Fire-fighting linkage monitoring system for electric bicycle charging station and monitoring method of fire-fighting linkage monitoring system

Abstract

The invention relates to the technical field of electric charging and fire-fighting monitoring, in particular to a fire-fighting linkage monitoring system for an electric bicycle charging station and a monitoring method thereof, and the monitoring system comprises the following functional modules: a platform convergence layer, a control analysis layer and a sensing acquisition layer; the system has the advantages that safety is improved, and the risk of fire disasters in the charging process of the electric bicycle is remarkably reduced through a real-time monitoring and quick response mechanism. Once a fire sign is detected, the system can quickly cut off a power supply and start a fire extinguishing program, so that the damage caused by the fire is reduced. Intelligent management: the integrated AI technology enables the fire extinguishing system to intelligently identify and respond to the fire situation, and the management efficiency is improved. And remote monitoring capability: the fire-fighting state of the charging station is allowed to be remotely monitored, and the safety and management efficiency of the charging station are enhanced. And continuous performance optimization: the system has self-learning and updating capabilities, and can continuously optimize fire identification and response strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of electric charging and fire monitoring, and in particular to a fire linkage monitoring system and a monitoring method thereof for an electric bicycle charging station. Background Art

[0002] In the field of electric bicycle charging stations, the linkage monitoring method of the fire protection system is a key technical development direction, the core of which is to improve the safety and response efficiency of charging stations. With the popularization of electric bicycles, the safety issues of charging stations, especially fire prevention and rapid response mechanisms, have become particularly important.

[0003] However, the monitoring system of the electric bicycle charging station in the prior art has the following defects:

[0004] There is a lack of real-time monitoring and rapid response mechanism, and there is a risk of fire during the charging process of electric bicycles, which has low safety. There is a lack of a rapid response mechanism to quickly detect signs of fire, quickly cut off the power supply and start the fire extinguishing procedure to reduce the damage caused by the fire, and the response speed is slow. There is a lack of intelligent management mechanism for intelligent identification and response to fire situations, and the management efficiency is low. The remote monitoring capability is poor, which is not convenient for remote monitoring of the fire status of the charging station, reducing the safety and management efficiency of the charging station. There is no continuous performance optimization function, which is not convenient for self-learning and updating, and it is impossible to optimize the fire identification and response strategy. Therefore, a fire linkage monitoring system and a monitoring method for electric bicycle charging stations are proposed. Summary of the invention

[0005] In order to overcome the technical defects in the prior art and effectively solve the technical problems in the background technology, the present invention provides the following technical solutions:

[0006] A fire linkage monitoring system for electric bicycle charging stations, the monitoring system includes the following functional modules: platform convergence layer, control analysis layer and perception collection layer;

[0007] The platform convergence layer is the core of the entire system, responsible for the centralized management and distribution of data, including the charging station cloud platform and the fire protection platform; the charging station cloud platform, as a centralized data processing center, is responsible for collecting data from various parts of the charging station, storing, analyzing and processing it, and is responsible for exchanging data with the fire protection platform to achieve information sharing; the fire protection platform is connected to the charging station cloud platform to receive and process fire protection-related data from the charging station, and achieve real-time monitoring of the fire safety status of the charging station;

[0008] The control and analysis layer is responsible for analyzing the collected data and making control decisions based on the analysis results. It includes a charging gateway, an on-board intelligent terminal, and a fire controller. As the hub of internal communication in the charging station, the charging gateway is responsible for coordinating data transmission between the charging pile and the cloud platform to ensure the safety and efficiency of the charging process. The on-board intelligent terminal is installed on the electric bicycle to communicate with the charging station, provide vehicle status information, and receive charging instructions. The fire controller is responsible for receiving instructions from the fire platform and controlling the operation of the fire equipment.

[0009] The perception and collection layer is responsible for collecting various status information of the charging station and electric bicycles, including the charging socket, BMS, infrared camera, AI camera and fire water cannon; the charging socket is used to physically connect the electric bicycle and the charging station, and is responsible for the transmission of electrical energy; the BMS is used to monitor the status of the electric bicycle battery to ensure safe charging of the battery; the infrared camera is used to capture thermal imaging of the charging station and identify potential fire risks by detecting abnormal temperature changes; the AI ​​camera uses artificial intelligence technology to analyze images of the charging station and identify signs of fire; when a fire occurs, the fire water cannon automatically locates and sprays water mist to extinguish the fire according to the instructions of the fire controller.

