Automatic fire extinguishing device and system for electric bicycle shed

Abstract

The invention relates to the technical field of fire safety, in particular to an electric bicycle shed automatic fire extinguishing device and system.The method comprises the following steps that S1, data of a plurality of fire factors are collected; s2, performing fusion analysis on various fire factor data, and outputting a fire risk judgment result; s3, dynamic fire risk assessment is carried out, and a fire early warning threshold value is adjusted in real time; s4, identifying a section where the fire occurs; s5, on the basis of the fire sections identified in the S4, automatically controlling fire extinguishing devices in the corresponding areas to be started; s6, the fire area is cooled through a water spraying device; and S7, after the fire is extinguished, storing all data to a remote cloud server. According to the electric bicycle shed, through multi-dimensional fire monitoring, intelligent algorithm dynamic evaluation and automatic control technologies, accurate fire early warning, effective fire extinguishing, continuous cooling and safety data storage are achieved, and the fire prevention and control efficiency and safety of the electric bicycle shed are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire safety, and in particular to an automatic fire extinguishing device and system for an electric bicycle shed. Background Art

[0002] With the widespread use of electric bicycles, the number of electric bicycles in my country has continued to grow, approaching 400 million, and maintaining an annual growth rate of about 8%. In order to meet the needs of centralized storage and charging of electric bicycles, more and more residential communities and public places have set up special electric bicycle sheds. However, the fire hazard of electric bicycles during the charging process is more prominent. Data show that in 2023, about 80% of electric bicycle fire incidents nationwide occurred during charging, resulting in significant property losses and safety threats. At present, traditional fire extinguishing methods mostly use portable dry powder fire extinguishers, hanging dry powder fire extinguishers and simple water sprinkler devices. These methods often cannot achieve accurate monitoring, alarm and suppression in the early stages of a fire. In addition, the existing fire extinguishing devices lack automated and intelligent control, making it difficult to respond to fire situations in a timely manner and unable to adjust according to the dynamic development of the fire. There is a risk of incomplete fire extinguishing and re-ignition.

[0003] The existing technology has obvious deficiencies in the prevention and control of fires in electric bicycle sheds, which are mainly reflected in: lack of real-time, multi-dimensional fire monitoring, inability to accurately locate the specific area where the fire occurred, fire-fighting measures are often delayed and inflexible, and difficult to adjust according to the actual development of the fire. At the same time, the existing fire-fighting system generally lacks automation and intelligence, and cannot achieve accurate fire extinguishing, continuous cooling, and complete storage and analysis of fire data. In view of this, designing an automatic fire-fighting system that can automatically monitor fires, accurately identify fire sources, activate fire-fighting devices in different areas, and continuously cool and store data after fire extinguishing has become an urgent need for fire prevention and control in electric bicycle sheds. Summary of the invention

[0004] Based on the above objectives, the present invention provides an automatic fire extinguishing device and system for an electric bicycle shed.

[0005] An automatic fire extinguishing system for an electric bicycle shed comprises the following steps:

[0006] S1: Through the sensor network installed in the electric bicycle shed, data on multiple fire factors including temperature, smoke concentration, carbon monoxide, carbon dioxide, humidity and flame spectrum in the air are collected; all collected data will be transmitted to the central control module via wired or wireless means;

[0007] S2: After receiving the multi-dimensional data in S1, the central control module performs a fusion analysis on various fire factor data based on a pre-set multi-layer neural network algorithm, determines the correlation between the data, and outputs the fire risk judgment result;

[0008] S3: Based on the fire risk judgment results in S2, combined with the number of vehicles in the electric bicycle shed, vehicle density, and wind speed and humidity data provided by environmental sensors, a dynamic fire risk assessment is performed, and the fire warning threshold is adjusted in real time;

[0009] S4: When the fire risk assessment result in S3 reaches the set threshold, the section where the fire occurs is identified through the distribution of sensors; and multi-level early warning signals are activated according to the risk assessment results;

[0010] S5: Based on the fire section identified in S4, the fire extinguishing device in the corresponding area is automatically controlled to start to ensure effective suppression of the fire source;

[0011] S6: After the fire extinguishing device is activated in S5, the continuous cooling system is activated according to the feedback information from the sensor, and the fire area is cooled down by the water spraying device; the water spraying frequency and time are adjusted according to the real-time temperature monitoring data to prevent re-ignition;

[0012] S7: After the fire is extinguished, all monitoring sensor data, fire identification process, fire extinguishing agent usage, and system operation records are stored in a remote cloud server.

[0013] Optionally, the S1 specifically includes:

[0014] S11: deploying a sensor network on the top, sides and surroundings of the electric bicycle shed and the parking area, wherein the sensor network includes a temperature sensor, a smoke sensor, a carbon monoxide sensor, a carbon dioxide sensor, a humidity sensor and a flame spectrum sensor, each of which is fixed through a standardized mounting interface to achieve comprehensive real-time monitoring of multiple fire factors;

[0015] S12: Continuously sample environmental data by deploying a sensor network, wherein the temperature sensor is used to collect temperature changes inside the carport; the smoke sensor is used to detect changes in particle concentration in the air; the carbon monoxide and carbon dioxide sensors monitor the content of harmful gases in the air; the humidity sensor detects changes in environmental humidity; the flame spectrum sensor monitors the spectral characteristics of the flame through optical principles; all collected data are converted into digital signals through the built-in analog-to-digital converter of the sensor;

[0016] S13: The digital signal is transmitted to the central control module via a wired connection or wireless communication protocol within the local area network, wherein wireless communication is preferentially used to reduce wiring complexity, and wired connection is enabled as a redundant transmission path when wireless signal interference occurs to ensure the stability and reliability of data transmission.

