A Fire Scene Auxiliary Decision Support System Based on Mobile Ad Hoc Network

Abstract

The present invention discloses a fire scene auxiliary decision support system based on a mobile ad hoc network, specifically relating to the technical field of fire decision-making. It includes constructing a mobile ad hoc network based on the fire according to the fire occurrence area, determining fixed nodes, mobile nodes and alternative nodes, determining the danger and influence of alternative nodes through graph analysis, performing uncertainty entropy value analysis on fire information data, collecting node importance data of alternative nodes, determining the delay time of fire spread through autocorrelation analysis of the temperature and time at the lost node, comparing it with the time from the alternative node to the lost node, collecting node timeliness data of alternative nodes, comprehensively evaluating the node importance data and node timeliness data, and quantifying the priority of each alternative node. The present invention helps to quickly select the most suitable node for intervention and monitoring and can adapt to fire scenes of different scales and complexities.

Description

Technical Field

[0001] The present invention relates to the technical field of fire decision-making, and more specifically, to a fire scene auxiliary decision support system based on a mobile ad hoc network. Background Art

[0002] With the acceleration of the urbanization process and the increase in the frequency of fires, traditional fire emergency response systems often face problems such as lagging information transmission, unstable network structure, and untimely response in the case of rapid fire spread and complex environments. Especially in complex environments such as large buildings, forests, or high-risk areas, the collection and transmission of fire information are crucial for emergency decision-making. However, traditional emergency response systems rely on fixed sensors and monitoring devices. When a fire occurs, fixed nodes may fail due to the impact of the fire, resulting in information loss or lag, which in turn affects decision-making efficiency. Therefore, it is not easy to ensure the information flow and effective monitoring when nodes are lost or fail.

[0003] To solve the above defects, a technical solution is provided now. Summary of the Invention

[0004] In order to overcome the above defects of the prior art, an embodiment of the present invention provides a fire scene auxiliary decision support system based on a mobile ad hoc network to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A fire scene auxiliary decision support system based on a mobile ad hoc network includes a mobile ad hoc network module, a node importance data module, a node timeliness data module, and an evaluation module, and the modules are signal-connected to each other;

[0007] The mobile ad hoc network module is used to construct a mobile ad hoc network based on the fire according to the fire occurrence area, and determine fixed nodes, mobile nodes, and alternative nodes;

[0008] The node importance data module is used to determine the danger and influence of alternative nodes through graph analysis, perform uncertainty entropy value analysis on fire information data, and collect node importance data of alternative nodes;

[0009] The node timeliness data module is used to determine the delay time of fire spread through autocorrelation analysis of the temperature and time at the lost node, and compare it with the time from the alternative node to the lost node, and collect node timeliness data of alternative nodes;

[0010] The evaluation module is used to comprehensively evaluate the node importance data and the node timeliness data to quantify the priority of each alternative node.

[0011] In a preferred embodiment, the node importance data includes:

[0012] The node importance data is represented by the graph key node coefficient and the uncertainty entropy value coefficient;

[0013] The acquisition logic of the graph key node coefficient is as follows: The fixed nodes and movable nodes are used as the nodes of the graph, two nodes are connected by an edge, and the relationship between the two nodes is represented by a data transmission link and a communication connection between the nodes;

[0014] Evaluate the influence of the alternative node through the degree centrality of the alternative node in the graph, and determine the danger weight of the alternative node based on the flammability at the geographical location of the alternative node. Mark the influence of the alternative node as: Mark the danger weight of the alternative node as: , where n = 1, 2, 3, ……, N, N is a positive integer, n is the number of the alternative node, and the alternative node is a movable node that can replace the lost node;

[0015] The calculation formula for the importance coefficient of the alternative node is: ; where is the importance coefficient of the nth alternative node;

[0016] Determine the geographical location of the lost node and the geographical location of the alternative node, obtain the shortest distance from the alternative node to the nearest fire occurrence location, and obtain the shortest distance from the lost node to the fire occurrence location. Calculate the graph key node coefficient, and the calculation formula is: ; where is the graph key node coefficient, is the shortest distance from the alternative node to the nearest fire occurrence location, is the shortest distance from the lost node to the fire occurrence location.

