Intelligent fire-fighting monitoring and early warning platform and method combined with Internet of Things

Abstract

The invention provides an intelligent fire-fighting monitoring and early warning platform and method combined with the Internet of Things, and relates to the technical field of fire-fighting early warning, and the method comprises the steps: determining a site type through an intelligent building space and a hazard source, mining related combustible materials and related explosives, and building a fire-fighting risk mapping table; determining a first edge computing node set according to the influence range of the fire scene based on a distributed computing core; determining a second edge computing node set according to the spreading path of the fire scene, and configuring an edge computing network; and establishing a fire emergency response mechanism based on the edge computing network. According to the method, the technical problems of low crowd evacuation efficiency and confusion caused by the fact that a matched crowd evacuation strategy cannot be accurately set due to the fact that fire monitoring data cannot be rapidly analyzed and processed in a traditional fire monitoring and early warning method can be solved, the crowd evacuation efficiency and safety can be remarkably improved, and the crowd evacuation experience is improved. Therefore, the timeliness and accuracy of fire emergency response are improved.

Description

Technical Field

[0001] The present application relates to the field of fire warning technology, and in particular to a smart fire monitoring and warning platform and method combined with the Internet of Things. Background Art

[0002] In the existing fire monitoring and early warning systems, traditional methods mainly rely on simple smoke, temperature sensors and other equipment to monitor the fire situation, and process and analyze the data manually. Such systems have obvious limitations, especially in the face of rapidly changing fire situations. They cannot analyze and process the monitored fire data efficiently in a timely manner, which in turn affects the formulation of emergency evacuation strategies. When a fire occurs, the delay in data processing makes it impossible to quickly provide an adaptive evacuation plan, and it is impossible to adjust the evacuation route according to the real-time fire situation, resulting in low efficiency of personnel evacuation, and even leading people into dangerous areas due to inaccurate evacuation instructions.

[0003] In summary, traditional fire monitoring and early warning methods have technical problems such as the inability to quickly analyze and process fire monitoring data, which leads to the inability to accurately set appropriate crowd evacuation strategies, resulting in inefficient and chaotic crowd evacuation. Summary of the invention

[0004] The purpose of this application is to provide a smart fire monitoring and early warning platform and method combined with the Internet of Things, so as to solve the technical problems in traditional fire monitoring and early warning methods, such as the inability to quickly analyze and process fire monitoring data, resulting in the inability to accurately set appropriate crowd evacuation strategies, resulting in inefficient and chaotic crowd evacuation.

[0005] In view of the above problems, the present application provides a smart fire monitoring and early warning platform and method combined with the Internet of Things.

[0006] In the first aspect, the present application provides a smart fire monitoring and early warning platform combined with the Internet of Things, including: a fire scene simulation module, which is used to mark the hazard source and simulate the fire scene in the smart building space, and the fire scene includes the spread path and the scope of influence; a risk mapping table establishment module, which is used to determine the location type and mine the associated combustibles and associated explosives through the smart building space and the hazard source, and establish a fire risk mapping table; a distributed computing core loading module, which is used to simultaneously, according to the fire scene, use the edge computing node associated with the hazard source as a distributed computing core and load the fire risk mapping table, and the distributed computing core works in conjunction with the lighting equipment and the monitoring equipment; a first edge computing node set A determination module is used to determine the first edge computing node set of the distributed computing core based on the distributed computing core and in comparison with the influence range of the fire scene; a second edge computing node set determination module is used to determine the second edge computing node set of the distributed computing core based on the distributed computing core and in comparison with the spread path of the fire scene; an edge computing network configuration module is used to configure the edge computing network with the distributed computing core as the center through the first edge computing node set and the second edge computing node set; an emergency response mechanism establishment module is used to collect simulated sensor data based on the edge computing network, synchronously upload it to the distributed computing core, and establish a fire emergency response mechanism.

[0007] On the second aspect, the present application also provides a smart fire monitoring and early warning method combined with the Internet of Things, including: in the smart building space, marking the hazard source and simulating the fire scene, the fire scene includes the spread path and the impact range; through the smart building space and the hazard source, determine the location type and mine the associated combustibles and associated explosives to establish a fire risk mapping table; at the same time, according to the fire scene, the edge computing node associated with the hazard source is used as a distributed computing core and loaded into the fire risk mapping table, and the distributed computing core works in coordination with lighting equipment and monitoring equipment; based on the distributed computing core, compare the impact range of the fire scene, and determine the first edge computing node set of the distributed computing core; based on the distributed computing core, compare the spread path of the fire scene, and determine the second edge computing node set of the distributed computing core; using the distributed computing core as the center, configure the edge computing network through the first edge computing node set and the second edge computing node set; based on the edge computing network, collect simulated sensor data, and upload it to the distributed computing core synchronously to establish a fire emergency response mechanism.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By marking the hazard sources and simulating the fire scene in the smart building space, and through the smart building space and the hazard sources, determining the location type and mining the associated combustibles and explosives, a fire risk mapping table is established; then based on the fire scene, the edge computing nodes associated with the hazard sources are used as distributed computing cores and loaded into the fire risk mapping table, where the distributed computing core works in collaboration with lighting equipment and monitoring equipment; then based on the distributed computing core, the first edge computing node set of the distributed computing core is determined by comparing the impact range of the fire scene; the second edge computing node set of the distributed computing core is determined by comparing the spread path of the fire scene; further, the distributed computing core is used as the center, and the edge computing network is configured through the first edge computing node set and the second edge computing node set; finally, based on the edge computing network, simulated sensor data is collected and uploaded to the distributed computing core synchronously, and a fire emergency response mechanism is established; the above method can improve the recognition and processing efficiency of fire monitoring data, and quickly set a matching crowd evacuation strategy based on the recognition results, significantly improving the efficiency and safety of crowd evacuation, thereby improving the timeliness and accuracy of fire emergency response.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 This is a structural diagram of a smart fire monitoring and early warning platform combined with the Internet of Things for this application; Figure 2 This application is a flow chart of a smart fire monitoring and early warning method combined with the Internet of Things; Description of reference numerals: Fire scene simulation module 11, risk mapping table establishment module 12, distributed computing core loading module 13, first edge computing node set determination module 14, second edge computing node set determination module 15, edge computing network configuration module 16, emergency response mechanism establishment module 17. DETAILED DESCRIPTION

