Intelligent fire extinguishing system based on neural network

Abstract

The invention discloses an intelligent fire fighting system based on a neural network. The AGV fire fighting system comprises an AGV fire fighting truck, the AGV fire fighting truck comprises an AGV platform and a fire extinguishing device, the fire extinguishing device is fixedly connected to the top of the AGV platform, and the fire extinguishing device comprises a supporting column, a guide pipe and a rotating nozzle; and the fire source sensing system is used for detecting whether a fire source exists in the warehouse area and positioning the fire source. The data processing module is used for processing fire-fighting data, and the fire-fighting data comprises data of a smoke sensor, an infrared sensor and a visual sensor; the AGV execution system is used for sending a control command to the AGV fire fighting truck according to a preset threshold value; and the system module is used for sending the fire-fighting data to the AGV execution system and instructing the AGV execution system to execute a fire extinguishing program. According to the invention, the problems of incapability of accurately extinguishing fire and high risk of manual fire extinguishing in industrial fire fighting in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire fighting and rescue, and in particular to an intelligent fire fighting system based on a neural network. Background Art

[0002] Currently, there is a traditional fixed sprinkler system in industrial fire fighting. The coverage area is fixed. When there is a local fire alarm, the fire sprinklers in the entire room and area are opened, resulting in problems such as false alarms and large coverage areas of the fire sprinklers. After the fire sprinklers are opened, the entire area is wet, causing losses to goods without a fire source; in case of a fire alarm, manual response is required, and the risk coefficient for manual firefighters to enter a high-risk environment is high.

[0003] Therefore, in the related art, the technical problems of inaccurate fire extinguishing during industrial fire fighting and high danger of manual fire extinguishing have not been effectively solved. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent fire fighting system based on a neural network to solve the problems of inaccurate fire extinguishing during industrial fire fighting and high danger of manual fire extinguishing in the related art.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] An intelligent fire fighting system based on a neural network, comprising an AGV fire truck, the AGV fire truck includes an AGV platform and a fire extinguishing device, the fire extinguishing device is fixedly connected to the top of the AGV platform, and the fire extinguishing device includes a support column, a conduit and a rotary nozzle; a fire source sensing system for detecting whether there is a fire source in the warehouse area and locating the fire source; the fire source sensing system includes a smoke sensor, an infrared sensor and a vision sensor, the smoke sensor is used to monitor the concentration of smoke particles in the industrial scene, and the infrared sensor is used to receive the infrared radiation emitted by the object and the fire source; a data processing module for processing fire fighting data, and the fire fighting data includes the data of the smoke sensor, the infrared sensor and the vision sensor; an AGV execution system for sending a control command to the AGV fire truck according to a preset threshold, controlling the AGV group to cooperate in division of labor, and real-time planning and adjusting the movement route of the AGV fire truck, wherein the AGV group includes at least one AGV fire truck; a system module for sending the fire fighting data to the AGV execution system to instruct the AGV execution system to execute the fire extinguishing procedure.

[0007] Further arranged as: an obstacle avoidance radar is installed on each side of the AGV platform; a base and a neural network controller are installed on the AGV platform, a motor is arranged on the base; a material box is installed at the bottom of the AGV platform, the material box is connected to the conduit through a hose, and a pressure signal sensor is installed in the material box.

[0008] Further set as: The fire extinguishing device is installed on the base through a support column, and the support column is perpendicular to the upper surface of the AGV platform.

[0009] Further set as: The conduit is fixedly connected to the support column, and the conduit is parallel to the support column; rotating nozzles are evenly arranged on the conduit, and the rotating nozzles are parallel to the upper surface of the AGV platform.

[0010] Further set as: The rotating nozzle is fixedly connected to the conduit through a nozzle control valve.

[0011] Further set as: A detection and communication unit is fixedly connected to the top of the support column.

[0012] Further set as: When the infrared sensor detects that the surface temperature of the area reaches 65±5°C, the data processing module identifies the position of the open fire according to the data of the vision sensor, locates the heat radiation center and range according to the temperature gradient in the data of the infrared sensor, calculates the size of the fire and determines the position of the fire source.

[0013] Further set as: The data model for the AGV execution system to select the AGV fire truck to perform the fire fighting task is , where is the optimal AGV fire truck, is the number of the AGV fire truck that can perform the out-of-warehouse task, is the capacity of the fire extinguishing medium carried by the AGV fire truck that can perform the out-of-warehouse task, represents the average moving speed that the AGV fire truck can reach, represents the remaining battery power coefficient of the AGV fire truck, represents from node to node the distance.

