Automatic fire extinguishing robot for electronic room and control method of automatic fire extinguishing robot

Abstract

The invention discloses an automatic fire extinguishing robot for an electronic room and a control method thereof, relates to the technical field of fire safety, and aims to solve the problems that smoldering fire identification of the electronic room lags behind and cannot go deep into a cabinet gap for fire extinguishing in the prior art. The system specifically comprises a multi-dimensional data acquisition and monitoring module, an intelligent analysis and planning module, an action execution and data interaction module, a driving module and a power supply module. The fire behavior grade is judged through a multi-sensor fusion fire recognition algorithm, positioning is conducted through an anti-interference SLAM navigation algorithm, a mechanical arm obstacle avoidance path is generated through a three-dimensional path planning algorithm, fire extinguishing agent parameters are determined through a fire extinguishing decision model, meanwhile, fire behavior data are uploaded, and remote instructions are received. According to the method, early fire recognition and fire extinguishing are realized, and the personnel safety risk is reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of fire safety, and particularly relates to an automatic fire extinguishing robot for an electronic room and a control method thereof. BACKGROUND

[0002] At present, the fire safety of an electronic room (such as an electronic equipment room of a power plant and a power distribution room) as a concentrated area of precision electronic equipment still depends on traditional fire-fighting technology, which has many defects and cannot meet the actual needs. On the one hand, the response of fire detection is lagging, the traditional smoke detector can only identify the high temperature or smoke signal in the open fire stage, and has low sensitivity to the smoldering fire of electronic equipment, and cannot identify in time. On the other hand, there is a lack of autonomous operation ability suitable for the environment of the electronic room. The cabinets in the electronic room are densely arranged, and the traditional fire extinguishing equipment still needs to be manually transported to the vicinity of the fire source for operation. However, this cannot reach the gaps between the cabinets for fire extinguishing, and the fire extinguishing efficiency is low and there are safety hazards.

[0003] The invention patent with publication number CN 115862258 B discloses a fire monitoring and disposal system, which is characterized in that the system comprises a robot module, a video acquisition and transmission module, a fire identification and analysis module, and a fire grading disposal module; the robot module comprises a robot, a binocular depth camera, a wireless transmission module, and an automatic navigation module; the robot is used for routine fire monitoring and patrol tasks of the environment, the binocular depth camera is used for acquiring surrounding environment video data and performing visual SLAM mapping, the automatic navigation module is used for autonomous path planning and navigation, and is also used for returning to a charging point for charging in a low power state, and the wireless transmission module is used for transmitting data collected by the binocular depth camera to the video acquisition and transmission module; the video acquisition and transmission module comprises a video acquisition unit and a 5G communication module, the video acquisition unit is used for transmitting environment video data collected by the binocular depth camera in real time through the 5G communication module, the video acquisition unit presents video data and its own position coordinates in real time on a cloud platform by using the binocular depth camera, and accurate on-site conditions and position information are obtained in real time by cooperating with 5G high-speed transmission; the fire identification and analysis module is used for receiving data transmitted by the video acquisition and transmission module, establishing a fire data set, setting an object for target detection in input data, and performing real-time identification and analysis frame by frame according to a deep learning method to judge related fire conditions, wherein the object for target detection includes smoke, fire, and pedestrians, the smoke includes white smoke and black smoke, and the pedestrians include pedestrians in danger and freely moving pedestrians; the fire identification and analysis module is based on deep learning, adopts a yolo v5 algorithm, trains a weight model by using a self-built data set, detects smoke, fire, and pedestrians in the environment, the smoke includes white smoke and black smoke, the pedestrians include pedestrians in danger and freely moving pedestrians, a video frame feature map is extracted by CSPdarknet, feature fusion is performed through PANet, and a target detection result is obtained by regression and classification of the features; the fire grading disposal module is used for receiving related fire conditions identified and analyzed by the fire identification and analysis module, and performing fire grading disposal; the fire grading disposal module comprises a knowledge graph construction unit, a knowledge graph searching unit, a result visualization unit, and an updating unit; the knowledge graph construction unit is used for constructing a fire knowledge graph; the knowledge graph searching unit is used for finding alarm signal information and disposal suggestions corresponding to related fire conditions; the result visualization unit is used for providing action suggestions to related personnel and on-site personnel in a visual and voice manner; the updating unit updates the knowledge graph according to feedback of related fire condition processing; the fire grading disposal module is also used for recording all situation information when a fire occurs to generate a log and store it, and archiving according to fire conditions.In the fire grading handling module, the objects detected by the robot according to the autonomous navigation route for daily patrol are divided into three types: when no target or only pedestrian target appears in the video frame, the robot continues normal cruising; when the detection algorithm identifies smoke and flame targets and no pedestrian target appears, it means that a fire has occurred, the robot stops cruising mode and continues to record the scene, sends a first-level fire alarm signal, and notifies the relevant staff of the actual coordinate position and fire situation so as to handle it in time, and the cloud platform archives the video for traceability investigation; when a pedestrian is detected in the fire scene, the position change and residence time of the pedestrian in the picture are used for judgment again, if the pedestrian stays in the same position for a long time, it means that the person is in danger, so in addition to fire extinguishing, medical assistance is also needed, at this time, the system sends a third-level fire alarm signal to remind the relevant personnel to extinguish the fire and provide professional rescue measures and steps, and remind the relevant personnel to bring the relevant tools and equipment to the scene as soon as possible to minimize the loss of life and property; when a movable pedestrian is detected in the fire scene, the relevant personnel receive a second-level fire warning signal according to the scene picture, and communicate with the scene through the external microphone of the robot, and preliminarily command the scene according to the judgment of the fire occurrence degree and the rescue ability of the movable pedestrian, if the scene has rescue conditions, remote guidance is used to stop the spread of the fire as much as possible and professional personnel are sent to the scene at the same time, if the scene does not have rescue conditions, the microphone is used to evacuate the scene personnel to reduce the harm of the fire to the surrounding personnel.