[0010] A monitoring method for a fire linkage monitoring system for an electric bicycle charging station, the monitoring method comprising:

[0011] S1: Identification and response process:

[0012] The identification and response process includes AI image recognition of smoke, triggering alarm and power off, AI identification of locked area, infrared scanning positioning, water cannon position adjustment, AI judgment of water landing point, temperature monitoring after water spraying, and continuous water spraying until the temperature drops;

[0013] S2: Additional functions and algorithm integration:

[0014] The additional functions and algorithm integration include communication interface and management platform communication, fire process video storage and uploading, online update function, continuous learning of fire characteristic images, fault diagnosis and self-inspection, user notification and interaction, and data recording and analysis.

[0015] Compared with the prior art, the present invention has the following beneficial effects:

[0016] 1. Improve safety: Through real-time monitoring and rapid response mechanisms, the risk of fire during the charging process of electric bicycles is significantly reduced.

[0017] 2. Improve response speed: Once signs of fire are detected, the system can quickly cut off power and initiate fire extinguishing procedures to reduce the damage caused by the fire.

[0018] 3. Intelligent management: Integrated AI technology enables the fire protection system to intelligently identify and respond to fire situations, improving management efficiency.

[0019] 4. Remote monitoring capability: allows remote monitoring of the fire status of the charging station, enhancing the safety and management efficiency of the charging station.

[0020] 5. Continuous performance optimization: The system has the ability to self-learn and update, and can continuously optimize fire identification and response strategies.

[0021] Specifically, by using image recognition technology and infrared thermal imaging technology, combined with machine learning algorithms, abnormal conditions during the charging process of electric bicycles can be monitored in real time. By analyzing image and thermal imaging data, the system can identify early signs of electric bicycle fires, such as smoke, flames, and abnormal temperature increases. The application of this technology makes battery vehicle fire management more scientific and standardized, providing reliable protection for safe operation.

[0022] The edge gateway of the fire protection system serves as the central control unit for all charging piles and monitoring equipment in the charging station. The edge gateway has edge computing capabilities, which can quickly process the collected data and immediately initiate emergency plans when a fire risk is detected. This includes automatically cutting off the power supply, activating the fire extinguishing system, and notifying the fire department and charging station managers through wireless communication technology. The design of the edge gateway ensures that when a fire occurs, the power-off command can be issued quickly and effectively to reduce the damage caused by the fire.

[0023] By integrating the monitoring system of the charging station, the charging pile, and the battery management system (BMS) of the electric bicycle, the charging process can be fully monitored. Once an abnormal situation is detected, such as battery overheating or abnormal current during charging, the system will respond quickly through the side gateway and take necessary safety measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a functional block diagram of the present invention.

[0025] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] See also Figure 1-2,The present invention provides a technical solution: a fire linkage monitoring system for electric bicycle charging stations, the monitoring system includes the following functional modules: a platform convergence layer, a control analysis layer and a perception collection layer;

[0028] The platform convergence layer is the core of the entire system, responsible for the centralized management and distribution of data, including the charging station cloud platform and the fire protection platform; the charging station cloud platform, as a centralized data processing center, is responsible for collecting data from various parts of the charging station, storing, analyzing and processing it, and is responsible for exchanging data with the fire protection platform to achieve information sharing; the fire protection platform is connected to the charging station cloud platform to receive and process fire protection-related data from the charging station, and achieve real-time monitoring of the fire safety status of the charging station;

[0029] The control and analysis layer is responsible for analyzing the collected data and making control decisions based on the analysis results, and includes a charging gateway, an on-board intelligent terminal, and a fire controller. The charging gateway, as the hub of internal communication in the charging station, is responsible for coordinating data transmission between the charging pile and the cloud platform to ensure the safety and efficiency of the charging process. The on-board intelligent terminal (T-box) is installed on the electric bicycle to communicate with the charging station, provide vehicle status information, such as battery management system (BMS) data, and receive charging instructions. The fire controller is responsible for receiving instructions from the fire platform and controlling the operation of fire equipment, such as starting the fire extinguishing system when a fire is detected.

[0030] The perception and collection layer is responsible for collecting various status information of the charging station and electric bicycles, including the charging socket, BMS (battery management system), infrared camera, AI camera and fire water cannon; the charging socket is used to physically connect the electric bicycle and the charging station, and is responsible for the transmission of electrical energy; the BMS (battery management system) is used to monitor the status of the electric bicycle battery, such as voltage, current, temperature, etc., to ensure safe charging of the battery; the infrared camera is used to capture thermal imaging of the charging station and identify potential fire risks by detecting abnormal temperature changes; the AI ​​camera uses artificial intelligence technology to analyze images of the charging station and identify signs of fire such as smoke and flames; when a fire occurs, the fire water cannon automatically locates and sprays water mist to extinguish the fire according to the instructions of the fire controller.

