire monitoring module as a constraint, the multiple first monitoring components are simulated for failure fire scenarios to generate multiple failure fire scenario sets, including: The block characteristics of the first monitoring block include block building distribution information, block building material information and component location information of the multiple first monitoring components; three-dimensional scene modeling is performed based on the block characteristics of the first monitoring block to generate a first block three-dimensional model; fire simulation is performed in combination with the first block three-dimensional model until the multiple first monitoring components fail, thereby generating the multiple failed fire scene sets.
[0021] The block characteristics of the first monitoring block include block building distribution information, block building material information and component location information of multiple first monitoring components; wherein, the block building distribution information includes the location, shape, height, number of floors, etc. of the building, and the block building material information includes the material type (such as wood, steel, concrete, etc.) of the building and its combustion performance. Based on the block characteristics of the first monitoring block, a three-dimensional model of the first block is constructed using three-dimensional modeling software, and the three-dimensional model of the first block accurately reflects the building distribution, material type and location of the monitoring components in the block. Fire simulation software is used to combine the three-dimensional model of the first block to perform fire simulation. During the simulation process, by adjusting simulation parameters (such as sensor sensitivity, data transmission speed, etc.), the failure of multiple first monitoring components is gradually simulated. When a monitoring component fails, its impact on fire monitoring and early warning capabilities is observed and recorded; through multiple simulations, multiple failed fire scene sets are generated, and each failed fire scene set contains a specific monitoring component failure and the fire changes caused by it.
[0022] When a fire warning is triggered in the predetermined area, the time series of multiple block monitoring data of the multiple fire monitoring modules are obtained in real time.
[0023] When one or more fire monitoring modules in the predetermined area detects abnormal data (such as smoke concentration exceeding the standard, temperature rising sharply, etc.), a fire warning signal will be triggered immediately, and block monitoring data time series will be collected from multiple fire monitoring modules. These data time series record the environmental changes in the monitoring block before and after the fire, such as temperature, smoke concentration, etc.
[0024] Failure monitoring components are identified based on the multiple block monitoring data time series to generate a first failure monitoring component and a first failure time.
[0025] Based on the time series of block monitoring data acquired in real time, trend analysis is performed to analyze abnormal fluctuations or mutations in the data. Abnormal fluctuations or mutations may indicate that the monitoring component has failed, and the first failed monitoring component and its failure time (first failure time) are determined.
[0026] Furthermore, the method of identifying a failure monitoring component based on the plurality of block monitoring data time series and generating a first failure monitoring component and a first failure time includes: Establish multiple first failure dominant features for the multiple first monitoring components; establish a failure identifier based on the multiple first failure dominant features; input the multiple block monitoring data into the failure identifier in time sequence to perform failure analysis, and generate the first failure monitoring component and the first failure time.
[0027] Preferably, for each first monitoring component, key features are extracted from the corresponding block monitoring data time series, including the fluctuation range of the data, the change trend, the frequency of abnormal values, etc.; based on historical data and experience, features that are highly correlated with the failure of the monitoring component are screened out as the first failure dominant feature, and the first failure dominant feature has the ability to clearly distinguish failed components from normal components; based on the nature and quantity of the first failure dominant feature, a suitable deep learning algorithm (such as a neural network) is selected to establish a failure identifier, and the failure identifier is trained using historical monitoring data and known failed component information. During the training process, the parameters and structure of the model are continuously adjusted to improve the recognition accuracy; the monitoring data time series of the current multiple blocks are input into the trained failure identifier, and the failure identifier will perform real-time analysis on the input data to detect whether there is a failed monitoring component. If a failed component is detected, the failure identifier will output the identification of the first failed monitoring component and the first failure time. The first failure time refers to the time point when the monitoring data first exhibits the failure feature.
