New energy vehicle underground garage fire treatment method and system based on Internet of Things

Abstract

The invention discloses a new energy vehicle underground garage fire treatment method and system based on the Internet of Things. The system comprises a sensor data acquisition module, an edge calculation and risk assessment module, an early warning and emergency response module and a data storage and cloud platform module. The sensors are arranged at positions such as parking spaces and ventilation systems in a garage, monitor environmental parameters such as temperature, smoke and gas in real time, and transmit data to the edge computing device through the wireless gateway. And the edge calculation module evaluates the fire risk in combination with a fuzzy Bayesian network. And the early warning and emergency response module triggers different levels of alarm signals according to the risk levels, and controls ventilation equipment, fire-fighting equipment and the like in a linkage manner. The data storage module is used for storing monitoring data. The system has the advantages of real-time monitoring, intelligent evaluation, multistage early warning and quick response, is suitable for fire prevention and safety management of closed environments such as underground garages, and effectively improves the accuracy of fire risk prediction and the efficiency of emergency response.

Description

Technical Field

[0001] The present invention belongs to the technical field of underground garage fire risk assessment and intelligent fire fighting system, and specifically relates to a fire handling method and system for an underground garage of a new energy vehicle based on the Internet of Things. Background Art

[0002] With the rapid popularization of new energy vehicles, especially the widespread use of pure electric and plug-in hybrid vehicles, underground garages have become an important part of urban parking facilities. However, due to the strong enclosure, poor ventilation and concentrated vehicles in underground garages, once a fire occurs, the fire spreads rapidly, smoke is difficult to exhaust, and fire extinguishing is difficult. In addition, the high-energy-density lithium batteries used in new energy vehicles have safety hazards such as thermal runaway and short circuit. Especially in the special scenario of underground garages, the risk of fire increases significantly.

[0003] The existing fire monitoring system mainly relies on traditional smoke and temperature sensors and other equipment. These devices have a slow response speed and are difficult to capture early signals of electric vehicle fires, especially lithium battery fires. In the early stages of new energy vehicle fires, the fire spreads very quickly. The lag and accuracy of traditional monitoring systems are insufficient, making it difficult to provide timely warnings. In addition, the emergency response mechanism of the existing fire protection system is relatively simple and cannot cope with the complex fire scenes in underground garages. The delayed emergency linkage in complex underground environments leads to inefficient initial fire fighting and personnel evacuation, further exacerbating the risk of fire. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a fire handling method and system for underground garages of new energy vehicles based on the Internet of Things.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] On the one hand, the present invention provides a method for handling fire in an underground garage of a new energy vehicle based on the Internet of Things, comprising the following steps:

[0007] Step S1: Real-time collection of underground garage environment data;

[0008] Step S2: preprocessing the environmental data, and using the preprocessed environmental data to conduct fire risk assessment through fuzzy logic and a pre-trained Bayesian network model to obtain a fire risk assessment result;

[0009] Step S3: Perform graded warnings based on the fire risk assessment results, and take corresponding emergency response measures according to the warning levels;

[0010] Step S4: Encrypt and store the collected environmental data and the generated fire risk assessment results.

[0011] Furthermore, the underground garage environmental data includes underground garage temperature, smoke concentration, harmful gas concentration, arc data and humidity.

[0012] Furthermore, the step S2 preprocessing includes:

[0013] Process environmental data through filtering algorithms to remove environmental interference data;

[0014] Correcting received environmental data based on stored historical environmental data and adjacent data;

[0015] Different environmental data are uniformly quantified to obtain preprocessed environmental data.