[0004] Therefore, it is necessary to provide an automatic fire extinguishing robot in an electronic room and a control method thereof to solve the above-mentioned defects in the prior art. SUMMARY

[0005] In view of the technical problems in the prior art that common smoldering fire cannot be identified and the cabinet gap cannot be in-depth extinguished, the present application provides an automatic fire extinguishing robot in an electronic room and a control method thereof to solve the above-mentioned technical problems.

[0006] In the first aspect, the present application provides an automatic fire extinguishing robot in an electronic room, comprising: a multi-dimensional data acquisition and monitoring module, an intelligent analysis and planning module, an action execution and data interaction module, a driving module, and a power supply module. Multi-dimensional data acquisition and monitoring module for capturing electronic fire characteristics, collecting spatial positioning and obstacle data, and verifying environmental status; The multi-dimensional data acquisition and monitoring module includes a volatile organic gas sensor, a dual-band infrared flame sensor, an infrared thermal imager, a laser radar, a depth camera, an ultrasonic sensor, an inertial measurement unit, and an environmental sensor. The volatile organic gas sensor is used to detect characteristic gases released when electronic equipment overheats or smolders. The dual-band infrared flame sensor is used to identify open flames and capture infrared light signals at specific wavelengths when the flame burns. The infrared thermal imager is used to locate the heat source and monitor temperature trends. The laser radar is used to collect three-dimensional point cloud data of the electronic environment. The depth camera is used to assist in identifying obstacle types and providing 3D environmental information. The ultrasonic sensor is used to assist the fire extinguishing execution body in identifying close-range obstacles in complex electronic environments. The inertial measurement unit is used to collect angular velocity data and acceleration data. The environmental sensor is used to collect environmental data, including temperature and humidity sensors and smoke sensors.

[0007] The intelligent analysis and planning module uses multi-sensor fusion fire identification algorithms and anti-interference SLAM navigation algorithms to locate and determine fire levels, then uses a three-dimensional path planning algorithm to generate an obstacle avoidance optimal path for the electronic room automatic fire extinguishing robot's mechanical arm, and finally determines the fire extinguishing agent action parameters through a fire extinguishing decision model. The data is transmitted to the action execution and data interaction module. The intelligent analysis and planning module uses multi-sensor fusion fire identification algorithms to determine fire levels and uses anti-interference SLAM navigation algorithms to fuse label data for positioning. The fire extinguishing agent action parameters include fire extinguishing agent spray volume, spray angle, and duration.