[0014] Further set as: Adjust the number of rotating nozzles, , where is the initial value of the number of rotating nozzles, is the fire source area, is the central temperature of the fire source point, is the weight coefficient of the fire source area, is the weight coefficient of the central temperature of the fire source point, is the characteristic coefficient of the fire extinguishing medium, is the quantity coefficient.

[0015] Further set as: The infrared sensor continuously monitors the temperature of the fire source area. When the temperature in the fire source area drops below 50°C within ten minutes, the neural network controller guides the AGV fire truck to leave the fire scene, generates a fire extinguishing log and ends the fire extinguishing process.

[0016] Compared with the prior art, the beneficial technical effects of the present invention are as follows:

[0017] The obstacle avoidance radar is installed on both sides of the AGV platform to monitor the surrounding environment in real time, effectively avoid obstacles, ensure driving safety, and ensure the smooth progress of the fire extinguishing task. The neural network controller analyzes and processes the operation data, accurately controls the vehicle driving parameters, realizes intelligent and adaptive operation, and improves the efficiency of multi-vehicle collaborative operation. In terms of the fire extinguishing device, the support column is vertically installed on the base to ensure stability and reasonable distribution of the center of gravity. The conduit is fixedly arranged in parallel with the support column to ensure the stable flow of the fire extinguishing agent. The rotary nozzles are evenly arranged and parallel to the upper surface of the platform, and can spray the fire extinguishing agent horizontally and evenly to cover a large area of fire sources. The nozzle control valve accurately controls the working state of the rotary nozzles to achieve accurate fire extinguishing.

[0018] The data processing module has outstanding technical effects. By cooperating with the infrared sensor and the vision sensor, the fire source is accurately identified, the position of the fire source is located, and the size of the fire is estimated, providing an accurate decision-making basis for the AGV execution system and greatly improving the fire fighting efficiency. In addition, the infrared sensor continuously monitors the temperature in the fire source area to provide a basis for judging the fire extinguishing effect. When the temperature reaches the standard, the neural network controller guides the AGV fire truck to evacuate the fire scene, realizes automatic process control, and generates a fire extinguishing log for subsequent traceability and analysis, helping to improve the overall performance of the fire fighting system. The pressure signal sensor in the material box monitors the remaining amount of the fire extinguishing agent in real time to ensure the continuous supply of the fire extinguishing agent during the fire extinguishing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a schematic diagram of an intelligent fire fighting system based on a neural network;

[0021] Figure 2 It is a schematic diagram of the fire fighting process of the fire fighting system of the present invention;

[0022] Figure 3 It is a schematic diagram of a fire truck of an intelligent fire fighting system based on a neural network.

[0023] Reference numerals: 1, AGV platform; 2, material box; 3, neural network controller; 4, obstacle avoidance radar; 5, base; 6, support column; 7, detection and communication unit; 8, conduit; 9, rotary nozzle; 10, nozzle control valve. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work shall fall within the protection scope of the present invention.

[0025] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0026] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] Embodiment

[0028] Referring to Figure 1-2 , an intelligent fire-fighting system based on a neural network disclosed in the present invention includes: an AGV fire truck, which includes an AGV platform 1 and a fire-extinguishing device. The fire-extinguishing device is fixedly connected to the top of the AGV platform 1. The fire-extinguishing device includes a support column 6, a conduit 8, and a rotating nozzle 9; a fire source perception system for detecting whether there is a fire source in the warehouse area and locating the fire source. The fire source perception system includes a smoke sensor, an infrared sensor, and a vision sensor. The smoke sensor is used to monitor the concentration of smoke particles in the industrial scene, and the infrared sensor is used to receive the infrared radiation emitted by the object and the fire source; a data processing module for processing fire-fighting data, where the fire-fighting data includes the data of the smoke sensor, the infrared sensor, and the vision sensor; an AGV execution system for sending control commands to the AGV fire truck according to a preset threshold, controlling the AGV group to cooperate in division of labor, and real-time planning and adjusting the movement route of the AGV fire truck. Among them, the AGV group includes at least one AGV fire truck; a system module for sending the fire-fighting data to the AGV execution system and instructing the AGV execution system to execute the fire-extinguishing procedure.