[0028] Furthermore, inputting the plurality of block monitoring data into the failure identifier in time sequence to perform failure analysis and generate the first failure monitoring component and the first failure time includes: If any first monitoring component is a video surveillance device, the corresponding first explicit failure feature is a signal interruption transmission feature and a smoke cover feature; if any first monitoring component is a non-video surveillance device, the corresponding first explicit failure feature is a signal interruption transmission feature; the failure identifier first identifies the data type of the multiple block monitoring data sequence and then matches the corresponding explicit failure feature, and uses the corresponding explicit failure feature to make a failure judgment, thereby generating the failure monitoring component and the first failure time.
[0029] Specifically, the failure identifier will first identify the data types of the input multiple block monitoring data sequences, and identify which data comes from video surveillance equipment and which data comes from non-video surveillance equipment by analyzing the source, format and content of the data; based on the results of data type identification, the failure identifier will match the corresponding failure explicit features for each type of monitoring component; for video surveillance equipment, its failure explicit features may include signal interruption transmission features and smoke coverage and occlusion features; for non-video surveillance equipment (such as temperature sensors, smoke detectors, etc.), its failure explicit features are mainly signal interruption transmission features; the failure identifier will make failure judgments on the input multiple block monitoring data sequences based on the matched failure explicit features; for video surveillance equipment, if signal interruption transmission is detected or the video screen is covered and occluded by smoke, the device is judged to be failed; for non-video surveillance equipment, if signal interruption transmission is detected, the device is judged to be failed; once the failure identifier determines that a monitoring component has failed, it will immediately generate the identification and first failure time of the failed monitoring component.
[0030] The multiple failure scenario features, the first failure monitoring component and the first failure time are used to perform a fire trigger simulation analysis under a dynamic environment load, and a fire visualization simulation result of the predetermined area is established.
[0031] Multiple failure scenario features, first failure monitoring components and first failure time are used to perform fire triggering simulation analysis under dynamic environmental loading. Through simulation analysis, fire visualization simulation results of the predetermined area are established to intuitively display the development process and potential impact of the fire.
[0032] Furthermore, the fire triggering simulation analysis under dynamic environment loading is performed using the multiple failure scenario features, the first failure monitoring component and the first failure time to establish a fire visualization simulation result of the predetermined area, including: Receive the fire monitoring data set of the multiple monitoring blocks collected by the non-failure monitoring component, perform preliminary simulation, and generate an initial fire visualization scene; locate the failure partition according to the first failure monitoring component, and extract real-time failure scene features from the multiple failure scene features; collect real-time dynamic environmental information of the predetermined area; optimize the initial fire visualization scene in combination with the real-time dynamic environmental information, the real-time failure scene features and the first failure time, and generate the fire visualization simulation result.
[0033] Specifically, a fire monitoring data set of multiple monitoring blocks from non-failed monitoring components is received, and the fire monitoring data set may include key information such as temperature, smoke concentration, and flame images; a preliminary simulation is performed using the received fire monitoring data set, including the establishment of a fire model, the setting of fire source intensity, and the analysis of combustible material distribution; based on the results of the preliminary simulation, an initial fire visualization scene is generated to display the initial development of the fire; based on the failure information of the first failed monitoring component, the failure partition is located, and the failure partition refers to the area where the fire cannot be accurately monitored due to the failure of the monitoring component; the real-time failure scene related to the current failure partition is extracted from multiple failure scene features Characteristics, including fire source type, combustible material type, building structure characteristics, etc.; collect real-time dynamic environmental information of the predetermined area, including wind speed, wind direction, temperature, humidity, etc.; integrate the real-time dynamic environmental information, real-time failure scenario characteristics and the first failure time into the initial fire visualization scene; optimize the initial fire visualization scene based on the integrated data, including adjusting the fire source intensity, modifying the combustible material distribution, updating the flame spread path, etc.; after optimization, generate the final fire visualization simulation result, which can accurately reflect the fire development in the predetermined area under specific failure conditions, including key information such as flame spread, smoke diffusion, and temperature distribution.
