Intelligent partition foam spray fire extinguishing early warning system for carport

Abstract

The invention discloses an intelligent partition foam spray fire extinguishing early warning system for a carport, which relates to the technical field of automatic fire extinguishing and comprises an intelligent early warning module, a thermal imaging monitoring module, a spray parameter adjusting module, a spray fire extinguishing module and a data monitoring feedback module. Through combination of the intelligent early warning module and the thermal imaging monitoring module, the system can rapidly detect and give an alarm in the initial stage of a fire, and fire loss is reduced; through cooperative work of the thermal imaging monitoring module and the spraying parameter adjusting module, the system can accurately position a fire source and intelligently adjust spraying parameters, and the fire extinguishing accuracy and efficiency are improved; the thermal imaging technology is combined with the image recognition capability of the convolutional neural network, so that the position and range of a fire source can be accurately positioned, and accurate information is provided for fire extinguishing actions; the thermal imaging technology is not influenced by light changes, effective monitoring can be carried out in the daytime and at night, and the reliability of the system is improved.

Description

Technical Field

[0001] The invention relates to the technical field of automatic fire extinguishing, and in particular to a carport intelligent partition foam spray fire extinguishing early warning system. Background Art

[0002] Carports usually park a large number of vehicles, and the total value of these vehicles may be very high. Once a fire occurs, the vehicles may be burned or seriously damaged, causing huge economic losses. Timely and effective fire-fighting measures can minimize property losses. Although carports are usually not crowded places, there may still be people in or near the carport when a fire occurs. Quick firefighting can prevent the spread of fire, reduce the threat to personnel, and ensure personal safety.

[0003] Carports are usually large in area, and zoning management can improve firefighting efficiency. The intelligent zoning system divides the carport into multiple independent areas, each equipped with independent monitoring and firefighting equipment. When a fire occurs in a certain area, the system can accurately locate and extinguish the fire only in that area, avoiding wasting resources and affecting other areas. Foam spray fire extinguishing technology is the core firefighting method of this system. Foam has strong covering and cooling capabilities, which can quickly suppress the fire and prevent it from re-igniting. The spray system quickly sprays the foam to the fire source through pipes and nozzles, forming a covering layer, effectively isolating oxygen and cooling.

[0004] The existing automatic fire extinguishing system for carports uses the communication module and the automatic dialing module to send the fire information to the staff's mobile phone in the form of text messages, and the WiFi module transmits the images taken by the surveillance camera to the cloud server, so that the cause of the fire can be checked after the fire is extinguished. However, the existing technology still has the following shortcomings: it is impossible to dynamically adjust the spraying parameters and intelligent control according to the real-time environment, thereby failing to reduce the waste of fire extinguishing agents and improve resource utilization efficiency, which increases operating costs.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of the problems in the related technology, the present invention proposes a carport intelligent partition foam spray fire extinguishing early warning system to overcome the above-mentioned technical problems existing in the existing related technology.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: The carport intelligent partition foam spray fire extinguishing warning system includes an intelligent warning module, a thermal imaging monitoring module, a spray parameter adjustment module, a spray fire extinguishing module and a data monitoring feedback module; wherein the intelligent warning module and the thermal imaging monitoring module are connected to the spray parameter adjustment module, the spray parameter adjustment module is connected to the spray fire extinguishing module, and the spray fire extinguishing module is connected to the data monitoring feedback module.

[0008] The intelligent early warning module is used to monitor the environmental conditions of the carport in real time and trigger the alarm device when a fire is detected.

[0009] The thermal imaging monitoring module is used to obtain fire conditions using thermal imaging technology, and based on convolutional neural networks, train and identify fire image features, locate the fire source and trigger the alarm device.

[0010] The spray parameter adjustment module is used to calculate the optimal spray parameters in real time based on fuzzy logic control and PID control algorithm.

[0011] The spray fire extinguishing module is used to spray the fire extinguishing agent into the fire area when a fire occurs.

[0012] The data monitoring feedback module is used to obtain real-time monitoring parameters and feed back the monitoring parameters to the cloud server platform and mobile application platform to achieve remote monitoring and management.