[0012] This application provides a smart fire monitoring and early warning platform and method combined with the Internet of Things, which solves the technical problem that the traditional fire monitoring and early warning method cannot quickly analyze and process fire monitoring data, resulting in the inability to accurately set the corresponding crowd evacuation strategy, causing low efficiency and confusion in crowd evacuation. It can improve the recognition and processing efficiency of fire monitoring data, and quickly set a matching crowd evacuation strategy based on the recognition results, significantly improving the efficiency and safety of crowd evacuation, thereby improving the timeliness and accuracy of fire emergency response.

[0013] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0014] For example, please refer to the attached Figure 1 , this application provides a smart fire monitoring and early warning platform combined with the Internet of Things, including: The fire scene simulation module 11 is used to mark the danger source and simulate the fire scene in the smart building space, and the fire scene includes the spreading path and the affected range.

[0015] Specifically, first, the three-dimensional structural information, building material properties and actual environmental data of the building are collected. For example, the three-dimensional structural information of the building is obtained through technical means such as laser scanning and drone mapping, including precise geometric data such as the building's shape, floor height, floor layout, and room size; then, within the three-dimensional simulation platform, the building is digitally modeled based on the building's three-dimensional structural information, building material properties and actual environmental data to construct a smart building space.

[0016] Then, in the smart building space, mark the hazard sources and simulate the fire scene, that is, according to the structure and functional areas of the building, identify potential hazard sources, such as electrical equipment, combustible storage areas, gas pipelines, chemical storage points, etc., and mark the hazard sources in the smart building space; then randomly select a point in the marked hazard sources as the starting point of the fire, such as a fire caused by electrical equipment failure or a fire caused by gas leakage, and simulate the spread of the fire, including simulating the spread of flames and smoke, and combining the fire spread path to calculate the impact of the fire on the surrounding areas, especially the impact on the building structure, key equipment, and personnel safety, including the coverage of high temperature, smoke, toxic gas and other factors on different areas. By marking hazard sources and simulating fires, the spread and impact of fires in buildings can be comprehensively evaluated, which helps to discover potential safety hazards in advance, optimize fire emergency plans, and improve the safety of smart buildings.

[0017] The risk mapping table establishment module 12 is used to determine the location type and mine related combustibles and related explosives through the smart building space and the hazard source to establish a fire risk mapping table.

[0018] Specifically, first, based on the three-dimensional structural information of the smart building space, the building is divided into different functional areas, such as office areas, storage areas, laboratories, underground parking lots, etc. The function and use nature of each area directly affect its fire risk level. Then, combined with the previously marked hazardous sources, the hazardous sources are assigned to the corresponding location types, such as underground parking lots may be associated with fuel hazardous sources. Then, according to the location type, the combustibles and explosives associated with each area are excavated, such as combustibles including industrial materials (paints, chemical solvents), electrical equipment (cables, electronic equipment), etc., and explosives include gas pipelines, stored gas tanks, battery energy storage devices, etc., and are classified according to their combustion characteristics.

[0019] Then, according to the location type, associated combustibles and associated explosives, the fire risk level of each location type is analyzed and determined. The risk classification can be based on comprehensive multi-dimensional factors, such as the speed of fire spread, the storage of flammable materials, the danger of explosives, the density of people, etc., and a fire risk mapping table is constructed. By constructing a fire risk mapping table, the fire risk of each area in the building can be fully understood, providing support for the formulation of targeted fire safety plans.

[0020] The distributed computing core loading module 13 is used to simultaneously, according to the fire scenario, use the edge computing node associated with the hazard source as a distributed computing core and load the fire risk mapping table. The distributed computing core works in coordination with the lighting equipment and the monitoring equipment.