[0017] Optionally, the S2 specifically includes:

[0018] S21: After receiving the transmitted multi-dimensional fire factor data, the central control module will pre-process the data, including filtering noise signals and identifying and eliminating abnormal data;

[0019] S22: inputting the preprocessed data into a multi-layer neural network model, wherein the input layer of the neural network model extracts features according to the received fire factor data, wherein the specific features include temperature gradient change, smoke concentration increment, carbon monoxide and carbon dioxide concentration increase rate, humidity change rate and flame spectrum characteristic band, and forms a fire factor feature vector;

[0020] S23: The hidden layer of the multi-layer neural network performs fusion analysis on the feature vectors of various fire factors, calculates the correlation between the features through the forward propagation algorithm, and compares them with historical fire data to determine the correlation strength between fire factors;

[0021] S24: The fire risk assessment result is obtained through the output layer of the neural network model. The output result includes the probability value and risk level of fire occurrence. According to the assessment result, the fire risk is divided into different levels, including low risk, medium risk and high risk.

[0022] Optionally, the S23 specifically includes:

[0023] S231: In the hidden layer of the multi-layer neural network, the input fire factor feature vector is calculated layer by layer using the forward propagation algorithm;

[0024] S232: Based on the calculation results of the forward propagation, the system compares the characteristic vectors of each fire factor with the data in the historical fire database according to their correlation. Specifically, the cosine similarity is used to calculate the similarity between the input characteristic vector and the historical fire characteristics.

[0025] S233: Combined with the calculation results of cosine similarity, the correlation strength between fire factors is quantified by the dynamic correlation strength calculation formula; the formula is: S = α·cos(θ)+β·ΔT+γ·ΔC, where S is the correlation strength, α, β and γ are weight coefficients adjusted according to specific fire factors, ΔT represents the temperature gradient change value, and ΔC represents the rate of change of gas concentration;

[0026] S234: According to the correlation strength calculated in S233, the closeness between the fire factors is determined, and a correlation strength matrix is ​​generated, in which each value in the matrix represents the degree of correlation between the fire factors.

[0027] Optionally, the S3 specifically includes:

[0028] S31: After receiving the fire risk judgment result in S2, the fire risk assessment model is initialized based on the result, and the current fire risk value R0 is calculated by the following formula: R0 = λ1·P f +λ2·N v +λ3·D v +λ4·S w +λ5·H e , where P f is the fire risk probability output in S2; N v is the number of vehicles; D v is the vehicle density; S w is wind speed; H e is the ambient humidity; λ1, λ2, λ3, λ4, and λ5 are weight coefficients set based on experience, representing the contribution of different parameters to the fire risk;

[0029] S32: After the fire risk assessment model is initialized, the central control module combines the environmental parameters obtained in real time to prioritize the assessment of vehicle-dense areas and areas with poor ventilation. Specifically, the weight of each parameter is adjusted in real time through the weighted average method, and the fire risk value is dynamically updated according to the changes in environmental conditions such as wind speed and humidity. The update formula is: Where: ΔS w is the real-time rate of change of wind speed; ΔH e is the real-time change rate of humidity; R t It is the updated risk value, which is used to reflect the changing trend of fire risk in the current environment in real time;

[0030] S33: According to the fire risk value R in S32 t and the set fire warning threshold T r For comparison, if R t Exceeds the currently set warning threshold T r , the threshold will be adjusted dynamically. The specific adjustment will linearly increase or decrease the warning threshold according to the rising speed of fire risk and environmental changes. The adjustment formula is: in, is the new fire warning threshold, is the previous threshold, and κ is the adjustment coefficient.

[0031] Optionally, the S4 specifically includes:

[0032] S41: When the fire risk assessment result in S3 reaches the set fire warning threshold When the fire occurs, the central control module obtains the real-time monitoring data of each sensor from the sensor network, and analyzes the spatial differences of temperature, smoke concentration, carbon monoxide, carbon dioxide, humidity and flame spectrum data according to the sensor layout inside the carport to determine the fire occurrence area A. f ;

[0033] S42: After identifying the fire zone, based on the specific location of the fire, the zone control module in the system activates the multi-level warning signal for the corresponding area. The activation of the warning signal is divided into two levels, namely the first-level warning signal and the second-level warning signal. The first-level warning signal reminds the on-site personnel through the sound and light alarm device inside the carport; the second-level warning signal sends a remote alarm to the relevant external monitoring equipment and personnel through wireless communication.

[0034] Optionally, the S5 specifically includes:

[0035] S51: When the central control module receives the fire section identified in S4, it immediately activates the fire extinguishing device control unit of the corresponding area, and the fire extinguishing device control unit is connected to the sensor of the fire section to receive multi-dimensional data of temperature, smoke, carbon monoxide, and carbon dioxide in the fire area in real time;

[0036] S52: The fire extinguishing device control unit will automatically select the appropriate fire extinguishing device according to the severity of the fire. If the fire is in the early stage, the system will first activate the gas fire extinguishing device to cover and suppress the fire source through gas fire extinguishing agents, including carbon dioxide and inert gas. If the fire develops rapidly, the system will simultaneously activate other fire extinguishing devices, including the sprinkler system that sprays fire extinguishing agents, to ensure that the fire source is effectively suppressed.

[0037] S53: After the fire extinguishing device is activated, the release amount Q of the fire extinguishing agent is dynamically adjusted according to the real-time data fed back by the sensor in the fire zone; the calculation formula is: Q = μ·A f ·ΔT, where μ is the flow coefficient of the extinguishing agent, A f is the area of ​​the fire section, ΔT is the temperature increment in the fire section;

[0038] S54: During the fire-fighting operation, the temperature and smoke concentration data in the fire section are continuously monitored. If the data fed back by the sensor shows that the fire has been effectively controlled and gradually weakened, the amount of fire-extinguishing agent released will be gradually reduced, and the operation of the fire-fighting device will be automatically stopped after the fire source is completely extinguished.

