Fire monitoring and early warning method and system for energy storage power station

By deploying Wi-Fi access points and comprehensive information flow analysis, the problem of slow response of traditional fire monitoring systems is solved, real-time fire monitoring and emergency response in energy storage power stations is achieved, and the efficiency and accuracy of emergency responses are improved.

CN118918673APending Publication Date: 2024-11-08STATE GRID JIANGSU ELECTRIC POWER CO LTD XUZHOU JIAWANG DISTRICT POWER SUPPLY BRANCH +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411158466.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Traditional fire monitoring systems have slow responses and are difficult to provide real-time fire information. In addition, infrared thermal sensing equipment is costly and difficult to maintain, which affects the rapidity and accuracy of emergency response.

Method used

Deploy Wi-Fi access points to cover energy storage power stations, collect Wi-Fi transmission wave information flow, establish a convolutional neural network behavior recognition model, combine meteorological and power grid information flow for comprehensive research and analysis, generate alarm trigger mechanisms, and realize real-time monitoring and Emergency communication.

Benefits of technology

It has achieved low-cost and real-time monitoring of the location and fire development of personnel in the energy storage power station, quickly identified behavior patterns, improved emergency response efficiency, and improved timeliness and accuracy of monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918673A_ABST
    Figure CN118918673A_ABST
Patent Text Reader

Abstract

The invention is suitable for the technical field of safety monitoring and fire protection, and provides a fire monitoring and early warning method and system for an energy storage power station, and the system comprises a real-time monitoring and visualization module, a holding mode recognition module, a self-adaptive Wi-Fi node configuration module, and a multi-source information comprehensive decision support and intelligent alarm linkage module. A traditional fire monitoring system may respond slowly and cannot provide real-time fire information. By deploying the Wi-Fi access points in a large area and using the Wi-Fi transmission wave information flow, the energy storage power station is monitored at low cost, the positions of personnel in the energy storage power station and fire behavior development are monitored in real time and dynamically updated, and the timeliness and accuracy of monitoring are improved. In emergency situations such as a fire disaster, the method can quickly identify and distinguish the holding mode of the personnel, and improves the response efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of safety monitoring and fire protection, and in particular relates to a fire monitoring and early warning method and system for an energy storage power station. Background Art

[0002] More and more devices and sensors are connected to the Internet of Things (IoT) to collect and transmit information in real time. These information flows are used for monitoring and analysis to improve the intelligence level of security monitoring systems. Intelligent monitoring system: Using artificial intelligence (AI) and machine learning technology, security monitoring systems can automatically identify abnormal behavior, intrusions, fires and other events, and respond quickly. Collect and analyze a large number of monitoring information flows, and use information flow mining and analysis technology to predict potential risks and optimize security management. Integrate multiple sensors (smoke, temperature, gas, etc.) and combine AI algorithms to improve the accuracy and response speed of fire detection. Networked smoke detectors, fire extinguishers and other equipment can achieve remote monitoring and management, and timely discover and coordinate the rectification of fire hazards.

[0003] Traditional fire monitoring systems have many limitations in practical applications. For example, due to the limitations of technical means, traditional systems often respond slowly and find it difficult to provide accurate fire information in a timely manner, affecting the speed and effectiveness of emergency response. Deployed cameras and other equipment are easily disturbed by smoke, resulting in blurred vision and inability to clearly capture the situation at the fire scene, thus affecting the accuracy of judgment. In addition, although temperature detection equipment can sense the occurrence of fire, its response speed is slow and there is a large delay, so it cannot provide fire information in the first place, resulting in the failure to coordinate and regulate the fire in the early stage. Although infrared thermal sensing technology can overcome the influence of smoke obstruction and provide a relatively accurate temperature information flow, its high cost makes large-scale deployment impractical, especially when funds and resources are limited. In addition, infrared thermal sensing equipment also requires regular maintenance and calibration to ensure its normal operation, which further increases operating costs and maintenance difficulties. Summary of the invention

[0004] The purpose of the present invention is to provide a fire monitoring and early warning method for an energy storage power station, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is implemented as follows: a fire monitoring and early warning method for an energy storage power station, the method comprising: Deploy Wi-Fi access points to cover the entire energy storage power station, collect Wi-Fi transmission wave strength and change information flow, coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout map of the energy storage power station on the interface, and display real-time personnel location and fire development information; Collect sample information flows of Wi-Fi transmission waves under normal conditions, define human behavior patterns of normal work, escape, and distress, establish a convolutional neural network behavior recognition model and identify these behavior patterns, analyze the monitored Wi-Fi transmission wave information flow in real time, and identify the current behavior patterns of personnel; Analyze the environmental characteristics and monitoring requirements of energy storage power stations, establish an excellent model for Wi-Fi coverage, adjust the location of Wi-Fi access points based on the results, test the coverage and stability of Wi-Fi transmission waves, regularly review the coverage effect, and make fine adjustments based on real-time information flow; Design and implement an information flow integration framework to collect meteorological information flow and external information flow of power grid status, combine external information flow with Wi-Fi monitoring information flow to perform comprehensive analysis, provide early warning and action guide, generate alarm trigger mechanism, automatically activate when dangerous mode is monitored, and realize emergency communication connection with rescue teams.

[0006] As a further solution of the present invention, the Wi-Fi access points are deployed to cover the entire energy storage power station, collect Wi-Fi transmission wave intensity and change information flow, and coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout diagram of the energy storage power station on the interface, and display the real-time personnel location and fire development information, specifically including: Deploy Wi-Fi access points in the energy storage power station, continuously capture the transmission wave strength information flow of the Wi-Fi access points, collect the information flow from the access points and forward it to the central coordination and regularization system, and filter out noise and irrelevant information from the collected information flow; Obtain the coordinated and organized information flow from the central coordination and organization system, convert the information flow into coordinate points, build a dynamic location map on the monitoring interface based on the coordinate points, and update the location map to reflect the real-time personnel and fire dynamics. The interface supports zooming in, zooming out and scrolling to view different areas.