[0029] Specifically, the fire source perception system detects the existence of a fire source in the warehouse area and locates the position of the fire source, and transmits the data detected by the infrared sensor, the vision sensor, and the smoke sensor to the data processing module. After processing the data, the data processing module sends the data to the AGV execution system through the collaborative control module. The AGV execution system controls the division of labor and cooperation of the AGV group, plans the movement route of the AGV fire truck in real time and adjusts the path, and sends control commands to the AGV fire truck according to the preset threshold to improve the fire fighting efficiency. After the AGV fire truck arrives at the position, the vision sensor and the infrared sensor carried by the rotatable detection and communication unit 7 accurately re-locate the fire source, and extinguish the fire by controlling one or more rotary nozzles 9 and the fire nozzle control valve 10. The material box 2 is filled with a flame retardant. The flame retardant is conveyed into the conduit 8 through a hose, and the fire nozzle control valve 10 on the conduit 8 controls the rotary nozzle 9 to spray out the flame retardant.

[0030] In addition, the positioning of the AGV fire truck is realized by using the UWB (Ultra Wide Band) wireless signal communication technology. A wireless base station is installed in the application site, and a wireless communication unit is installed in the detection and communication unit 7 of the AGV fire truck. The relative position of the AGV fire truck is calculated according to the time difference of the wireless signal reaching different wireless base stations.

[0031] Refer to Figure 3 , a collision avoidance radar 4 is installed on each side of the AGV platform 1; a base 5 and a neural network controller 3 are installed on the AGV platform 1, and a motor is arranged on the base 5; a material box 2 is installed at the bottom of the AGV platform 1, and the material box 2 is connected to the conduit 8 through a hose, and a pressure signal sensor is installed in the material box 2.

[0032] Specifically, the motor on the base 5 of the support column 6 can drive the support column 6 to rotate 360 degrees to adjust the angle. A pressure signal sensor is installed in the material box 2 to detect the remaining amount of the combustion-supporting agent. The collision avoidance radars 4 installed on both sides of the AGV platform 1 can monitor the environmental conditions around the AGV platform 1 in real time. When an obstacle is detected ahead, the signal is transmitted to the control system in time, so that the AGV fire truck can automatically stop or adjust the driving direction, avoiding the occurrence of collision accidents, ensuring the safety and reliability of the vehicle during driving, especially in a complex warehouse environment, it can effectively prevent collisions with goods, shelves or other obstacles, and ensure that the fire extinguishing task can be carried out smoothly. The neural network controller 3 installed on the AGV platform 1 can analyze and process various operation data of the AGV fire truck, and based on the preset algorithms and models, realize the precise control of parameters such as the driving speed and steering angle of the vehicle. It can automatically adjust the operation state of the AGV fire truck according to different working conditions and task requirements, improve the intelligent level and adaptive ability of the vehicle, and enable it to complete the fire extinguishing task more flexibly and efficiently.

[0033] Furthermore, the fire extinguishing device is installed on the base 5 through the support column 6, and the support column 6 is perpendicular to the upper surface of the AGV platform 1. The conduit 8 is fixedly connected to the support column 6, and the conduit 8 is parallel to the support column 6; rotating nozzles 9 are arranged uniformly on the conduit 8, and the rotating nozzles 9 are parallel to the upper surface of the AGV platform 1. The rotating nozzles 9 are fixedly connected to the conduit 8 through nozzle control valves 10.

[0034] Specifically, the fire extinguishing device is vertically installed on the base 5 through the support column 6, so that the fire extinguishing device is at a suitable height and position, which can not only ensure a good spraying range and angle of the rotating nozzles 9, but also ensure the stability of the entire fire extinguishing device. The rotating nozzles 9 are arranged uniformly on the conduit 8 and the rotating nozzles 9 are parallel to the upper surface of the AGV platform. The uniform arrangement can make the fire extinguishing agent be sprayed evenly in a certain area, cover a larger area and improve the fire extinguishing efficiency. The rotating nozzles 9 are fixedly connected to the conduit 8 through nozzle control valves 10, and the nozzle control valves 10 can accurately control the opening, closing and spraying flow rate of each rotating nozzle 9. In this way, according to the actual situation such as the size, position and fire intensity of the fire source, the working state of the rotating nozzles 9 can be flexibly adjusted to achieve accurate fire extinguishing.

[0035] Furthermore, a detection and communication unit 7 is fixedly connected to the top of the support column 6. The detection and communication unit 7 rotates 360 degrees along the support column 6 through its own motor, and an infrared sensor, a vision sensor and a wireless communication unit are installed on the rotatable detection and communication unit 7.

[0036] Furthermore, the data processing module is used to when the infrared sensor detects that the surface temperature of the area reaches 65±5°C, the data processing module identifies the position of the open fire according to the data of the vision sensor, locates the heat radiation center and range according to the temperature gradient in the data of the infrared sensor, calculates the size of the fire and judges the position of the fire source.