[0013] Furthermore, the environmental conditions of the carport are monitored in real time, and when a fire is detected, the alarm device is triggered, including: Obtain the collected data of each monitoring sensor; Setting a threshold value for each collected data, and comparing the collected data with the collected data threshold value; Based on the threshold judgment result, a fire determination is made, and an alarm signal is generated to trigger the alarm device.

[0014] Furthermore, the alarm device includes an audible and visual alarm, a text message notification module and an automatic emergency call module.

[0015] Furthermore, thermal imaging technology is used to obtain fire conditions, and based on convolutional neural networks, fire image features are trained and identified to locate the fire source and trigger an alarm, including: Initialize the convolutional neural network model and prepare the training data set; Train the convolutional neural network model using the training dataset; Use the trained convolutional neural network model to identify fire features from real-time collected and pre-processed thermal imaging images; Analyze the identification results to determine the location and scope of the fire source; The alarm device is triggered according to the location and scope of the fire source, and the alarm event is recorded.

[0016] Furthermore, preparing the training dataset includes: Collect raw thermal imaging data in the carport; Performing a preprocessing operation on the original thermal imaging data to obtain a preprocessed thermal imaging image; Fire features are annotated in the preprocessed thermal imaging images to construct a training dataset.

[0017] Furthermore, based on fuzzy logic control and PID control algorithms, the optimal spraying parameters are calculated in real time including: Obtain the initial settings of the parameters for spraying the fire extinguishing agent, as well as relevant information about the fire area and the fire scene; Define fuzzy sets and fuzzy variables, and build a fuzzy rule base to realize the construction of fuzzy logic controller; Set the parameters of the PID controller and determine the control target; The fuzzy logic controller is used to perform fuzzy reasoning on the current fire situation to obtain preliminary spraying parameters, and the preliminary spraying parameters are adjusted through the PID controller; According to the fire area and severity, determine the zone control valve that needs to be activated and adjust the spraying parameters of the corresponding zone.

[0018] Furthermore, fuzzy sets and fuzzy variables are defined, and a fuzzy rule base is constructed to realize the construction of a fuzzy logic controller, including: Determine the fuzzy variables that affect the spraying strategy, and define different fuzzy sets for each fuzzy variable, and define the membership function of each fuzzy set; Collect historical fire data and fire extinguishing experience data, construct fuzzy rules, and organize all constructed fuzzy rules into a library; Design fuzzy controller according to the selected fuzzy reasoning method and fuzzy rule base; Test the fuzzy controller and adjust the membership functions and fuzzy rules based on the test results.

[0019] Furthermore, the fuzzy logic controller is used to perform fuzzy reasoning on the current fire situation to obtain preliminary spraying parameters, and the preliminary spraying parameters are adjusted by the PID controller, including: Acquire fire scene data in real time and pre-process the acquired fire scene data; The pre-processed fire scene data is converted into fuzzy values, and fuzzy reasoning is performed using the fuzzy rule base to determine the preliminary spraying parameters according to the input fuzzy values; The preliminary spraying parameters obtained by fuzzy reasoning are used as the set points of the PID controller, and the parameters of the PID controller are adjusted according to the current spraying parameters and the set points; Activate the PID controller, adjust the spraying parameters according to the real-time feedback data, collect the feedback data after spraying, and input the feedback data into the fuzzy logic controller again for a new round of fuzzy reasoning; A closed-loop mechanism of fuzzy reasoning and PID control is formed to continuously iterate and optimize the spraying parameters.

[0020] Furthermore, according to the fire area and severity, determine the partition control valve that needs to be activated, and adjust the spraying parameters of the corresponding partitions including: Use fire detectors to detect the occurrence of fire and determine the location of the fire area. Based on the data collected by the fire detectors, assess the severity of the fire; Determine the zone control valves that need to be activated and the initial spraying parameters according to the location of the fire area and the severity of the fire; The initial spraying parameters are adjusted in real time according to the fuzzy controller and PID controller.

[0021] Furthermore, the formula of the membership function is: ; In the formula, μ A ( x ) represents a fuzzy set A For exact value x The degree of membership; x low and x high represent the lower and upper limits of the membership function respectively.