[0008] The multi-sensor fusion fire identification algorithm collects and preprocesses multi-dimensional fire data, and inputs the preprocessed data into a trained classification model to obtain fire probability based on multi-dimensional fire data value range division. The multi-dimensional fire data includes VOC concentration, infrared thermal imaging data, and dual-band infrared flame sensor feature light intensity ratio data. VOC concentration represents volatile organic compound concentration. Preprocessing the collected data includes removing outliers using sliding average filtering for VOC concentration, calculating temperature rise rate based on infrared thermal imaging data, and filtering background interference for dual-band infrared flame sensor feature light intensity ratio. The fire level is divided into: I level: smoldering, II level: local open fire, III level: global open fire.

[0009] The anti-interference SLAM navigation algorithm calculates and optimizes the robot pose by preprocessing multi-source positioning data, and the anti-interference SLAM navigation algorithm is an anti-interference simultaneous localization and mapping navigation algorithm; The multi-source positioning data includes the three-dimensional point cloud data collected by the laser radar, the angular velocity data and acceleration data collected by the inertial measurement unit, and the pre-deployed RFID / UWB positioning tag. The preprocessing of multi-source positioning data includes statistical filtering of three-dimensional point cloud data to eliminate point cloud distortion caused by strong electromagnetic interference; temperature compensation and zero offset correction of angular velocity data and acceleration data to reduce motion drift caused by vibration and electromagnetic interference; and extended Kalman filter fusion of laser radar collected data and inertial measurement unit collected data to generate the initial pose of the robot, combined with the absolute position constraint of the RFID / UWB positioning tag for pose graph optimization.

[0010] The three-dimensional path planning algorithm constructs a three-dimensional voxel grid map based on the data collected by the laser radar, fits the ground plane and marks obstacles through the RANSAC algorithm, and clearly defines the passable area and forbidden area in the electronic room, while setting the minimum safety distance between the robot and the obstacle and the joint motion constraint of the mechanical arm. The RANSAC algorithm is a random sample consensus algorithm.

[0011] The fire extinguishing decision model calculates the fire extinguishing agent injection amount, injection angle and duration based on fire parameters and equipment parameters; The fire parameters include fire level, fire type, burning area, center temperature, and three-dimensional coordinates of the fire source. The fire type is divided into electrical fire and solid fire. The burning area is the area where the infrared thermal imaging temperature is greater than 300℃. The center temperature is the maximum temperature of infrared thermal imaging. The equipment parameters include the extinguishing concentration of the fire extinguishing agent, the density of the fire extinguishing agent, and the flow of the injection device. The fire extinguishing agent injection amount The mathematical expression is: , is the burning area, is the height coverage range of the fire source, is the extinguishing concentration; The mathematical expression of the injection angle is: , , is the pitch angle, is the horizontal angle, is the end-of-arm coordinate, Fire source coordinates; The mathematical expression of the duration t is: Q is the flow rate of the injection device, and k is a safety redundancy coefficient that can be dynamically adjusted according to the fire class.

[0012] The action execution and data interaction module receives the extinguishing agent action parameter data and drives the mechanical arm of the electronic room automatic fire extinguishing robot to extend into the narrow space, accurately positions the atomizing nozzle to the root of the fire source, accurately controls the supply amount through the pump pressure system in cooperation with the precision pressure reducing valve and flow meter, atomizes the extinguishing agent into micron-level particles through the piezoelectric ceramic atomizing nozzle, and uploads the alarm information, on-site fire scene picture and extinguishing system operation state data to the cloud or fire control center in real time through the communication module, and synchronously receives remote control instructions. The extinguishing agent is selected from perfluorohexanone liquid extinguishing agent or Novec 1230 gas extinguishing agent; the mechanical arm adopts a 3-6 axis multi-degree-of-freedom structure for adjusting the posture and extending into the closed area to accurately position the atomizing nozzle to the root of the fire source.

[0013] The driving module is used to provide the electronic room automatic fire extinguishing robot with a moving power suitable for the narrow equipment environment of the electronic room. The chassis design of the driving module adopts a low gravity center and a compact structure, and the driving mode adopts four-wheel differential driving, which cooperates with each module of the electronic room automatic fire extinguishing robot.

[0014] The power supply module is used to provide each module of the electronic room automatic fire extinguishing robot with a working power supply suitable for the voltage.