[0037] Specifically, in a complex industrial scenario, it is difficult to quickly and accurately detect a fire source simply by relying on manual labor or a single sensor. This module utilizes the sensitive characteristics of the infrared sensor to temperature and the intuitive recognition ability of the vision sensor to open fire, and can quickly intervene when the temperature is abnormal, accurately judge the position of the open fire, the heat radiation center and range, effectively solve the problem of the accuracy of fire source detection, and avoid misjudgment or missed judgment caused by factors such as environmental interference. Knowing the specific position of the fire source accurately is crucial for fire extinguishing operations. The data processing module comprehensively analyzes the temperature gradient data of the infrared sensor and the data of the vision sensor, and can accurately calculate the position of the fire source, providing key information for the accurate positioning and path planning of the AGV fire truck, solving the problem of quickly locating the fire source in complex environments such as large warehouses, and enabling the fire truck to reach the fire extinguishing location efficiently.

[0038] Further: The data model selected by the AGV execution system for the AGV fire truck to perform fire-fighting tasks is , where is the optimal AGV fire truck, is the number of the AGV fire truck that can perform the outbound task, is the capacity of the fire extinguishing medium carried by the AGV fire truck that can perform the outbound task, represents the average moving speed that the AGV fire truck can reach, represents the remaining battery power coefficient of the AGV fire truck, represents from node to node distance.

[0039] Further: Adjust the number of the rotating nozzles 9, , where is the initial value of the number of the rotating nozzles 9, is the fire source area, is the central temperature of the fire source point, is the weight coefficient of the fire source area, is the weight coefficient of the central temperature of the fire source point, is the characteristic coefficient of the fire extinguishing medium, is the quantity coefficient.

[0040] Further: The infrared sensor continuously monitors the temperature of the fire source area. When the temperature in the fire source area drops below 50°C within ten minutes, the neural network controller 3 guides the AGV fire truck to leave the fire scene, generates a fire-fighting log, and ends the fire-fighting process.

[0041] Specifically, by continuously monitoring the temperature of the fire source area through the infrared sensor, the effect of the fire-fighting operation can be understood in real time. Taking the temperature dropping below 50°C within ten minutes as the judgment standard provides a clear evacuation signal for the AGV fire truck, solves the problems of how to determine that the fire has been effectively controlled and when it is safe to evacuate the fire scene, and avoids the impact of premature or late evacuation on the fire-fighting work and equipment safety. Generating a fire-fighting log helps record the key information of the entire fire-fighting process, including temperature changes, fire-fighting time, equipment operation status, etc. This solves the problems of information recording and traceability in the fire-fighting process, provides important data support for subsequent fire cause analysis, equipment performance evaluation, and emergency plan optimization, and helps continuously improve the reliability and effectiveness of the fire-fighting system.

[0042] The working principle and beneficial effects of the present invention are:

[0043] The use of AGV fire trucks can achieve precise positioning and fire extinguishing, avoiding the problems of the current traditional fixed sprinkler system in industrial fire protection, which has a fixed coverage area. When a local fire alarm occurs, the fire sprinklers in the entire room and area are turned on, resulting in false alarms, and the fire sprinklers have a large coverage area, and the entire area is wetted after opening, causing the loss of goods without fire sources. The use of AGV fire trucks during fire extinguishing solves the current problem of manual response to fire alarms and the high risk factor of manual firefighters entering high-risk environments. The intelligent fire source perception system of fire trucks combines infrared sensors, visual sensors, and smoke sensors to perceive the fire source in real time, and deploys AGV fire trucks to extinguish fires through the AGV execution system in real time, eliminating fire accidents in the bud.

[0044] The obstacle avoidance radar 4 is installed on both sides of the AGV platform to monitor the surrounding environment in real time, effectively avoid obstacles, ensure driving safety, and ensure the smooth implementation of fire extinguishing tasks. The neural network controller 3 analyzes and processes the operating data, accurately controls the vehicle driving parameters, realizes intelligent and adaptive operation, and improves the efficiency of multi-vehicle collaborative operations. In terms of the fire extinguishing device, the support column 6 is vertically installed on the base 5 to ensure stability and reasonable distribution of the center of gravity. The conduit 8 is fixed parallel to the support column 6 to ensure the stable flow of the fire extinguishing agent. The rotating nozzles 9 are evenly arranged and parallel to the upper surface of the platform, and can spray the fire extinguishing agent horizontally and evenly to cover a large area of ​​fire sources. The nozzle control valve 10 accurately controls the working state of the rotating nozzle 9 to achieve precise fire extinguishing.