[0034] Furthermore, the initial fire visualization scene is optimized in combination with the real-time dynamic environment information, the real-time failure scene characteristics and the first failure time to generate the fire visualization simulation result, including: Based on the real-time failure scenario characteristics, digital simulation of the failure block is performed to establish an initialized failure scenario digital model; with the first failure time as the starting point and the current time as the end point, the real-time dynamic environment information is loaded into the initialized failure scenario digital model to predict the evolution of the fire situation under the dynamic environment and generate a visualized fire scene for the failure block; the block scene of the initial fire visualization scene is replaced with the visualized fire scene of the failure block to generate the fire visualization simulation result.
[0035] Specifically, based on the real-time failure scenario characteristics, digital simulation technology (such as CFD simulation, fire dynamics simulation, etc.) is used to digitally simulate the failure block. Through digital simulation, an initialization failure scenario digital model is established. The initialization failure scenario digital model should be able to accurately reflect the state of the failure block at the initial stage of the fire, including temperature distribution, smoke concentration, flame shape, etc.; taking the first failure time as the starting point and the current time as the end point, a time range is set, and this time range will be used to guide the process of fire evolution prediction; real-time dynamic environmental information is loaded in the initialization failure scenario digital model, including wind speed, wind direction, temperature, humidity, etc.; in the initialization failure scenario digital model loaded with real-time dynamic environmental information, fire evolution prediction is performed to generate a visualization fire scene of the failure block. The visualization fire scene of the failure block can accurately reflect the state changes of the failure block during the occurrence and development of the fire; the corresponding block in the initial fire visualization scene is replaced with the visualization fire scene of the failure block to generate the final fire visualization simulation result.
[0036] The fire visualization simulation result is used to perform a matching analysis of the current firefighting strategy. If the firefighting matching degree is less than a preset matching degree threshold, a strategy optimization reminder message is generated and sent to the fire dispatch center.
[0037] The fire visualization simulation results are matched and analyzed with the current fire fighting strategy. Specifically, the fire development trend in the simulation results is compared with the response measures in the fire fighting strategy, and whether the fire fighting resources can meet the needs of fire fighting and evacuation. According to the matching analysis results, the fire fighting matching degree is calculated using the Euclidean distance. The fire fighting matching degree is used to measure the degree of fit between the current fire fighting strategy and the actual fire situation. A matching degree threshold is preset based on historical data, expert experience or industry standards to determine whether the current fire fighting strategy needs to be optimized. The calculated fire fighting matching degree is compared with the preset matching degree threshold. If the matching degree is less than the threshold, it means that the current strategy may not be able to effectively deal with the current fire situation and needs to be optimized. At this time, a strategy optimization reminder message (including problems with the current fire fighting strategy and recommended optimization measures) is generated and sent to the fire dispatch center to remind the dispatch personnel to adjust and optimize the fire fighting strategy in time.
[0038] In summary, the embodiments of the present application have at least the following technical effects: First, multiple fire monitoring modules in a predetermined area are obtained, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks. Then, the block fire analysis under monitoring failure is performed for the multiple fire monitoring modules respectively, and multiple failure scenario features corresponding to the multiple monitoring blocks are generated. When the predetermined area triggers a fire warning, the multiple block monitoring data time series of the multiple fire monitoring modules are obtained in real time. Further, the failure monitoring component is identified based on the multiple block monitoring data time series, and the first failure monitoring component and the first failure time are generated. Then, the fire triggering simulation analysis under dynamic environment loading is performed using multiple failure scenario features, the first failure monitoring component and the first failure time, and the fire visualization simulation result of the predetermined area is established. Finally, the matching analysis of the current fire strategy is performed through the fire visualization simulation result. If the fire matching degree is less than the preset matching degree threshold, the strategy optimization reminder information is generated and sent to the fire dispatch center. The technical problem that the fire strategy lacks dynamic adaptability in the prior art and does not match the actual situation is solved. The fire triggering simulation analysis under dynamic environment loading realizes the real-time optimization and intelligent reminder of the fire strategy, and achieves the technical effect of improving the effectiveness and pertinence of the fire strategy.