[0022] The beneficial effects of the present invention are: (1) The carport intelligent partition foam spray fire extinguishing early warning system provided by the present invention, through the combination of intelligent early warning module and thermal imaging monitoring module, enables the system to quickly detect and alarm in the early stage of fire, thereby reducing fire losses. Through the coordinated work of thermal imaging monitoring and spray parameter adjustment modules, the system can accurately locate the fire source and intelligently adjust the spray parameters, thereby improving the accuracy and efficiency of fire extinguishing.

[0023] (2) By combining thermal imaging technology with the image recognition capabilities of convolutional neural networks, the location and range of the fire source can be accurately located, providing accurate information for firefighting operations. Thermal imaging technology is not affected by changes in light and can effectively monitor both during the day and at night, improving the reliability of the system.

[0024] (3) The present invention combines fuzzy logic control and PID control algorithms to enable the system to dynamically adjust spraying parameters according to the real-time environment and realize intelligent control. The application of intelligent adjustment and zoning control technology reduces the waste of fire extinguishing agents and improves resource utilization efficiency.

[0025] (4) The remote monitoring and management functions provided by the data monitoring feedback module enable users to understand the system status at any time and improve management efficiency and response speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 It is a principle block diagram of a carport intelligent partition foam spray fire extinguishing early warning system according to an embodiment of the present invention.

[0028] In the figure: 1. Intelligent early warning module; 2. Thermal imaging monitoring module; 3. Spray parameter adjustment module; 4. Spray fire extinguishing module; 5. Data monitoring feedback module. DETAILED DESCRIPTION

[0029] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0030] According to an embodiment of the present invention, a carport intelligent partition foam spray fire extinguishing early warning system is provided.

[0031] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the embodiment of the present invention, the carport intelligent partition foam spray fire extinguishing warning system includes an intelligent warning module 1, a thermal imaging monitoring module 2, a spray parameter adjustment module 3, a spray fire extinguishing module 4 and a data monitoring feedback module 5. Among them, the intelligent warning module 1 and the thermal imaging monitoring module 2 are connected to the spray parameter adjustment module 3, the spray parameter adjustment module 3 is connected to the spray fire extinguishing module 4, and the spray fire extinguishing module 4 is connected to the data monitoring feedback module 5.

[0032] Intelligent early warning module 1 is used to monitor the environmental conditions of the carport in real time and use temperature detectors and wireless smoke sensors to detect signs of fire. When a fire is detected, an alarm device is triggered; By monitoring the environmental conditions of the carport in real time through heat detectors and wireless smoke sensors, signs of fire can be quickly detected in the early stages of a fire. When a fire is detected, the alarm device is immediately triggered to provide early warning and reduce fire losses. Combining temperature and smoke data improves the accuracy of fire detection and reduces false alarms and missed alarms.

[0033] The temperature detector uses an 85℃ linear temperature detector and is connected to the fire extinguishing controller; the linear temperature detector is laid on the top of the carport, and its length should be consistent with the length of the carport; when a fire occurs, the linear temperature detector should be able to transmit the signal to the fire extinguishing controller in time to start the foam water spray fire extinguishing. The carport intelligent partition foam spray fire extinguishing early warning system should adopt a linear temperature detector layout for one fire extinguishing partition. When the smoke sensor detects a certain concentration of smoke, the alarm device should be able to emit a buzzer in time and send an alarm signal to the cloud server management platform and the mobile WeChat applet. The mobile WeChat applet can view the on-site video and issue disposal instructions to the fire extinguishing controller.

[0034] The WeChat applet (fire disposal assistant) should be able to automatically receive data transmitted by the fire extinguishing controller, remotely control the on-site fire extinguishing system, and support one smartphone to monitor multiple fire-fighting places (carports, garages, fire safety places, etc.).

[0035] Smartphones should be able to share information sent by intelligent fire extinguishing systems, thermal imaging cameras, smoke alarms, fire detectors, water pressure sensors, liquid level sensors, fire host and other modules with the cloud server management platform through WeChat applet. Smartphones should be able to share fire extinguishing system status information data, operation and maintenance data, fault data, automatic display and alarm with the cloud server management platform in real time through WeChat applet, and can remotely view on-site videos in real time, support video playback, and remotely control the opening and closing of fire extinguishing devices.

