Unmanned energy storage power station fire prevention and control method and system based on Internet of Things

Abstract

The invention relates to the technical field of power station fire prevention and control, and discloses an unmanned energy storage power station fire prevention and control method and system based on the Internet of Things, and the method comprises the steps: obtaining an environment map database, a real-time environment data flow, and an initial fire environment information set; performing data updating to obtain obstacle space distribution information; performing fire behavior influence prediction to obtain a fire behavior influence area range; key nodes are extracted, connectivity detection is carried out on the key nodes, and a passable area range is determined; performing path feasibility evaluation to obtain an initial passable path set; adjusting the initial passable path set in real time, and determining an optimal path option in the current environment; and acquiring position information of the fire fighting equipment, and generating a final navigation instruction set by combining the position information of the fire fighting equipment and the optimal path option. According to the method, the position of a fire source can be accurately identified during fire prevention and control of the unmanned energy storage power station, the spreading trend is pre-judged, and a safe path plan is generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power station fire prevention and control, and particularly relates to a fire prevention and control method and system for unmanned energy storage power stations based on the Internet of Things. BACKGROUND

[0002] At present, as the core link of the new energy system, the safe operation of energy storage power stations is related to the stability of the energy system, but the rapid spread caused by fire risks and environmental personnel hazards urgently need efficient prevention and control means.

[0003] In one prior art, energy storage power stations are generally equipped with basic fire monitoring and extinguishing equipment, and only rely on static control maps to deal with fire. However, this method has obvious deficiencies in adaptability and response speed in complex environments, and has shortcomings in building accurate environmental maps, and is difficult to fully grasp the distribution of obstacles and fire changes inside the power station. Especially when a fire occurs, it is difficult to quickly identify the location of the fire source and the spread trend, and it is also difficult to effectively respond to the complex spatial layout and dynamically changing environment inside the power station, resulting in low efficiency of fire extinguishing operations, and even missing the best rescue opportunity.

[0004] In summary, the prior art has the problems of being unable to accurately identify the location of the fire source, predict the spread trend, and generate a safe path planning. SUMMARY

[0005] The present application provides a fire prevention and control method and system for unmanned energy storage power stations based on the Internet of Things, to solve the problem of being unable to accurately identify the location of the fire source, predict the spread trend, and generate a safe path planning when preventing and controlling fires in unmanned energy storage power stations.

[0006] In a first aspect, to solve the above technical problems, the present application provides a fire prevention and control method for unmanned energy storage power stations based on the Internet of Things, comprising: acquiring a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environment information set; wherein the real-time environmental data streams include changes in environmental temperature, types of burning materials, heat radiation intensity, and oxygen concentration distribution over time when a fire occurs; updating data according to the initial fire environment information set, in combination with the changes in environmental temperature and the types of burning materials, to obtain obstacle spatial distribution information; performing fire influence prediction according to the obstacle spatial distribution information, in combination with the heat radiation intensity and the oxygen concentration distribution, to obtain a fire influence area range; extracting key nodes from the environmental map database according to the fire influence area range, performing connectivity detection for the key nodes, and determining a passable area range; The dynamic updating of the obstacles in the passable area range obtains the latest obstacle information, and the path feasibility evaluation is performed on the obstacle thermal deformation data and the visibility in the latest obstacle information, to obtain an initial passable path set; The current thermal radiation perception peak value and air flow direction offset are obtained, and the initial passable path set is adjusted in real time to determine an optimal path option in the current environment; The position information of the fire-fighting equipment is obtained, and the optimal path option is combined with the position information of the fire-fighting equipment to generate a final navigation instruction set.

[0007] In an optional implementation, the data updating according to the initial fire environment information set, in combination with the environmental temperature change and the combustion species, obtains obstacle spatial distribution information, including: Based on the initial fire environment information set, the obstacle distribution is mapped to a three-dimensional space model to obtain initial obstacle spatial distribution information; In combination with the environmental temperature change and the combustion species, the initial obstacle spatial distribution information is updated to obtain the obstacle spatial distribution information.

[0008] In an optional implementation, the fire influence prediction according to the obstacle spatial distribution information, in combination with the thermal radiation intensity and the oxygen concentration distribution, obtains a fire influence area range, including: Based on the obstacle spatial distribution information, the thermal radiation intensity and the oxygen concentration distribution are monitored and classified to obtain a preliminary fire distribution data set; According to the preliminary fire distribution data set, the spatial mapping prediction processing is performed on the fire source offset path and the fire spread path to determine a preliminary fire influence range; According to the preliminary fire influence range, the regions in the preliminary fire influence range are compared in terms of danger level and calibrated in terms of path to obtain a final fire influence area range.

[0009] In an optional implementation, the key nodes are extracted from the environmental map database according to the fire influence area range, including: According to the fire influence area range, the corresponding complex spatial layout in the environmental map database is obtained; The position information of the main entrances and exits and the fire crossroads in the complex spatial layout is extracted to obtain the key nodes.

[0010] In an optional implementation, the connectivity detection is performed on the key nodes to determine a passable area range, including: acquire local temperature data and smoke concentration information corresponding to the key node, compare the local temperature data with a preset temperature threshold for the first time, and if it is detected that the local temperature data does not exceed the preset temperature threshold, make a non-passable mark to obtain a first non-passable area; based on the first non-passable area, compare the smoke concentration information with a preset concentration threshold for the second time, and if it is detected that the smoke concentration information exceeds the preset concentration threshold, make a non-passable mark to obtain a second non-passable area; divide the areas comprehensively based on the first non-passable area and the second non-passable area to obtain the final passable area range.