[0039] Optionally, the S6 specifically includes:

[0040] S61: When the fire extinguishing device in S5 is successfully started and begins to suppress the fire source, it will continue to monitor the sensor data in the fire section, especially the real-time temperature change data fed back by the temperature sensor; if the temperature in the fire section gradually decreases but still remains within the temperature range of the risk of re-ignition, the cooling control unit will be automatically started and the water spray device corresponding to the fire area will be activated;

[0041] S62: The water spraying device will spray water intermittently on the fire section. The water spraying frequency f and the water spraying duration t are calculated by the following formula: f = α·ΔTt = β·A f , where α is the water spray frequency adjustment coefficient, ΔT is the difference between the current fire zone temperature and the preset safety temperature, β is the water spray time adjustment coefficient, A f is the area of ​​the fire zone.

[0042] Optionally, the S7 specifically includes:

[0043] S71: After the fire is extinguished and the cooling operation is completed, the central control module collects data for the entire fire monitoring and handling process, including historical data collected from all monitoring sensors installed in the carport, execution records of each step in the fire identification process, use of fire extinguishing agents, and operation logs of each module of the system;

[0044] S72: After the data collection is completed, the collected data is formatted and the information of the sensor data, fire identification records, and fire extinguishing operation records is structured and stored according to a preset standard data format;

[0045] S73: After the data is formatted, the processed data is packaged through a preset communication module and encrypted through a security encryption protocol to ensure the security of the data transmission process;

[0046] S74: The encrypted data packet is transmitted to a remote cloud server via a wireless communication network or a wired network;

[0047] S75: After receiving the data packet, the remote cloud server immediately performs data decryption and storage operations. The server stores the data in layers according to different categories to facilitate subsequent analysis and query.

[0048] An automatic fire extinguishing device for an electric bicycle shed is used to implement the above-mentioned automatic fire extinguishing system for an electric bicycle shed, and comprises the following modules:

[0049] Sensor network module: used to arrange multiple sensors inside the electric bicycle shed to monitor the environmental status inside the shed in real time and collect multi-dimensional data related to fire; and transmit the data to the central control module via wired or wireless means;

[0050] Central control module: used to receive multi-dimensional data from the sensor network module, and perform fusion analysis on the fire factor data based on the built-in multi-layer neural network algorithm to output the fire risk assessment results;

[0051] Fire section identification module: connected to the central control module, used to identify the specific section where the fire occurs based on the fire risk assessment results of the central control module and the multi-dimensional data provided by the sensor network module;

[0052] Fire extinguishing device module: connected with the fire section identification module and the central control module, used to automatically start the fire extinguishing device in the corresponding area and implement the fire extinguishing operation according to the fire occurrence area information provided by the fire section identification module;

[0053] Early warning system module: connected to the central control module and the fire section identification module, used to activate the early warning signal according to the fire risk level after the fire section is identified;

[0054] Continuous cooling module: connected to the central control module and the fire extinguishing device module, used to start the water spray device to continuously cool the fire area according to the temperature data of the fire area after the fire extinguishing operation is completed to prevent re-ignition;

[0055] Data storage and analysis module: connected to the central control module, used to store data collected by all sensors, fire section identification process, fire extinguishing agent usage and system operation records after the fire is extinguished, and encrypt the data and transmit it to the remote cloud server via wireless or wired network for subsequent fire analysis.

[0056] Beneficial effects of the present invention:

[0057] The present invention, by introducing multi-dimensional fire monitoring technology, realizes real-time monitoring of multiple fire factors such as temperature, smoke concentration, carbon monoxide, carbon dioxide, humidity and flame spectrum in the electric bicycle shed. With the help of intelligent algorithms, the system can dynamically evaluate and quickly respond to fire risks and automatically identify the specific section where the fire occurs, which greatly improves the accuracy and timeliness of fire warning. At the same time, through automatic control technology based on the development of the fire, the fire extinguishing operation can be adjusted in real time to ensure that the fire source is effectively suppressed, which significantly improves the fire extinguishing effect.

[0058] The present invention prevents the re-ignition of fire through the application of continuous cooling technology and data storage technology, and safely stores the monitoring data, identification records and operation records of the entire fire process to facilitate subsequent analysis, effectively making up for the defects of the existing fire extinguishing system such as slow response, incomplete fire extinguishing, and imperfect data management, and significantly improving the intelligence level and safety of fire prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 It is a schematic diagram of the operation flow of the automatic fire extinguishing system of the carport according to an embodiment of the present invention;

[0061] Figure 2 Schematic diagram of an automatic fire extinguishing device for a carport according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0063] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0064] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0065] like Figure 1 As shown, an automatic fire extinguishing system for an electric bicycle shed comprises the following steps:

[0066] S1: Through the sensor network installed in the electric bicycle shed, data on multiple fire factors including temperature, smoke concentration, carbon monoxide (CO), carbon dioxide (CO2), humidity and flame spectrum in the air are collected; all collected data will be transmitted to the central control module via wired or wireless means;

[0067] S2: After receiving the multi-dimensional data in S1, the central control module performs a fusion analysis on various fire factor data based on a pre-set multi-layer neural network algorithm, determines the correlation between the data, and outputs the fire risk judgment result. This step avoids misjudgment of a single data through a comprehensive analysis of multiple fire factors;