[0021] Specifically, first, according to the fire scenario, edge computing nodes are deployed in key areas of the building (such as high-risk areas, near dangerous sources). These nodes can directly interact with fire-related equipment (such as fire alarms, smoke sensors, temperature sensors, etc.). Each edge computing node will be associated with the dangerous source near it, and monitor the status of the dangerous source in real time, such as temperature changes of electrical equipment, concentration changes of chemical gases, etc. When an abnormal situation occurs near the dangerous source, the edge computing node can quickly make a judgment and send a fire warning signal to the system. Then the edge computing node associated with the dangerous source is used as a distributed computing core and loaded into the fire risk mapping table. By deploying edge computing nodes, a large amount of sensor data, such as smoke concentration, temperature rise rate, flame detection, etc., can be processed in time, and fires can be quickly identified and warning signals can be issued. The distributed computing core works in coordination with lighting equipment and monitoring equipment. That is, the distributed computing core can be linked with the lighting equipment and monitoring equipment of the building. For example, when a fire occurs, the edge computing node can be linked with the lighting equipment of the building to activate emergency lighting or evacuation indicator lights to guide people to evacuate. At the same time, in high-risk areas, lighting equipment can automatically adjust the brightness according to sensor data to ensure that the monitoring equipment obtains clear image information; the monitoring equipment can automatically retrieve videos of relevant areas and transmit them to the management center in real time to help personnel promptly grasp the dynamics of the spread of the fire.

[0022] By deploying distributed computing cores, rapid and accurate early warning and response can be achieved in fire scenarios. At the same time, through the collaborative work of distributed computing cores, it can be ensured that fire warning signals and risk information can be transmitted in a timely manner, effectively improving the efficiency of fire safety management.

[0023] The first edge computing node set determination module 14 is used to determine the first edge computing node set of the distributed computing core based on the distributed computing core and in comparison with the influence range of the fire scene.

[0024] Specifically, according to the impact range of the fire scene, the edge computing nodes of the distributed computing core are deployed, that is, the edge computing nodes are distributed in various areas of the building, including high-risk areas (such as places where flammable and explosive materials are stored) and conventional areas (such as office areas, public corridors, etc.), and each edge computing node has its own monitoring range, usually including temperature, smoke, gas leakage and other sensors. Then, according to the impact range of the fire scene, the distributed computing core will screen out those edge computing nodes that are within the fire spread path or are directly affected by the high temperature, smoke, etc. of the fire, and use these nodes as the first edge computing nodes to build a first edge computing node set, where the nodes in the first edge computing node set are linked with other nearby edge nodes through the distributed computing core. When a node detects abnormal temperature or smoke concentration, it will share data with other nodes in the same area in real time to ensure that the fire warning signal in the entire area can be effectively transmitted and verified.

[0025] The second edge computing node set determination module 15 is used to determine the second edge computing node set of the distributed computing core based on the distributed computing core and in comparison with the spreading path of the fire scene.

[0026] Specifically, based on the distributed computing core, edge computing nodes along the fire spread path and its surrounding areas are screened out according to the spread path of the fire scene. These nodes may soon enter the fire impact range, and these nodes are divided into a second edge computing node set to ensure that they can prepare in advance, receive and process possible future fire impacts, where the priority of the second edge computing node set depends on the distance of the fire spread path. For example, closer nodes have higher priorities, and farther nodes have lower priorities. High-priority nodes will enter an alert state in advance to monitor changes in temperature, smoke concentration, etc. during the spread of the fire.

[0027] The edge computing network configuration module 16 is used to configure the edge computing network by taking the distributed computing core as the center through the first edge computing node set and the second edge computing node set.

[0028] Specifically, the distributed computing core is used as the central coordination node of the edge computing network, responsible for managing and scheduling the task allocation, data processing and communication coordination of the first edge computing node set and the second edge computing node set. The distributed computing core will process the real-time data of the fire scene through local computing and dynamically adjust the topological structure of the edge computing network; the distributed computing core coordinates the operations of all edge computing nodes, including the collection and analysis of fire data, communication between nodes, processing of fire warning signals, linkage between monitoring equipment and emergency systems, etc. Then, the edge computing network is configured according to the first edge computing node set and the second edge computing node set.

[0029] By forming an efficient edge computing network through the distributed computing core, the first edge computing node set and the second edge computing node set, it can ensure that emergencies can be quickly identified, processed and responded to in fire scenes, thereby improving the fire safety level of smart buildings.

[0030] The emergency response mechanism establishment module 17 is used to collect simulated sensor data based on the edge computing network, upload it to the distributed computing core synchronously, and establish a fire emergency response mechanism.

[0031] Specifically, sensor data collection is performed based on the edge computing network, including but not limited to temperature sensors, smoke sensors, gas leakage sensors, flame detectors, humidity sensors, etc., to obtain simulated sensor data, and the simulated sensor data is synchronously uploaded to the distributed computing core; then, in the distributed computing core, an automated emergency response mechanism is triggered based on the synchronously transmitted data, for example, the severity of the fire is automatically judged based on the initial data of the fire (such as the temperature rise rate, smoke concentration changes, burning materials, etc.), and the fire is graded (such as minor, general, serious, etc.), where different levels of fire will trigger different emergency response processes; through the simulated data of the fire spread path, the distributed computing core can automatically plan the best evacuation route, and through the lighting system in the edge computing network, start the emergency evacuation indicator light to guide the people in the building to evacuate through the safe passage. By building a fire emergency response mechanism based on the edge computing network and the distributed computing core, rapid response and real-time adjustment can be achieved, effectively ensuring the safety of people in the smart building and the efficient operation of the fire protection system.