[0011] In an optional embodiment, the dynamic updating of the obstacles in the passable area range obtains the latest obstacle information, the path feasibility evaluation is performed on the obstacle thermal deformation data and the visibility in the latest obstacle information to obtain an initial passable path set, including: acquire the update information of the obstacles in the passable area range, record the position and shape change of the obstacles to obtain the latest obstacle information; according to the latest obstacle information, compare the obstacle thermal deformation data of the latest obstacle information with a preset thermal deformation threshold, and if the obstacle thermal deformation data exceeds the preset thermal deformation threshold, make a non-passable mark to obtain a preliminary non-passable path; according to the preliminary non-passable path and the latest obstacle information, compare the visibility of the latest obstacle information with a preset visibility threshold, and if the visibility is lower than the preset visibility threshold, make a high-risk mark to obtain a high-risk area set; adjust the areas of the passable area range comprehensively based on the preliminary non-passable path and the high-risk area set to obtain the initial passable path set.

[0012] In an optional embodiment, the current thermal radiation perception peak value and the air flow direction offset are acquired, and the initial passable path set is adjusted in real time to determine the optimal path option under the current environment, including: perform path scanning on the initial passable path set to obtain the current thermal radiation perception peak value and the air flow direction offset; according to the initial passable path set, compare the thermal radiation perception peak value with a preset peak threshold value, and if the thermal radiation perception peak value exceeds the preset peak threshold value, make a limited mark to obtain limited path distribution data; According to the initial passable path set, the air flow direction offset is compared with a preset offset threshold, if the air flow direction offset exceeds the preset offset threshold, a blocked mark is made, and blocked path distribution data is obtained; Based on the initial passable path set, local path correction is performed in combination with the restricted path distribution data and the blocked path distribution data, and a final passable path set under the current environment is obtained. The final passable path set is screened based on an optimal path selection standard, and the optimal path option is obtained.

[0013] In a second aspect, the present application provides an unmanned energy storage power station fire prevention and control system based on Internet of Things, comprising: A data acquisition module is configured to acquire a pre-established environment map database, real-time environment data stream collected by a sensor, and an initial fire environment information set; wherein the real-time environment data stream includes environmental temperature variation, combustion species, heat radiation intensity, and oxygen concentration distribution varying with time when a fire occurs. An information updating module is configured to update data according to the initial fire environment information set in combination with the environmental temperature variation and the combustion species, and obtain obstacle spatial distribution information. A fire prediction module is configured to predict the influence of fire according to the obstacle spatial distribution information in combination with the heat radiation intensity and the oxygen concentration distribution, and obtain a fire influence area range. A path analysis module is configured to extract key nodes from the environment map database according to the fire influence area range, perform connectivity detection on the key nodes, and determine a passable area range. A path evaluation module is configured to dynamically update obstacles in the passable area range to obtain the latest obstacle information, perform path feasibility evaluation on obstacle data and visibility in the latest obstacle information, and obtain an initial passable path set. A path optimization module is configured to acquire a current heat radiation perception peak value and an air flow direction offset, and perform real-time adjustment on the initial passable path set to determine an optimal path option under the current environment. An instruction generation module is configured to acquire position information of a fire-fighting device, combine the position information of the fire-fighting device with the optimal path option, and generate a final navigation instruction set.

[0014] In a third aspect, the present application further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the fire prevention and control method of the unmanned energy storage power station based on Internet of Things when executing the computer program.

[0015] Fourthly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the fire prevention and control method for unmanned energy storage power stations based on the Internet of Things as described above.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention utilizes a pre-established environmental map database as a foundation, which contains detailed layout information of the energy storage power station. Simultaneously, real-time environmental data streams are collected via sensors, including information such as changes in ambient temperature over time during a fire. When a fire occurs, the temperature around the fire source exhibits a clear pattern of change. This real-time temperature change data is used, combined with the initial fire environment information set and the type of combustible material, to update the data. The type of combustible material affects the heat generated by combustion and the temperature distribution pattern. By comprehensively processing this information, the location of the fire source can be determined more accurately.

[0017] (2) After obtaining the spatial distribution information of obstacles, this invention further combines the thermal radiation intensity and oxygen concentration distribution to predict the impact of fire. Thermal radiation intensity is one of the key factors in fire propagation, determining the speed and range at which the fire transfers heat to the surrounding environment. Oxygen concentration distribution affects the persistence and direction of combustion, as combustion requires oxygen. By analyzing these factors, the potential area of ​​fire spread can be predicted.

[0018] (3) This invention can generate safe and effective path planning. First, key nodes are extracted from the environmental map database based on the fire-affected area. These key nodes may be important passages, safety exits, or fire-fighting facilities within the power plant. Then, connectivity detection is performed on the key nodes to determine the passable area, thus eliminating areas that are impassable due to the fire. Next, obstacles in the passable area are dynamically updated. Taking into account the thermal deformation data and visibility of obstacles in the fire environment, a path feasibility assessment is performed to obtain an initial set of passable paths. At the same time, the current thermal radiation sensing peak and airflow direction shift information are obtained in real time, and the initial set of passable paths is adjusted in real time to finally determine the optimal path option under the current environment. Through this series of analyses and adjustments based on real-time environmental data, safer and more reliable path planning can be generated, facilitating firefighters or fire-fighting equipment to quickly and safely reach the fire scene for firefighting and rescue. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of a fire prevention and control method for an unmanned energy storage power station based on the Internet of Things, provided in the first embodiment of the present invention. Figure 2 This is a flowchart illustrating a method for obtaining an initial set of passable paths according to the first embodiment of the present invention; Figure 3 This is a flowchart illustrating a method for determining the optimal path option in the current environment, provided in the first embodiment of the present invention. Figure 4 This is a schematic diagram of a fire prevention and control structure for an unmanned energy storage power station based on the Internet of Things, provided in the second embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Reference Figure 1 The first embodiment of the present invention provides a fire prevention and control method for unmanned energy storage power stations based on the Internet of Things, including the following steps: S11, acquire a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environmental information set. The real-time environmental data streams include changes in ambient temperature over time, types of combustibles, heat radiation intensity, and oxygen concentration distribution when the fire occurs. S12, based on the initial fire environment information set, and combined with the changes in ambient temperature and the types of combustibles, data is updated to obtain the spatial distribution information of obstacles; S13. Based on the spatial distribution information of the obstacles, and combined with the thermal radiation intensity and the oxygen concentration distribution, the fire impact is predicted to obtain the range of the fire impact area. S14. Based on the range of the fire-affected area, extract key nodes from the environmental map database, perform connectivity detection on the key nodes, and determine the range of passable areas. S15, dynamically update the obstacles in the passable area to obtain the latest obstacle information, and perform path feasibility assessment based on the obstacle thermal deformation data and visibility in the latest obstacle information to obtain an initial set of passable paths; S16, obtain the current thermal radiation sensing peak and air flow direction shift, and adjust the initial set of passable paths in real time to determine the optimal path option under the current environment; S17, Obtain the location information of the fire-fighting equipment, and generate the final navigation instruction set by combining the location information of the fire-fighting equipment and the optimal path option.