[0017] In a preferred embodiment, the uncertainty entropy value coefficient includes:

[0018] The acquisition logic of the uncertainty entropy value coefficient is as follows: Collect the fire information data of the alternative node. The fire information data includes temperature, smoke concentration, gas concentration, and humidity. Use the Gaussian kernel function to estimate the probability density of the fire information data for the collected fire information data. The calculation formula is: ; where is the probability density of the ith fire information data, i is the number of the fire information data, m = 1, 2, 3, ……, M, M is a positive integer, m is the number of the alternative node for collecting the ith fire information data, h is the bandwidth parameter, and K is the Gaussian kernel function;

[0019] Calculate the uncertainty entropy value coefficient, and the calculation formula is: ; wherein, is the uncertainty entropy value coefficient of the nth alternative node.

[0020] In a preferred embodiment, the node timeliness data includes:

[0021] The node timeliness data is represented by the autocorrelation timeliness coefficient;

[0022] The acquisition logic of the autocorrelation timeliness coefficient is as follows: According to the temperature time series at the lost node, calculate the autocorrelation function of temperature and time, and evaluate the correlation between temperature and time through different time lags;

[0023] Calculate the correlation between temperature and time at different time lags. The calculation formula is: ; wherein, is the correlation between temperature and time at the kth time lag, t is 1, 2, 3, ……, T, T is a positive integer, t is the number of the unit time for each temperature acquisition, is the temperature at the alternative node at the tth unit time, is the average value of the temperature at the alternative node at the tth unit time, k = 0, 1, 2, 3, ……, K, k is the number of unit time lags;

[0024] Obtain the correlation between temperature and time at the optimal time lag. The calculation formula is: ; wherein, is the correlation between temperature and time at the optimal time lag;

[0025] Set the correlation threshold. If the correlation between temperature and time at the optimal time lag is greater than the correlation threshold, obtain the time required for the alternative node to go to the lost node, and mark the time required for the alternative node to go to the lost node as: , calculate the autocorrelation timeliness coefficient. The calculation formula is: ; wherein, is the autocorrelation timeliness coefficient of the nth alternative node;

[0026] If the correlation between temperature and time at the optimal time lag is less than the correlation threshold, record the autocorrelation timeliness coefficient as: 0.

[0027] In a preferred embodiment, comprehensively evaluate the node importance data and the node timeliness data, including:

[0028] Construct an alternative node evaluation model with the graph key node coefficient, the uncertainty entropy value coefficient, and the autocorrelation timeliness coefficient, and generate an alternative node evaluation coefficient. The calculation formula of the alternative node evaluation coefficient is: ; wherein, is the substitution node evaluation coefficient of the nth substitution node, , , are respectively the proportionality coefficients of the key node coefficient of the graph spectrum, the uncertainty entropy value coefficient, and the autocorrelation timeliness coefficient, , , are all greater than 0.

[0029] In a preferred embodiment, the priority of each substitution node is quantified, including:

[0030] Set the substitution node evaluation coefficient threshold, compare the substitution node evaluation coefficient of each substitution node with the substitution node evaluation coefficient threshold. If the substitution node evaluation coefficient is greater than the substitution node evaluation coefficient threshold, then use the substitution node as the substitution for the lost node to go to the lost node. If the substitution node evaluation coefficient is less than the substitution node evaluation coefficient threshold, then do not use the substitution node as the substitution for the lost node to go to the lost node. Collect the substitution nodes with an evaluation coefficient greater than the substitution node evaluation coefficient threshold, generate the preferred selection order of the substitution nodes based on the magnitude order of the substitution node evaluation coefficients greater than the substitution node evaluation coefficient threshold, and select the substitution node with the largest substitution node evaluation coefficient to go to the lost node.