[0036] When an early fire occurs on site and the automatic alarm device has not yet triggered the alarm, the smartphone should be able to activate the one-button alarm device through the WeChat applet, which can send an alarm message to the cloud server management platform while also issuing an audible and visual alarm.

[0037] WeChat mini-programs should have functions such as daily inspections, casual photography, equipment repair reporting, fire drills, fire training, fire facility inspections, fire prevention inspections, supervisory responses, fire maintenance, file inquiries, announcement push and personal information viewing.

[0038] The big data cloud service management platform should have an alarm map, which can display the fire-fighting site building, location, and all equipment that have been marked. After the fire-fighting system alarms, the homepage should be able to remind linkage in real time, and display it by alarm level; after clicking on the alarm information, you can check the status of fire-fighting facilities near the alarm location, and check the surrounding video surveillance, and the alarm prompt should be eliminated after the processing is completed.

[0039] The big data cloud service management platform should be able to view the registered firefighting unit information, and support account management and equipment management; it can view all the accounts, names, roles, telephone numbers, creation time, whether they are enabled, and manage the firefighting unit accounts. The big data cloud service management platform should be able to view the name, location, person in charge, telephone number, firefighting materials, etc. of the micro fire station. The big data cloud service management platform should have alarm query, casual photo, one-click post check, fire prevention inspection, equipment maintenance information, fire management regulations, supervision feedback, inspection, announcement viewing, etc.

[0040] In one embodiment, the environmental conditions of the carport are monitored in real time, and when a fire is detected, the alarm device is triggered, including: Obtain the collected data of each monitoring sensor; Setting a threshold value for each collected data, and comparing the collected data with the collected data threshold value; Based on the threshold judgment result, a fire determination is made, and an alarm signal is generated to trigger the alarm device.

[0041] For example, set the temperature threshold to 85°C. Set the smoke concentration threshold to 50 ppm.

[0042] Fire determination: If both the temperature and smoke concentration exceed the threshold, it is determined to be a fire risk.

[0043] In one embodiment, the alarm device includes an audible and visual alarm, a text message notification module, and an automatic emergency call module.

[0044] The sound and light alarm can quickly remind on-site personnel to evacuate urgently, reducing casualties. SMS notification and automatic emergency call ensure that remote management personnel and emergency service agencies can respond in time, improving the efficiency of fire emergency response. Through multiple alarm methods, it is ensured that information can be transmitted to different relevant parties, facilitating multi-party collaborative response to fire.

[0045] The thermal imaging monitoring module 2 is used to obtain the fire situation using thermal imaging technology, and based on the convolutional neural network, train and identify the fire image features, locate the fire source and trigger the alarm device.

[0046] Thermal imaging technology can accurately locate the source of fire and improve the accuracy of fire extinguishing. Fire image feature recognition based on convolutional neural network (CNN) can quickly and accurately detect fires and improve response speed. Thermal imaging technology is not affected by light and can effectively monitor during the day and at night, improving the reliability of the system.

[0047] In one embodiment, using thermal imaging technology to obtain fire conditions, and based on a convolutional neural network, training and identifying fire image features, locating the fire source and triggering an alarm includes: Initialize the convolutional neural network model and prepare the training dataset.

[0048] The convolutional neural network model is trained using the training data set. The model performance is comprehensively evaluated using multiple evaluation indicators such as accuracy, recall, and F1-score to ensure the accuracy and robustness of the model in fire feature recognition.

[0049] Use the trained convolutional neural network model to identify fire features from real-time collected and pre-processed thermal imaging images; Analyze the identification results to determine the location and scope of the fire source; for example, use multi-scale detection technology to identify and locate fire sources of different sizes to improve the comprehensiveness of detection. Generate a heatmap to visualize the location and scope of the fire source to facilitate subsequent firefighting operations.

[0050] The alarm device is triggered according to the location and scope of the fire source, and the alarm event is recorded.

[0051] Among them, the thermal imaging camera should be able to monitor the fire situation in real time. Once an open flame is detected, the thermal imaging camera should be able to trigger an alarm signal in time, and report it to the cloud server management platform and the mobile phone WeChat applet, and at the same time send an alarm signal to the fire extinguishing system controller to start fire extinguishing.