[0022] In step S11, a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environmental information set are acquired. The real-time environmental data streams include changes in ambient temperature over time, types of combustibles, heat radiation intensity, and oxygen concentration distribution when the fire occurs.

[0023] It should be noted that the environmental map database is pre-established based on the physical layout of the energy storage power station, storing its static spatial layout information, including three-dimensional spatial mapping data such as passage dimensions, fire equipment locations, key node locations, and initial obstacle distribution. Sensors refer to the Internet of Things (IoT) sensor network deployed at the energy storage power station, supporting continuous monitoring to ensure coverage of all high-risk points and acquiring environmental parameters. This sensor network consists of, but is not limited to, gas sensors, temperature sensors, humidity sensors, smoke detectors, wind speed sensors, and thermal imaging equipment. Real-time environmental data streams are dynamic parameters collected by the sensor network over time when a fire occurs, including changes in ambient temperature, type of combustible material, thermal radiation intensity, and oxygen concentration distribution. These elements collectively form the basis of fire situational awareness.

[0024] The real-time environmental data stream includes changes in ambient temperature, type of combustible material, thermal radiation intensity, and oxygen concentration distribution over time during a fire. Specifically, ambient temperature changes refer to the continuous monitoring of temperature fluctuations over time, used to detect the onset and spread of the fire. Combustible material type is identified by sensors and used to construct fire spread models. Thermal radiation intensity, measured using thermal imaging equipment, reflects the thermal influence range of the fire source and is used to predict fire source location shifts. Oxygen concentration distribution is obtained by detecting changes in oxygen levels using gas sensors and is used to assess fire severity and smoke diffusion.

[0025] The initial fire environment information set is a dataset of environmental dynamic parameters and environmental map databases acquired by the sensor network at the time of a fire, used to construct a basic spatial distribution map of the fire. Specifically, it compares the temperature change and gas concentration data acquired by sensors at the time of the fire with preset thresholds. If a temperature change or gas concentration exceeds the preset threshold, a potential initial fire risk is identified in the dataset. The location of the data set is determined, the area is marked as an anomaly, and the area is then subjected to 3D spatial mapping based on the environmental map database, followed by graphic rendering to generate a visual distribution map. For example, if the temperature in a certain area suddenly rises from 25 degrees Celsius to 60 degrees Celsius, and the carbon monoxide concentration exceeds 50 ppm, exceeding the preset threshold of 40 ppm, the system can determine that there is a potential fire risk. Through time series analysis of the data, combined with wind speed and equipment spacing, the estimated fire spread rate is 0.5 meters per minute, and the smoke spread range is a 10-meter radius around the perimeter, thus determining the location of the anomaly area to be the middle section of a narrow passage inside the power plant.

[0026] In step S12, based on the initial fire environment information set and combined with the changes in ambient temperature and the types of combustibles, data is updated to obtain obstacle spatial distribution information, including: Based on the initial fire environment information set, the obstacle distribution is mapped into a three-dimensional spatial model to obtain the initial obstacle spatial distribution information; By combining the changes in ambient temperature and the type of combustible material, the initial spatial distribution information of obstacles is updated to obtain the spatial distribution information of obstacles.

[0027] It should be noted that obstacles refer to physical entities or dynamically changing structures within an energy storage power station that may impede the movement of firefighting equipment, affect fire extinguishing path planning, or exacerbate the spread of fire. These include, but are not limited to, fixed equipment, mobile devices, building structures, temporary storage materials, and dynamic objects that subsequently undergo thermal deformation or positional shift due to the fire. Obstacle distribution data refers to the location, size, and shape information of obstacles within the energy storage power station, acquired from environmental sensors and thermal imaging equipment.

[0028] The three-dimensional spatial model refers to a three-dimensional map model based on the energy storage power station; it is a virtual model. The initial obstacle spatial distribution information refers to the three-dimensional spatial dataset obtained by spatially mapping obstacle distribution data. The obstacle spatial distribution information is a three-dimensional spatial dataset obtained by labeling temperature changes and combustible material types data on the initial obstacle spatial distribution information; it reflects the real-time location, shape, and hazard level of obstacles within the energy storage power station.

[0029] In this embodiment, within the abnormal and non-abnormal areas of the initial fire environment information set, obstacle information obtained from environmental sensors and thermal imaging equipment is mapped into a three-dimensional spatial model through spatial distribution construction, thus obtaining initial obstacle spatial distribution information. Specifically, environmental sensors can collect data on smoke concentration and gas composition in the air, while thermal imaging equipment captures temperature distribution images using infrared technology. Multiple piles of materials are identified in a warehouse area within the park, and through three-dimensional mapping, the location and volume of these obstacles in space can be clearly displayed.