[0015] In a second aspect, the technical scheme of the present application further provides an electronic room automatic fire extinguishing control method, which comprises the following steps: Step S1: a multi-dimensional data acquisition and monitoring step, used for capturing the electronic room fire characteristics, acquiring spatial positioning and obstacle data, and verifying the environment state; Step S2: a step of intelligent analysis and planning, which is used for positioning and determining the fire class through a multi-sensor fusion fire identification algorithm and an anti-interference SLAM navigation algorithm, then generating an obstacle avoidance optimal path for the mechanical arm of the robot through a three-dimensional path planning algorithm, and finally determining the extinguishing agent action parameters through a fire extinguishing decision model, and transmitting the extinguishing agent action parameter data to the action execution step; Step S3: the action performs the step of data interaction, receives the fire extinguishing agent action parameter data and drives the mechanical arm of the robot to extend into the narrow space, accurately positions the atomizing nozzle to the root of the fire source, accurately controls the supply amount through the pump pressure system cooperating with the precision pressure reducing valve and flow meter, atomizes the fire extinguishing agent into micron-level particles through the piezoelectric ceramic atomizing nozzle, and uploads the alarm information, on-site fire picture and fire extinguishing system operation state data to the cloud or fire control center in real time, and synchronously receives remote control instructions.

[0016] The electronic room automatic fire extinguishing robot and the control method thereof provided by the application provide an adaptive solution for the special needs of electronic room fire fighting: early fire identification and positioning are realized through a multi-sensor fusion fire identification algorithm and an anti-interference SLAM navigation algorithm, a three-dimensional path planning algorithm and a multi-degree-of-freedom mechanical arm are relied on to penetrate into narrow areas such as cabinet gaps, piezoelectric ceramic atomizing nozzles are combined to atomize fire extinguishing agents into micron-level particles, secondary damage to precision equipment by traditional fire extinguishing methods is avoided, alarm information, on-site fire pictures and fire extinguishing system operation state data are uploaded to the cloud or fire control center, multi-device remote control is realized, personnel safety risks are reduced, and the flexibility of multi-scene fire extinguishing operations is improved.

[0017] In addition, the design principle of the application is reliable, the structure is simple, and the application prospect is very wide. DETAILED DESCRIPTION

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description, and obviously, other drawings can be obtained by those skilled in the art without creative labor on the premise of the drawings.

[0019] Figure 1 is a principle block diagram of an electronic room automatic fire extinguishing robot provided by the application.

[0020] Figure 2 is a flowchart of an electronic room automatic fire extinguishing control method provided by the application. DETAILED DESCRIPTION

[0021] In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present application.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0023] Example 1: like Figure 1 As shown, this embodiment of the invention provides an automatic fire extinguishing robot for electronic rooms, including: a multi-dimensional data acquisition and monitoring module 1, an intelligent analysis and planning module 2, an action execution and data interaction module 3, a drive module 4, and a power supply module 5; Multi-dimensional data acquisition and monitoring module 1 is used to capture fire characteristics in the electronic room, collect spatial positioning and obstacle data, and verify the environmental status. The multi-dimensional data acquisition and monitoring module 1 includes a volatile organic compound gas sensor 11, a dual-band infrared flame sensor 12, an infrared thermal imager 13, a lidar 14, a depth camera 15, an ultrasonic sensor 16, an inertial measurement unit 17, and an environmental sensor 18. Volatile organic gas sensor 11 is used to detect characteristic gases released when electronic equipment overheats or smolders; For example, electronic devices include PCB boards and cables, and characteristic gases include benzene and carbon monoxide.

[0024] A dual-band infrared flame sensor 12 is used to identify open flames and capture infrared light signals of a specific band when the flame is burning. Infrared thermal imager 13 is used to locate fire hotspots and monitor temperature change trends; LiDAR 14 is used to collect three-dimensional point cloud data of the electronic environment; Depth camera 15 is used to assist in identifying obstacle types and provide 3D environmental information; For example, obstacle types include cables, cabinets, and steps.

[0025] Ultrasonic sensor 16 is used to assist the fire extinguishing unit in identifying nearby obstacles in the complex electronic environment; Inertial measurement unit 17 is used to collect angular velocity data and acceleration data; The environmental sensor 18 is used to collect environmental data, including a temperature and humidity sensor 181 and a smoke sensor 182; The temperature and humidity sensor 181 is used to monitor the temperature and humidity parameters of the electronic room environment in real time. It is fused with the data collected by the dual-band infrared flame sensor 12 and infrared thermal imaging 13. By analyzing abnormal changes in environmental temperature and humidity, it assists the multi-sensor fusion algorithm to more accurately distinguish between normal equipment heat dissipation and fire, and reduce false alarms. The smoke sensor 182 is used to capture smoke particle signals in the electronic room in real time, and cooperates with the dual-band infrared flame sensor 12 and the infrared thermal imaging 13 to detect early smoke before the formation of open fire when the device causes smoldering due to short circuit and overheating, and triggers fire warning in advance.