[0052] In one embodiment, preparing a training dataset includes: Collect raw thermal imaging data inside the carport.

[0053] The original thermal imaging data is subjected to preprocessing operations such as image denoising and contrast enhancement to obtain a preprocessed thermal imaging image.

[0054] Fire features are annotated in the preprocessed thermal imaging images to construct a training dataset.

[0055] The spray parameter adjustment module 3 is used to calculate the optimal spray parameters in real time based on fuzzy logic control and PID control algorithm.

[0056] In one embodiment, based on fuzzy logic control and PID control algorithm, real-time calculation of optimal spraying parameters includes: Obtain the initial settings of the parameters for spraying the fire extinguishing agent, including the status of the zone control valve, the type and number of spray heads, and relevant information of the fire area and fire scene, such as temperature and smoke concentration.

[0057] The spray head should be made of 304 stainless steel and used for the end-stage mixed spray of foam and water. According to the site conditions, a spray head should be set at every 1.3m-1.6m distance. Under normal working conditions, the spray coverage area of ​​the spray head on the ground should be ≥8m 2 .

[0058] The fire extinguishing pipeline of the carport intelligent partition foam spray fire extinguishing warning system should adopt compression type galvanized high carbon steel pipe. The length of the main pipeline should be within the range of 1.8m-2.2m. The length of the fire extinguishing pipeline of each fire extinguishing zone should not exceed 16m, and a maximum of 10 foam water spray heads can be installed.

[0059] The partition control valve should be a normally closed solenoid valve installed in front of each fire extinguishing partition. When the linear temperature detector activates the fire extinguishing system, the corresponding partition control valve should be able to open in time so that the foam fire extinguishing agent can be sprayed to the fire area. There is a one-to-one correspondence between the partition control valve and the linear temperature detector, and each fire extinguishing partition has a partition control valve.

[0060] Define fuzzy sets and fuzzy variables, such as spraying amount, spraying speed, etc., and build a fuzzy rule base to realize the construction of fuzzy logic controller.

[0061] Set the parameters of the PID controller, including the proportional (P), integral (I), and derivative (D) coefficients, and determine the control target, such as maintaining a constant spraying pressure or flow rate.

[0062] The fuzzy logic controller is used to perform fuzzy reasoning on the current fire situation to obtain preliminary spraying parameters, and the preliminary spraying parameters are adjusted through the PID controller to optimize the spraying parameters and achieve more precise control.

[0063] According to the fire area and severity, determine the zone control valve that needs to be activated, and adjust the spraying parameters of the corresponding zone to achieve targeted fire extinguishing.

[0064] In one embodiment, fuzzy sets and fuzzy variables are defined, and a fuzzy rule base is constructed to implement the construction of a fuzzy logic controller, including: Determine the fuzzy variables that affect the spraying strategy, such as fire intensity, smoke concentration, temperature, and the area of ​​the fire area, and define different fuzzy sets for each fuzzy variable. For example, the fire intensity can have three sets of "low", "medium", and "high", and define the membership function of each fuzzy set; Collect historical fire data and fire-fighting experience data to provide a basis for fuzzy rules, construct fuzzy rules, and organize all constructed fuzzy rules into a library for the convenience of fuzzy inference engine; Design a fuzzy controller based on the selected fuzzy reasoning method and fuzzy rule base, such as the Mamdani or Sugeno model, which can accept input variables and output control instructions; Test the fuzzy controller to ensure that the rule base can generate reasonable control instructions, and adjust the membership functions and fuzzy rules according to the test results to optimize the performance of the fuzzy controller.

[0065] In one embodiment, a fuzzy logic controller is used to perform fuzzy reasoning on the current fire situation to obtain preliminary spraying parameters, and the preliminary spraying parameters are adjusted by a PID controller including: Obtain fire scene data in real time, including temperature, smoke density, fire source location and size, and pre-process the acquired fire scene data; Convert the pre-processed fire scene data into fuzzy values, such as converting the temperature into fuzzy sets such as "low", "medium", and "high"; use the fuzzy rule base to perform fuzzy reasoning and determine the preliminary spraying parameters based on the input fuzzy values; The preliminary spraying parameters obtained by fuzzy reasoning are used as the set points of the PID controller, and the proportional, integral and differential parameters of the PID controller are adjusted according to the current spraying parameters and the set points; Activate the PID controller, adjust the spraying parameters according to the real-time feedback data to get close to the set point, collect the feedback data such as temperature and smoke concentration after spraying, and input the feedback data into the fuzzy logic controller again for a new round of fuzzy reasoning; A closed-loop mechanism of fuzzy reasoning and PID control is formed to continuously iterate and optimize the spraying parameters.