[0030] For example, after obtaining the initial spatial distribution information of obstacles, the spatial distribution information of obstacles is updated by updating the data on temperature changes and types of combustibles. For example, after obtaining the distribution of abnormal areas in the initial spatial distribution information of obstacles, the data on changes in ambient temperature is updated. If a change in the type of combustibles is detected, the hazard level parameter of the obstacle distribution is adjusted to obtain the distribution details updated in real time. Based on the distribution details updated in real time, a three-dimensional dynamic distribution map is generated, and high-hazard level areas are marked with color to determine whether the obstacle distribution has changed significantly and to determine the final spatial distribution information.

[0031] Specifically, if the smoke concentration in a certain area reaches 0.5 milligrams per cubic meter, and the thermal imaging shows a temperature of 80 degrees Celsius, the system will classify and record this data along with information on the type of combustible material, such as wood or chemicals. If the ambient temperature exceeds a preset threshold, such as 80 degrees Celsius, the system will automatically mark the distribution of obstacles in that area with high priority, highlighting their potential hazards. This marking helps to quickly locate fire hazard areas, thus providing accurate spatial location information for subsequent emergency response. If the ambient temperature is detected to rise from 80 degrees Celsius to 100 degrees Celsius, and the type of combustible material changes from wood to chemicals, the system will adjust the hazard level parameters of the obstacle distribution according to the increased risk, for example, upgrading from medium risk to high risk, and generating real-time updated distribution details. This dynamic adjustment can promptly reflect the severity of the fire's development, providing the latest basis for decision-making.

[0032] In step S13, based on the spatial distribution information of the obstacles, and combined with the thermal radiation intensity and oxygen concentration distribution, the fire impact prediction is performed to obtain the range of the fire impact area, including: Based on the spatial distribution information of the obstacles, the thermal radiation intensity and the oxygen concentration distribution are monitored and classified to obtain a preliminary fire distribution dataset. Based on the preliminary fire distribution dataset, spatial mapping prediction processing is performed on the fire source offset path and fire spread path to determine the preliminary fire impact range. Based on the preliminary fire impact range, the area within the preliminary fire impact range is compared for hazard level and the path is calibrated to obtain the final fire impact range.

[0033] It should be noted that the thermal radiation intensity and oxygen concentration distribution are derived from real-time environmental data streams. For example, temperature data from temperature sensors and oxygen concentration data from gas sensors can be categorized into thermodynamic parameters and environmental parameters, respectively. After being organized using a standardized format, a preliminary fire distribution dataset is formed. This classification helps to quickly extract key information during subsequent analysis, improving data processing efficiency.

[0034] Among them, the fire source offset path refers to the movement trajectory of the fire source center point over time and with changes in the environment during a fire. Its spatial position is affected by ambient temperature, airflow, and the distribution of obstacles, causing real-time shifts. The fire spread path refers to the main direction and boundary of the spread of flames from the fire source to the surrounding area. Its shape is constrained by obstacle properties and environmental parameters. Spatial mapping preprocessing refers to the algorithmic process of transforming the abstract data of the fire source offset path and spread path into a three-dimensional spatial visual model. The core is to construct the spatial mapping relationship of the fire's impact.

[0035] Specifically, in the fire source offset path prediction processing, vector analysis can be performed to calculate the fire source movement direction based on the input thermal radiation intensity gradient data, oxygen concentration distribution differences, and obstacle spatial distribution information. The thermal radiation intensity gradient data can be the intensity values ​​decreasing from the fire source center to the periphery. In the fire spread path prediction processing, the possible expansion direction of the fire can be simulated based on a preliminary fire distribution dataset combined with thermal radiation intensity data. For example, if the thermal radiation intensity in a certain area continues to increase, the system predicts that the fire may spread along the direction of flammable material accumulation inside the warehouse, and delineates the preliminary fire impact range boundary accordingly; if the oxygen concentration distribution in a certain area continues to decrease, and the oxygen concentration drops below a preset threshold, the corresponding area is marked as high-risk, and this area is designated as a severely affected fire area. This prediction provides an important reference for advance planning of emergency measures. The preliminary fire impact range refers to the uncalibrated fire impact area space generated through spatial mapping prediction processing, including the fire source offset path and the fire spread path.

[0036] Hazard level comparison refers to the comprehensive comparison of data within the initial fire impact area, and the corresponding levels are marked with colors in a visualization layer, thus obtaining a dynamic fire situation visualization layer. For example, if the oxygen concentration in a high-risk marked area further decreases to 16%, while the heat radiation intensity increases to 600 watts per square meter, the system will upgrade the hazard level of that area from moderate to high hazard, and the color marking will also change from light red to dark red. This dynamic adjustment can promptly reflect changes in the fire situation and provide the latest support for decision-making.

[0037] Path calibration refers to analyzing the path of fire spread. If the fire's impact exceeds preset boundaries, such as expanding from inside the warehouse to surrounding passageways, the system adjusts the dynamic fire map in real time to reassess the final fire-affected area. If, after adjustment, the fire approaches the main road of the park, the system further updates the map information to ensure the accuracy of the fire's extent. This calibration mechanism provides more reliable spatial information support for developing evacuation and firefighting plans.

[0038] In step S14, key nodes are extracted from the environmental map database based on the range of the fire-affected area, and connectivity detection is performed on the key nodes to determine the range of passable areas.

[0039] In one implementation, extracting key nodes from the environmental map database based on the fire-affected area includes: Based on the extent of the fire's impact, obtain the corresponding complex spatial layout in the environmental map database; The location information of the main entrances and exits and fire intersections in the complex spatial layout is extracted to obtain the key nodes.