[0031] The technical effects and advantages of the present invention:

[0032] The present invention establishes an ad-hoc network composed of fixed nodes, movable nodes, and substitution nodes, and uses graph spectrum analysis to evaluate the danger and influence of nodes. Combining uncertainty entropy value analysis, the information diversity and uncertainty of each node are obtained to further evaluate the importance of the nodes. At the same time, through autocorrelation analysis of the fire data at the lost node, the delay time of fire spread is determined and compared with the response time of the substitution node. Finally, by integrating the importance and timeliness data of the nodes, the priority of the substitution node is quantified, so that when a fire occurs, the most suitable node can be quickly selected for intervention and monitoring, thereby optimizing the fire response strategy and ensuring the stability and real-time nature of information transmission and on-site monitoring. The present invention helps to quickly select the most suitable node for intervention and monitoring and can adapt to fire scenarios of different scales and complexities. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings;

[0034] Figure 1 is a schematic structural diagram of a fire scene auxiliary decision-making support system based on a mobile ad-hoc network of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0036] Embodiment 1

[0037] Figure 1 A structural schematic diagram of a fire scene auxiliary decision-making support system based on a mobile ad hoc network is given, which specifically includes a mobile ad hoc network module, a node importance data module, a node timeliness data module, and an evaluation module. The modules are signal-connected to each other;

[0038] The mobile ad hoc network module is used to construct a mobile ad hoc network based on the fire according to the fire occurrence area, and determine fixed nodes, mobile nodes, and alternative nodes;

[0039] The node importance data module is used to determine the danger and influence of alternative nodes through graph analysis, perform uncertainty entropy value analysis on fire information data, and collect node importance data of alternative nodes;

[0040] The node timeliness data module is used to determine the delay time of fire spread through autocorrelation analysis of the temperature and time at the lost node, and compare it with the time from the alternative node to the lost node, and collect node timeliness data of alternative nodes;

[0041] The evaluation module is used to comprehensively evaluate the node importance data and the node timeliness data, and quantify the priority of each alternative node.

[0042] Construct a mobile ad hoc network for the location where the fire occurs, and define the labels of each node. The node labels include fixed nodes and mobile nodes. The mobile ad hoc network combines fixed nodes and mobile nodes (such as drones, fire robots, etc.) to work together to provide efficient fire monitoring, data transmission, and emergency response capabilities, including:

[0043] Fixed nodes: These nodes are usually deployed in various areas of the fire scene and are responsible for monitoring environmental changes, such as temperature, smoke concentration, gas composition, fire source location, etc. These sensor nodes can be temperature sensors, smoke sensors, CO2 sensors, temperature and humidity sensors, etc., and they share data with other nodes through wireless communication;

[0044] Mobile Nodes (UAVs, fire-fighting robots, etc.): Mobile nodes can move dynamically at the fire scene, offering higher flexibility and mobility. UAVs can obtain real-time images or video data of the fire area through aerial flight, and fire-fighting robots can enter the fire scene to perform fire extinguishing or search tasks. They act as communication nodes in the network, helping to ensure network coverage and stability through dynamic path planning and data transmission;

[0045] Sensor Data Collection: Each node (whether fixed or mobile) is equipped with different sensors to collect fire-related data. The environmental information (such as temperature, smoke, humidity, etc.) collected by these sensors can reflect the state and development of the fire;

[0046] Node Communication: Fixed nodes and mobile nodes are connected to each other through wireless communication technologies (such as Wi-Fi, Zigbee, LoRa, LTE, etc.) to form a self-organizing network. At the fire scene, both fixed nodes and mobile nodes can transmit data to each other and share information, thus enabling real-time monitoring and dynamic assessment of the fire.

[0047] Based on the location of the fixed nodes, the position of the mobile nodes is adjusted to ensure effective information monitoring of the fire occurrence area and its surrounding areas. According to the speed and direction of fire spread, the mobile nodes can obtain real-time sensor data of the fire area, and adjust their paths through an adaptive routing protocol or task planning algorithm to ensure coverage of the hot spots of the fire occurrence and the adjacent areas that may be affected by fire spread, thus forming a full coverage of fire information in the fire occurrence area and its surrounding areas.