[0032] By providing a smart fire monitoring and early warning platform combined with the Internet of Things, the technical problems existing in traditional fire monitoring and early warning methods, such as the inability to quickly analyze and process fire monitoring data, the inability to accurately set appropriate crowd evacuation strategies, and the resulting in inefficient and chaotic crowd evacuation, can be solved. By marking the hazard sources and simulating the fire scene in the smart building space, and through the smart building space and the hazard sources, determining the location type and mining the associated combustibles and explosives, a fire risk mapping table is established; then based on the fire scene, the edge computing nodes associated with the hazard sources are used as distributed computing cores and loaded into the fire risk mapping table, where the distributed computing core works in collaboration with lighting equipment and monitoring equipment; then based on the distributed computing core, the first edge computing node set of the distributed computing core is determined by comparing the impact range of the fire scene; the second edge computing node set of the distributed computing core is determined by comparing the spread path of the fire scene; further, the distributed computing core is used as the center, and the edge computing network is configured through the first edge computing node set and the second edge computing node set; finally, based on the edge computing network, simulated sensor data is collected and uploaded to the distributed computing core synchronously, and a fire emergency response mechanism is established; the above method can improve the recognition and processing efficiency of fire monitoring data, and quickly set a matching crowd evacuation strategy based on the recognition results, significantly improving the efficiency and safety of crowd evacuation, thereby improving the timeliness and accuracy of fire emergency response.

[0033] Furthermore, the distributed computing core works in coordination with the lighting equipment and the monitoring equipment. The present application includes: In the smart building space, M evacuation routes are generated by marking hazardous sources; based on the M evacuation routes, the directional lighting guidance in the lighting equipment is enabled; at the same time, the monitoring equipment is used to identify the density and movement speed of human flow, and a collaborative scheduling strategy is obtained with evacuation efficiency as the goal.

[0034] Specifically, first, based on the hazard source markings in the smart building space, the distributed computing core identifies the starting location of the fire and the dangerous areas (such as high temperature areas, smoke-dense areas, and flame spread areas). The marking information of these hazard sources will be used as the basis for generating evacuation routes; then, based on the three-dimensional structure of the building, the fire-affected area, available exits, stairs, elevators and other resources, M evacuation routes are generated. Each of the M routes should try to avoid the fire spread path, and give priority to routes that are safe and have the shortest evacuation time.

[0035] Then, through the lighting system in the smart building, the distributed computing core will automatically turn on the emergency lighting system in the corresponding area according to the M evacuation routes, providing directional lighting guidance. The lights on each evacuation route will be gradually guided in the direction of the path to help people find the evacuation exit quickly and safely. In addition, the distributed computing core monitors the density of people in each area in real time through the surveillance cameras inside the building. Especially during the evacuation process, the monitoring equipment will collect the distribution data of people in key locations such as stairs, passages, and exits to detect whether there is crowding or detention; at the same time, the monitoring equipment will also capture the movement speed data of people and analyze whether the speed of people moving during the evacuation is smooth. By comparing the movement speed of each area, the system can identify the bottlenecks and blocking points that may occur during the evacuation, and obtain the crowd density recognition results and movement speed recognition results.

[0036] Finally, with the goal of optimizing evacuation efficiency, crowd evacuation analysis is performed based on crowd density identification results and movement speed identification results, that is, reasonable diversion and guidance are used to ensure a smoother evacuation process. For example, dynamic diversion of personnel can be achieved by controlling lighting, closing or opening some channels, etc., to prevent serious congestion in certain evacuation channels and generate collaborative scheduling strategies. By utilizing the edge computing network and smart devices in smart buildings, effective evacuation routes can be generated, and dynamic scheduling combined with crowd density and movement speed can improve evacuation efficiency and maximize personnel safety.

[0037] Furthermore, in the smart building space, M evacuation routes are generated by marking the hazard sources. The present application includes: Taking the distributed computing core as the center, a distributed computing framework is established through the first edge computing node set and the second edge computing node set; based on the distributed computing framework, a path planning module is connected to generate N evacuation routes, where N ≥ M; in the smart building space, potential danger areas are determined through hazard source markings; an overlap analysis is performed on the N evacuation routes and the potential danger areas, overlapping evacuation routes are eliminated, and the M evacuation routes are obtained.

[0038] Specifically, the distributed computing core is used as the center, and a distributed computing framework is constructed through the first edge computing node set and the second edge computing node set, wherein the core node of the distributed computing framework is responsible for the integration and scheduling of global data, and the edge nodes perform distributed processing, which can not only ensure the real-time nature of fire monitoring, but also improve the efficiency of evacuation route generation and optimization. Then, based on the distributed computing framework, the path planning module is connected to perform evacuation route analysis, that is, through the distributed computing framework, data such as building structure, floor layout, exit location, hazard source marking and personnel distribution in the smart building are collected as input to the path planning module; the path planning module will generate N evacuation routes through calculation, where N is greater than or equal to M, and each route will avoid currently known hazard sources, and take into account factors such as the shortest evacuation distance and optimal personnel distribution.