[0068] S3: Based on the fire risk judgment results in S2, combined with the number of vehicles in the electric bicycle shed, vehicle density, and wind speed and humidity data provided by environmental sensors, a dynamic fire risk assessment is performed, and the fire warning threshold is adjusted in real time. The adjusted threshold is used to further optimize the accuracy of the fire warning;

[0069] S4: When the fire risk assessment result in S3 reaches the set threshold, the section where the fire occurs is identified through the distribution of sensors; and multi-level early warning signals are activated according to the risk assessment results;

[0070] S5: Based on the fire section identified in S4, the fire extinguishing device in the corresponding area is automatically controlled to start, and gas fire extinguishing agent is used first to ensure effective suppression of the fire source;

[0071] S6: After the fire extinguishing device is activated in S5, the continuous cooling system is activated according to the feedback information from the sensor, and the fire area is cooled down by the water spraying device; the water spraying frequency and time are adjusted according to the real-time temperature monitoring data to ensure that the fire area is fully cooled to prevent re-ignition;

[0072] S7: After the fire is extinguished, all monitoring sensor data, fire identification process, fire extinguishing agent usage and system operation records are stored in the remote cloud server. This data can be used for subsequent fire accident analysis and system optimization and maintenance.

[0073] S1 specifically includes:

[0074] S11: A sensor network is deployed on the top, sides and around the parking area of ​​the electric bicycle shed. The sensor network includes temperature sensors, smoke sensors, carbon monoxide sensors, carbon dioxide sensors, humidity sensors and flame spectrum sensors. Each sensor is fixed through a standardized installation interface to ensure that it covers different monitoring areas inside the shed to achieve comprehensive real-time monitoring of multiple fire factors.

[0075] The above deployment of sensor network can refer to the following rules:

[0076] The temperature sensor is installed at the top center of the carport to monitor the temperature of the entire carport;

[0077] The smoke sensor is installed in the middle area of ​​the wall height on the side of the carport to detect the change of smoke concentration in the early stage of fire;

[0078] Carbon monoxide (CO) sensors and carbon dioxide (CO2) sensors are installed at low locations inside the carport close to the parking area to ensure monitoring of the concentration of harmful gases released during a fire;

[0079] Humidity sensors are evenly distributed at the four corners of the carport to ensure full coverage of environmental humidity monitoring;

[0080] The flame spectrum sensor is installed in the upper corner of the vehicle parking area of ​​the carport to ensure that the spectral characteristics of the flame are maximized.

[0081] S12: Environmental data is continuously sampled by deploying a sensor network. The temperature sensor is used to collect temperature changes inside the carport; the smoke sensor is used to detect changes in the concentration of particulate matter in the air; the carbon monoxide and carbon dioxide sensors monitor the content of harmful gases in the air; the humidity sensor detects changes in environmental humidity; the flame spectrum sensor monitors the spectral characteristics of the flame through optical principles; all collected data are converted into digital signals through the built-in analog-to-digital converter of the sensor;

[0082] S13: The digital signal is transmitted to the central control module through a wired connection or wireless communication protocol (such as Wi-Fi, LoRa, ZigBee, etc.) within the local area network. Wireless communication is used preferentially to reduce wiring complexity, and wired connection is enabled as a redundant transmission path when wireless signal interference occurs to ensure the stability and reliability of data transmission. The above steps ensure that stable data transmission can be achieved through wired connection when wireless communication is interfered, fails or the signal is insufficient through clear sensor installation methods and redundant design of data transmission, thereby improving the reliability and emergency response capabilities of the system.

[0083] S2 specifically includes:

[0084] S21: After receiving the transmitted multi-dimensional fire factor data, the central control module will pre-process the data, including filtering noise signals and identifying and eliminating abnormal data. This step ensures the accuracy and consistency of the input data by adopting data cleaning algorithms such as outlier detection and moving average filtering;

[0085] S22: input the preprocessed data into the multi-layer neural network model. The input layer of the neural network model will extract features based on the received fire factor data. The specific features include temperature gradient change, smoke concentration increment, carbon monoxide and carbon dioxide concentration increase rate, humidity change rate and flame spectrum characteristic band, and form a series of fire factor feature vectors.

[0086] S23: The hidden layer of the multi-layer neural network performs fusion analysis on the feature vectors of various fire factors, calculates the correlation between the features through the forward propagation algorithm, and compares them with historical fire data to determine the correlation strength between the fire factors. This step continuously adjusts the model weights through the back propagation algorithm to improve the accuracy of the model judgment;

[0087] S24: The fire risk assessment results are obtained through the output layer of the neural network model. The output results include the probability value and risk level of fire occurrence. According to the assessment results, the fire risk is divided into different levels, including low risk, medium risk and high risk, to provide a basis for subsequent fire response measures.

[0088] S23 specifically includes:

[0089] S231: In the hidden layer of the multi-layer neural network, the input fire factor feature vector is calculated layer by layer using the forward propagation algorithm. The forward propagation process can be expressed by the following formula: l =W l ·a l-1 +b l , where z l Represents the linear combination result of the l-th layer of neurons, W l is the weight matrix of the lth layer, a l-1 is the activation value of the previous layer, b l is the bias term of the lth layer; then, z l Input into the activation function to generate the activation value a of the lth layer l , calculated by the following formula: l =f(z l ), where f is the activation function, and the ReLU function can be used, which is defined as: f(z) = max(0, z). This process will propagate the feature vector layer by layer until the output layer, ensuring that the relevance of each fire factor feature can be gradually quantified through layer-by-layer weight changes;