[0026] The intelligent analysis and planning module 2 determines the fire level by the multi-sensor fusion fire identification algorithm and the anti-interference SLAM navigation algorithm, generates an obstacle avoidance optimal path for the mechanical arm of the electronic room automatic fire extinguishing robot by a three-dimensional path planning algorithm, and finally determines the fire extinguishing agent action parameters by a fire extinguishing decision model, and transmits the fire extinguishing agent action parameter data to the action execution and data interaction module. The intelligent analysis and planning module 2 determines the fire level by the multi-sensor fusion fire identification algorithm and the anti-interference SLAM navigation algorithm, generates an obstacle avoidance optimal path for the mechanical arm of the electronic room automatic fire extinguishing robot by a three-dimensional path planning algorithm, and finally determines the fire extinguishing agent action parameters by a fire extinguishing decision model, and transmits the fire extinguishing agent action parameter data to the action execution and data interaction module.

[0027] The multi-sensor fusion fire identification algorithm acquires and pre-processes multi-dimensional fire data, and inputs the pre-processed data into a trained classification model to obtain a fire probability based on a three-dimensional feature vector, and divides the fire level based on the numerical range of the multi-dimensional fire data. The multi-dimensional fire data includes VOC concentration, infrared thermal imaging data, and dual-band infrared flame sensor characteristic light intensity ratio data, and the VOC concentration represents volatile organic compound concentration. The pre-processing of the collected data includes removing abnormal values by using sliding average filtering for VOC concentration, calculating temperature rise rate based on infrared thermal imaging data, and filtering background interference for dual-band infrared flame sensor characteristic light intensity ratio. The fire level is divided into: I level: smoldering, II level: local open fire, and III level: global open fire.

[0028] The anti-interference SLAM navigation algorithm pre-processes multi-source positioning data, calculates and optimizes the robot pose, and is an anti-interference simultaneous localization and mapping navigation algorithm. The multi-source positioning data includes three-dimensional point cloud data collected by the laser radar, angular velocity data and acceleration data collected by the inertial measurement unit, and pre-deployed RFID / UWB positioning tags. The preprocessing of multi-source positioning data includes statistical filtering of environment three-dimensional point cloud data to eliminate point cloud distortion caused by strong electromagnetic interference; temperature compensation and zero offset correction of angular velocity data and acceleration data to reduce motion drift caused by vibration and electromagnetic interference, and extended Kalman filter fusion of data collected by laser radar and data collected by inertial measurement unit to generate initial pose of the robot, combined with absolute position constraint of RFID / UWB positioning tag to optimize pose graph.

[0029] The three-dimensional path planning algorithm constructs a three-dimensional voxel grid map based on the data collected by the laser radar, fits the ground plane and marks obstacles through the RANSAC algorithm, and clearly defines the passable area and forbidden area in the electronic room, while setting the minimum safety distance between the robot and the obstacle and the joint motion constraint of the robot arm. The RANSAC algorithm is a random sample consensus algorithm.

[0030] The fire extinguishing decision model calculates the fire extinguishing agent injection amount, injection angle and duration based on fire condition parameters and equipment parameters; The fire condition parameters include fire condition level, fire condition type, burning area, center temperature, and three-dimensional coordinates of the fire source. The fire condition type is divided into electrical fire and solid fire. The burning area is the area where the infrared thermal imaging temperature is greater than 300℃. The center temperature is the maximum temperature of infrared thermal imaging; The equipment parameters include fire extinguishing agent concentration, fire extinguishing agent density, and injection device flow rate; The fire extinguishing agent injection amount is calculated as follows: The mathematical expression is: , is the burning area, is the height coverage of the fire source, is the fire extinguishing concentration; The mathematical expression of the injection angle is: , , is the pitch angle, is the horizontal angle, is the end-of-arm coordinate, is the fire source coordinate; The mathematical expression of the duration t is: Q is the injection device flow rate, and k is the safety redundancy coefficient, which can be dynamically adjusted according to the fire condition level.