[0048] Due to the high risk of loss of fixed nodes in the fire environment, such as building collapse, equipment damage, fire spread, and drastic environmental changes, etc., resulting in the loss of fire information data in the lost area. When a fixed node is lost, a lost signal is generated, and the lost signal is broadcast to the mobile ad-hoc network. After receiving the lost signal, the nearby mobile nodes update their task queues and determine whether to go to the location of the lost node for monitoring or replacement. Among them, the basic factors considered by the mobile nodes for going to the location of the lost node include:

[0049] Battery Power: If the battery power of the mobile node is insufficient, it may not be able to complete the task, so it is necessary to select a node with sufficient power;

[0050] Distance: The distance between the node and the lost location. Nodes that are farther away may require more time or energy. Selecting nodes that are closer can improve the response efficiency;

[0051] Current Task Load: Some nodes may already be executing other tasks. If the tasks are too many, they may not be able to respond to the lost signal in time;

[0052] Path selection: It is necessary to evaluate the surrounding fire spread situation, ensure the path safety, and avoid passing through areas with strong fire.

[0053] After determining the movable nodes that can replace the lost nodes, mark the movable nodes that can replace the lost nodes as replacement nodes, and collect the node importance data and node timeliness data of each replacement node. The node importance data is represented by the graph key node coefficient and the uncertainty entropy value coefficient, and the node timeliness data is represented by the autocorrelation timeliness coefficient.

[0054] The graph key node coefficient helps to evaluate the priority order of replacement nodes to lost nodes. The specific reasons include:

[0055] It can help identify the most influential nodes in the network topology. By evaluating the importance of the lost nodes, the most suitable replacement nodes can be quickly found and dispatched first, which can accelerate the emergency response speed and reduce the network communication interruption caused by node loss;

[0056] If a key node is lost, it may affect a large number of communication links. Using the graph key node coefficient, the impact of the fault on the network can be predicted, and by adjusting the routing strategy in time and preferentially selecting replacement nodes, the spread effect of network faults can be reduced;

[0057] In disaster scenarios such as fires, the availability and importance of nodes change over time. Through the key node coefficient in the graph, the priority of nodes can be adjusted in real time according to the trend of fire spread.

[0058] The acquisition logic of the graph key node coefficient is as follows: Take the fixed nodes and movable nodes as the nodes of the graph, connect two nodes through edges, and represent the relationship between two nodes through the data transmission link and the communication connection between nodes;

[0059] Evaluate the influence of replacement nodes through the degree centrality of replacement nodes in the graph, and determine the danger weight of replacement nodes based on the flammability at the geographical location of replacement nodes. Mark the influence of replacement nodes as: Mark the danger weight of replacement nodes as: where n = 1, 2, 3,..., N, N is a positive integer, and n is the number of replacement nodes;

[0060] It should be noted that replacement nodes with high degree centrality usually have greater influence, which means they can quickly transmit information and provide key data or signals during a fire. The flammability at the geographical location of replacement nodes is evaluated and determined by analyzing the environmental characteristics of this area.

[0061] The calculation formula for the importance coefficient of the alternative node is as follows: ; where is the importance coefficient of the nth alternative node;

[0062] It should be noted that the larger the importance coefficient of the alternative node, the higher the importance of the position of the alternative node, and the lower the priority of going to the lost node for the replacement task.

[0063] Determine the geographical location of the lost node and the geographical location of the alternative node, obtain the shortest distance from the alternative node to the nearest fire occurrence location, and obtain the shortest distance from the lost node to the fire occurrence location. Calculate the key node coefficient of the graph, and the calculation formula is: ; where is the key node coefficient of the graph, is the shortest distance from the alternative node to the nearest fire occurrence location, is the shortest distance from the lost node to the fire occurrence location.

[0064] It can be seen from the formula that the larger the key node coefficient of the graph, the higher the importance degree of the alternative node relative to the lost node. If the alternative node is used as a replacement for the lost node, it is easy to cause the loss of fire information at the original alternative node.

[0065] The uncertainty entropy value coefficient helps to evaluate the priority order of the alternative node going to the lost node. The uncertainty entropy value can effectively quantify the information uncertainty of the node in the fire environment. When the uncertainty entropy value of a node is relatively high, it indicates that the information source of the node is not reliable enough or there is a greater risk of change. By taking the entropy value as part of the node priority, it can help evaluate which nodes need to be restored or replaced first to ensure the accuracy and stability of the information flow. For example, if a node is in the edge area of the fire spread, its entropy value may be relatively high, indicating that the information it collects is not accurate enough or the probability of change is relatively large. At this time, the alternative node should be sent to supplement the information first to ensure the real-time nature of the fire dynamics.