[0066] In one embodiment, according to the fire area and severity, determining the zone control valve to be activated and adjusting the spraying parameters of the corresponding zone includes: Use fire detectors to detect the occurrence of fire and determine the location of the fire area. According to the data collected by the fire detectors, such as temperature and smoke concentration, the severity of the fire is assessed; Determine the zone control valves that need to be activated and the initial spraying parameters according to the location of the fire area and the severity of the fire; The initial spraying parameters are adjusted in real time according to the fuzzy controller and PID controller.

[0067] In one embodiment, the formula of the membership function is: ; In the formula, μ A ( x ) represents a fuzzy set A For exact value x The degree of membership (or the value of the membership function) of x low and x high represent the lower and upper limits of the membership function respectively.

[0068] The spray fire extinguishing module 4 is used to spray the fire extinguishing agent to the fire area through the partition control valve and the foam water spray head when a fire occurs, so as to achieve rapid fire extinguishing.

[0069] In addition, the fire extinguishing system host should provide stable power to deliver foam fire extinguishing agent to the fire extinguishing system. When the foam stock agent is sprayed, it should be able to stop automatically. Use 20 liters of 1% water-forming protein foam stock and place it in the foam barrel of the fire extinguishing system host. When spraying is required, the proportional control valve controls the flow and mixes it with water to form foam. The shell of the fire extinguishing system host and controller should be made of 1.5mm thick cold-rolled plate. The fire extinguishing system controller should be able to collect fire signals sent by various sensors and automatically start the host partition work; when the fire extinguishing system is automatically started, the sound and light alarm should be able to start synchronously and automatically send signals to the mobile phone WeChat applet and cloud server management platform. The fire extinguishing system controller should have automatic, manual and emergency mechanical manual start modes. Under normal working conditions, it should be able to monitor the working conditions of various parts of the fire extinguishing system in real time and send information to the cloud server management platform and mobile phone WeChat applet in real time. When the fire extinguishing system controller receives a fire signal, the response time of the automatic control fire extinguishing system should be ≤60s when the system pipeline is filled with water and the flow rate is 8L / s.

[0070] Under normal working conditions, the fire extinguishing system controller should be able to monitor the working conditions of water pressure, liquid level, temperature detectors, smoke sensors, thermal imaging cameras, etc. in real time, and send information to the cloud server management platform and WeChat applet on mobile phones in real time. The shell protection level of the fire extinguishing system host and controller should comply with IP54. (Note: If installed indoors, the requirements can be lowered, for example: IP40).

[0071] The main engine and controller of the fire extinguishing system are powered on and operated for 4 hours in a low temperature test chamber at -20℃±2℃. During the test, the main engine and controller of the system should work normally. The main engine and controller of the fire extinguishing system are powered on and operated for 4 hours in a high temperature test chamber at +55℃±2℃. During the test, the main engine and controller of the system should work normally. The main engine and controller of the fire extinguishing system are powered on and operated for 6 hours in a constant damp heat test chamber with a temperature of +40℃±2℃ and a relative humidity of 93%±2%. During the test, the main engine and controller of the system should work normally.

[0072] In addition, the fire extinguishing system host and controller should have leakage protection function and lightning protection function. The maximum resistance from the ground terminal of the fire extinguishing system host and controller to the protected device should be ≤0.1Ω. The insulation resistance between the power input terminal and the ground terminal of the fire extinguishing system host and controller should be ≥1MΩ. A test voltage of 50Hz, 1500V is applied between the power input terminal and the ground terminal of the fire extinguishing system host and controller for 1min. During the test, no breakdown discharge should occur.