[0007] As a further solution of the present invention, the sample information flow of Wi-Fi transmission waves under normal conditions is collected, human behavior patterns of normal work, escape, and distress are defined, a convolutional neural network behavior recognition model is established and these behavior patterns are recognized, and the monitored Wi-Fi transmission wave information flow is analyzed in real time to recognize the current person's behavior pattern, specifically including: Set the sampling frequency and duration parameters for information flow aggregation, deploy the sensor network to aggregate Wi-Fi transmission wave information flow in real time, clean the aggregated original transmission wave information flow, and standardize and coordinate the information flow; Use the labeled information stream set to train the model, identify normal working, escape, and distress behavior patterns, build a Wi-Fi behavior recognition model, verify the model accuracy, analyze the model performance, and adjust the model parameters to optimize the recognition effect; Receive new Wi-Fi transmission wave information streams in real time, apply processes to coordinate and normalize the instant information streams, use Wi-Fi behavior recognition models to analyze the coordinated and normalized information streams, and convert the recognized behavior patterns into output transmission waves.

[0008] As a further solution of the present invention, the environmental characteristics and monitoring requirements of the energy storage power station are analyzed, an excellent model of Wi-Fi coverage is established, the location of the Wi-Fi access point is adjusted according to the results, the coverage and stability of the Wi-Fi transmission wave are tested, the coverage effect is reviewed regularly, and fine-tuning is performed according to the real-time information flow, specifically including: Collect information flow about the layout and environmental characteristics of the energy storage power station, determine the coverage and transmission wave strength of the existing Wi-Fi network, analyze the current load and usage of the Wi-Fi network, and determine the stability of the Wi-Fi transmission wave; An excellent model of Wi-Fi coverage is established based on the particle swarm, and the environmental information flow and demand analysis results are input to generate an excellent Wi-Fi access point layout plan; Deploy Wi-Fi access points according to the layout plan proposed by the excellent model of Wi-Fi coverage, monitor the Wi-Fi transmission wave coverage and performance indicators under the new layout, collect user feedback and network usage information flow after implementation, and continuously monitor the information flow.

[0009] As a further solution of the present invention, the design and implementation of an information flow integration framework collects meteorological information flow and external information flow of power grid status, combines the external information flow with the Wi-Fi monitoring information flow to perform comprehensive analysis, provides early warning and action guidelines, generates an alarm trigger mechanism, and automatically activates when a dangerous mode is monitored to achieve emergency communication connection with the rescue team, specifically including: Integrate weather information flow and external information sources of power grid status, collect information from various information flow sources in real time, integrate Wi-Fi monitoring information flow with external information flow, and implement information flow trend analysis; The alarm conditions are triggered according to the location of personnel and the fire status. When the monitoring information flow meets the preset conditions, the alarm is automatically triggered and conveyed to the personnel. After the alarm is triggered, emergency measures are automatically initiated and the rescue team is notified.

[0010] Another object of the present invention is to provide a fire monitoring and early warning system for an energy storage power station, the system comprising: The real-time monitoring and visualization module is used to deploy Wi-Fi access points to cover the entire energy storage power station, collect Wi-Fi transmission wave strength and change information flow, and coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout diagram of the energy storage power station on the interface, and display the real-time personnel location and fire development information; The behavior pattern recognition module is used to collect sample information flows of Wi-Fi transmission waves under normal conditions, define human behavior patterns of normal work, escape, and distress, establish a convolutional neural network behavior recognition model and identify these behavior patterns, analyze the monitored Wi-Fi transmission wave information flow in real time, and identify the current person's behavior pattern; Adaptive Wi-Fi node configuration module, used to analyze the environmental characteristics and monitoring requirements of energy storage power stations, establish an excellent model of Wi-Fi coverage, adjust the location of Wi-Fi access points based on the results, test the coverage and stability of Wi-Fi transmission waves, regularly review the coverage effect, and make fine adjustments based on real-time information flow; The multi-source information comprehensive decision support and intelligent alarm linkage module is used to design and implement an information flow integration framework, collect meteorological information flow and external information flow of power grid status, combine external information flow with Wi-Fi monitoring information flow to perform comprehensive analysis, provide early warning and action guidelines, generate alarm trigger mechanism, and automatically activate when dangerous mode is detected to achieve emergency communication connection with rescue teams.

[0011] As a further solution of the present invention, the real-time monitoring and visualization module specifically includes: The information flow capture unit is used to deploy Wi-Fi access points in the energy storage power station, continuously capture the transmission wave strength information flow of the Wi-Fi access points, collect the information flow from the access points and forward it to the central coordination and regularization system, and filter out noise and irrelevant information from the collected information flow; The visualization unit is used to obtain the coordinated and organized information flow from the central coordination and organization system, convert the information flow into coordinate points, build a dynamic location map on the monitoring interface based on the coordinate points, and update the location map to reflect the real-time personnel and fire dynamics. The interface supports zooming in, zooming out and scrolling to view different areas.

[0012] As a further solution of the present invention, the behavior pattern recognition module specifically includes: Information flow aggregation and unit, used to set the information flow aggregation sampling frequency and duration parameters, deploy sensor networks to aggregate Wi-Fi transmission wave information flow in real time, clean the collected original transmission wave information flow, and standardize and coordinate the information flow; The behavior pattern modeling unit is used to train the model using the labeled information flow set, identify the normal working, escape, and distress behavior patterns, establish the Wi-Fi behavior recognition model, verify the model accuracy, judge the model performance, and adjust the model parameters to optimize the recognition effect; The Wi-Fi behavior recognition model recognition and output unit is used to receive new Wi-Fi transmission wave information flow in real time, apply the process to coordinate and normalize the real-time information flow, use the Wi-Fi behavior recognition model to analyze the coordinated and normalized information flow, and convert the recognized behavior pattern into an output transmission wave.