[0066] The acquisition logic of the uncertainty entropy value coefficient is as follows: Collect the fire information data of the alternative node. The fire information data includes temperature, smoke concentration, gas concentration, and humidity. Use the Gaussian kernel function to estimate the probability density of the fire information data for the collected fire information data. The calculation formula is: ; where is the probability density of the ith fire information data, i is the number of the fire information data, m = 1, 2, 3,..., M, M is a positive integer, m is the number of the alternative node collecting the ith fire information data, h is the bandwidth parameter, and K is the Gaussian kernel function;

[0067] Calculate the uncertainty entropy value coefficient, and the calculation formula is: ; where is the uncertainty entropy value coefficient of the nth alternative node.

[0068] As can be seen from the formula, the larger the uncertainty entropy value coefficient, the less predictable the fire information data is, and it may be more likely to have new fire situations. Therefore, the node needs to closely monitor this area, and the lower the priority of the alternative node to go to the lost node position.

[0069] The self - correlation timeliness coefficient helps to evaluate the priority order of the alternative node to go to the lost node. The specific reasons are as follows:

[0070] In a fire scenario, the spread of fire is not completely random but is affected by many factors (such as wind speed, temperature, humidity, terrain, combustible substances, etc.) and usually has a certain time pattern. The self - correlation timeliness coefficient can capture these regularities, enabling us to infer the delay time for the fire to spread to a certain node;

[0071] If the delay time is greater than or close to the consumption time of the mobile node, it means that before the mobile node arrives at the lost node, the fire spread may not reach that node quickly. Therefore, a larger delay time of the node indicates that the fire spread rate may be slower, and the fire situation change can be evaluated within a certain time, giving the mobile node more time to prepare and deploy;

[0072] If the delay time is large and the mobile node can reach the lost node within a reasonable time, the spread state of the fire is more stable (not likely to change drastically), and the system can conduct more effective monitoring, information collection, and decision - making intervention by arriving at that node in advance. This will help formulate a reasonable resource scheduling and fire extinguishing plan.

[0073] The acquisition logic of the self - correlation timeliness coefficient is as follows: According to the temperature time series at the lost node, calculate the self - correlation function of temperature and time, and evaluate the correlation between temperature and time through different time lags;

[0074] Calculate the correlation between temperature and time at different time lags. The calculation formula is: ; where is the correlation between temperature and time at the kth time lag, t is 1, 2, 3, ……, T, T is a positive integer, t is the number of the unit time for each temperature acquisition, is the temperature at the alternative node at the tth unit time, is the average value of the temperature at the alternative node at the tth unit time, k = 0, 1, 2, 3, ……, K, k is the number of lagged unit times;

[0075] It should be noted that the unit time is a relatively small specific time period, set by the staff in the professional field.

[0076] Obtain the correlation between temperature and time at the optimal time lag, and the calculation formula is: ; where is the correlation between temperature and time at the optimal time lag;

[0077] Set the correlation threshold. If the correlation between temperature and time at the optimal time lag is greater than the correlation threshold, obtain the time required for the alternative node to travel to the lost node, and mark the time required for the alternative node to travel to the lost node as: , calculate the autocorrelation timeliness coefficient, and the calculation formula is: ; where is the autocorrelation timeliness coefficient of the nth alternative node;

[0078] If the correlation between temperature and time at the optimal time lag is less than the correlation threshold, record the autocorrelation timeliness coefficient as: 0.

[0079] It should be noted that if the correlation between temperature and time at the optimal time lag is greater than the correlation threshold, it indicates that the spread of the fire in this area is correlated with time, which means that the spread of the fire in this area has a certain regularity and predictability. This regularity is relatively important for optimizing resource scheduling and emergency response. If the correlation between temperature and time at the optimal time lag is less than the correlation threshold, it indicates that the spread of the fire in this area has no correlation with time and is not easy to predict, and the priority of the alternative node to travel to the lost node is relatively low.

[0080] As can be seen from the formula, the larger the autocorrelation timeliness coefficient, the stronger the correlation between the spread of the fire in the lost node area and time, and the alternative node can timely travel to the lost node to collect fire information data, indicating that the priority of this alternative node to travel to the lost node is higher.