[0090] S232: Based on the calculation results of forward propagation, the system compares the characteristic vectors of each fire factor with the data in the historical fire database according to their correlation. Specifically, the cosine similarity is used to calculate the similarity between the input characteristic vector and the historical fire characteristics. The formula is as follows: Among them, A represents the feature vector of the current fire factor, B represents the feature vector in the historical fire database, and ∥A∥ and ∥B∥ respectively represent the modulus lengths of the two vectors; the similarity between the current fire factor and the historical fire pattern can be determined through the cosine similarity value;

[0091] S233: Combined with the calculation results of cosine similarity, the correlation strength between fire factors is quantified through the dynamic correlation strength calculation formula; the formula is: S = α·cos(θ)+β·ΔT+γ·ΔC, where S is the correlation strength, α, β and γ are weight coefficients adjusted according to specific fire factors, ΔT represents the temperature gradient change value, and ΔC represents the rate of change of gas concentration (CO, CO2); through this formula, the similarity of temperature, gas concentration and historical data can be comprehensively evaluated to determine the correlation strength between fire factors;

[0092] S234: According to the correlation strength calculated by S233, the closeness between the fire factors is judged, and a correlation strength matrix is ​​generated. Each value in the matrix represents the degree of correlation between the fire factors. Through this correlation strength matrix, a more accurate basis can be provided for subsequent fire risk assessment. The above steps are compared with historical fire data through the forward propagation algorithm and cosine similarity, so as to achieve accurate matching of current fire factors with historical fire patterns, and then calculate the correlation strength between fire factors. This method can quickly and accurately identify fire precursors, provide reliable data support for fire risk assessment, and significantly improve the system's response capability to complex fire patterns.

[0093] S3 specifically includes:

[0094] S31: After receiving the fire risk judgment result in S2, the fire risk assessment model is initialized based on the result, and the current fire risk value R0 is calculated by the following formula: R0 = λ1·P f +λ2·N v +λ3·D v +λ4·S w +λ5·H e , where P f is the fire risk probability output in S2; N v is the number of vehicles; D v is the vehicle density, calculated by the number of vehicles per unit area of ​​the carport; S w is wind speed; H e is the ambient humidity; λ1, λ2, λ3, λ4, and λ5 are weight coefficients set based on experience, representing the contribution of different parameters to the fire risk;

[0095] S32: After the fire risk assessment model is initialized, the central control module combines the environmental parameters obtained in real time to prioritize the assessment of vehicle-dense areas and areas with poor ventilation. Specifically, the weight of each parameter is adjusted in real time through the weighted average method, and the fire risk value is dynamically updated according to the changes in environmental conditions such as wind speed and humidity. The update formula is: Where: ΔS w is the real-time rate of change of wind speed; ΔHe is the real-time change rate of humidity; R t It is the updated risk value, which is used to reflect the changing trend of fire risk in the current environment in real time;

[0096] S33: According to the fire risk value R in S32 t and the set fire warning threshold T r For comparison, if R t Exceeds the currently set warning threshold T r , the threshold will be adjusted dynamically. The specific adjustment will linearly increase or decrease the warning threshold according to the rising speed of fire risk and environmental changes. The adjustment formula is: in, is the new fire warning threshold, is the previous threshold, and κ is the adjustment coefficient, which ensures that the system can flexibly respond to fluctuations in fire risk. By combining the number of vehicles, vehicle density and environmental sensor data in the above steps, the system can dynamically evaluate the fire risk and adjust the warning threshold in real time according to changes in environmental conditions. This technology not only improves the response sensitivity to fire, but also effectively reduces the risks of false alarms and missed alarms, and enhances the system's ability to predict fire risks under complex environmental conditions.

[0097] S4 specifically includes:

[0098] S41: When the fire risk assessment result in S3 reaches the set fire warning threshold When the fire occurs, the central control module obtains the real-time monitoring data of each sensor from the sensor network, and analyzes the spatial differences of temperature, smoke concentration, carbon monoxide, carbon dioxide, humidity and flame spectrum data according to the sensor layout inside the carport to determine the fire occurrence area A. f , the formula is: Among them, w i is the preset weight of the sensor at different positions in the carport, ΔP i is the rate of change of each sensor monitoring data, n is the number of sensors in the monitoring area, and the specific section A where the fire occurs is identified by calculating the weight change of each sensor position. f ;

[0099] S42: After identifying the fire zone, based on the specific location of the fire, the zone control module in the system activates the multi-level warning signal for the corresponding area. The activation of the warning signal is divided into two levels, namely the first-level warning signal and the second-level warning signal. The first-level warning signal reminds the on-site personnel through the sound and light alarm device inside the carport; the second-level warning signal sends a remote alarm to the relevant external monitoring equipment and personnel through wireless communication; the above steps can identify the specific section where the fire occurs in real time through accurate analysis of the distribution of sensors, and activate the multi-level warning signal in a zoned manner according to the fire risk assessment results. This method ensures the accuracy and timeliness of the warning signal, and can effectively notify the personnel inside and outside the carport to take emergency measures.

[0100] S5 specifically includes:

[0101] S51: When the central control module receives the fire section identified in S4, it immediately activates the fire extinguishing device control unit of the corresponding area. The fire extinguishing device control unit is connected to the sensor of the fire section to receive multi-dimensional data of temperature, smoke, carbon monoxide and carbon dioxide in the fire area in real time to accurately judge the development of the fire;

[0102] S52: The fire extinguishing device control unit will automatically select the appropriate fire extinguishing device according to the severity of the fire. If the fire is in the early stage, the system will first activate the gas fire extinguishing device to cover and suppress the fire source through gas fire extinguishing agents, including carbon dioxide and inert gas. If the fire develops rapidly, the system will simultaneously activate other fire extinguishing devices, including the sprinkler system that sprays fire extinguishing agents, to ensure that the fire source is effectively suppressed.