[0013] As a further solution of the present invention, the adaptive Wi-Fi node configuration module specifically includes: The environmental analysis and demand assessment unit is used to collect information about the layout and environmental characteristics of the energy storage power station, assess the coverage and transmission wave strength of the existing Wi-Fi network, analyze the current load and usage of the Wi-Fi network, and determine the stability of the Wi-Fi transmission wave; The excellent model unit of Wi-Fi coverage is used to establish an excellent model of Wi-Fi coverage based on the particle swarm, input the environmental information flow and demand analysis results, and generate an excellent Wi-Fi access point layout plan; The implementation and adjustment unit is used to deploy Wi-Fi access points according to the layout plan proposed by the excellent model of Wi-Fi coverage, monitor the Wi-Fi transmission wave coverage and performance indicators under the new layout, collect user feedback and network usage information flow after implementation, and continuously monitor the information flow.

[0014] As a further solution of the present invention, the multi-source information comprehensive decision support and intelligent alarm linkage module specifically includes: Multi-source information integration and analysis unit, used to integrate meteorological information flow and external information sources of power grid status, collect information from various information flow sources in real time, integrate Wi-Fi monitoring information flow with external information flow, and implement information flow trend analysis; The intelligent alarm and linkage mechanism unit is used to trigger alarm conditions according to the location of personnel and the fire status. When the monitoring information flow meets the preset conditions, the alarm is automatically triggered and communicated to the personnel. After the alarm is triggered, emergency measures are automatically initiated and the rescue team is notified.

[0015] The beneficial effects of the present invention are as follows: Traditional fire monitoring systems may be slow to respond and fail to provide real-time fire information. By deploying Wi-Fi access points over a large area and using Wi-Fi transmission wave information flow, low-cost monitoring of energy storage power stations is achieved, and real-time monitoring and dynamic updates of personnel locations and fire development in energy storage power stations are achieved, which improves the timeliness and accuracy of monitoring. In emergency situations such as fires, the behavior patterns of personnel can be quickly identified and distinguished, improving the efficiency of response. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a fire monitoring and early warning method for an energy storage power station provided by an embodiment of the present invention; Figure 2 A flow chart of generating and updating a dynamic layout diagram of an energy storage power station on an interface provided by an embodiment of the present invention; Figure 3 A flow chart for identifying the behavior pattern of a current person provided by an embodiment of the present invention; Figure 4A flowchart of establishing an excellent model of Wi-Fi coverage provided by an embodiment of the present invention; Figure 5 A flow chart of collecting meteorological information flow and power grid status external information flow provided by an embodiment of the present invention; Figure 6 A structural block diagram of a fire monitoring and early warning system for an energy storage power station provided by an embodiment of the present invention; Figure 7 A structural block diagram of a real-time monitoring and visualization module provided in an embodiment of the present invention; Figure 8 A structural block diagram of a behavior pattern recognition module provided by an embodiment of the present invention; Fig. 9 A structural block diagram of an adaptive Wi-Fi node configuration module provided in an embodiment of the present invention; Fig.10 A structural block diagram of the multi-source information comprehensive decision support and intelligent alarm linkage module provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0019] Figure 1 A flow chart of a fire monitoring and early warning method for an energy storage power station provided by an embodiment of the present invention, such as Figure 1 As shown, a fire monitoring and early warning method for an energy storage power station comprises: S100 deploys Wi-Fi access points to cover the entire energy storage power station, collects Wi-Fi transmission wave strength and change information flow, and coordinates and regularizes the information flow, maps it to the real-time monitoring interface, generates and updates the dynamic layout map of the energy storage power station on the interface, and displays real-time personnel location and fire development information; S200, collects sample information flows of Wi-Fi transmission waves under normal conditions, defines human behavior patterns of normal work, escape, and distress, establishes a convolutional neural network behavior recognition model and recognizes these behavior patterns, analyzes the monitored Wi-Fi transmission wave information flows in real time, and recognizes the current person's behavior pattern; This step sets the sampling frequency and duration parameters. According to the specific needs of the energy storage power station, set the frequency (e.g., sampling once per second) and duration (e.g., each sampling lasts 1 minute) of information flow sampling. Deploy the sensor network and arrange the Wi-Fi sensor network reasonably in the energy storage power station to ensure that the transmission wave covers every corner and collects the Wi-Fi transmission wave information flow in real time. Clean the collected original Wi-Fi transmission wave information flow to remove noise and invalid information flow. Standardize and coordinate the cleaned information flow so that information flows from different sources can be uniformly coordinated and analyzed.

[0020] This step uses a set of labeled information flows to collect and use a set of labeled human behavior information flows, which should include behavior patterns such as normal work, escape, and distress. Model selection and training, use deep learning technologies such as convolutional neural networks (CNNs) to train the behavior recognition model. Optimize the recognition accuracy of the model through multiple iterations and adjustment of model parameters. Use the validation set information flow to test the trained model to determine its recognition accuracy under different conditions. Determine the overall performance of the model through indicators such as confusion matrix, precision, recall, and F1 score. According to the results of the judgment, adjust the model parameters to further optimize the recognition effect of the model.

[0021] This step receives the Wi-Fi transmission wave information flow from the sensor network in real time. And the real-time information flow is collected and the unit process is applied to clean and standardize the real-time information flow. Use the trained Wi-Fi behavior recognition model to analyze the real-time information flow after coordination and identify the behavior pattern of the current personnel. Convert the identified behavior pattern into an output transmission wave for real-time monitoring and visualization and multi-source information comprehensive decision support and intelligent alarm linkage. The output transmission wave is transmitted to the monitoring system to realize real-time monitoring and early warning of the behavior of the energy storage power station personnel.