[0081] Construct an alternative node evaluation model with the graph key node coefficient, uncertainty entropy value coefficient, and autocorrelation timeliness coefficient, and generate an alternative node evaluation coefficient. The calculation formula for the alternative node evaluation coefficient is: ; where is the alternative node evaluation coefficient of the nth alternative node, , , are the proportionality coefficients of the graph key node coefficient, uncertainty entropy value coefficient, and autocorrelation timeliness coefficient respectively, , , are all greater than 0.

[0082] Set the threshold of the alternative node evaluation coefficient, compare the alternative node evaluation coefficients of each alternative node with the alternative node evaluation coefficient threshold. If the alternative node evaluation coefficient is greater than the alternative node evaluation coefficient threshold, use the alternative node as the replacement for the lost node to go to the lost node. If the alternative node evaluation coefficient is less than the alternative node evaluation coefficient threshold, do not use the alternative node as the replacement for the lost node to go to the lost node. Collect the alternative nodes with evaluation coefficients greater than the alternative node evaluation coefficient threshold, generate the preferred selection order of the alternative nodes based on the magnitude order of the alternative node evaluation coefficients greater than the alternative node evaluation coefficient threshold, and select the alternative node with the largest alternative node evaluation coefficient to go to the lost node.

[0083] The present invention establishes an ad hoc network composed of fixed nodes, movable nodes and alternative nodes, and uses graph spectrum analysis to evaluate the danger and influence of nodes. Combining with uncertainty entropy value analysis, the information diversity and uncertainty of each node are obtained, and the importance of nodes is further evaluated. At the same time, through autocorrelation analysis of the fire data at the lost node, the delay time of fire spread is determined and compared with the response time of the alternative node. Finally, by integrating the importance and timeliness data of the nodes, the priority of the alternative node is quantified, so that when a fire occurs, the most suitable node can be quickly selected for intervention and monitoring, thereby optimizing the fire response strategy and ensuring the stability and real-time nature of information transmission and on-site monitoring. The present invention helps to quickly select the most suitable node for intervention and monitoring and can adapt to fire scenarios of different scales and complexities.

[0084] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0085] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0086] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0087] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0088] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0089] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0090] If the described functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0091] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

Claims

1. A fire scene auxiliary decision-making support system based on a mobile ad hoc network, characterized in that, It includes a mobile ad hoc network module, a node importance data module, a node timeliness data module, and an evaluation module, with signal connections between the modules; The mobile ad hoc network module is used to construct a mobile ad hoc network based on the fire according to the fire occurrence area, and determine fixed nodes, mobile nodes, and alternative nodes; The node importance data module is used to determine the danger and influence of alternative nodes through graph analysis, perform uncertainty entropy value analysis on fire information data, and collect node importance data of alternative nodes; The node timeliness data module is used to determine the delay time of fire spread through autocorrelation analysis of the temperature and time at the lost node, and compare it with the time from the alternative node to the lost node, and collect node timeliness data of alternative nodes; The evaluation module is used to comprehensively evaluate the node importance data and the node timeliness data to quantify the priority of each alternative node; The node importance data includes: The node importance data is represented by the graph key node coefficient and the uncertainty entropy value coefficient; The acquisition logic of the graph key node coefficient is: taking the fixed node and the mobile node as the nodes of the graph, connecting the two nodes through edges, and representing the relationship between the two nodes through the data transmission link and the communication connection between the nodes; Evaluate the influence of alternative nodes through the degree centrality of alternative nodes in the graph, and determine the risk weight of alternative nodes based on the flammability at the geographical location of alternative nodes. Mark the influence of alternative nodes as: , and mark the risk weight of alternative nodes as: , where n = 1, 2, 3, ……, N, N is a positive integer, n is the number of alternative nodes, and alternative nodes are movable nodes that can replace lost nodes; The calculation formula for the importance coefficient of the alternative node is as follows: ; where is the importance coefficient of the nth alternative node; Determine the geographical locations of the lost nodes and the alternative nodes, obtain the shortest distance from the alternative nodes to the nearest fire occurrence location, and obtain the shortest distance from the lost nodes to the fire occurrence location, and calculate the key node coefficient of the graph spectrum. The calculation formula is as follows: ; where is the key node coefficient of the graph spectrum, is the shortest distance from the alternative node to the nearest fire occurrence location, is the shortest distance from the lost node to the fire occurrence location.