[0016] Furthermore, in step S2, the preprocessed environmental data is subjected to fire risk assessment through fuzzy logic and a pre-trained Bayesian network model to obtain a fire risk assessment result, which specifically includes the following steps: the preprocessed environmental data is input into the trained Bayesian network model, and the fire risk assessment probability is output. The assessment formula is:

[0017]

[0018] Among them, F represents the event of fire, D1, D2, ..., D n Represents the monitoring data from different sensors, P(D1,D2,…,D n |F) is the conditional probability of the currently monitored environmental data when a fire occurs, P(F) is the prior probability of a fire occurring, P(D1,D2,…,D n ) is the marginal probability of sensor data, P(F|D1,D2,…,D n ) is the fire risk assessment probability output by the Bayesian network.

[0019] Furthermore, the step S3 specifically includes the following steps:

[0020] Make judgment based on the fire risk assessment probability P in the fire risk assessment results;

[0021] If P<0.3, a first-level warning is triggered, and the fire risk assessment result is sent to relevant management personnel via wireless communication;

[0022] If 0.3≤P≤0.7, a secondary warning is triggered, the smoke exhaust system is started, the fire shutter door is closed, and the fire risk assessment result is sent to all management personnel via wireless communication;

[0023] If P>0.7, the third-level warning will be triggered, triggering all emergency equipment, activating fire alarms and fire broadcasts, activating high-pressure water mist fire extinguishing systems, and sending alarm information to external fire-fighting agencies through wireless communication protocols.

[0024] On the other hand, the present invention provides a fire handling system for underground garages of new energy vehicles based on the Internet of Things, the system comprising: a sensor data acquisition module, an edge computing and risk assessment module, an early warning and emergency response module, a data storage and cloud platform module and a central control module;

[0025] The sensor data acquisition module is connected to the edge computing and risk assessment module and the data storage and cloud platform module to monitor the environmental data of the underground garage;

[0026] The edge computing and risk assessment module is connected to the early warning and emergency response module, the data storage and cloud platform module, and is used to receive the underground garage environmental data transmitted by the sensor data acquisition module in real time, and perform real-time fire risk assessment on the underground garage according to the underground garage environmental data through fuzzy logic and pre-trained Bayesian network model;

[0027] The early warning and emergency response module is used to receive the fire risk assessment results transmitted by the edge computing and risk assessment module, and determine the early warning level according to the fire risk assessment results, and take corresponding emergency response measures according to the early warning level;

[0028] The data storage and cloud platform module is used to encrypt and back up all collected underground garage environmental data and fire risk assessment results generated by the edge computing and risk assessment module.

[0029] Furthermore, the sensor data acquisition module includes: a temperature sensor, a smoke sensor, a gas sensor, an arc detection sensor and a humidity sensor.

[0030] Furthermore, the temperature sensor is used to monitor the ambient temperature of the underground garage and is installed above the parking space and at the air outlet of the ventilation system on the ceiling of the underground garage;

[0031] The smoke sensor is used to monitor smoke caused by thermal runaway, short circuit or fire of new energy vehicle batteries and is installed above the parking space and at the air outlet of the ventilation system;

[0032] The gas sensor is used to monitor harmful gases released when the battery of a new energy vehicle is under thermal runaway, and is installed on both sides of the parking space and at the smoke exhaust system and the vents of the underground garage;

[0033] The arc detection sensor is used to detect arcs caused by battery failure or circuit problems in new energy vehicles and is installed on both sides of the parking space and the charging station;

[0034] The humidity sensor is used to monitor the humidity of the underground garage environment and is installed on both sides of the parking space and near the ventilation system.

[0035] Furthermore, the data stored in the data storage and cloud platform modules are used to optimize the Bayesian network model in the edge computing and risk assessment modules.

[0036] Furthermore, the central control module is used to coordinate data transmission between modules and realize remote monitoring and command.

[0037] The present invention proposes that the system uses a multi-dimensional sensor network, combined with edge computing technology and fuzzy Bayesian network model, and can quickly identify fire hazards and generate accurate fire risk assessment results through real-time monitoring and processing of various data such as temperature, smoke, gas composition, arc, etc. The system also has a graded early warning function, which can automatically initiate corresponding emergency response measures according to the fire risk level, including the activation of fire shutter doors, smoke exhaust systems, emergency lighting and accident broadcasts, and at the same time, it can be linked with external fire-fighting agencies through the cloud platform to achieve efficient emergency management.