[0022] S300, analyzes the environmental characteristics and monitoring requirements of energy storage power stations, establishes an excellent model for Wi-Fi coverage, adjusts the location of Wi-Fi access points based on the results, tests the coverage and stability of Wi-Fi transmission waves, regularly reviews coverage results, and makes fine adjustments based on real-time information flows; This step collects the information flow of the energy storage power station layout, and obtains information such as the building structure, equipment layout, and personnel activity areas of the energy storage power station. Collect information flows that may interfere with Wi-Fi transmission waves due to environmental factors such as temperature, humidity, and physical obstacles. Analyze the coverage and transmission wave strength of existing Wi-Fi networks: Use test equipment and software tools to analyze the coverage of existing Wi-Fi networks and the transmission wave strength of each area. Analyze the load and usage of Wi-Fi networks, monitor and analyze the load of the current Wi-Fi network, determine the average and peak usage, and identify potential bottlenecks and congestion points. Through long-term monitoring, analyze the stability and reliability of Wi-Fi transmission waves and identify areas with large fluctuations.

[0023] This step uses the particle swarm optimization (PSO) algorithm to establish an excellent model of Wi-Fi coverage based on the environmental information flow and demand analysis results. The PSO algorithm simulates the flight of a group of particles in a multi-dimensional space, and finds an excellent solution through mutual cooperation and competition. The information flow provided by the environmental analysis and demand analysis unit 310 is input into the particle swarm optimization model to generate multiple possible Wi-Fi access point layout solutions. Through iterative calculation and optimization, the Wi-Fi access point layout solution with the best coverage and the most uniform transmission wave intensity is selected.

[0024] In this step, Wi-Fi access points are deployed. According to the optimal layout plan, Wi-Fi access points are deployed in the energy storage power station to ensure that the location and direction of each access point meet the design requirements. Use tools such as network speed test and transmission wave strength measurement to monitor the coverage, transmission wave strength, throughput and stability of Wi-Fi under the new layout. Obtain user feedback and actual network usage information flow after implementation through questionnaires, user interviews and automatic log collection. Regularly monitor the performance of the Wi-Fi network, collect new usage information flows and environmental change information, and ensure that the network is always in the best working state. Analyze the collected information flows to identify coverage blind spots, weak transmission wave areas and performance bottlenecks. Based on the analysis results, make fine adjustments, including adjusting the access point location, power settings, channel selection, etc., to adapt to the real-time changing environment and needs and maintain efficient operation of the network.

[0025] S400 designs and implements an information flow integration framework to collect meteorological information flows and external information flows of power grid status, combines external information flows with Wi-Fi monitoring information flows to perform comprehensive analysis, provides early warnings and action guidelines, generates alarm trigger mechanisms, and automatically activates when dangerous modes are detected to achieve emergency communication connections with rescue teams.

[0026] This step obtains real-time weather information, including temperature, humidity, wind speed, precipitation, etc., by accessing the meteorological information flow source. These information flows can help analyze the fire risk and the possibility of fire spread. Connect to the power grid status monitoring system to obtain power grid operation parameters such as voltage, current, load, etc. These information flows can help determine the stability of the power system and potential fire causes. Use API interfaces or information flow technology to collect information flows from the above external information flow sources and internal Wi-Fi monitoring systems in real time to ensure the real-time and accuracy of information flows. Integrate the Wi-Fi monitoring information flow with the external information flow to form a comprehensive information flow set, which provides a basis for further analysis. Use information flow mining and machine learning technology to analyze the comprehensive information flow set and identify potential trends and abnormal situations. For example, by analyzing the changing trends of personnel location information flow and meteorological information flow, the possibility and scope of fire can be predicted.

[0027] This step analyzes the monitoring information flow in real time according to the preset alarm conditions (such as abnormally high temperatures in crowded areas or people's behavior patterns showing escape or distress). When the monitoring information flow meets the preset conditions, the alarm is triggered immediately. The alarm message is conveyed to the staff and managers of the energy storage power station through various channels (such as text messages, emails, mobile application notifications, etc.) to ensure that they can be informed of the emergency in a timely manner. At the same time as the alarm is triggered, the preset emergency measures are automatically started. For example, the fire protection system is turned on, the power is turned off, etc., to reduce the harm of the fire. Through the emergency communication system, emergency alarms are automatically sent to local fire brigades and other rescue teams, providing real-time fire information and personnel locations to help them quickly carry out rescue work. Control the relevant equipment in the energy storage power station (such as ventilation systems, entrance and exit controls, etc.), and automatically make corresponding adjustments according to the development of the fire to ensure the safety of personnel and effective control of the fire. Record the triggering situation, response measures and overall regularization results of each alarm, review and analyze the alarm mechanism, and identify potential problems and improvement points. Based on the feedback information flow and actual situation, continuously optimize the alarm triggering conditions and linkage mechanism to improve the overall response speed and accuracy of the system.

[0028] Figure 2 A flowchart of generating and updating a dynamic layout diagram of an energy storage power station on an interface provided by an embodiment of the present invention, such as Figure 2 As shown, the Wi-Fi access points are deployed to cover the entire energy storage power station, collect Wi-Fi transmission wave strength and change information flow, and coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout diagram of the energy storage power station on the interface, and display the real-time personnel location and fire development information, including: S110, deploys Wi-Fi access points in the energy storage power station, continuously captures the transmission wave strength information flow of the Wi-Fi access points, collects the information flow from the access points and forwards it to the central coordination and regularization system, and performs the collected information flow to filter out noise and irrelevant information; S120 obtains the coordinated and organized information flow from the central coordination and organization system, converts the information flow into coordinate points, builds a dynamic location map on the monitoring interface based on the coordinate points, and updates the location map to reflect the real-time personnel and fire dynamics. The interface supports zooming in, zooming out and scrolling to view different areas.