[0040] It should be noted that complex spatial layouts refer to local map data in the environmental database that have a high degree of spatial overlap with the fire-affected area and high structural complexity. Key nodes refer to strategic locations within the complex spatial layout that play a decisive role in path connectivity, including main entrances / exits and fire lane intersections. For example, a multi-story warehouse area within the park has a complex spatial layout containing multiple passageways and storage points. Using a pre-established environmental map database, the locations of key nodes within the warehouse, such as main entrances / exits and fire lane intersections, can be quickly identified, providing a preliminary understanding of their distribution. This approach helps lay the foundation for subsequent path analysis.

[0041] In one implementation, the step of performing connectivity detection on the key nodes to determine the passable area range includes: Obtain local temperature data and smoke concentration information corresponding to the key nodes; The local temperature data is initially compared with a preset temperature threshold. If the local temperature data does not exceed the preset temperature threshold, an impassable mark is made to obtain the first impassable area. Based on the first impassable area, the smoke concentration information is compared with a preset concentration threshold a second time. If the smoke concentration information is detected to exceed the preset concentration threshold, an impassable mark is made to obtain a second impassable area. The first impassable area and the second impassable area are combined to divide the area into regions, resulting in the final range of the passable area.

[0042] It should be noted that the local temperature data and smoke concentration information are collected by sensors located in the area between key nodes. The preset temperature threshold refers to a pre-set ambient temperature critical value used to determine the fire risk level of the area surrounding the key nodes. The preset concentration threshold refers to a pre-set smoke concentration critical value used to assess the toxicity risk and visibility conditions of the key node area. Impassable markings refer to spatial markers dynamically displayed on the environmental map indicating areas with fire risk and where passage is prohibited. The first impassable area is the area marked as impassable due to temperature. The second impassable area is the area marked as impassable due to smoke concentration.

[0043] Specifically, the local temperature data is initially compared with a preset temperature threshold. If the local temperature data does not exceed the preset temperature threshold, an "unpassable" marker is created. For example, in a passageway between two key nodes within a warehouse, if the local temperature exceeds a preset threshold (e.g., 60 degrees Celsius), while the normal safe range is 40 degrees Celsius, the system will immediately mark the path as unpassable, initially determining a potential risk of passage. The marker will be updated again during subsequent real-time data updates.

[0044] The second impassable area is defined based on the first impassable area. Specifically, on the overall environmental map area of ​​the energy storage power station, passable areas outside the first impassable area are marked as impassable based on smoke concentration, thus obtaining the second impassable area. In this application, different colors are used to visually distinguish various impassable markers; for example, impassable markers based on smoke concentration data are dark purple, those based on temperature data are purple, and those based on obstacle thermal deformation data are light purple.

[0045] The first and second impassable areas are combined to divide the area into zones, resulting in the final traversable area. Specifically, on the energy storage power station environment map, the area outside the first and second impassable areas is defined as the traversable area.

[0046] In step S15, the obstacles in the passable area are dynamically updated to obtain the latest obstacle information. The path feasibility is evaluated based on the obstacle thermal deformation data and visibility in the latest obstacle information to obtain an initial set of passable paths.

[0047] The latest obstacle information in this step includes real-time data on obstacle displacement and shape changes caused by fire in passable areas, especially obstacle thermal deformation data and visibility data. Path feasibility assessment involves comparing obstacle thermal deformation and visibility data against safety thresholds. If the data exceeds the safety threshold, appropriate marking is required, enabling dynamic adjustment. Through dual physical models of thermal deformation and visibility, combined with real-time algorithm optimization, a highly reliable path planning system for fire environments has been constructed, providing core technical support for unmanned firefighting systems.

[0048] like Figure 2 As shown, step S15 involves dynamically updating the obstacles within the passable area to obtain the latest obstacle information. Based on the obstacle thermal deformation data and visibility from the latest obstacle information, a path feasibility assessment is performed to obtain an initial set of passable paths, including: S151, obtain updated information on obstacles in the passable area, record the position and shape changes of the obstacles, and obtain the latest obstacle information; S152, based on the latest obstacle information, compare the obstacle thermal deformation data of the latest obstacle information with a preset thermal deformation threshold. If the obstacle thermal deformation data exceeds the preset thermal deformation threshold, mark the path as impassable to obtain a preliminary impassable path. S153, based on the preliminary impassable path and the latest obstacle information, compare the visibility of the latest obstacle information with a preset visibility threshold. If the visibility is lower than the preset visibility threshold, mark it as high-risk to obtain a set of high-risk areas. S154, the range of passable areas is adjusted by combining the initial impassable paths and the set of high-risk areas to obtain the initial set of passable paths.

[0049] It should be noted that in step S151, obtaining updated information on obstacles within the passable area involves recording the changes in the position and shape of the obstacles to obtain the latest obstacle information. Specifically, this can be achieved by performing in-depth processing on the passable area based on a pre-established environmental map database to obtain updated information on dynamic obstacles. Combined with real-time collected thermal deformation data, the changes in the position and shape of the obstacles are recorded to obtain the latest obstacle information. These changes in position and shape include, but are not limited to, equipment collapse and thermal expansion. For example, in a fire monitoring scenario within an industrial park, for path planning and obstacle distribution analysis under complex spatial layouts, in-depth processing of relevant data can be performed in various ways. First, based on the pre-established environmental map database, a detailed scan of the passable area can be performed to obtain updated information on dynamic obstacles. For instance, in a multi-story warehouse, a fire causes a shelf collapse in a certain area, creating a new obstacle. Through real-time updates of the database, the changes in the position and shape of the obstacle can be recorded. For example, after the shelf collapse, it occupies the path from the east aisle to the central area, with a width of approximately 2.5 meters, thus initially forming the obstacle distribution result. This approach helps provide foundational information for subsequent route planning.