[0038] Compared with the prior art, the present invention has the following advantages:

[0039] (1) The present invention combines the Internet of Things technology and deploys various types of sensors (temperature, humidity, smoke, gas, arc, etc.) to achieve comprehensive monitoring of the underground garage environment. Through wireless communication protocols (such as LoRaWAN, NB-IoT or Zigbee), various sensors transmit environmental data to the edge computing subsystem in real time. This wireless architecture overcomes the problems of insufficient coverage, difficult wiring, and delayed response of traditional wired systems in the garage, making the system more flexible and adaptable in complex environments.

[0040] (2) The present invention uses a fuzzy Bayesian network model to combine and analyze the real-time data collected by sensors with historical data to dynamically evaluate fire risks. Unlike traditional fixed threshold alarm systems, this system improves the accuracy of fire warnings through probability models, avoiding false alarms and missed alarms. The system supports graded warnings (low risk, medium risk, high risk) and can automatically generate response plans based on different risk levels to ensure that the warning mechanism is more scientific and accurate.

[0041] (3) According to the risk assessment results of different levels of fire, the present invention designs a multi-level linkage response mechanism. In the low-risk stage, the system only issues a warning to relevant personnel; in the medium-risk stage, the smoke exhaust system and fireproof roller shutter are activated; in the high-risk stage, all fire-fighting equipment is activated, including the high-pressure water mist system, fire broadcast, emergency lighting, and automatically sends alarm information to external fire-fighting agencies. This multi-level response design ensures that the system can make reasonable responses according to risk dynamics, improving the timeliness and effectiveness of fire-fighting measures.

[0042] (4) The present invention ensures the encrypted storage and remote backup of all monitoring and evaluation data through the data storage and cloud platform modules, and supports the unified management and data sharing of multiple garages. Compared with the traditional system, the present invention not only improves the automation level of the fire protection system, but also performs long-term data storage and model optimization through the cloud platform, ensuring the security and traceability of the data and the intelligent upgrade of the subsequent system.

[0043] (5) The present invention has achieved significant improvements over the prior art in data collection, risk assessment, early warning response and data storage, solving the technical bottleneck of fire prevention and control of new energy vehicles in underground garages, and providing a complete and efficient solution for intelligent fire protection in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is the overall system architecture diagram;

[0045] Figure 2 This is a schematic diagram of the sensor layout;

[0046] Figure 3 Block diagram of edge computing and risk assessment module;

[0047] Figure 4 It is a flowchart of early warning and emergency response mechanism;

[0048] Figure 5 This is a flowchart of the steps of a real-time assessment and intelligent fire fighting method for new energy vehicle fires in underground garages based on the Internet of Things. DETAILED DESCRIPTION

[0049] 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 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 should fall within the scope of protection of the present invention.

[0050] This embodiment provides a real-time assessment and intelligent fire fighting system for new energy vehicle fires in underground garages based on the Internet of Things. Figure 1 As shown, the real-time assessment and intelligent fire fighting system for new energy vehicle fires in underground garages based on the Internet of Things includes a sensor data acquisition module, an edge computing and risk assessment module, an early warning and emergency response module, a data storage and cloud platform module, and a central control module.

[0051] The sensor data acquisition module is used to monitor the environmental status of the underground garage. The sensors include temperature sensors, smoke sensors, gas sensors, arc detection sensors and humidity sensors.