[0103] S53: After the fire extinguishing device is activated, the release amount Q of the fire extinguishing agent is dynamically adjusted according to the real-time data fed back by the sensor in the fire zone; the calculation formula is: Q = μ·A f ·ΔT, where μ is the flow coefficient of the extinguishing agent, A f is the area of ​​the fire section, and ΔT is the temperature increment in the fire section. By calculating the required amount of fire extinguishing agent, the system ensures that the appropriate amount of fire extinguishing agent is released at different fire stages to avoid waste and secondary hazards.

[0104] S54: During the fire-fighting operation, the temperature and smoke concentration data in the fire section are continuously monitored. If the data feedback from the sensor indicates that the fire has been effectively controlled and gradually weakened, the amount of fire-extinguishing agent released will be gradually reduced, and the operation of the fire-fighting device will be automatically stopped after the fire source is completely extinguished. Through the real-time identification and dynamic data feedback of the fire section in the above steps, the system can accurately control the activation of the fire-fighting device and the release amount of the fire-fighting agent to ensure that the fire source is effectively suppressed in the initial stage. This technology can automatically adjust the fire-fighting strategy according to the development of the fire, avoid unnecessary waste of resources, and improve the accuracy and efficiency of fire-fighting.

[0105] S6 specifically includes:

[0106] S61: When the fire extinguishing device in S5 is successfully started and begins to suppress the fire source, it will continue to monitor the sensor data in the fire section, especially the real-time temperature change data fed back by the temperature sensor; if the temperature in the fire section gradually decreases but still remains within the temperature range of the risk of re-ignition, the cooling control unit will be automatically started and the water spray device corresponding to the fire area will be activated;

[0107] S62: The water spraying device will spray water intermittently on the fire section. The water spraying frequency f and the water spraying duration t are calculated by the following formula: f = α·ΔTt = β·A f , where α is the water spray frequency adjustment coefficient, ΔT is the difference between the current fire zone temperature and the preset safety temperature, β is the water spray time adjustment coefficient, A f is the area of ​​the fire section. Through this calculation method, the system can reasonably adjust the water spraying operation according to the real-time temperature feedback to ensure that the fire area is fully cooled.

[0108] S7 specifically includes:

[0109] S71: After the fire is extinguished and the cooling operation is completed, the central control module collects data for the entire fire monitoring and processing process, including historical data collected from all monitoring sensors installed in the carport, execution records of each step in the fire identification process, use of fire extinguishing agents (such as release amount, time, area, etc.), and operation logs of each module of the system;

[0110] S72: After data collection is completed, the collected data is formatted and the information of sensor data, fire identification records, and fire extinguishing operation records is structured and stored according to a preset standard data format. The data formatting standards include timestamp, data type, data source, operation instructions, and feedback status, etc., to ensure the integrity and consistency of the data;

[0111] S73: After the data is formatted, the processed data is packaged through a preset communication module and encrypted through a secure encryption protocol (such as AES-256) to ensure the security of the data transmission process and prevent data leakage or tampering;

[0112] S74: The encrypted data packet is transmitted to the remote cloud server via a wireless communication network (such as Wi-Fi, 4G / 5G, LoRa) or a wired network. The wireless network is preferred for data transmission. If the network connection is unstable or the signal is interfered, it will automatically switch to a wired connection to ensure the reliability of data transmission.

[0113] S75: After receiving the data packet, the remote cloud server immediately performs data decryption and storage operations. The server stores the data in layers according to different categories (monitoring data, identification records, fire extinguishing agent usage, system operation logs) to facilitate subsequent analysis and query; through the above-mentioned monitoring data collection, formatting processing, secure encryption and remote transmission, the system can ensure that all fire-related data is safely and reliably stored after the fire is extinguished. This method not only helps with subsequent fire cause analysis and system optimization, but also provides reliable data records, providing a strong reference for the prevention and handling of similar situations in the future.

[0114] like Figure 2 As shown, an automatic fire extinguishing device for an electric bicycle shed is used to implement the above-mentioned automatic fire extinguishing system for an electric bicycle shed, and includes the following modules:

[0115] Sensor network module: used to arrange multiple sensors inside the electric bicycle shed to monitor the environmental status inside the shed in real time and collect multi-dimensional data related to fire; and transmit the data to the central control module via wired or wireless means;

[0116] Central control module: used to receive multi-dimensional data from the sensor network module, and perform fusion analysis on the fire factor data based on the built-in multi-layer neural network algorithm to output the fire risk assessment results;

[0117] Fire section identification module: connected to the central control module, used to identify the specific section where the fire occurs based on the fire risk assessment results of the central control module and the multi-dimensional data provided by the sensor network module;

[0118] Fire extinguishing device module: connected with the fire section identification module and the central control module, used to automatically start the fire extinguishing device in the corresponding area and implement the fire extinguishing operation according to the fire occurrence area information provided by the fire section identification module;

[0119] Early warning system module: connected to the central control module and the fire section identification module, used to activate the early warning signal according to the fire risk level after the fire section is identified;

[0120] Continuous cooling module: connected to the central control module and the fire extinguishing device module, used to start the water spray device to continuously cool the fire area according to the temperature data of the fire area after the fire extinguishing operation is completed to prevent re-ignition;

[0121] Data storage and analysis module: connected to the central control module, used to store data collected by all sensors, fire section identification process, fire extinguishing agent usage and system operation records after the fire is extinguished, and encrypt the data and transmit it to the remote cloud server via wireless or wired network for subsequent fire analysis.