[0050] In step S152, the obstacle deformation data refers to the real-time change in the physical shape of obstacles caused by the high temperature of a fire. The preset thermal deformation threshold is a critical value for obstacle deformation due to high temperature, set before a fire occurs. This threshold can be derived from safety standards for energy storage systems and is used to determine whether the structural stability of an obstacle threatens passage safety in a fire environment. The impassable marker is an unpassable marker based on the obstacle's thermal deformation data in a three-dimensional spatial mapping layer. The preliminary impassable path refers to a path segment dynamically marked on the environmental map based solely on the thermal deformation threshold determination mechanism, indicating a passage safety risk due to obstacle deformation. This provides a basis for avoiding restricted areas in subsequent path planning, addressing the problem of insufficient dynamic adaptability of paths.

[0051] In step S153, the information is based on the initially impassable path and the latest obstacle information. Specifically, this means extracting the latest obstacle information from the passable area that does not overlap with the initially impassable area in the three-dimensional spatial map, particularly the visibility value in the latest obstacle information, to facilitate subsequent comparison. The visibility value refers to the maximum visible distance of firefighters or equipment in a smoke environment. The preset visibility value is the minimum visibility threshold to ensure safe passage for firefighters and can be derived from international standard values. High-risk markings are implemented in a similar way to impassable markings, distinguished only by different marking colors, to indicate the danger level and prohibit safe passage. The high-risk area set is the set of areas marked with high-risk markings.

[0052] In step S154, the accessible area is adjusted by combining the initial impassable paths and the set of high-risk areas to obtain the initial accessible path set. Specifically, path planning is performed within the accessible area on a 3D spatially mapped map. This can involve avoiding the initial impassable paths and the set of high-risk areas, or avoiding areas overlapping with the initial impassable paths and the set of high-risk areas, resulting in a set of all initial accessible paths. The initial accessible path set refers to a dataset of safe accessible path sequences generated within the accessible area after dynamic obstacle updates, thermal deformation, and visibility dual risk assessments.

[0053] In step S16, the current thermal radiation sensing peak and airflow direction shift are obtained, and the initial set of passable paths is adjusted in real time to determine the optimal path option under the current environment.

[0054] It should be noted that this step only processes the initial set of passable paths. It utilizes dual dynamic parameters of thermal radiation and airflow direction to real-time mark restricted and obstructed paths, thereby achieving real-time optimization of the initial set of passable paths and addressing the core issue of insufficient dynamic adaptability of paths. These markings can be distinguished by different colors on a 3D spatially mapped map.

[0055] like Figure 3 As shown, step S16, which involves obtaining the current peak value of thermal radiation sensing and the shift in airflow direction, and adjusting the initial set of passable paths in real time to determine the optimal path option under the current environment, includes: S161, Perform a path scan on the initial set of passable paths to obtain the current thermal radiation sensing peak and the airflow direction shift; S162, based on the initial set of passable paths, compare the heat radiation sensing peak with a preset peak threshold. If the heat radiation sensing peak exceeds the preset peak threshold, mark it as restricted to obtain restricted path distribution data. S163, based on the initial set of passable paths, compare the airflow direction offset with a preset offset threshold. If the airflow direction offset exceeds the preset offset threshold, mark the obstructed path and obtain obstructed path distribution data. S164, Based on the initial set of passable paths, local path correction is performed by combining the restricted path distribution data and the blocked path distribution data to obtain the final set of passable paths under the current environment; S165, the final set of passable paths is filtered based on the optimal path selection criteria to obtain the optimal path option.

[0056] It should be noted that in step S161, the peak value of thermal radiation sensing refers to the highest value of the thermal radiation sensing data, which is the thermal radiation value continuously collected by sensors in the initial set of passable paths. Airflow direction offset is generated by real-time recording of airflow direction offset information around the path; this can be wind speed fluctuation data or airflow direction data.

[0057] In step S162, the preset peak threshold is the highest thermal radiation critical value to ensure the safe passage of firefighters or equipment. The restricted marking is used to mark restricted path segments due to excessive thermal radiation. For example, assuming a path leading from the east side of a warehouse to a safety exit has a monitored thermal radiation value of 75 degrees Celsius, far exceeding the preset threshold of 40 degrees Celsius, the system will immediately mark that path segment as temporarily restricted, forming restricted path distribution data. This method can promptly identify potential high-temperature risk areas, providing a basis for subsequent path adjustments.

[0058] Step S163 can be performed either on the initial set of passable paths or based on the restricted path distribution data, and its purpose is to identify road segments where airflow is obstructed. In this embodiment, it is performed on the initial set of passable paths. The preset offset threshold is the maximum wind speed offset value that ensures safe passage. The obstruction marker is used to mark road segments where passage is obstructed due to airflow turbulence.

[0059] In step S164, the local path correction refers to dynamic path topology reconstruction based on restricted and obstructed markers in the initial set of traversable paths. Specifically, it may involve merging restricted and obstructed paths to obtain a comprehensive set of unsuitable traversable paths, and then outputting the non-overlapping portions of the initial set of traversable paths with the unsuitable traversable paths to obtain the final set of traversable paths.

[0060] In step S165, the optimal path selection criterion can be a pre-built multi-objective decision-making system or optimal path selection tool with preset filtering rules, which assign weights to various dynamic parameters to match the required optimal path option. These dynamic parameters can include path length, travel difficulty, peak thermal radiation impact, airflow stability impact, and visibility impact. For example, among multiple alternative paths, the northern route has a longer path distance and no abnormal high temperature or wind speed was detected, while the western route, although slightly shorter, has a slight smog impact. The system will prioritize the northern route as the final travel path option.

[0061] In step S17, the location information of the fire-fighting equipment is obtained, and the final navigation instruction set is generated by combining the location information of the fire-fighting equipment with the optimal path option.