[0031] The action execution and data interaction module 3 receives the extinguishing agent action parameter data and drives the robotic arm of the electronic room automatic fire extinguishing robot to extend into the narrow space, accurately aligning the atomizing nozzle to the root of the fire source. At the same time, the pump pressure system, together with the precision pressure reducing valve and flow meter, accurately controls the supply. The extinguishing agent is then atomized into micron-sized particles through the piezoelectric ceramic atomizing nozzle. The module also uploads alarm information, on-site fire scene images, and fire extinguishing system operation status data to the cloud or fire control center in real time through the communication module, and simultaneously receives remote control commands. The extinguishing agent used is either perfluorohexanone liquid extinguishing agent or Novec 1230 gaseous extinguishing agent; the robotic arm adopts a 3-6 axis multi-degree-of-freedom structure to adjust its posture and extend into the confined area to precisely align the atomizing nozzle to the base of the fire source.

[0032] Drive module 4 is used to provide the automatic fire extinguishing robot in the electronics room with the mobility to adapt to the narrow equipment environment of the electronics room; Among them, the chassis design of drive module 4 adopts a low center of gravity and compact structure, and the drive method adopts four-wheel differential drive, which works in coordination with the various modules of the electronic room automatic fire extinguishing robot.

[0033] Power supply module 5 is used to provide working power with adapted voltage for each module of the automatic fire extinguishing robot in the electronics room; For example, power supply module 5 uses a high-energy-density lithium battery pack.

[0034] Example 2: like Figure 2 As shown, this embodiment also provides an automatic fire suppression control method for an electronic room, including the following steps: Step S1: Multi-dimensional data acquisition and monitoring steps, used to capture fire characteristics in electronic compartments, collect spatial positioning and obstacle data, and verify environmental conditions; Multispectral fire detectors capture fire characteristics in electronic compartments, navigation and obstacle avoidance sensors collect spatial positioning and obstacle data, and environmental sensors verify environmental conditions.

[0035] Step S2: The intelligent analysis and planning step involves locating and determining the fire level by using a multi-sensor fusion fire identification algorithm and an anti-interference SLAM navigation algorithm. Then, a three-dimensional path planning algorithm is used to generate the optimal obstacle avoidance path for the robot's robotic arm. Finally, the fire extinguishing decision model determines the fire extinguishing agent action parameters and transmits the fire extinguishing agent action parameter data to the action execution step. Step S3: the action execution and data interaction step receives the extinguishing agent action parameter data and drives the mechanical arm of the robot to extend into the narrow space, accurately positions the atomizing nozzle to the root of the fire source, accurately controls the supply amount through the pump pressure system cooperating with the precision pressure reducing valve and flow meter, atomizes the extinguishing agent into micron-level particles through the piezoelectric ceramic atomizing nozzle, and uploads the alarm information, on-site fire picture and extinguishing system operation state data to the cloud or fire control center in real time through the communication module, and synchronously receives remote control instructions; The mechanical arm adopts a 3-6 axis multi-degree-of-freedom structure for adjusting the posture and accurately positioning the atomizing nozzle to the root of the fire source in a closed area. The action execution of the mechanical arm is cooperated with the movement platform, wherein the chassis of the movement platform is designed in a low gravity center and compact structure, and the driving mode adopts four-wheel differential driving.

[0036] The RFID (Radio Frequency Identification) tag in the technical solution realizes non-contact information transmission and identification through radio frequency signals, and the UWB (Ultra-Wideband) utilizes wireless signals with extremely wide frequency to perform high-precision ranging and positioning.

[0037] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other. For the method disclosed by the embodiments, since it corresponds to the system disclosed by the embodiments, the description is relatively simple, and the related parts can be referred to the method part description.

[0038] The skilled person can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present text can be realized in electronic hardware, computer software or combination of both, and in order to clearly show the interchangeability of hardware and software, the composition and steps of each example have been described in the above description. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0039] In several embodiments provided by the present application, it should be understood that the disclosed system, system and method can be implemented in other manners. For example, the system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, and can be in electrical, mechanical or other forms.

[0040] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units. That is, they can be located in one place, or can also be distributed on a plurality of network units. In actual implementation, some or all of the units can be selected according to the actual needs to achieve the purposes of the embodiments.

[0041] In addition, each function module in each embodiment of the present application can be integrated in one processing unit, or each module can be a physically independent unit, or two or more modules can be integrated in one unit.