[0031] The entire system realizes the linkage monitoring of the fire protection system of the electric bicycle charging station through the collaborative work of the above three levels. Specifically, the platform aggregation layer is responsible for the centralized management of data, the control analysis layer performs data analysis and control decisions, and the perception collection layer collects various status information of the charging station and electric bicycles to provide data support for linkage monitoring. This multi-level architecture design ensures the fire safety of the charging station and improves the prevention and response capabilities of fires.

[0032] A monitoring method for a fire linkage monitoring system for an electric bicycle charging station, the monitoring method comprising:

[0033] S1: Identification and response process:

[0034] The identification and response process includes AI image recognition of smoke, triggering alarm and power off, AI identification of locked area, infrared scanning positioning, water cannon position adjustment, AI judgment of water drop point, temperature monitoring after water spraying, and continuous water spraying until the temperature drops; the specific contents are as follows:

[0035] 1. AI image recognition of smoke: Using deep learning algorithms, the AI ​​camera performs real-time image analysis of the environment inside the charging station and uses the smoke recognition function detect_smoke(image) to determine whether there is smoke.

[0036] detect_smoke(image): A deep learning-based image processing algorithm that analyzes image data captured by an AI camera and identifies smoke features. The algorithm trains a model to identify the shape, color, and movement of smoke to determine if there is a fire risk.

[0037] 2. Trigger alarm and cut off power: Once detect_smoke(image) returns a positive result, the system triggers an alarm and executes the power-off instruction function cut_power(charging_station_id) through the charging gateway.

[0038] cut_power(charging_station_id): Control algorithm used to cut off the power supply to a specific charging station through the charging gateway when a fire risk is detected. The algorithm receives the ID of the charging station as a parameter and performs a power-off operation to prevent the fire from spreading.

[0039] 3. AI identifies locked areas: AI cameras use area locking algorithms

[0040] lock_area(smoke_coordinates), lock the fire area according to the smoke coordinates.

[0041] lock_area(smoke_coordinates): used to lock the possible fire area according to the coordinates of the smoke after the AI ​​camera recognizes the smoke. It determines the area that needs to be monitored by analyzing the distribution and movement trajectory of the smoke.

[0042] 4. Infrared scanning and positioning: The infrared camera uses flame detection detect_flame(infrared_data) to scan and locate the core point of the flame in the locked area, and collects temperature data in real time.

[0043] detect_flame(infrared_data): Using data captured by an infrared camera, this algorithm identifies flames by analyzing thermal imaging data. The algorithm is able to identify the specific thermal spectrum of the flame and thus accurately locate the core of the flame.

[0044] 5. Water cannon position adjustment: The fire controller runs the water cannon positioning algorithm adjust_water_cannon(position_data) to adjust the position of the water cannon outlet according to the position information of the flame core point.

[0045] adjust_water_cannon(position_data): A control algorithm used to adjust the direction of the fire monitor according to the position information of the flame core point. The algorithm calculates the spatial relationship between the water monitor and the flame core point to ensure that the water monitor can accurately cover the flame area.

[0046] 6. AI determines water drop point: AI camera uses water drop point monitoring algorithm

[0047] verify_water_droplets(water_cannon_data) determines whether the water spray from the water cannon accurately covers the flame area.

[0048] verify_water_droplets(water_cannon_data): The algorithm verifies whether the water cannon’s water spray accurately covers the flame area by analyzing the water cannon spray images captured by the AI ​​camera. The algorithm identifies the distribution and movement of water droplets to evaluate the fire extinguishing effect.

[0049] 7. Temperature monitoring after water spraying: Infrared camera uses temperature change monitoring algorithm

[0050] monitor_temperature_change(infrared_data), evaluate the effect of water spraying.

[0051] monitor_temperature_change(infrared_data): Using infrared camera data, this algorithm monitors the temperature change at the core of the flame. The algorithm evaluates the fire extinguishing effect by comparing the temperature data before and after the water spray.

[0052] 8. Continue to spray water until the temperature drops:

[0053] monitor_temperature_change(infrared_data) shows that the temperature has dropped. The system confirms that the water spraying direction is correct and continues to execute the water spraying instruction function spray_water(water_cannon_id).

[0054] spray_water(water_cannon_id): Control algorithm used to continuously control the fire cannon to spray water after confirming that the fire extinguishing direction is correct. The algorithm receives the cannon ID as a parameter and performs a continuous water spray operation.

[0055] S2: Additional functions and algorithm integration:

[0056] The additional functions and algorithm integration include communication interface and management platform communication, fire process video storage and upload, online update function, continuous learning of fire characteristic images, fault diagnosis and self-checking, user notification and interaction, and data recording and analysis. The specific contents are as follows:

[0057] 1. Communication interface communicates with the management platform: The system exchanges data with the management platform through the communication protocol algorithm.