[0062] This step involves converting the optimal path options into executable navigation commands for firefighters and fire equipment, enabling precise action scheduling in a fire environment. The location information of the fire equipment refers to its real-time coordinates and motion status data in three-dimensional space.

[0063] Specifically, based on the optimal route option, real-time demand data is collected and compared according to the urgency of the firefighting operation. If the urgency exceeds a preset threshold, the route is prioritized, resulting in priority route distribution data. Using this priority route distribution data, the location information of firefighting equipment is collected in real time and calibrated using distance measurements from the fire source. If the distance error exceeds a preset threshold, the location information is adjusted to determine the calibrated location coordinates. The calibrated location coordinates are then acquired, and changes in the dynamic route are continuously monitored. Fluctuations in the route changes are compared to identify route segments requiring adjustment. Based on the required adjusted route segments, the navigation data is updated in real time and processed according to navigation command generation rules to obtain the final navigation command set.

[0064] In summary, this invention discloses a fire prevention and control method for unmanned energy storage power stations based on the Internet of Things (IoT). The method includes acquiring a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environment information set. The real-time environmental data streams include changes in ambient temperature over time, types of combustibles, thermal radiation intensity, and oxygen concentration distribution during the fire. Based on the initial fire environment information set, and in conjunction with the changes in ambient temperature and the types of combustibles, the data is updated to obtain spatial distribution information of obstacles. Based on the spatial distribution information of obstacles, and in conjunction with the thermal radiation intensity and oxygen concentration distribution, the fire impact is predicted to obtain the fire impact area. Based on the fire... The impact area is determined by extracting key nodes from the environmental map database, performing connectivity detection on these key nodes, and identifying the passable area. Obstacles within the passable area are dynamically updated to obtain the latest obstacle information. Path feasibility is assessed based on obstacle thermal deformation data and visibility from the latest obstacle information to obtain an initial set of passable paths. The current peak thermal radiation and airflow deviation are acquired, and the initial set of passable paths is adjusted in real time to determine the optimal path option for the current environment. The location information of fire-fighting equipment is acquired, and combined with the location information of the fire-fighting equipment and the optimal path option, a final navigation command set is generated. This invention achieves precise and intelligent fire prevention and control in energy storage power stations through a technological reconstruction from real-time environmental perception and multiple dynamic decision-making to execution. It addresses the problems of accurately identifying the fire source location, predicting the spread trend, and generating safe path planning in fire prevention and control of unmanned energy storage power stations.

[0065] Reference Figure 4 The second embodiment of the present invention provides a fire prevention and control system for unmanned energy storage power stations based on the Internet of Things, comprising: The data acquisition module is used to acquire a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environmental information set; wherein, the real-time environmental data streams include changes in ambient temperature over time, types of combustibles, heat radiation intensity, and oxygen concentration distribution during the fire. The information update module is used to update the data based on the initial fire environment information set, combined with the changes in ambient temperature and the type of combustible material, to obtain the spatial distribution information of obstacles; The fire prediction module is used to predict the fire impact based on the spatial distribution information of the obstacles, combined with the thermal radiation intensity and the oxygen concentration distribution, to obtain the range of the fire impact area. The pathway analysis module is used to extract key nodes from the environmental map database based on the range of the fire-affected area, perform connectivity detection on the key nodes, and determine the range of passable areas. The path evaluation module is used to dynamically update the obstacles in the passable area to obtain the latest obstacle information, and to evaluate the path feasibility based on the obstacle data and visibility in the latest obstacle information to obtain an initial set of passable paths. The path optimization module is used to obtain the current thermal radiation sensing peak and air flow direction shift, and to adjust the initial set of passable paths in real time to determine the optimal path option under the current environment. The instruction generation module is used to obtain the location information of the fire-fighting equipment and generate the final navigation instruction set by combining the location information of the fire-fighting equipment and the optimal path option.

[0066] It should be noted that the Internet of Things-based fire prevention and control system for unmanned energy storage power stations provided in this embodiment of the invention is used to execute all the process steps of the Internet of Things-based fire prevention and control method for unmanned energy storage power stations described in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0067] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, it implements the steps described in the various embodiments of the IoT-based unmanned energy storage power station fire prevention method, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments, such as the data acquisition module.

[0068] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0069] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0070] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0071] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0072] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0073] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0074] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A fire prevention and control method for unmanned energy storage power stations based on the Internet of Things, characterized in that, include: The system acquires a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environmental information set. The real-time environmental data streams include changes in ambient temperature over time, types of combustibles, heat radiation intensity, and oxygen concentration distribution during the fire. Based on the initial fire environment information set, and combined with the changes in ambient temperature and the types of combustibles, the data is updated to obtain the spatial distribution information of obstacles; Based on the spatial distribution information of the obstacles, and combined with the thermal radiation intensity and oxygen concentration distribution, the fire impact is predicted to obtain the range of the fire impact area. Based on the range of the fire-affected area, key nodes are extracted from the environmental map database, and connectivity detection is performed on the key nodes to determine the range of passable areas. The obstacles in the passable area are dynamically updated to obtain the latest obstacle information. The path feasibility is evaluated based on the obstacle thermal deformation data and visibility in the latest obstacle information to obtain an initial set of passable paths. The system acquires the current peak value of thermal radiation and the shift in airflow direction, and adjusts the initial set of passable paths in real time to determine the optimal path option under the current environment. The location information of the fire-fighting equipment is obtained, and the final navigation instruction set is generated by combining the location information of the fire-fighting equipment with the optimal path option.

2. The fire prevention and control method for unmanned energy storage power stations based on the Internet of Things according to claim 1, characterized in that, The step of updating the data based on the initial fire environment information set, combined with the changes in ambient temperature and the types of combustibles, to obtain the spatial distribution information of obstacles includes: Based on the initial fire environment information set, the obstacle distribution is mapped into a three-dimensional spatial model to obtain the initial obstacle spatial distribution information; By combining the changes in ambient temperature and the type of combustible material, the initial spatial distribution information of obstacles is updated to obtain the spatial distribution information of obstacles.