[0039] Embodiment 2 is based on the same inventive concept as the fire fighting strategy optimization method combining dynamic environment data in the above embodiment. Figure 2 As shown, the present application provides a fire strategy optimization platform combined with dynamic environmental data. The platform includes: A monitoring module acquisition module 11, the monitoring module acquisition module 11 is used to acquire multiple fire monitoring modules in a predetermined area, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks; a fire condition analysis module 12, the fire condition analysis module 12 is used to perform block fire condition analysis under monitoring failure for the multiple fire monitoring modules, and generate multiple failure scenario features corresponding to the multiple monitoring blocks; a data acquisition module 13, the data acquisition module 13 is used to acquire the multiple block monitoring data time series of the multiple fire monitoring modules in real time when the predetermined area triggers a fire warning; a failure component identification module 14, the failure component identification module 14 is used to Based on the timing of the monitoring data of the multiple blocks, failure monitoring components are identified to generate a first failure monitoring component and a first failure time; a simulation analysis module 15, the simulation analysis module 15 is used to use the multiple failure scenario features, the first failure monitoring component and the first failure time to perform fire trigger simulation analysis under dynamic environment loading, and establish a fire visualization simulation result for the predetermined area; a matching analysis module 16, the matching analysis module 16 is used to perform a matching analysis of the current fire fighting strategy through the fire visualization simulation result, and if the fire fighting matching degree is less than a preset matching degree threshold, a strategy optimization reminder message is generated and sent to the fire dispatch center.
[0040] Furthermore, the fire situation analysis module 12 is used to perform the following method: Extract multiple first monitoring components included in the first fire monitoring module among the multiple fire monitoring modules; use the block characteristics of the first monitoring block corresponding to the first fire monitoring module as a constraint, perform failure fire scenario simulation on the multiple first monitoring components, and generate multiple failure fire scenario sets; extract fire characteristics from the multiple failure fire scenario sets, and generate multiple first failure scenario characteristics; establish a mapping relationship between the multiple first failure scenario characteristics and the multiple first monitoring components, and add them to the multiple failure scenario characteristics.
[0041] Furthermore, the fire situation analysis module 12 is used to perform the following method: The block characteristics of the first monitoring block include block building distribution information, block building material information and component location information of the multiple first monitoring components; three-dimensional scene modeling is performed based on the block characteristics of the first monitoring block to generate a first block three-dimensional model; fire simulation is performed in combination with the first block three-dimensional model until the multiple first monitoring components fail, thereby generating the multiple failed fire scene sets.
[0042] Furthermore, the failed component identification module 14 is used to perform the following method: Establish multiple first failure dominant features for the multiple first monitoring components; establish a failure identifier based on the multiple first failure dominant features; input the multiple block monitoring data into the failure identifier in time sequence to perform failure analysis, and generate the first failure monitoring component and the first failure time.
[0043] Furthermore, the failed component identification module 14 is used to perform the following method: If any first monitoring component is a video surveillance device, the corresponding first explicit failure feature is a signal interruption transmission feature and a smoke cover feature; if any first monitoring component is a non-video surveillance device, the corresponding first explicit failure feature is a signal interruption transmission feature; the failure identifier first identifies the data type of the multiple block monitoring data sequence and then matches the corresponding explicit failure feature, and uses the corresponding explicit failure feature to make a failure judgment, thereby generating the failure monitoring component and the first failure time.
[0044] Furthermore, the simulation analysis module 15 is used to perform the following method: Receive the fire monitoring data set of the multiple monitoring blocks collected by the non-failure monitoring component, perform preliminary simulation, and generate an initial fire visualization scene; locate the failure partition according to the first failure monitoring component, and extract real-time failure scene features from the multiple failure scene features; collect real-time dynamic environmental information of the predetermined area; optimize the initial fire visualization scene in combination with the real-time dynamic environmental information, the real-time failure scene features and the first failure time, and generate the fire visualization simulation result.