[0042] Similarly, each processing unit in each embodiment of the present application can be integrated in one function module, or each processing unit can be a physically independent unit, or two or more processing units can be integrated in one function module.

[0043] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, a processor executing software modules, or a combination of the two. The software modules can be stored in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0044] Finally, it needs to be explained that in this text, relational terms such as first and second and the like can merely be used to distinguish one entity or action from another, without necessarily requiring or implying any actual such relationship or order between or among the entities or actions. Also, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0045] The above disclosed are only the preferred embodiments of the present application, but the present application is not limited thereto, any non-creative changes and several improvements and refinements made by any person skilled in the art without departing from the principles of the present application should fall within the protection scope of the present application.

Claims

1. An automatic fire extinguishing robot for electronic rooms, characterized in that, The application relates to an electronic room automatic fire extinguishing robot, which comprises a multi-dimensional data acquisition and monitoring module, an intelligent analysis and planning module, an action execution and data interaction module, a driving module and a power supply module. The multi-dimensional data acquisition and monitoring module is used for capturing electronic room fire characteristics, acquiring spatial positioning and obstacle data and verifying environmental states. The intelligent analysis and planning module is used for positioning and determining a fire grade through a multi-sensor fusion fire identification algorithm and an anti-interference SLAM navigation algorithm, generating an obstacle-avoiding optimal path for a mechanical arm of the electronic room automatic fire extinguishing robot through a three-dimensional path planning algorithm, and determining fire extinguishing agent action parameters through a fire extinguishing decision model. The action execution and data interaction module receives the fire extinguishing agent action parameter data and drives the mechanical arm of the electronic room automatic fire extinguishing robot to extend into a narrow space, accurately positions a atomizing nozzle to a fire source root, accurately controls a supply amount through a pump pressure system, a precision pressure reducing valve and a flowmeter, atomizes the fire extinguishing agent into micron-level particles through a piezoelectric ceramic atomizing nozzle, and uploads alarm information, a fire scene picture and fire extinguishing system operation state data to a cloud or a fire control center in real time through a communication module and synchronously receives remote control instructions. The driving module is used for providing the electronic room automatic fire extinguishing robot with moving power suitable for a narrow equipment environment in an electronic room. The power supply module is used for providing all the modules of the electronic room automatic fire extinguishing robot with working power sources with adaptive voltages.

2. The automatic fire extinguishing robot for electronic room according to claim 1, wherein The multi-dimensional data acquisition and monitoring module comprises volatile organic compound gas sensors, double-waveband infrared flame sensors, infrared thermal imagers, laser radars, depth cameras, ultrasonic sensors, inertial measurement units and environmental sensors. The volatile organic compound gas sensors are used for detecting characteristic gases released when electronic equipment is overheated or smolders. The double-waveband infrared flame sensors are used for identifying open fire flames and capturing infrared light signals of specific wavebands when the flames burn. The infrared thermal imagers are used for positioning fire source hot spots and monitoring temperature change trends. The laser radars are used for collecting three-dimensional point cloud data of an electronic room environment. The depth cameras are used for assisting in identifying obstacle types and providing 3D environmental information. The ultrasonic sensors are used for assisting the fire extinguishing execution body in identifying close-range obstacles in a complex electronic room environment. The inertial measurement units are used for collecting angular velocity data and acceleration data. The environmental sensors are used for collecting environmental data, and comprise temperature and humidity sensors and smoke sensors.

3. The automatic fire extinguishing robot for electronic room according to claim 1, wherein The intelligent analysis and planning module determines a fire grade through a multi-sensor fusion fire identification algorithm, and performs positioning through an anti-interference SLAM navigation algorithm.

4. The electronic room automatic fire extinguishing robot according to claim 3, wherein, The multi-sensor fusion fire identification algorithm collects and pre-processes multi-dimensional fire data, inputs three-dimensional feature vectors of the pre-processed data into a trained classification model to obtain a fire probability, and divides fire grades based on multi-dimensional fire data value ranges. The multi-dimensional fire data includes VOC concentration, infrared thermal imaging data, and double-band infrared flame sensor characteristic light intensity ratio data, and the VOC concentration represents volatile organic compound concentration; The collected data is preprocessed, including removing abnormal values by using sliding average filtering for VOC concentration, calculating temperature rise rate based on infrared thermal imaging data, and filtering background interference for double-band infrared flame sensor characteristic light intensity ratio; The fire grade is divided into: Grade I: smoldering, Grade II: local open fire, and Grade III: global open fire.