[0052] Specifically, Figure 2 As shown, temperature sensors are installed above the parking space, at the air outlet of the ventilation system and on the ceiling of the underground garage to monitor the ambient temperature in the garage; smoke sensors are installed above the parking space and at the air outlet of the ventilation system to monitor smoke generated by battery thermal runaway, short circuit or fire; gas sensors are installed near the parking space, exhaust system and vents to monitor harmful gases released when the lithium battery has thermal runaway, such as hydrogen and carbon monoxide; arc detection sensors are installed near the parking space and charging station to detect arc phenomena caused by battery failure or circuit problems; humidity sensors are installed around the parking space and near the ventilation system to monitor humidity changes in the garage environment in real time.

[0053] In the present invention, the sensor transmits the monitoring data to the edge computing and risk assessment module through wireless communication protocols (such as LoRaWAN, NB-IoT or Zigbee). The data transmission method greatly improves the flexibility of the system, especially under the complex layout conditions in the garage, avoiding the limitations of traditional wired system wiring.

[0054] The edge computing and risk assessment module is installed in the gateway device and is used to perform data preprocessing and fusion analysis based on the collected environmental data through edge computing, and to conduct real-time assessment of fire risks by combining fuzzy logic and Bayesian network models, so as to identify potential fire hazards and provide decision support;

[0055] Specifically, Figure 3 As shown, edge computing is used to perform real-time processing and preliminary analysis of data. The data preprocessing steps include: S31, noise filtering: sensor data may contain noise signals, and the environmental interference data is removed through filtering algorithms. S32, outlier correction: when the readings fed back by the sensor are abnormal, the system corrects them based on historical data and data from adjacent sensors. S33, data standardization: the data from different sensors are quantified uniformly to facilitate subsequent fusion analysis. After data preprocessing, the system combines historical data and fuzzy Bayesian network models to conduct real-time assessment of fire risks. Fuzzy logic is used to deal with uncertainties in sensor data, and Bayesian networks dynamically infer fire risks through conditional probability models. The evaluation formula is:

[0056]

[0057] Among them, F represents the event of fire, D1, D2, ..., D n Represents the monitoring data from different sensors, P(D1,D2,…,D n |F) is the conditional probability of the currently monitored environmental data when a fire occurs, P(F) is the prior probability of a fire occurring, P(D1,D2,…,D n) is the marginal probability of sensor data, P(F|D1,D2,…,D n ) is the fire risk assessment probability output by the Bayesian network;

[0058] The Bayesian formula calculates the conditional probability of fire occurrence through various monitoring data to achieve real-time risk assessment. The system is equipped with a self-learning algorithm that can automatically adjust the threshold and model weights based on past fire warning records and actual fire situations, ensuring that the system has high prediction accuracy in different environments. Through this model, the system can dynamically evaluate fire hazards and promptly identify possible fire risks in underground garages for new energy vehicles.

[0059] The early warning and emergency response module is installed in the control room of the underground garage and is used to automatically trigger the three-level early warning mechanism and implement corresponding emergency linkage measures according to the risk assessment results, so as to ensure that fire-fighting equipment is quickly activated, alarms are sounded, and relevant personnel are notified when a fire occurs;

[0060] Specifically, Figure 4 As shown in the figure, according to the fire risk assessment results, the system implements a three-level early warning mechanism. When the first-level early warning (low risk, P<0.3) is triggered, the system only issues a warning to the relevant management personnel, and does not enable any hardware emergency equipment, which is mainly used for early risk warnings; when the second-level early warning (medium risk, 0.3≤P≤0.7) is triggered, the system activates some protective equipment, such as starting the smoke exhaust system and closing the fire shutter door, and notifies the management personnel to strengthen on-site monitoring and use portable perfluorohexanone fire extinguishers when necessary; when the third-level early warning (high risk, P>0.7) is triggered, the system triggers all emergency equipment, first turning on the basement fire alarm or sound and light alarm and fire broadcast, notifying personnel to evacuate as soon as possible, turning on the smoke exhaust system of the evacuation channel, cutting off non-fire power supply, putting the fire elevator into emergency operation, and turning on the fire emergency lighting; at the same time, the high-pressure water mist system is automatically started, and the alarm information is sent to the external fire agency through the wireless communication protocol; in addition, a secondary confirmation mechanism can be set to reduce false alarms and ensure that the system is automatically activated at critical moments;