[0039] Then, the distributed computing core combines the sensor data to identify the sources of danger in the smart building (such as overheating of electrical equipment, chemical leakage, flame spread area, etc.), and marks the location of these sources of danger in the three-dimensional simulation platform. At the same time, it marks potential high-risk areas, such as areas near potential sources of danger such as flammable accumulation areas and gas leakage areas, to determine the potential danger areas. Then, the N evacuation routes are overlapped with the potential danger areas, that is, the coordinates of each evacuation route are compared with the boundary of the potential danger area, and the routes that overlap with or are close to the danger area are identified, and the overlapping evacuation routes are eliminated to obtain M evacuation routes. By eliminating overlapping evacuation routes based on potential danger areas, the scientificity, effectiveness and rationality of evacuation route determination can be improved.

[0040] Further, the N evacuation routes and the potential danger area are overlapped and analyzed, overlapping evacuation routes are eliminated, and the M evacuation routes are obtained. The present application further includes the following steps: Connecting to a data storage unit, obtaining a fire evacuation instance of the smart building space, wherein the fire evacuation instance is obtained from a fire drill; based on the hazard source and the potential hazard area, respectively evaluating the smoothness of personnel flow of the N evacuation routes; predicting the evacuation duration through the smoothness of personnel flow of the N evacuation routes in combination with the fire evacuation instance, and arranging the evacuation duration in ascending order to obtain a priority level of the evacuation routes; and prioritizing the N evacuation routes according to the priority level of the evacuation routes before eliminating overlapping evacuation routes.

[0041] Specifically, a data storage unit is connected, which stores historical data related to fire evacuation, including fire drill data, actual fire event data, personnel flow records, evacuation time and personnel density of each area, etc.; then, a fire evacuation instance of the smart building space is obtained, which is generated through a fire drill, that is, through a previous fire drill or simulation scenario, and includes detailed information such as the use of evacuation routes, personnel distribution, personnel flow speed, and congestion points. According to the danger sources and potential danger areas, the smoothness of personnel flow of the N evacuation routes is evaluated. For example, using the data of previous fire drills and the danger source information monitored in real time, a flow smoothness analysis model is constructed, in which the existence of danger sources and potential danger areas will directly affect the safety of the route, thereby reducing the evacuation efficiency, and the flow smoothness analysis model is used for evaluation to obtain the smoothness of personnel flow of the N evacuation routes.

[0042] Then, data is extracted based on the fire evacuation example to obtain a sample personnel flow smoothness set and a sample evacuation time set, and an evacuation time prediction model is constructed based on the BP neural network. The sample personnel flow smoothness set and the sample evacuation time set are used as training data to supervise the evacuation time prediction model. Then, the evacuation time prediction model is used to predict the evacuation time according to the personnel flow smoothness of N evacuation routes, and N predicted evacuation times are obtained; then, the predicted evacuation times are arranged in order from small to large to obtain the priority level of the evacuation routes. Finally, before the overlapping evacuation routes are eliminated, the N evacuation routes are marked with priorities according to the evacuation route priority levels.

[0043] Furthermore, the present application also includes the following steps: An evacuation route optimization space is established with the maximization of the overlapping degree of the overlapping evacuation routes and the minimization of the priority levels of the evacuation routes as elimination constraints; based on the evacuation route optimization space, evacuation routes are eliminated in combination with multiple iterative learning, and after the search converges, the M evacuation routes are determined.

[0044] Specifically, the overlap refers to the overlap between different evacuation routes and the dangerous area in space. The higher the overlap, the greater the possibility that the route passes through the potential dangerous area. Therefore, the maximization of the overlap is used as one of the elimination constraints, the purpose is to eliminate those routes that have a large overlap with the dangerous area and reduce the impact of dangerous factors on evacuation. The lower the priority level, the higher the evacuation efficiency of the route, and the more suitable it is as a priority evacuation path. In the optimization process, the goal is to retain those routes with lower priority levels as much as possible. Therefore, the minimization of the priority level is another elimination constraint, and the routes with higher evacuation efficiency are preferentially retained, and those routes with higher priority levels and poorer evacuation efficiency are eliminated. Then, the maximization of the overlap of the overlapping evacuation routes and the minimization of the priority level of the evacuation routes are used as elimination constraints to establish the evacuation route optimization space, that is, based on the N initially generated evacuation routes, an optimization space containing all routes is constructed, and based on the constraints of maximizing the overlap and minimizing the priority level, the routes are eliminated to optimize the route selection in the evacuation route space.

[0045] Then, based on the evacuation route optimization space, evacuation routes are eliminated in combination with multiple iterative learning. For example, in the iterative learning process, initial conditions are first set, including a tolerance threshold for overlap and a minimum requirement for priority. These conditions will affect the retention and elimination criteria of routes in each iteration; then, from the N routes in the optimization space, a number of routes are randomly selected as the starting candidate set. Each iteration will evaluate the overlap and priority of these routes, and eliminate and retain them according to the objective function; iterative search is performed until a predetermined convergence condition is met, that is, when the value of the objective function no longer changes significantly or when the number of iterations reaches a preset upper limit, M evacuation routes are obtained. These routes are the results of optimization under the dual constraints of overlap and priority, and can provide the most efficient evacuation paths in emergency situations such as fires.