[0029] Figure 3 A flowchart for identifying the behavior pattern of a current person provided by an embodiment of the present invention, such as Figure 3 As shown, the method collects sample information flows of Wi-Fi transmission waves under normal conditions, defines human behavior patterns of normal work, escape, and distress, establishes a convolutional neural network behavior recognition model and recognizes these behavior patterns, analyzes the monitored Wi-Fi transmission wave information flows in real time, and recognizes the current person's behavior patterns, specifically including: S210, setting the information flow collection sampling frequency and duration parameters, deploying the sensor network to collect the Wi-Fi transmission wave information flow in real time, cleaning the collected original transmission wave information flow, and standardizing and coordinating the information flow; S220, training a model using the labeled information flow set to identify normal working, escape, and distressed behavior patterns, establishing a Wi-Fi behavior recognition model, verifying the accuracy of the model, evaluating the model performance, and adjusting model parameters to optimize the recognition effect; S230, receiving new Wi-Fi transmission wave information flow in real time, applying a process to coordinate and normalize the real-time information flow, using a Wi-Fi behavior recognition model to analyze the coordinated and normalized information flow, and converting the recognized behavior pattern into an output transmission wave.

[0030] Figure 4 A flowchart of establishing an excellent model of Wi-Fi coverage provided by an embodiment of the present invention, such as Figure 4 As shown, the environmental characteristics and monitoring requirements of the energy storage power station are analyzed, an excellent model of Wi-Fi coverage is established, the location of Wi-Fi access points is adjusted according to the results, the coverage and stability of Wi-Fi transmission waves are tested, the coverage effect is reviewed regularly, and fine-tuning is performed according to real-time information flow, including: S310, collecting layout and environmental feature information flow of the energy storage power station, determining the coverage and transmission wave strength of the existing Wi-Fi network, analyzing the current load and usage of the Wi-Fi network, and determining the stability of the Wi-Fi transmission wave; S320, establishing an excellent model of Wi-Fi coverage according to the particle swarm, inputting environmental information flow and demand analysis results, and generating an excellent Wi-Fi access point layout plan; S330 deploys Wi-Fi access points according to the layout plan proposed by the excellent model of Wi-Fi coverage, monitors the Wi-Fi transmission wave coverage and performance indicators under the new layout, collects user feedback and network usage information flow after implementation, and continuously monitors the information flow.

[0031] Figure 5 The flow chart of collecting meteorological information flow and power grid status external information flow provided by the embodiment of the present invention is as follows: Figure 5 As shown, the design and implementation of an information flow integration framework collects meteorological information flow and external information flow of power grid status, combines the external information flow with the Wi-Fi monitoring information flow to perform comprehensive analysis, provides early warning and action guidelines, generates an alarm trigger mechanism, and automatically activates when a dangerous mode is detected to achieve emergency communication connection with the rescue team, including: S410 integrates meteorological information flow and external information sources of power grid status, collects information from various information flow sources in real time, integrates Wi-Fi monitoring information flow with external information flow, and implements information flow trend analysis; S420, triggers alarm conditions based on personnel location and fire status. When the monitoring information flow meets the preset conditions, the alarm is automatically triggered and communicated to the personnel. After the alarm is triggered, emergency measures are automatically initiated and the rescue team is notified.

[0032] Figure 6 A structural block diagram of a fire monitoring and early warning system for an energy storage power station provided by an embodiment of the present invention, such as Figure 6 As shown, a fire monitoring and early warning system for an energy storage power station, the system comprises: The real-time monitoring and visualization module 100 is used to deploy Wi-Fi access points to cover the entire energy storage power station, collect Wi-Fi transmission wave strength and change information flow, and coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout diagram of the energy storage power station on the interface, and display the real-time personnel location and fire development information; The behavior pattern recognition module 200 is used to collect sample information flows of Wi-Fi transmission waves under normal conditions, define human behavior patterns of normal work, escape, and distress, establish a convolutional neural network behavior recognition model and recognize these behavior patterns, analyze the monitored Wi-Fi transmission wave information flow in real time, and recognize the current person's behavior pattern; This module sets the sampling frequency and duration parameters. According to the specific needs of the energy storage power station, the frequency (e.g., sampling once per second) and duration (e.g., each sampling lasts for 1 minute) of information flow sampling are set. Deploy the sensor network and arrange the Wi-Fi sensor network reasonably in the energy storage power station to ensure that the transmission wave covers every corner and collects the Wi-Fi transmission wave information flow in real time. Clean the collected original Wi-Fi transmission wave information flow to remove noise and invalid information flow. Standardize and coordinate the cleaned information flow so that information flows from different sources can be uniformly coordinated and analyzed.

[0033] This module uses labeled information stream sets to collect and use labeled human behavior information stream sets, which should include behavior patterns such as normal work, escape, and distress. Model selection and training, using deep learning technologies such as convolutional neural networks (CNNs) to train behavior recognition models. Optimize the recognition accuracy of the model through multiple iterations and adjustment of model parameters. Use the validation set information stream to test the trained model and determine its recognition accuracy under different conditions. Determine the overall performance of the model through indicators such as confusion matrix, precision, recall, and F1 score. According to the results of the judgment, adjust the model parameters to further optimize the recognition effect of the model.

[0034] This module receives the Wi-Fi transmission wave information flow from the sensor network in real time. It also collects and aggregates the real-time information flow, and uses the process of information flow aggregation and unit to clean and standardize the real-time information flow. It uses the trained Wi-Fi behavior recognition model to analyze the real-time information flow after coordination and identify the behavior pattern of the current personnel. The identified behavior pattern is converted into an output transmission wave for real-time monitoring and visualization, and multi-source information comprehensive decision support and intelligent alarm linkage. The output transmission wave is transmitted to the monitoring system to realize real-time monitoring and early warning of the behavior of the energy storage power station personnel.