[0122] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0123] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An automatic fire extinguishing system for an electric bicycle shed, characterized in that: The following steps are involved: S1: Through the sensor network installed in the electric bicycle shed, data on multiple fire factors including temperature, smoke concentration, carbon monoxide, carbon dioxide, humidity and flame spectrum in the air are collected; all collected data will be transmitted to the central control module via wired or wireless means; S2: After receiving the multi-dimensional data in S1, the central control module performs a fusion analysis on various fire factor data based on a pre-set multi-layer neural network algorithm, determines the correlation between the data, and outputs the fire risk judgment result; S3: Based on the fire risk judgment results in S2, combined with the number of vehicles in the electric bicycle shed, vehicle density, and wind speed and humidity data provided by environmental sensors, a dynamic fire risk assessment is performed, and the fire warning threshold is adjusted in real time; S4: When the fire risk assessment result in S3 reaches the set threshold, the section where the fire occurs is identified through the distribution of sensors; and multi-level early warning signals are activated according to the risk assessment results; S5: Based on the fire section identified in S4, the fire extinguishing device in the corresponding area is automatically controlled to start to ensure effective suppression of the fire source; S6: After the fire extinguishing device is activated in S5, the continuous cooling system is activated according to the feedback information from the sensor, and the fire area is cooled down by the water spraying device; the water spraying frequency and time are adjusted according to the real-time temperature monitoring data to prevent re-ignition; S7: After the fire is extinguished, all monitoring sensor data, fire identification process, fire extinguishing agent usage, and system operation records are stored in a remote cloud server.

2. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S1 specifically includes: S11: deploying a sensor network on the top, sides and surroundings of the electric bicycle shed and the parking area, wherein the sensor network includes a temperature sensor, a smoke sensor, a carbon monoxide sensor, a carbon dioxide sensor, a humidity sensor and a flame spectrum sensor, each of which is fixed by a standardized mounting interface to achieve comprehensive real-time monitoring of multiple fire factors; S12: Continuously sample environmental data by deploying a sensor network, wherein the temperature sensor is used to collect temperature changes inside the carport; the smoke sensor is used to detect changes in particle concentration in the air; the carbon monoxide and carbon dioxide sensors monitor the content of harmful gases in the air; the humidity sensor detects changes in environmental humidity; the flame spectrum sensor monitors the spectral characteristics of the flame through optical principles; all collected data are converted into digital signals through the built-in analog-to-digital converter of the sensor; S13: The digital signal is transmitted to the central control module via a wired connection or wireless communication protocol within the local area network, wherein wireless communication is preferentially used to reduce wiring complexity, and wired connection is enabled as a redundant transmission path when wireless signal interference occurs to ensure the stability and reliability of data transmission.

3. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S2 specifically includes: S21: After receiving the transmitted multi-dimensional fire factor data, the central control module will pre-process the data, including filtering noise signals and identifying and eliminating abnormal data; S22: inputting the preprocessed data into a multi-layer neural network model, wherein the input layer of the neural network model extracts features according to the received fire factor data, wherein the specific features include temperature gradient change, smoke concentration increment, carbon monoxide and carbon dioxide concentration increase rate, humidity change rate and flame spectrum characteristic band, and forms a fire factor feature vector; S23: The hidden layer of the multi-layer neural network performs fusion analysis on the feature vectors of various fire factors, calculates the correlation between the features through the forward propagation algorithm, and compares them with historical fire data to determine the correlation strength between fire factors; S24: The fire risk assessment result is obtained through the output layer of the neural network model. The output result includes the probability value and risk level of fire occurrence. According to the assessment result, the fire risk is divided into different levels, including low risk, medium risk and high risk.

4. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S23 specifically includes: S231: In the hidden layer of the multi-layer neural network, the input fire factor feature vector is calculated layer by layer using the forward propagation algorithm; S232: Based on the calculation results of the forward propagation, the system compares the characteristic vectors of each fire factor with the data in the historical fire database according to their correlation. Specifically, the cosine similarity is used to calculate the similarity between the input characteristic vector and the historical fire characteristics. S233: Combined with the calculation results of cosine similarity, the correlation strength between fire factors is quantified by the dynamic correlation strength calculation formula; the formula is: S = α·cos(θ)+β·ΔT+γ·ΔC, where S is the correlation strength, α, β and γ are weight coefficients adjusted according to specific fire factors, ΔT represents the temperature gradient change value, and ΔC represents the rate of change of gas concentration; S234: According to the correlation strength calculated in S233, the closeness between the fire factors is determined, and a correlation strength matrix is ​​generated, in which each value in the matrix represents the degree of correlation between the fire factors.

5. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S3 specifically includes: S31: After receiving the fire risk judgment result in S2, the fire risk assessment model is initialized based on the result, and the current fire risk value R0 is calculated by the following formula: R0 = λ1·P f +λ2·N v +λ3·D v +λ4·S w +λ5·H e , where P f is the fire risk probability output in S2; N v is the number of vehicles; D v is the vehicle density; S w is wind speed; H e is the ambient humidity; λ1, λ2, λ3, λ4, and λ5 are weight coefficients set based on experience, representing the contribution of different parameters to the fire risk; S32: After the fire risk assessment model is initialized, the central control module combines the environmental parameters obtained in real time to prioritize the assessment of vehicle-dense areas and areas with poor ventilation. Specifically, the weight of each parameter is adjusted in real time through the weighted average method, and the fire risk value is dynamically updated according to the changes in environmental conditions such as wind speed and humidity. The update formula is: Where: ΔS w is the real-time rate of change of wind speed; ΔH e is the real-time change rate of humidity; R t It is the updated risk value, which is used to reflect the changing trend of fire risk in the current environment in real time; S33: According to the fire risk value R in S32 t and the set fire warning threshold T r For comparison, if R t Exceeds the currently set warning threshold T r , the threshold will be adjusted dynamically. The specific adjustment will linearly increase or decrease the warning threshold according to the rising speed of fire risk and environmental changes. The adjustment formula is: in, is the new fire warning threshold, Adjustment factor.