[0061] The data storage and cloud platform module is used to securely store all data collected and analyzed, implement data encryption and backup, and provide support for subsequent analysis and model optimization;

[0062] Specifically, all sensor data and fire risk assessment results are encrypted and stored on the cloud platform. This module supports long-term data backup and remote access, providing support for subsequent data analysis and model optimization. The cloud platform not only ensures data security, but also enables remote unified management of multiple garages. System administrators can monitor and manage the fire protection systems of different garages through the cloud platform.

[0063] The central control module is responsible for the comprehensive management of the operation of all modules, coordinating the data transmission and display between the local console and the cloud control platform, and realizing remote monitoring and command of the system.

[0064] Specifically, this module is responsible for coordinating the work of each submodule to ensure the overall operation of the system. The central control module exchanges data with the local console and the cloud control platform to achieve remote monitoring and command. Both on-site operators and remote fire management personnel can obtain system status and fire risk information in real time through this module to make decisions and commands.

[0065] This embodiment also provides a real-time assessment and intelligent fire fighting method for new energy vehicle fires in underground garages based on the Internet of Things. Figure 5 As shown, the following steps are included:

[0066] S1, monitor the environmental parameters in the garage in real time through the sensor data acquisition module, and transmit the data to the edge computing and risk assessment module through the wireless communication protocol;

[0067] S2, the edge computing and risk assessment module performs data preprocessing and fusion analysis, combines historical data to conduct fire risk assessment, and sends the risk assessment results to the early warning and emergency response module;

[0068] S3, the early warning and emergency response module provides graded early warnings based on the probability of fire risk and implements corresponding emergency measures;

[0069] S4. When different warning levels are triggered, the system activates some or all emergency equipment accordingly and notifies external firefighting agencies through wireless communication protocols;

[0070] S5. The data is uploaded to the data storage and cloud platform module and stored in encrypted form for subsequent analysis and model optimization.

[0071] The system is suitable for large-scale places such as new energy garages, underground parking lots, shopping malls, etc., and can effectively improve the intelligent level of fire risk management. Especially in the context of large-scale popularization of new energy vehicles, this system can effectively solve the problems of high false alarm rate and slow response of traditional fire alarm systems through the combination of Internet of Things and intelligent analysis technology.

[0072] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0073] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A fire handling method for underground garages of new energy vehicles based on the Internet of Things, characterized in that: The following steps are involved: Step S1: Real-time collection of underground garage environment data; Step S2: preprocessing the environmental data, and using the preprocessed environmental data to conduct fire risk assessment through fuzzy logic and a pre-trained Bayesian network model to obtain a fire risk assessment result; Step S3: Perform graded warnings based on the fire risk assessment results, and take corresponding emergency response measures according to the warning levels; Step S4: Encrypt and store the collected environmental data and the generated fire risk assessment results.

2. According to a method for handling fire in an underground garage of a new energy vehicle based on the Internet of Things according to claim 1, it is characterized in that: The underground garage environmental data includes underground garage temperature, smoke concentration, harmful gas concentration, arc data and humidity.

3. According to a method for handling fire in an underground garage of a new energy vehicle based on the Internet of Things according to claim 1, it is characterized in that: The step S2 pre-processing comprises: Process environmental data through filtering algorithms to remove environmental interference data; Correcting received environmental data based on stored historical environmental data and adjacent data; Different environmental data are uniformly quantified to obtain preprocessed environmental data.