[0035] Adaptive Wi-Fi node configuration module 300, used to analyze the environmental characteristics and monitoring requirements of the energy storage power station, establish an excellent model of Wi-Fi coverage, adjust the location of Wi-Fi access points based on the results, test the coverage and stability of Wi-Fi transmission waves, regularly review the coverage effect, and make fine adjustments based on real-time information flow; This module collects information flow on the layout of energy storage power stations, and obtains information on the building structure, equipment layout, personnel activity areas, etc. of the energy storage power station. Collect information flow on environmental factors such as temperature, humidity, physical obstacles, etc. that may interfere with Wi-Fi transmission waves. Analyze the coverage and transmission wave strength of existing Wi-Fi networks: Use test equipment and software tools to analyze the coverage of existing Wi-Fi networks and the transmission wave strength of each area. Analyze the load and usage of Wi-Fi networks, monitor and analyze the load of current Wi-Fi networks, determine average and peak usage, and identify potential bottlenecks and congestion points. Through long-term monitoring, analyze the stability and reliability of Wi-Fi transmission waves and identify areas with large fluctuations.

[0036] This module uses the particle swarm optimization (PSO) algorithm to establish an excellent model of Wi-Fi coverage based on the environmental information flow and demand analysis results. The PSO algorithm simulates the flight of a group of particles in a multi-dimensional space and finds an excellent solution through mutual cooperation and competition. The information flow provided by the environmental analysis and demand analysis unit 310 is input into the particle swarm optimization model to generate multiple possible Wi-Fi access point layout solutions. Through iterative calculation and optimization, the Wi-Fi access point layout solution with the best coverage and the most uniform transmission wave intensity is selected.

[0037] This module deploys Wi-Fi access points. According to the optimal layout plan, Wi-Fi access points are deployed in the energy storage power station to ensure that the location and direction of each access point meet the design requirements. Use tools such as network speed test and transmission wave strength measurement to monitor the coverage, transmission wave strength, throughput and stability of Wi-Fi under the new layout. Obtain user feedback and actual network usage information flow after implementation through questionnaires, user interviews and automatic log collection. Regularly monitor the performance of the Wi-Fi network, collect new usage information flows and environmental change information, and ensure that the network is always in the best working state. Analyze the collected information flows to identify coverage blind spots, weak transmission wave areas and performance bottlenecks. Based on the analysis results, make fine adjustments, including adjusting the access point location, power settings, channel selection, etc., to adapt to real-time changing environments and needs and maintain efficient network operation.

[0038] The multi-source information comprehensive decision support and intelligent alarm linkage module 400 is used to design and implement an information flow integration framework, collect meteorological information flow and external information flow of power grid status, combine the external information flow with the Wi-Fi monitoring information flow to perform comprehensive analysis, provide early warning and action guidelines, generate an alarm trigger mechanism, and automatically activate when a dangerous mode is monitored to achieve emergency communication connection with the rescue team.

[0039] This module obtains real-time weather information, including temperature, humidity, wind speed, precipitation, etc., by accessing the meteorological information flow source. These information flows can help analyze the fire risk and the possibility of fire spread. Connect to the power grid status monitoring system to obtain power grid operation parameters such as voltage, current, load, etc. These information flows can help determine the stability of the power system and potential fire causes. Use API interfaces or information flow technology to collect information flows from the above external information flow sources and internal Wi-Fi monitoring systems in real time to ensure the real-time and accuracy of information flows. Integrate the Wi-Fi monitoring information flow with the external information flow to form a comprehensive information flow set, which provides a basis for further analysis. Use information flow mining and machine learning technology to analyze the comprehensive information flow set and identify potential trends and anomalies. For example, by analyzing the changing trends of personnel location information flow and meteorological information flow, the possibility and scope of fire can be predicted.

[0040] This module analyzes the monitoring information flow in real time according to the preset alarm conditions (such as abnormally high temperatures in crowded areas or people's behavior patterns showing escape or distress). When the monitoring information flow meets the preset conditions, the alarm is triggered immediately. The alarm message is conveyed to the staff and managers of the energy storage power station through various channels (such as SMS, email, mobile application notifications, etc.) to ensure that they can be informed of the emergency in time. At the same time as the alarm is triggered, the preset emergency measures are automatically started. For example, the fire protection system is turned on, the power is turned off, etc., to reduce the harm of the fire. Through the emergency communication system, emergency alarms are automatically sent to local fire brigades and other rescue teams, providing real-time fire information and personnel locations to help them quickly carry out rescue work. Control the relevant equipment in the energy storage power station (such as ventilation systems, access control, etc.), and automatically make corresponding adjustments according to the development of the fire to ensure the safety of personnel and effective control of the fire. Record the triggering situation, response measures and overall regularization results of each alarm, review and analyze the alarm mechanism, and identify potential problems and improvement points. Based on the feedback information flow and actual situation, the alarm triggering conditions and linkage mechanisms are continuously optimized to improve the overall response speed and accuracy of the system.

[0041] Figure 7 The structure diagram of the real-time monitoring and visualization module provided by the embodiment of the present invention is as follows: Figure 7 As shown, the real-time monitoring and visualization module specifically includes: The information flow capture unit 110 is used to deploy Wi-Fi access points in the energy storage power station, continuously capture the transmission wave strength information flow of the Wi-Fi access points, collect the information flow from the access points and forward it to the central coordination and regularization system, and filter out noise and irrelevant information from the collected information flow; The visualization unit 120 is used to obtain the coordinated and organized information flow from the central coordination and organization system, convert the information flow into coordinate points, build a dynamic location map on the monitoring interface according to the coordinate points, and update the location map to reflect the real-time personnel and fire dynamics. The interface supports zooming in, zooming out and scrolling to view different areas.