[0058] 2. Storage and upload of video recording of the fire process: Once triggered, the system automatically calls the recording function and uploads it to the management platform after confirming the fire.

[0059] 3. Online update function: The system checks for updates regularly and obtains the latest software version through the online update algorithm.

[0060] 4. Continuously learning fire characteristic images: The AI ​​system continuously optimizes the accuracy of smoke and flame recognition through machine learning algorithms.

[0061] 5. Fault diagnosis and self-test: The system runs self-test algorithms regularly to ensure that all components are functioning properly.

[0062] 6. User notification and interaction: Once a fire is detected, the user notification algorithm will notify the user via SMS or app push.

[0063] 7. Data recording and analysis: The system records all events and response data, and conducts post-analysis through data analysis algorithms to improve system performance.

[0064] When using:

[0065] By using image recognition technology and infrared thermal imaging technology, combined with machine learning algorithms, abnormal conditions during the charging process of electric bicycles can be monitored in real time. By analyzing image and thermal imaging data, the system can identify early signs of electric bicycle fires, such as smoke, flames, and abnormal temperature increases. The application of this technology makes battery vehicle fire management more scientific and standardized, providing reliable protection for safe operation.

[0066] The edge gateway of the fire protection system serves as the central control unit for all charging piles and monitoring equipment in the charging station. The edge gateway has edge computing capabilities, which can quickly process the collected data and immediately initiate emergency plans when a fire risk is detected. This includes automatically cutting off the power supply, activating the fire extinguishing system, and notifying the fire department and charging station managers through wireless communication technology. The design of the edge gateway ensures that when a fire occurs, the power-off command can be issued quickly and effectively to reduce the damage caused by the fire.

[0067] By integrating the monitoring system of the charging station, the charging pile, and the battery management system (BMS) of the electric bicycle, the charging process can be fully monitored. Once an abnormal situation is detected, such as battery overheating or abnormal current during charging, the system will respond quickly through the side gateway and take necessary safety measures.

[0068] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Fire linkage monitoring system for electric bicycle charging stations, characterized by: The monitoring system includes the following functional modules: platform convergence layer, control analysis layer and perception collection layer; The platform convergence layer is the core of the entire system, responsible for the centralized management and distribution of data, including the charging station cloud platform and the fire protection platform; the charging station cloud platform, as a centralized data processing center, is responsible for collecting data from various parts of the charging station, storing, analyzing and processing it, and is responsible for exchanging data with the fire protection platform to achieve information sharing; the fire protection platform is connected to the charging station cloud platform to receive and process fire protection-related data from the charging station, and achieve real-time monitoring of the fire safety status of the charging station; The control and analysis layer is responsible for analyzing the collected data and making control decisions based on the analysis results. It includes a charging gateway, an on-board intelligent terminal, and a fire controller. As the hub of internal communication in the charging station, the charging gateway is responsible for coordinating data transmission between the charging pile and the cloud platform to ensure the safety and efficiency of the charging process. The on-board intelligent terminal is installed on the electric bicycle to communicate with the charging station, provide vehicle status information, and receive charging instructions. The fire controller is responsible for receiving instructions from the fire platform and controlling the operation of the fire equipment. The perception and collection layer is responsible for collecting various status information of the charging station and electric bicycles, including the charging socket, BMS, infrared camera, AI camera and fire water cannon; the charging socket is used to physically connect the electric bicycle and the charging station, and is responsible for the transmission of electrical energy; the BMS is used to monitor the status of the electric bicycle battery to ensure safe charging of the battery; the infrared camera is used to capture thermal imaging of the charging station and identify potential fire risks by detecting abnormal temperature changes; the AI ​​camera uses artificial intelligence technology to analyze images of the charging station and identify signs of fire; when a fire occurs, the fire water cannon automatically locates and sprays water mist to extinguish the fire according to the instructions of the fire controller.

2. The monitoring method of the fire linkage monitoring system for electric bicycle charging stations according to claim 1 is characterized in that: The monitoring method comprises: S1: Identification and response process: The identification and response process includes AI image recognition of smoke, triggering alarm and power off, AI identification of locked area, infrared scanning positioning, water cannon position adjustment, AI judgment of water landing point, temperature monitoring after water spraying, and continuous water spraying until the temperature drops; S2: Additional functions and algorithm integration: The additional functions and algorithm integration include communication interface and management platform communication, fire process video storage and uploading, online update function, continuous learning of fire characteristic images, fault diagnosis and self-inspection, user notification and interaction, and data recording and analysis.

Images