[0045] The technical effect of the data processing module is outstanding. Through the cooperation of infrared sensors and visual sensors, the fire source can be accurately identified, the location of the fire source can be located, and the size of the fire can be estimated, providing an accurate decision-making basis for the AGV execution system, greatly improving the efficiency of fire fighting. In addition, the infrared sensor continuously monitors the temperature of the fire source area to provide a basis for judging the fire extinguishing effect. When the temperature reaches the standard, the neural network controller 3 guides the AGV fire truck to evacuate the fire scene, realizes automated process control, and generates a fire extinguishing log for subsequent tracing and analysis, helping to improve the overall performance of the fire fighting system. The pressure signal sensor in the material box 2 monitors the remaining amount of fire extinguishing agent in real time to ensure the continuous supply of fire extinguishing agent during the fire extinguishing process.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent fire protection system based on a neural network, characterized in that, Including: An AGV fire truck, which includes an AGV platform (1) and a fire extinguishing device. The fire extinguishing device is fixedly connected to the top of the AGV platform (1), and the fire extinguishing device includes a support column (6), a conduit (8), and a rotary nozzle (9); A fire source sensing system for detecting whether there is a fire source in the warehouse area and locating the fire source; The fire source sensing system includes a smoke sensor, an infrared sensor, and a vision sensor. The smoke sensor is used to monitor the concentration of smoke particles in the industrial scene, and the infrared sensor is used to receive the infrared radiation emitted by objects and the fire source; A data processing module for processing fire fighting data, where the fire fighting data includes the data of the smoke sensor, the infrared sensor, and the vision sensor; An AGV execution system for sending control commands to the AGV fire truck according to preset thresholds, controlling the AGV group to cooperate in division of labor, and real-time planning and adjusting the movement route of the AGV fire truck. Among them, the AGV group includes at least one AGV fire truck; The system module is used to send the fire fighting data to the AGV execution system to instruct the AGV execution system to execute the fire extinguishing procedure.

2. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: One obstacle avoidance radar (4) is installed on each side of the AGV platform (1); A base (5) and a neural network controller (3) are installed on the AGV platform (1), and a motor is arranged on the base (5); A material box (2) is installed at the bottom of the AGV platform (1). The material box (2) is connected to the conduit (8) through a hose, and a pressure signal sensor is installed in the material box (2).

3. The intelligent fire protection system based on a neural network according to claim 2, characterized in that, Including: The fire extinguishing device is installed on the base (5) through the support column (6), and the support column (6) is perpendicular to the upper surface of the AGV platform (1).

4. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: The conduit (8) is fixedly connected to the support column (6), and the conduit (8) is parallel to the support column (6); The rotary nozzles (9) are evenly arranged on the conduit (8), and the rotary nozzles (9) are parallel to the upper surface of the AGV platform (1).

5. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: The rotary nozzle (9) is fixedly connected to the conduit (8) through a nozzle control valve (10).

6. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: A detection and communication unit (7) is fixedly connected to the top of the support column (6).

7. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: When the infrared sensor detects that the surface temperature of the area reaches 65 ± 5 °C, the data processing module identifies the position of the open fire according to the data of the vision sensor, locates the heat radiation center and range according to the temperature gradient in the data of the infrared sensor, calculates the size of the fire and judges the position of the fire source.

8. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: The data model selected by the AGV execution system for the AGV fire truck to perform fire fighting tasks is , where is the optimal AGV fire truck, is the number of the AGV fire truck that can perform the outbound task, is the capacity of the fire extinguishing medium carried by the AGV fire truck that can perform the outbound task, represents the average moving speed that the AGV fire truck can reach, represents the remaining battery power coefficient of the AGV fire truck, represents the distance from node to node .

9. The intelligent fire protection system based on a neural network according to claim 1, characterized in that, Including: Adjust the number of the rotary nozzles (9), , wherein, is the initial value of the number of the rotary nozzles (9), is the fire source area, is the center temperature of the fire source point, is the weight coefficient of the fire source area, is the weight coefficient of the center temperature of the fire source point, is the characteristic coefficient of the fire extinguishing medium, is the quantity coefficient.

10. An intelligent fire-fighting system based on a neural network according to claim 2, characterized in that, Including: The infrared sensor continuously monitors the temperature of the fire source area. When the temperature of the fire source area drops below 50 °C within ten minutes, the neural network controller (3) guides the AGV fire truck to leave the fire scene, generates a fire extinguishing log and ends the fire extinguishing process.

Images