6. The automatic fire extinguishing system for an electric bicycle shed according to claim 5, characterized in that: The S4 specifically includes: S41: When the fire risk assessment result in S3 reaches the set fire warning threshold When the fire occurs, the central control module obtains the real-time monitoring data of each sensor from the sensor network, and analyzes the spatial differences of temperature, smoke concentration, carbon monoxide, carbon dioxide, humidity and flame spectrum data according to the sensor layout inside the carport to determine the fire occurrence area A. f ; S42: After identifying the fire zone, based on the specific location of the fire, the zone control module in the system activates the multi-level warning signal for the corresponding area. The activation of the warning signal is divided into two levels, namely the first-level warning signal and the second-level warning signal. The first-level warning signal reminds the on-site personnel through the sound and light alarm device inside the carport; the second-level warning signal sends a remote alarm to the relevant external monitoring equipment and personnel through wireless communication.

7. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S5 specifically includes: S51: When the central control module receives the fire section identified in S4, it immediately activates the fire extinguishing device control unit of the corresponding area, and the fire extinguishing device control unit is connected to the sensor of the fire section to receive multi-dimensional data of temperature, smoke, carbon monoxide, and carbon dioxide in the fire area in real time; S52: The fire extinguishing device control unit will automatically select the appropriate fire extinguishing device according to the severity of the fire. If the fire is in the early stage, the system will first activate the gas fire extinguishing device to cover and suppress the fire source through gas fire extinguishing agents, including carbon dioxide and inert gas. If the fire develops rapidly, the system will simultaneously activate other fire extinguishing devices, including the sprinkler system that sprays fire extinguishing agents, to ensure that the fire source is effectively suppressed. S53: After the fire extinguishing device is activated, the release amount Q of the fire extinguishing agent is dynamically adjusted according to the real-time data fed back by the sensor in the fire zone; the calculation formula is: Q = μ·A f ·ΔT, where μ is the flow coefficient of the extinguishing agent, A f is the area of ​​the fire section, ΔT is the temperature increment in the fire section; S54: During the fire-fighting operation, the temperature and smoke concentration data in the fire section are continuously monitored. If the data fed back by the sensor shows that the fire has been effectively controlled and gradually weakened, the amount of fire-extinguishing agent released will be gradually reduced, and the operation of the fire-fighting device will be automatically stopped after the fire source is completely extinguished.

8. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S6 specifically includes: S61: When the fire extinguishing device in S5 is successfully started and begins to suppress the fire source, it will continue to monitor the sensor data in the fire section, especially the real-time temperature change data fed back by the temperature sensor; if the temperature in the fire section gradually decreases but still remains within the temperature range of the risk of re-ignition, the cooling control unit will be automatically started and the water spray device corresponding to the fire area will be activated; S62: The water spraying device will spray water intermittently on the fire section. The water spraying frequency f and the water spraying duration t are calculated by the following formula: f = α·ΔTt = β·A f , where α is the water spray frequency adjustment coefficient, ΔT is the difference between the current fire zone temperature and the preset safety temperature, β is the water spray time adjustment coefficient, A f is the area of ​​the fire zone.

9. The automatic fire extinguishing system for an electric bicycle shed according to claim 1, characterized in that: The S7 specifically includes: S71: After the fire is extinguished and the cooling operation is completed, the central control module collects data for the entire fire monitoring and handling process, including historical data collected from all monitoring sensors installed in the carport, execution records of each step in the fire identification process, use of fire extinguishing agents, and operation logs of each module of the system; S72: After the data collection is completed, the collected data is formatted and the information of the sensor data, fire identification records, and fire extinguishing operation records is structured and stored according to a preset standard data format; S73: After the data is formatted, the processed data is packaged through a preset communication module and encrypted through a security encryption protocol to ensure the security of the data transmission process; S74: The encrypted data packet is transmitted to a remote cloud server via a wireless communication network or a wired network; S75: After receiving the data packet, the remote cloud server immediately performs data decryption and storage operations. The server stores the data in layers according to different categories to facilitate subsequent analysis and query.

10. An automatic fire extinguishing device for an electric bicycle shed, used to implement an automatic fire extinguishing system for an electric bicycle shed as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Sensor network module: used to arrange multiple sensors inside the electric bicycle shed to monitor the environmental status inside the shed in real time and collect multi-dimensional data related to fire; and transmit the data to the central control module via wired or wireless means; Central control module: used to receive multi-dimensional data from the sensor network module, and perform fusion analysis on the fire factor data based on the built-in multi-layer neural network algorithm to output the fire risk assessment results; Fire section identification module: connected to the central control module, used to identify the specific section where the fire occurs based on the fire risk assessment results of the central control module and the multi-dimensional data provided by the sensor network module; Fire extinguishing device module: connected with the fire section identification module and the central control module, used to automatically start the fire extinguishing device in the corresponding area and implement the fire extinguishing operation according to the fire occurrence area information provided by the fire section identification module; Early warning system module: connected to the central control module and the fire section identification module, used to activate the early warning signal according to the fire risk level after the fire section is identified; Continuous cooling module: connected to the central control module and the fire extinguishing device module, used to start the water spray device to continuously cool the fire area according to the temperature data of the fire area after the fire extinguishing operation is completed to prevent re-ignition; Data storage and analysis module: connected to the central control module, used to store data collected by all sensors, fire section identification process, fire extinguishing agent usage and system operation records after the fire is extinguished, and encrypt the data and transmit it to the remote cloud server via wireless or wired network for subsequent fire analysis.

Images