[0046] Furthermore, the present application also includes the following steps: In the process of eliminating evacuation routes, an elimination taboo table is established, and the elimination taboo table has an elimination ranking number; if the decreasing rate of the evacuation efficiency exceeds a preset value, a release instruction is issued; according to the release instruction, one or more eliminated evacuation routes with the largest elimination ranking number in the elimination taboo table are unlocked; through one or more eliminated evacuation routes, the M evacuation routes are expanded, and the evacuation route optimization space is updated at the same time.

[0047] Specifically, in the process of eliminating evacuation routes, an elimination taboo table is established, in which the elimination taboo table has an elimination ranking number. The elimination taboo table is a table used to record the routes that have been eliminated in the evacuation route optimization process and their ranking numbers. Each eliminated evacuation route will be recorded in the taboo table in the order of elimination to avoid repeated selection of eliminated routes in a short period of time. Whenever an evacuation route is eliminated, the ranking number of the route will be recorded in the taboo table. The ranking number will help to determine which routes should be lifted first in the subsequent lifting of the ban process.

[0048] When the rate of decrease of the evacuation efficiency exceeds the preset value, it indicates that the current route elimination may have caused the routes to be too concentrated or the available evacuation paths to be insufficient, and a lifting instruction is issued; and according to the lifting instruction, one or more eliminated evacuation routes with the largest elimination ranking number in the elimination taboo table are unlocked; and the M evacuation routes are expanded by one or more eliminated evacuation routes, and then the evacuation route optimization space is updated, that is, the optimization space is re-expanded. In this way, the eliminated routes can be flexibly handled in the evacuation route optimization process, and the selection of evacuation routes can be dynamically adjusted by combining the elimination taboo table and the lifting mechanism, thereby improving the efficiency of optimization analysis.

[0049] Furthermore, the monitoring equipment is used to identify the density and movement speed of people flow, and a coordinated scheduling strategy is obtained with evacuation efficiency as the goal. The application includes: Based on the M evacuation routes, the path intersections are located; according to the M evacuation routes and the moving speed, a first type of collaborative scheduling strategy is set; according to the path intersections and the crowd density, a second type of collaborative scheduling strategy is set; through the first type of collaborative scheduling strategy and the second type of collaborative scheduling strategy, the collaborative scheduling strategy is generated with evacuation efficiency as the goal.

[0050] Specifically, based on the M evacuation routes, the path intersections are located. Among the M evacuation routes, different paths may intersect or overlap in the building structure. These places are called path intersections. Intersections are often where bottlenecks and congestion may occur during the evacuation process. Then, according to the M evacuation routes and the moving speeds, a type of collaborative scheduling strategy is set. That is, when the moving speed of an evacuation route drops significantly, it may indicate that the route has been congested or bottlenecked. According to the real-time speed data, the flow of people can be automatically diverted to other routes with faster moving speeds, such as turning off the lighting of the slower evacuation passages to guide people to use faster passages.

[0051] On the other hand, according to the intersection of the path and the density of the crowd, a second type of collaborative scheduling strategy is set, that is, according to the real-time density of the crowd at the intersection, the priority of the evacuation route is dynamically adjusted to avoid too many people gathering at the same intersection. For example, if the density of a certain intersection is too high, the personnel will be guided to other routes with fewer intersections first to reduce the pressure on the point. Finally, with the goal of optimizing the evacuation efficiency, a collaborative scheduling strategy is generated through the first type of collaborative scheduling strategy and the second type of collaborative scheduling strategy. For example, by combining the first and second types of collaborative scheduling strategies, emergency lighting, evacuation signs, broadcasting systems, etc. are used to guide people to the optimal route in real time to avoid congestion. At the same time, people will be guided to routes with faster moving speeds and intersections with too high density will be avoided. By setting the first and second types of collaborative scheduling strategies based on the real-time moving speed and crowd density, respectively, and then generating an efficient comprehensive evacuation strategy, it can be ensured that in emergency situations such as fires, the efficiency and safety of personnel evacuation are maximized.

[0052] In summary, the smart fire monitoring and early warning platform combined with the Internet of Things provided by this application has the following technical effects: By marking the hazard sources and simulating the fire scene in the smart building space, and through the smart building space and the hazard sources, determining the location type and mining the associated combustibles and explosives, a fire risk mapping table is established; then based on the fire scene, the edge computing nodes associated with the hazard sources are used as distributed computing cores and loaded into the fire risk mapping table, where the distributed computing core works in collaboration with lighting equipment and monitoring equipment; then based on the distributed computing core, the first edge computing node set of the distributed computing core is determined by comparing the impact range of the fire scene; the second edge computing node set of the distributed computing core is determined by comparing the spread path of the fire scene; further, the distributed computing core is used as the center, and the edge computing network is configured through the first edge computing node set and the second edge computing node set; finally, based on the edge computing network, simulated sensor data is collected and uploaded to the distributed computing core synchronously, and a fire emergency response mechanism is established; the above method can improve the recognition and processing efficiency of fire monitoring data, and quickly set a matching crowd evacuation strategy based on the recognition results, significantly improving the efficiency and safety of crowd evacuation, thereby improving the timeliness and accuracy of fire emergency response.