[0045] Furthermore, the simulation analysis module 15 is used to perform the following method: Based on the real-time failure scenario characteristics, digital simulation of the failure block is performed to establish an initialized failure scenario digital model; with the first failure time as the starting point and the current time as the end point, the real-time dynamic environment information is loaded into the initialized failure scenario digital model to predict the evolution of the fire situation under the dynamic environment and generate a visualized fire scene for the failure block; the block scene of the initial fire visualization scene is replaced with the visualized fire scene of the failure block to generate the fire visualization simulation result.
[0046] 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. 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.
[0047] 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 shall be included in the protection scope of the present application.
[0048] This specification and 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 fighting strategy optimization method combining dynamic environmental data, characterized in that: The method comprises: Acquire multiple fire monitoring modules in a predetermined area, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks; Performing block fire condition analysis under monitoring failure for the multiple fire monitoring modules respectively, and generating multiple failure scenario features corresponding to the multiple monitoring blocks; When a fire warning is triggered in the predetermined area, a time sequence of monitoring data of multiple blocks of the multiple fire monitoring modules is obtained in real time; Identify the failure monitoring component based on the multiple block monitoring data time series, and generate a first failure monitoring component and a first failure time; Using the multiple failure scenario features, the first failure monitoring component and the first failure time to perform fire trigger simulation analysis under dynamic environmental loading, and establish a fire visualization simulation result for the predetermined area; The fire visualization simulation result is used to perform a matching analysis of the current firefighting strategy. If the firefighting matching degree is less than a preset matching degree threshold, a strategy optimization reminder message is generated and sent to the fire dispatch center.
2. A fire strategy optimization method combining dynamic environment data as claimed in claim 1, characterized in that: The multiple fire monitoring modules are respectively subjected to block fire condition analysis under monitoring failure, and multiple failure scenario features corresponding to the multiple monitoring blocks are generated, including: Extracting a plurality of first monitoring components included in a first fire monitoring module among the plurality of fire monitoring modules; Taking the block characteristics of the first monitoring block corresponding to the first fire monitoring module as a constraint, performing failure fire scenario simulation on the plurality of first monitoring components to generate a plurality of failure fire scenario sets; Extracting fire characteristics from the plurality of failure fire scene sets to generate a plurality of first failure scene characteristics; A mapping relationship between the multiple first failure scenario features and the multiple first monitoring components is established, and they are added to the multiple failure scenario features.
3. A firefighting strategy optimization method combining dynamic environmental data as claimed in claim 2, characterized in that: Taking the block characteristics of the first monitoring block corresponding to the first fire monitoring module as a constraint, performing failure fire scenario simulation on the multiple first monitoring components to generate multiple failure fire scenario sets, including: The block characteristics of the first monitoring block include block building distribution information, block building material information and component position information of the plurality of first monitoring components; Performing three-dimensional scene modeling based on the block features of the first monitoring block to generate a first block three-dimensional model; A fire simulation is performed in combination with the first block three-dimensional model until the multiple first monitoring components fail, thereby generating the multiple failed fire scene sets.
4. A firefighting strategy optimization method combining dynamic environmental data as claimed in claim 3, characterized in that: Identifying a failure monitoring component based on the multiple block monitoring data time series and generating a first failure monitoring component and a first failure time include: Establishing a plurality of first failure-dominant features for the plurality of first monitoring components; Establishing a failure identifier using the plurality of first failure-dominant features; The plurality of block monitoring data are sequentially input into the failure identifier for failure analysis to generate the first failure monitoring component and the first failure time.