[0042] Figure 8 A structural block diagram of a behavior pattern recognition module provided by an embodiment of the present invention, such as Figure 8 As shown, the behavior pattern recognition module specifically includes: The information flow aggregation unit 210 is used to set the information flow aggregation sampling frequency and duration parameters, deploy the sensor network to aggregate the Wi-Fi transmission wave information flow in real time, clean the aggregated original transmission wave information flow, and standardize and coordinate the information flow; The behavior pattern modeling unit 220 is used to train the model using the labeled information flow set, identify the normal working, escape, and distress behavior patterns, establish a Wi-Fi behavior recognition model, verify the model accuracy, judge the model performance, and adjust the model parameters to optimize the recognition effect; The Wi-Fi behavior recognition model recognition and output unit 230 is used to receive new Wi-Fi transmission wave information flow in real time, apply the process to coordinate and regularize the real-time information flow, use the Wi-Fi behavior recognition model to analyze the coordinated and regularized information flow, and convert the recognized behavior pattern into an output transmission wave.

[0043] Fig. 9 The structure diagram of the adaptive Wi-Fi node configuration module provided in the embodiment of the present invention is as follows: Fig. 9 As shown, the adaptive Wi-Fi node configuration module specifically includes: The environment analysis and demand assessment unit 310 is used to collect the layout and environment characteristic information flow of the energy storage power station, assess the coverage and transmission wave strength of the existing Wi-Fi network, assess the current load and usage of the Wi-Fi network, and determine the stability of the Wi-Fi transmission wave; The excellent model unit 320 of Wi-Fi coverage is used to establish an excellent model of Wi-Fi coverage according to the particle swarm, input the environmental information flow and the demand analysis result, and generate an excellent Wi-Fi access point layout plan; The implementation and adjustment unit 330 is used to deploy Wi-Fi access points according to the layout plan proposed by the excellent model of Wi-Fi coverage, monitor the Wi-Fi transmission wave coverage and performance indicators under the new layout, collect user feedback and network usage information flow after implementation, and continuously monitor the information flow.

[0044] Fig.10 The structural block diagram of the multi-source information comprehensive decision support and intelligent alarm linkage module provided by the embodiment of the present invention is as follows: Fig.10As shown, the multi-source information comprehensive decision support and intelligent alarm linkage module specifically includes: The multi-source information integration and analysis unit 410 is used to integrate the meteorological information flow and the external information source of the power grid status, collect information from each information flow source in real time, integrate the Wi-Fi monitoring information flow with the external information flow, and implement information flow trend analysis; The intelligent alarm and linkage mechanism unit 420 is used to trigger alarm conditions according to the location of personnel and the fire status. When the monitoring information flow meets the preset conditions, the alarm is automatically triggered and communicated to the personnel. After the alarm is triggered, emergency measures are automatically initiated and the rescue team is notified. It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0045] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, information flow library or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAM bus dynamic RAM (RDRAM), etc.

[0046] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0047] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A fire monitoring and early warning method for an energy storage power station, characterized in that: The method comprises: Deploy Wi-Fi access points to cover the entire energy storage power station, collect Wi-Fi transmission wave strength and change information flow, coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout map of the energy storage power station on the interface, and display real-time personnel location and fire development information; Collect sample information flows of Wi-Fi transmission waves under normal conditions, define human behavior patterns of normal work, escape, and distress, establish a convolutional neural network behavior recognition model and identify these behavior patterns, analyze the monitored Wi-Fi transmission wave information flow in real time, and identify the current behavior patterns of personnel; Analyze the environmental characteristics and monitoring requirements of energy storage power stations, establish an excellent model for Wi-Fi coverage, adjust the location of Wi-Fi access points based on the results, test the coverage and stability of Wi-Fi transmission waves, regularly review the coverage effect, and make fine adjustments based on real-time information flow; Design and implement an information flow integration framework to collect meteorological information flow and external information flow of power grid status, combine external information flow with Wi-Fi monitoring information flow to perform comprehensive analysis, provide early warning and action guide, generate alarm trigger mechanism, automatically activate when dangerous mode is monitored, and realize emergency communication connection with rescue teams.

2. The method according to claim 1, characterized in that The Wi-Fi access points are deployed to cover the entire energy storage power station, collect Wi-Fi transmission wave intensity and change information flow, and coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout diagram of the energy storage power station on the interface, and display the real-time personnel location and fire development information, specifically including: Deploy Wi-Fi access points in the energy storage power station, continuously capture the transmission wave strength information flow of the Wi-Fi access points, collect the information flow from the access points and forward it to the central coordination and regularization system, and filter out noise and irrelevant information from the collected information flow; Obtain the coordinated and organized information flow from the central coordination and organization system, convert the information flow into coordinate points, build a dynamic location map on the monitoring interface based on the coordinate points, and update the location map to reflect the real-time personnel and fire dynamics. The interface supports zooming in, zooming out and scrolling to view different areas.

3. The method according to claim 2, characterized in that The method collects sample information flows of Wi-Fi transmission waves under normal conditions, defines human behavior patterns of normal work, escape, and distress, establishes a convolutional neural network behavior recognition model and recognizes these behavior patterns, analyzes the monitored Wi-Fi transmission wave information flows in real time, and recognizes the current behavior patterns of personnel, specifically including: Set the sampling frequency and duration parameters for information flow aggregation, deploy the sensor network to aggregate Wi-Fi transmission wave information flow in real time, clean the aggregated original transmission wave information flow, and standardize and coordinate the information flow; Use the labeled information stream set to train the model, identify normal working, escape, and distress behavior patterns, build a Wi-Fi behavior recognition model, verify the model accuracy, analyze the model performance, and adjust the model parameters to optimize the recognition effect; Receive new Wi-Fi transmission wave information streams in real time, apply processes to coordinate and normalize the instant information streams, use Wi-Fi behavior recognition models to analyze the coordinated and normalized information streams, and convert the recognized behavior patterns into output transmission waves.