4. According to a method for handling fire in an underground garage of a new energy vehicle based on the Internet of Things according to claim 1, it is characterized in that: In step S2, the pre-processed environmental data is subjected to fire risk assessment through fuzzy logic and a pre-trained Bayesian network model to obtain a fire risk assessment result, which specifically includes the following steps: The preprocessed environmental data is input into the trained Bayesian network model to output the fire risk assessment probability. The evaluation formula is: Among them, F represents the event of fire, D1, D2, ..., D n Represents the monitoring data from different sensors, P(D1,D2,…,D n |F) is the conditional probability of the currently monitored environmental data when a fire occurs, P(F) is the prior probability of a fire occurring, P(D1,D2,…,D n ) is the marginal probability of sensor data, P(F|D1,D2,…,D n ) is the fire risk assessment probability output by the Bayesian network.

5. According to a method for handling fire in an underground garage of a new energy vehicle based on the Internet of Things according to claim 1, it is characterized in that: The step S3 specifically comprises the following steps: Make judgment based on the fire risk assessment probability P in the fire risk assessment results; If P<0.3, a first-level warning is triggered, and the fire risk assessment result is sent to relevant management personnel via wireless communication; If 0.3≤P≤0.7, a secondary warning is triggered, the smoke exhaust system is started, the fire shutter door is closed, and the fire risk assessment result is sent to all management personnel via wireless communication; If P>0.7, the third-level warning will be triggered, triggering all emergency equipment, activating fire alarms and fire broadcasts, activating high-pressure water mist fire extinguishing systems, and sending alarm information to external fire-fighting agencies through wireless communication protocols.

6. A fire handling system for underground garages of new energy vehicles based on the Internet of Things, characterized in that: The system includes: a sensor data acquisition module, an edge computing and risk assessment module, an early warning and emergency response module, a data storage and cloud platform module and a central control module; The sensor data acquisition module is connected to the edge computing and risk assessment module and the data storage and cloud platform module to monitor the environmental data of the underground garage; The edge computing and risk assessment module is connected to the early warning and emergency response module, the data storage and cloud platform module, and is used to receive the underground garage environmental data transmitted by the sensor data acquisition module in real time, and perform real-time fire risk assessment on the underground garage according to the underground garage environmental data through fuzzy logic and pre-trained Bayesian network model; The early warning and emergency response module is used to receive the fire risk assessment results transmitted by the edge computing and risk assessment module, and determine the early warning level according to the fire risk assessment results, and take corresponding emergency response measures according to the early warning level; The data storage and cloud platform module is used to encrypt and back up all collected underground garage environmental data and fire risk assessment results generated by the edge computing and risk assessment module.

7. According to claim 6, a fire handling system for underground garages of new energy vehicles based on the Internet of Things is characterized in that: The sensor data acquisition module includes: a temperature sensor, a smoke sensor, a gas sensor, an arc detection sensor and a humidity sensor.

8. According to the Internet of Things-based new energy vehicle underground garage fire handling system of claim 7, it is characterized in that: The temperature sensor is used to monitor the ambient temperature of the underground garage and is installed above the parking space and at the ventilation system outlet on the ceiling of the underground garage; The smoke sensor is used to monitor smoke caused by thermal runaway, short circuit or fire of new energy vehicle batteries and is installed above the parking space and at the air outlet of the ventilation system; The gas sensor is used to monitor harmful gases released when the battery of a new energy vehicle is under thermal runaway, and is installed on both sides of the parking space and at the smoke exhaust system and the vents of the underground garage; The arc detection sensor is used to detect arcs caused by battery failure or circuit problems in new energy vehicles and is installed on both sides of the parking space and the charging station; The humidity sensor is used to monitor the humidity of the underground garage environment and is installed on both sides of the parking space and near the ventilation system.

9. According to claim 6, a fire handling system for underground garages of new energy vehicles based on the Internet of Things is characterized in that: The data stored in the data storage and cloud platform modules are used to optimize the Bayesian network model in the edge computing and risk assessment modules.

10. The fire handling system for underground garage of new energy vehicles based on Internet of Things according to claim 6 is characterized in that: The central control module is used to coordinate data transmission between modules and realize remote monitoring and command.

Images