[0073] The water is placed in the water storage device. The water bucket of the water storage device should be made of thickened PE plastic material. During the installation and construction of the water storage device, the outside should be wrapped with thickened waterproof and heat-insulating materials to prevent the water in the bucket from freezing. The water bucket of the water storage device should be able to withstand a pressure of 0.35MPa to prevent the water storage device from rupturing.

[0074] When a fire occurs, the spray fire extinguishing module 4 can immediately spray the fire extinguishing agent to the fire area to achieve rapid fire extinguishing. Through the partition control valve and the foam water spray head, different areas can be independently controlled to improve the flexibility and effectiveness of fire extinguishing. The foam spray fire extinguishing technology can quickly cover the fire source, isolate the air, suppress the spread of the fire, and improve the efficiency of fire extinguishing.

[0075] The data monitoring feedback module 5 is used to obtain real-time monitoring parameters (such as key parameters such as water pressure and liquid level) and feed back the monitoring parameters to the cloud server platform and mobile application platform (such as WeChat applet) to achieve remote monitoring and management.

[0076] The normal working atmospheric conditions of the carport intelligent partition foam spray fire extinguishing early warning system should meet the following requirements: a) Ambient temperature: -20℃ to +55℃; relative humidity: 5%-93%; b) Atmospheric pressure: 86kPa-106kPa.

[0077] The surrounding environment should meet the following requirements: a) No explosion hazard, no corrosive gas and conductive dust, no violent vibration source, etc.; b) There are reliable grounding facilities and they comply with the relevant standards; c) Strong electromagnetic interference is not allowed.

[0078] The working power supply should meet the following requirements: a) The AC power supply voltage is single-phase 220V, and the voltage tolerance is -10% to +10%; b) The AC power frequency is 50Hz / 60Hz, with an allowable deviation of ±0.5Hz; c) The AC power waveform is a sinusoidal wave, and the waveform distortion is no more than 5%.

[0079] In summary, the carport intelligent partition foam spray fire extinguishing early warning system provided by the present invention, through the combination of intelligent early warning module and thermal imaging monitoring module, enables the system to quickly detect and alarm in the early stage of fire, thereby reducing fire losses. Through the collaborative work of thermal imaging monitoring and spray parameter adjustment module, the system can accurately locate the fire source and intelligently adjust the spraying parameters to improve the accuracy and efficiency of fire extinguishing. By combining thermal imaging technology with the image recognition ability of convolutional neural network, the location and range of the fire source can be accurately located to provide accurate information for fire extinguishing operations. Thermal imaging technology is not affected by light changes and can be effectively monitored during the day and at night to improve the reliability of the system. The present invention combines fuzzy logic control and PID control algorithm to enable the system to dynamically adjust the spraying parameters according to the real-time environment and realize intelligent control. The application of intelligent adjustment and partition control technology reduces the waste of fire extinguishing agent and improves resource utilization efficiency. The remote monitoring and management functions provided by the data monitoring feedback module enable users to understand the system status at any time, improve management efficiency and response speed.

[0080] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. The carport intelligent partition foam spray fire extinguishing early warning system is characterized by: The system includes an intelligent early warning module, a thermal imaging monitoring module, a spray parameter adjustment module, a spray fire extinguishing module and a data monitoring feedback module; Among them, the intelligent early warning module and the thermal imaging monitoring module are connected to the spray parameter adjustment module, the spray parameter adjustment module is connected to the spray fire extinguishing module, and the spray fire extinguishing module is connected to the data monitoring feedback module; The intelligent early warning module is used to monitor the environmental conditions of the carport in real time and trigger the alarm device when a fire is detected; The thermal imaging monitoring module is used to obtain fire conditions using thermal imaging technology, and based on a convolutional neural network, train and identify fire image features, locate the fire source and trigger an alarm device; The spray parameter adjustment module is used to calculate the optimal spray parameters in real time based on fuzzy logic control and PID control algorithm; The spray fire extinguishing module is used to spray the fire extinguishing agent to the fire area when a fire occurs; The data monitoring feedback module is used to obtain real-time monitoring parameters and feed back the monitoring parameters to the cloud server platform and the mobile application platform to achieve remote monitoring and management.

2. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 1 is characterized in that: The real-time monitoring of the environmental conditions of the carport and triggering of the alarm device when a fire is detected include: Obtain the collected data of each monitoring sensor; Setting a threshold value for each collected data, and comparing the collected data with the collected data threshold value; Based on the threshold judgment result, a fire determination is made, and an alarm signal is generated to trigger the alarm device.

3. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 2 is characterized in that: The alarm device includes an audible and visual alarm, a text message notification module and an automatic emergency call dialing module.

4. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 1 is characterized in that: The method of using thermal imaging technology to obtain fire conditions, and based on a convolutional neural network, training and identifying fire image features, locating the fire source and triggering an alarm includes: Initialize the convolutional neural network model and prepare the training data set; Train the convolutional neural network model using the training dataset; Use the trained convolutional neural network model to identify fire features from real-time collected and pre-processed thermal imaging images; Analyze the identification results to determine the location and scope of the fire source; The alarm device is triggered according to the location and scope of the fire source, and the alarm event is recorded.

5. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 4 is characterized in that: The preparing of the training data set comprises: Collect raw thermal imaging data in the carport; Performing a preprocessing operation on the original thermal imaging data to obtain a preprocessed thermal imaging image; Fire features are annotated in the preprocessed thermal imaging images to construct a training dataset.

6. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 1 is characterized in that: The real-time calculation of the optimal spraying parameters based on fuzzy logic control and PID control algorithm includes: Obtain the initial settings of the parameters for spraying the fire extinguishing agent, as well as relevant information about the fire area and the fire scene; Define fuzzy sets and fuzzy variables, and build a fuzzy rule base to realize the construction of fuzzy logic controller; Set the parameters of the PID controller and determine the control target; The fuzzy logic controller is used to perform fuzzy reasoning on the current fire situation to obtain preliminary spraying parameters, and the preliminary spraying parameters are adjusted through the PID controller; According to the fire area and severity, determine the zone control valve that needs to be activated and adjust the spraying parameters of the corresponding zone.

7. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 6 is characterized in that: The definition of fuzzy sets and fuzzy variables, and the construction of a fuzzy rule base to realize the construction of a fuzzy logic controller include: Determine the fuzzy variables that affect the spraying strategy, and define different fuzzy sets for each fuzzy variable, and define the membership function of each fuzzy set; Collect historical fire data and fire extinguishing experience data, construct fuzzy rules, and organize all constructed fuzzy rules into a library; Design fuzzy controller according to the selected fuzzy reasoning method and fuzzy rule base; Test the fuzzy controller and adjust the membership functions and fuzzy rules based on the test results.

8. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 7 is characterized in that: The method of using a fuzzy logic controller to perform fuzzy reasoning on the current fire situation to obtain preliminary spraying parameters, and adjusting the preliminary spraying parameters through a PID controller includes: Acquire fire scene data in real time and pre-process the acquired fire scene data; The pre-processed fire scene data is converted into fuzzy values, and fuzzy reasoning is performed using the fuzzy rule base to determine the preliminary spraying parameters according to the input fuzzy values; The preliminary spraying parameters obtained by fuzzy reasoning are used as the set points of the PID controller, and the parameters of the PID controller are adjusted according to the current spraying parameters and the set points; Activate the PID controller, adjust the spraying parameters according to the real-time feedback data, collect the feedback data after spraying, and input the feedback data into the fuzzy logic controller again for a new round of fuzzy reasoning; A closed-loop mechanism of fuzzy reasoning and PID control is formed to continuously iterate and optimize the spraying parameters.

9. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 8 is characterized in that: Determining the partition control valve to be activated according to the fire area and severity, and adjusting the spraying parameters of the corresponding partitions includes: Use fire detectors to detect the occurrence of fire and determine the location of the fire area. Based on the data collected by the fire detectors, assess the severity of the fire; Determine the zone control valves that need to be activated and the initial spraying parameters according to the location of the fire area and the severity of the fire; The initial spraying parameters are adjusted in real time according to the fuzzy controller and PID controller.

10. The carport intelligent partition foam spray fire extinguishing early warning system according to claim 9 is characterized in that: The formula of the membership function is: ； In the formula, μ A ( x ) represents a fuzzy set A For exact value x The degree of membership; x low and x high represent the lower and upper limits of the membership function respectively.

Images