3. The fire prevention and control method for unmanned energy storage power stations based on the Internet of Things according to claim 1, characterized in that, The fire impact prediction is performed based on the spatial distribution information of the obstacles, combined with the thermal radiation intensity and the oxygen concentration distribution, to obtain the fire impact area, including: Based on the spatial distribution information of the obstacles, the thermal radiation intensity and the oxygen concentration distribution are monitored and classified to obtain a preliminary fire distribution dataset. Based on the preliminary fire distribution dataset, spatial mapping prediction processing is performed on the fire source offset path and fire spread path to determine the preliminary fire impact range. Based on the preliminary fire impact range, the area within the preliminary fire impact range is compared for hazard level and the path is calibrated to obtain the final fire impact range.

4. The fire prevention and control method for unmanned energy storage power stations based on the Internet of Things according to claim 1, characterized in that, The step of extracting key nodes from the environmental map database based on the range of the fire-affected area includes: Based on the extent of the fire's impact, obtain the corresponding complex spatial layout in the environmental map database; The location information of the main entrances and exits and fire intersections in the complex spatial layout is extracted to obtain the key nodes.

5. The fire prevention and control method for unmanned energy storage power stations based on the Internet of Things according to claim 4, characterized in that, The process of performing connectivity detection on the key nodes to determine the passable area includes: Obtain local temperature data and smoke concentration information corresponding to the key nodes; The local temperature data is initially compared with a preset temperature threshold. If the local temperature data does not exceed the preset temperature threshold, an impassable mark is made to obtain the first impassable area. Based on the first impassable area, the smoke concentration information is compared with a preset concentration threshold a second time. If the smoke concentration information is detected to exceed the preset concentration threshold, an impassable mark is made to obtain a second impassable area. The first impassable area and the second impassable area are combined to divide the area into regions, resulting in the final range of the passable area.

6. The fire prevention and control method for unmanned energy storage power stations based on the Internet of Things according to claim 1, characterized in that, The obstacle information within the passable area is dynamically updated to obtain the latest obstacle information. Based on the obstacle thermal deformation data and visibility from the latest obstacle information, a path feasibility assessment is performed to obtain an initial set of passable paths, including: Obtain updated information on obstacles within the passable area, record the changes in the position and shape of the obstacles, and obtain the latest obstacle information; Based on the latest obstacle information, the obstacle thermal deformation data of the latest obstacle information is compared with a preset thermal deformation threshold. If the obstacle thermal deformation data exceeds the preset thermal deformation threshold, an impassable mark is made to obtain a preliminary impassable path. Based on the preliminary impassable path and the latest obstacle information, the visibility of the latest obstacle information is compared with a preset visibility threshold. If the visibility is lower than the preset visibility threshold, a high-risk marker is created to obtain a set of high-risk areas. By combining the initial set of impassable paths and the set of high-risk areas, the range of passable areas is adjusted to obtain the initial set of passable paths.

7. The fire prevention and control method for unmanned energy storage power stations based on the Internet of Things according to claim 1, characterized in that, The process of acquiring the current peak value of thermal radiation sensing and the shift in airflow direction, and adjusting the initial set of passable paths in real time to determine the optimal path option under the current environment includes: A path scan is performed on the initial set of passable paths to obtain the current thermal radiation sensing peak and the airflow direction shift; Based on the initial set of passable paths, the peak value of thermal radiation sensing is compared with a preset peak threshold. If the peak value of thermal radiation sensing exceeds the preset peak threshold, a restricted mark is made to obtain restricted path distribution data. Based on the initial set of passable paths, the airflow direction offset is compared with a preset offset threshold. If the airflow direction offset exceeds the preset offset threshold, an obstruction mark is made to obtain obstruction path distribution data. Based on the initial set of passable paths, local path correction is performed by combining the restricted path distribution data and the blocked path distribution data to obtain the final set of passable paths under the current environment. The final set of passable paths is filtered based on the optimal path selection criteria to obtain the optimal path option.

8. A fire prevention and control system for an unmanned energy storage power station based on the Internet of Things, characterized in that, include: The data acquisition module is used to acquire a pre-established environmental map database, real-time environmental data streams collected by sensors, and an initial fire environmental information set; wherein, the real-time environmental data streams include changes in ambient temperature over time, types of combustibles, heat radiation intensity, and oxygen concentration distribution during the fire. The information update module is used to update the data based on the initial fire environment information set, combined with the changes in ambient temperature and the type of combustible material, to obtain the spatial distribution information of obstacles; The fire prediction module is used to predict the fire impact based on the spatial distribution information of the obstacles, combined with the thermal radiation intensity and the oxygen concentration distribution, to obtain the range of the fire impact area. The pathway analysis module is used to extract key nodes from the environmental map database based on the range of the fire-affected area, perform connectivity detection on the key nodes, and determine the range of passable areas. The path evaluation module is used to dynamically update the obstacles in the passable area to obtain the latest obstacle information, and to evaluate the path feasibility based on the obstacle data and visibility in the latest obstacle information to obtain an initial set of passable paths. The path optimization module is used to obtain the current thermal radiation sensing peak and air flow direction shift, and to adjust the initial set of passable paths in real time to determine the optimal path option under the current environment. The instruction generation module is used to obtain the location information of the fire-fighting equipment and generate the final navigation instruction set by combining the location information of the fire-fighting equipment and the optimal path option.

9. An electronic device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the Internet of Things-based fire prevention and control method for unmanned energy storage power stations as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the fire prevention and control method for an unmanned energy storage power station based on the Internet of Things as described in any one of claims 1 to 7.

Images