5. A firefighting strategy optimization method combining dynamic environmental data as claimed in claim 4, characterized in that: Inputting the plurality of block monitoring data into the failure identifier in time sequence to perform failure analysis, and generating the first failure monitoring component and the first failure time, comprises: If any first monitoring component is a video monitoring device, any corresponding first failure dominant feature is a signal interruption transmission feature and a smoke covering and blocking feature; If any first monitoring component is a non-video monitoring device, any corresponding first failure dominant feature is a signal interruption transmission feature; The failure identifier first identifies the data type of the plurality of block monitoring data sequences and then matches the corresponding failure dominant features, performs failure judgment based on the corresponding failure dominant features, and generates the failure monitoring component and the first failure time.
6. A firefighting strategy optimization method combining dynamic environmental data as claimed in claim 1, characterized in that: Using the multiple failure scenario features, the first failure monitoring component and the first failure time to perform fire trigger simulation analysis under dynamic environment loading, and establish a fire visualization simulation result of the predetermined area, including: Receiving the fire monitoring data sets of the plurality of monitoring blocks collected by the non-failure monitoring components, performing preliminary simulation, and generating an initial fire visualization scene; Locate the failure partition according to the first failure monitoring component, and extract real-time failure scenario features from the multiple failure scenario features; Collecting real-time dynamic environmental information of the predetermined area; The initial fire visualization scene is optimized in combination with the real-time dynamic environment information, the real-time failure scene characteristics and the first failure time to generate the fire visualization simulation result.
7. A firefighting strategy optimization method in combination with dynamic environment data as claimed in claim 6, characterized in that: The initial fire visualization scene is optimized in combination with the real-time dynamic environment information, the real-time failure scene characteristics and the first failure time to generate the fire visualization simulation result, including: Perform digital simulation of the failure block based on the real-time failure scenario characteristics to establish an initialization failure scenario digital model; Taking the first failure time as the starting point and the current time as the end point, loading the real-time dynamic environment information into the initialized failure scene digital model, predicting the evolution of the fire situation under the dynamic environment, and generating a visualized fire scene of the failure block; The initial fire visualization scene is replaced by the block scene with the failed block visualization fire scene to generate the fire visualization simulation result.
8. A fire strategy optimization platform combined with dynamic environmental data, characterized in that: The platform is used to implement a fire strategy optimization method combined with dynamic environmental data as described in any one of claims 1 to 7, comprising: A monitoring module acquisition module, the monitoring module acquisition module is used to acquire multiple fire monitoring modules in a predetermined area, wherein the multiple fire monitoring modules correspond to multiple monitoring blocks; A fire condition analysis module, the fire condition analysis module is used to perform block fire condition analysis under monitoring failure for the multiple fire monitoring modules respectively, and generate multiple failure scenario features corresponding to the multiple monitoring blocks; A data acquisition module, wherein the data acquisition module is used to acquire the time series of multiple block monitoring data of the multiple fire monitoring modules in real time when a fire warning is triggered in the predetermined area; A failure component identification module, the failure component identification module is used to identify the failure monitoring component based on the time series of the plurality of block monitoring data, and generate a first failure monitoring component and a first failure time; A simulation analysis module, the simulation analysis module is used to perform a fire trigger simulation analysis under a dynamic environment load by using the multiple failure scenario features, the first failure monitoring component and the first failure time, and establish a fire visualization simulation result of the predetermined area; The matching analysis module is used to perform matching analysis on the current fire fighting strategy through the fire visualization simulation results. If the fire fighting matching degree is less than a preset matching degree threshold, a strategy optimization reminder message is generated and sent to the fire fighting dispatch center.
Citation Information
Patent Citations
Intelligent fire safety pre-judgment management linkage platform
CN109147253A
Method and system for evaluating maintenance effectiveness of fire detection system
CN113096372A
Intelligent fire safety monitoring system
CN117649130A
Intelligent fire-fighting management system
CN118735246A
A decision-making support system for responding to natural disasters rapidly
KR1020150089604A