4. The method according to claim 3, characterized in that The above mentioned process includes analyzing the environmental characteristics and monitoring requirements of energy storage power stations, establishing an excellent model for Wi-Fi coverage, adjusting the location of Wi-Fi access points based on the results, testing the coverage and stability of Wi-Fi transmission waves, regularly reviewing the coverage effect, and making fine adjustments based on real-time information flows. Specifically, it includes: Collect information flow about the layout and environmental characteristics of the energy storage power station, determine the coverage and transmission wave strength of the existing Wi-Fi network, analyze the current load and usage of the Wi-Fi network, and determine the stability of the Wi-Fi transmission wave; An excellent model of Wi-Fi coverage is established based on the particle swarm, and the environmental information flow and demand analysis results are input to generate an excellent Wi-Fi access point layout plan; Deploy Wi-Fi access points according to the layout plan proposed by the excellent model of Wi-Fi coverage, monitor the Wi-Fi transmission wave coverage and performance indicators under the new layout, collect user feedback and network usage information flow after implementation, and continuously monitor the information flow.

5. The method according to claim 4, characterized in that The design and implementation of an information flow integration framework collects meteorological information flow and external information flow of power grid status, combines external information flow with Wi-Fi monitoring information flow to perform comprehensive analysis, provide early warning and action guide, generate alarm trigger mechanism, automatically activate when dangerous mode is detected, and realize emergency communication connection with rescue teams, including: Integrate weather information flow and external information sources of power grid status, collect information from various information flow sources in real time, integrate Wi-Fi monitoring information flow with external information flow, and implement information flow trend analysis; The alarm conditions are triggered according to the location of personnel and the fire status. When the monitoring information flow meets the preset conditions, the alarm is automatically triggered and conveyed to the personnel. After the alarm is triggered, emergency measures are automatically initiated and the rescue team is notified.

6. A fire monitoring and early warning system for an energy storage power station, characterized in that: The system comprises: The real-time monitoring and visualization module is used to deploy Wi-Fi access points to cover the entire energy storage power station, collect Wi-Fi transmission wave strength and change information flow, and coordinate and regularize the information flow, map it to the real-time monitoring interface, generate and update the dynamic layout diagram of the energy storage power station on the interface, and display the real-time personnel location and fire development information; The behavior pattern recognition module is used to collect sample information flows of Wi-Fi transmission waves under normal conditions, define human behavior patterns of normal work, escape, and distress, establish a convolutional neural network behavior recognition model and identify these behavior patterns, analyze the monitored Wi-Fi transmission wave information flow in real time, and identify the current person's behavior pattern; Adaptive Wi-Fi node configuration module, used to analyze the environmental characteristics and monitoring requirements of energy storage power stations, establish an excellent model of Wi-Fi coverage, adjust the location of Wi-Fi access points based on the results, test the coverage and stability of Wi-Fi transmission waves, regularly review the coverage effect, and make fine adjustments based on real-time information flow; The multi-source information comprehensive decision support and intelligent alarm linkage module is used to design and implement an information flow integration framework, collect meteorological information flow and external information flow of power grid status, combine external information flow with Wi-Fi monitoring information flow to perform comprehensive analysis, provide early warning and action guidelines, generate alarm trigger mechanism, and automatically activate when dangerous mode is detected to achieve emergency communication connection with rescue teams.

7. The system according to claim 6, characterized in that The real-time monitoring and visualization module specifically includes: The information flow capture unit is used to deploy Wi-Fi access points in the energy storage power station, continuously capture the transmission wave strength information flow of the Wi-Fi access points, collect the information flow from the access points and forward it to the central coordination and regularization system, and filter out noise and irrelevant information from the collected information flow; The visualization unit is used to obtain the coordinated and organized information flow from the central coordination and organization system, convert the information flow into coordinate points, build a dynamic location map on the monitoring interface based on the coordinate points, and update the location map to reflect the real-time personnel and fire dynamics. The interface supports zooming in, zooming out and scrolling to view different areas.

8. The system according to claim 7, characterized in that The behavior pattern recognition module specifically includes: Information flow aggregation and unit, used to set the information flow aggregation sampling frequency and duration parameters, deploy sensor networks to aggregate Wi-Fi transmission wave information flow in real time, clean the collected original transmission wave information flow, and standardize and coordinate the information flow; The behavior pattern modeling unit is used to train the model using the labeled information flow set, identify the normal working, escape, and distress behavior patterns, establish the Wi-Fi behavior recognition model, verify the model accuracy, judge the model performance, and adjust the model parameters to optimize the recognition effect; The Wi-Fi behavior recognition model recognition and output unit is used to receive new Wi-Fi transmission wave information flow in real time, apply the process to coordinate and normalize the real-time information flow, use the Wi-Fi behavior recognition model to analyze the coordinated and normalized information flow, and convert the recognized behavior pattern into an output transmission wave.

9. The system according to claim 8, characterized in that The adaptive Wi-Fi node configuration module specifically includes: The environmental analysis and demand assessment unit is used to collect information about the layout and environmental characteristics of the energy storage power station, assess the coverage and transmission wave strength of the existing Wi-Fi network, analyze the current load and usage of the Wi-Fi network, and determine the stability of the Wi-Fi transmission wave; The excellent model unit of Wi-Fi coverage is used to establish an excellent model of Wi-Fi coverage based on the particle swarm, input the environmental information flow and demand analysis results, and generate an excellent Wi-Fi access point layout plan; The implementation and adjustment unit is used to deploy Wi-Fi access points according to the layout plan proposed by the excellent model of Wi-Fi coverage, monitor the Wi-Fi transmission wave coverage and performance indicators under the new layout, collect user feedback and network usage information flow after implementation, and continuously monitor the information flow.

10. The system according to claim 9, characterized in that The multi-source information comprehensive decision support and intelligent alarm linkage module specifically includes: Multi-source information integration and analysis unit, used to integrate meteorological information flow and external information sources of power grid status, collect information from various information flow sources in real time, integrate Wi-Fi monitoring information flow with external information flow, and implement information flow trend analysis; The intelligent alarm and linkage mechanism unit is used to trigger alarm conditions according to the location of personnel and the fire status. When the monitoring information flow meets the preset conditions, the alarm is automatically triggered and communicated to the personnel. After the alarm is triggered, emergency measures are automatically initiated and the rescue team is notified.