2. The fire scene auxiliary decision-making support system based on mobile ad hoc network according to claim 1, characterized in that, The uncertainty entropy value coefficient includes: The acquisition logic of the uncertainty entropy value coefficient is as follows: Collect the fire information data of the alternative nodes. The fire information data includes temperature, smoke concentration, gas concentration, and humidity. Use the Gaussian kernel function to estimate the probability density of the fire information data for the collected fire information data. The calculation formula is: ; where is the probability density of the i-th fire information data, i is the number of the fire information data, m = 1, 2, 3,..., M, M is a positive integer, m is the number of the alternative node collecting the i-th fire information data, h is the bandwidth parameter, and K is the Gaussian kernel function; Calculate the uncertainty entropy value coefficient, and the calculation formula is: ; where is the uncertainty entropy value coefficient of the nth alternative node.

3. The fire scene auxiliary decision-making support system based on mobile ad hoc network according to claim 2, wherein, The node timeliness data includes: The node timeliness data is represented by the autocorrelation timeliness coefficient; The acquisition logic of the autocorrelation timeliness coefficient is: according to the temperature time series at the lost node, calculate the autocorrelation function of the temperature and time, and evaluate the correlation between the temperature and time through different time lags; Calculate the correlation between temperature and time at different time lags. The calculation formula is as follows: ; where is the correlation between temperature and time at the k-th time lag, t is 1, 2, 3, ……, T, T is a positive integer, t is the number of the unit time for each temperature acquisition, is the temperature at the replacement node at the t-th unit time, is the average value of the temperature at the replacement node at the t-th unit time, k = 0, 1, 2, 3, ……, K, k is the number of unit time lags; Obtain the correlation between temperature and time at the optimal time lag, and the calculation formula is: ; where is the correlation between temperature and time at the optimal time lag; Set a correlation threshold. If the correlation between temperature and time under the optimal time lag is greater than the correlation threshold, obtain the time required for the replacement node to reach the lost node, and mark the time required for the replacement node to reach the lost node as: , calculate the autocorrelation timeliness coefficient, and the calculation formula is: ; where is the autocorrelation timeliness coefficient of the nth replacement node; If the correlation between the temperature and time under the optimal time lag is less than the correlation threshold, the autocorrelation timeliness coefficient is recorded as:

0.

4. The fire scene auxiliary decision-making support system based on mobile ad hoc network according to claim 3, characterized in that, The comprehensive evaluation of the node importance data and the node timeliness data includes: Construct a substitute node evaluation model with the graph key node coefficient, uncertainty entropy value coefficient, and autocorrelation timeliness coefficient to generate a substitute node evaluation coefficient. The calculation formula for the substitute node evaluation coefficient is: ; where is the substitute node evaluation coefficient of the nth substitute node, , , are the proportionality coefficients of the graph key node coefficient, uncertainty entropy value coefficient, and autocorrelation timeliness coefficient respectively, , , are all greater than 0.

5. The fire scene auxiliary decision support system based on mobile ad hoc network according to claim 4, characterized in that Quantifying the priority of each alternative node includes: Setting the alternative node evaluation coefficient threshold, comparing the alternative node evaluation coefficients of each alternative node with the alternative node evaluation coefficient threshold. If the alternative node evaluation coefficient is greater than the alternative node evaluation coefficient threshold, the alternative node is used as the alternative to the lost node to go to the lost node. If the alternative node evaluation coefficient is less than the alternative node evaluation coefficient threshold, the alternative node is not used as the alternative to the lost node to go to the lost node. Collect the alternative nodes with an alternative node evaluation coefficient greater than the alternative node evaluation coefficient threshold, generate the preferred order of the alternative nodes based on the magnitude order of the alternative node evaluation coefficients greater than the alternative node evaluation coefficient threshold, and select the alternative node with the largest alternative node evaluation coefficient to go to the lost node.

Images