[0053] Embodiment 2, based on the same invention concept as the smart fire monitoring and early warning platform combined with the Internet of Things in the previous embodiment, this application also provides a smart fire monitoring and early warning method combined with the Internet of Things, please refer to the attached Figure 2 ,include: In a smart building space, the hazard source is marked and a fire scenario is simulated, wherein the fire scenario includes a spreading path and an impact range; through the smart building space and the hazard source, the location type is determined, and associated combustibles and explosives are mined to establish a fire risk mapping table; at the same time, according to the fire scenario, the edge computing node associated with the hazard source is used as a distributed computing core and loaded into the fire risk mapping table, and the distributed computing core works in coordination with lighting equipment and monitoring equipment; based on the distributed computing core, the first edge computing node set of the distributed computing core is determined in comparison with the impact range of the fire scenario; based on the distributed computing core, the second edge computing node set of the distributed computing core is determined in comparison with the spreading path of the fire scenario; with the distributed computing core as the center, an edge computing network is configured through the first edge computing node set and the second edge computing node set; based on the edge computing network, simulated sensor data is collected and uploaded to the distributed computing core synchronously to establish a fire emergency response mechanism.

[0054] Furthermore, the smart fire monitoring and early warning method combined with the Internet of Things also includes: In the smart building space, M evacuation routes are generated by marking hazardous sources; based on the M evacuation routes, the directional lighting guidance in the lighting equipment is enabled; at the same time, the monitoring equipment is used to identify the density and movement speed of human flow, and a collaborative scheduling strategy is obtained with evacuation efficiency as the goal.

[0055] Furthermore, the smart fire monitoring and early warning method combined with the Internet of Things also includes: Based on the M evacuation routes, the path intersections are located; according to the M evacuation routes and the moving speed, a first type of collaborative scheduling strategy is set; according to the path intersections and the crowd density, a second type of collaborative scheduling strategy is set; through the first type of collaborative scheduling strategy and the second type of collaborative scheduling strategy, the collaborative scheduling strategy is generated with evacuation efficiency as the goal.

[0056] Furthermore, the smart fire monitoring and early warning method combined with the Internet of Things also includes: Taking the distributed computing core as the center, a distributed computing framework is established through the first edge computing node set and the second edge computing node set; based on the distributed computing framework, a path planning module is connected to generate N evacuation routes, where N ≥ M; in the smart building space, potential danger areas are determined through hazard source markings; an overlap analysis is performed on the N evacuation routes and the potential danger areas, overlapping evacuation routes are eliminated, and the M evacuation routes are obtained.

[0057] Furthermore, the smart fire monitoring and early warning method combined with the Internet of Things also includes: Connecting to a data storage unit, obtaining a fire evacuation instance of the smart building space, wherein the fire evacuation instance is obtained from a fire drill; based on the hazard source and the potential hazard area, respectively evaluating the smoothness of personnel flow of the N evacuation routes; predicting the evacuation duration through the smoothness of personnel flow of the N evacuation routes in combination with the fire evacuation instance, and arranging the evacuation duration in ascending order to obtain a priority level of the evacuation routes; and prioritizing the N evacuation routes according to the priority level of the evacuation routes before eliminating overlapping evacuation routes.

[0058] Furthermore, the smart fire monitoring and early warning method combined with the Internet of Things also includes: An evacuation route optimization space is established with the maximization of the overlapping degree of the overlapping evacuation routes and the minimization of the priority levels of the evacuation routes as elimination constraints; based on the evacuation route optimization space, evacuation routes are eliminated in combination with multiple iterative learning, and after the search converges, the M evacuation routes are determined.

[0059] Furthermore, the smart fire monitoring and early warning method combined with the Internet of Things also includes: In the process of eliminating evacuation routes, an elimination taboo table is established, and the elimination taboo table has an elimination ranking number; if the decreasing rate of the evacuation efficiency exceeds a preset value, a release instruction is issued; according to the release instruction, one or more eliminated evacuation routes with the largest elimination ranking number in the elimination taboo table are unlocked; through one or more eliminated evacuation routes, the M evacuation routes are expanded, and the evacuation route optimization space is updated at the same time.

[0060] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The smart fire monitoring and early warning platform combined with the Internet of Things and the specific examples in the aforementioned embodiment 1 are also applicable to a smart fire monitoring and early warning method combined with the Internet of Things in this embodiment. Through the aforementioned detailed description of a smart fire monitoring and early warning platform combined with the Internet of Things, those skilled in the art can clearly know a smart fire monitoring and early warning method combined with the Internet of Things in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the method disclosed in the embodiment, since it corresponds to the platform disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the platform part description.

[0061] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0062] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. The intelligent fire monitoring and early warning platform combined with the Internet of Things is characterized by: include: A fire scene simulation module is used to mark the hazard source and simulate the fire scene in the smart building space, wherein the fire scene includes the spread path and the impact range; A risk mapping table establishment module is used to determine the location type and mine related combustibles and related explosives through the smart building space and the hazard source to establish a fire risk mapping table; A distributed computing core loading module is used to simultaneously, according to the fire scenario, use the edge computing node associated with the hazard source as a distributed computing core and load the fire risk mapping table, wherein the distributed computing core works in coordination with the lighting equipment and the monitoring equipment; A first edge computing node set determination module, configured to determine a first edge computing node set of a distributed computing core based on the distributed computing core and in comparison with an impact range of the fire scenario; A second edge computing node set determination module, configured to determine a second edge computing node set of the distributed computing core based on the distributed computing core and in comparison with the spread path of the fire scene; An edge computing network configuration module, configured to configure an edge computing network by taking the distributed computing core as a center through the first edge computing node set and the second edge computing node set; The emergency response mechanism establishment module is used to collect simulated sensor data based on the edge computing network, upload it to the distributed computing core synchronously, and establish a fire emergency response mechanism.

2. The smart fire monitoring and early warning platform combined with the Internet of Things as claimed in claim 1 is characterized in that: The distributed computing core works in coordination with the lighting equipment and the monitoring equipment, including: In the smart building space, M evacuation routes are generated by marking the hazard sources; Based on the M evacuation routes, activating the directional lighting guidance in the lighting device; At the same time, the monitoring equipment is used to identify the density and movement speed of human traffic, and a collaborative scheduling strategy is obtained with evacuation efficiency as the goal.

3. The smart fire monitoring and early warning platform combined with the Internet of Things as claimed in claim 2 is characterized in that: The monitoring equipment is used to identify the density and movement speed of people flow, and to obtain a coordinated dispatching strategy with evacuation efficiency as the goal, including: Based on the M evacuation routes, locate the path intersection; According to the M evacuation routes and the moving speed, a type of collaborative scheduling strategy is set; According to the path intersection and the crowd density, two types of collaborative scheduling strategies are set; The collaborative scheduling strategy is generated by using the first type of collaborative scheduling strategy and the second type of collaborative scheduling strategy with evacuation efficiency as the goal.

4. The smart fire monitoring and early warning platform combined with the Internet of Things as claimed in claim 3 is characterized in that: In the smart building space, M evacuation routes are generated by marking the hazard sources, including: Taking the distributed computing core as the center, establishing a distributed computing framework through the first edge computing node set and the second edge computing node set; Based on the distributed computing framework, connecting the path planning module, generating N evacuation routes, where N ≥ M; In the smart building space, potential danger areas are identified by marking danger sources; An overlap analysis is performed on the N evacuation routes and the potential danger area, overlapping evacuation routes are eliminated, and the M evacuation routes are obtained.

5. The smart fire monitoring and early warning platform combined with the Internet of Things as claimed in claim 4 is characterized in that: Performing overlap analysis on the N evacuation routes and the potential danger area, eliminating overlapping evacuation routes, and obtaining the M evacuation routes, further comprising: Connecting to a data storage unit to obtain a fire evacuation instance of the smart building space, where the fire evacuation instance is obtained from a fire drill; Based on the danger sources and potential danger areas, respectively evaluate the smoothness of personnel flow of the N evacuation routes; The evacuation time is predicted by combining the smoothness of personnel flow of the N evacuation routes with the fire evacuation example, and the evacuation time is arranged in ascending order to obtain the priority level of the evacuation routes; Before eliminating overlapping evacuation routes, the N evacuation routes are marked with priorities according to the evacuation route priorities.

6. The smart fire monitoring and early warning platform combined with the Internet of Things as claimed in claim 5, characterized in that: Taking the maximization of the overlap degree of the overlapping evacuation routes and the minimization of the priority levels of the evacuation routes as elimination constraints, an evacuation route optimization space is established; Based on the evacuation route optimization space, evacuation routes are eliminated in combination with multiple iterative learning, and after the search converges, the M evacuation routes are determined.

7. The smart fire monitoring and early warning platform combined with the Internet of Things as claimed in claim 6 is characterized in that: In the process of eliminating evacuation routes, an elimination taboo table is established, and the elimination taboo table has elimination arrangement numbers; If the decreasing rate of the evacuation efficiency exceeds a preset value, a release command is issued; According to the ban release instruction, unlock one or more eliminated evacuation routes with the largest elimination ranking number in the elimination taboo table; The M evacuation routes are expanded through one or more eliminated evacuation routes, and the evacuation route optimization space is updated at the same time.

8. The intelligent fire monitoring and early warning method combined with the Internet of Things is characterized by: The method is implemented by a smart fire monitoring and early warning platform combined with the Internet of Things according to any one of claims 1 to 7, including: In the smart building space, mark the hazard source and simulate the fire scenario, wherein the fire scenario includes the spread path and the impact range; Through the smart building space and the hazard source, the location type is determined and related combustibles and related explosives are mined to establish a fire risk mapping table; At the same time, according to the fire scenario, the edge computing node associated with the hazard source is used as a distributed computing core and loaded into the fire risk mapping table, and the distributed computing core works in coordination with the lighting equipment and the monitoring equipment; Based on the distributed computing core, and in comparison with the impact range of the fire scene, determining a first edge computing node set of the distributed computing core; Based on the distributed computing core, and comparing the spreading path of the fire scene, determining a second edge computing node set of the distributed computing core; Taking the distributed computing core as the center, configuring an edge computing network through the first edge computing node set and the second edge computing node set; Based on the edge computing network, simulated sensor data is collected and synchronously uploaded to the distributed computing core to establish a fire emergency response mechanism.

Images