5. The electronic room automatic fire extinguishing robot according to claim 3, wherein, The anti-interference SLAM navigation algorithm calculates and optimizes the robot pose by preprocessing multi-source positioning data; The multi-source positioning data includes three-dimensional point cloud data collected by a laser radar, angular velocity data and acceleration data collected by an inertial measurement unit, and pre-deployed RFID / UWB positioning tags; The preprocessing of the multi-source positioning data includes statistical filtering of the three-dimensional point cloud data to eliminate point cloud distortion caused by strong electromagnetic interference, temperature compensation and zero offset correction of the angular velocity data and acceleration data to reduce motion drift caused by vibration and electromagnetic interference, and fusion of the data collected by the laser radar and the data collected by the inertial measurement unit to generate an initial pose of the robot by using extended Kalman filtering, and combining the absolute position constraint of the RFID / UWB positioning tag for pose graph optimization.

6. The electronic room automatic fire extinguishing robot according to claim 3, wherein, The three-dimensional path planning algorithm constructs a three-dimensional voxel grid map based on the data collected by the laser radar, fits the ground plane and marks obstacles by using the RANSAC algorithm, and clearly defines the passable area and forbidden area in the electronic room, while setting the minimum safety distance between the robot and the obstacle and the joint motion constraint of the robot.

7. The electronic room automatic fire extinguishing robot according to claim 3, wherein, The fire extinguishing decision model calculates the injection amount, injection angle, and duration of the fire extinguishing agent based on fire parameters and equipment parameters; The fire parameters include fire grade, fire type, burning area, center temperature, and three-dimensional coordinates of the fire source, the fire type is divided into electrical fire and solid fire, the burning area is the area of the region with an infrared thermal imaging temperature greater than 300℃, and the center temperature is the maximum temperature of the infrared thermal imaging; The equipment parameters include the fire extinguishing concentration of the fire extinguishing agent, the density of the fire extinguishing agent, and the flow rate of the injection device; wherein the fire extinguishing agent injection amount The mathematical expression is: , is the burning area, is the fire source height coverage, is the fire extinguishing concentration; The mathematical expression of the spray angle is: , , is the pitch angle, is the horizontal angle, is the coordinate of the end of the mechanical arm, is the coordinate of the fire source; The mathematical expression for the duration t is: Q is the flow rate of the injection device, and k is a safety redundancy factor that can be dynamically adjusted depending on the fire class.

8. The automatic fire extinguishing robot for electronic room according to claim 1, wherein The fire extinguishing agent selected in the action execution and data interaction module is liquid perfluorohexanone fire extinguishing agent or Novec 1230 gas fire extinguishing agent; The robot arm adopts a 3-6-axis multi-degree-of-freedom structure for adjusting the posture and precisely aligning the atomizing nozzle to the root of the fire source in the closed area.

9. The robot for automatically extinguishing fire in an electrical room according to claim 1, wherein The chassis design of the driving module adopts a low gravity center and a compact structure, and the driving mode adopts four-wheel differential driving, which cooperates with each module of the electronic room automatic fire extinguishing robot.

10. An automatic fire extinguishing control method for an electronic room, characterized by comprising: The method comprises the following steps: Step S1: multi-dimensional data acquisition and monitoring, for capturing electronic room fire characteristics, collecting spatial positioning and obstacle data, and verifying the environment state; Step S2: The step of intelligent analysis and planning, through multi-sensor fusion fire identification algorithm and anti-interference SLAM navigation algorithm to locate and determine the fire grade, then use three-dimensional path planning algorithm to generate the optimal obstacle avoidance path for the robot arm, finally through the fire extinguishing decision model to determine the fire extinguishing agent action parameters, and pass the data to the action execution step; Step S3: The step of action execution and data interaction, receive the fire extinguishing agent action parameter data and drive the robot arm to extend into the narrow space, accurately align the atomizing nozzle to the root of the fire source, at the same time, through the pump pressure system, cooperate with the precision pressure reducing valve and flowmeter to accurately control the supply amount, then through the piezoelectric ceramic atomizing nozzle to atomize the fire extinguishing agent into micron level particles, and through the communication module to upload the alarm information, on-site fire picture and fire extinguishing system running state data to the cloud or fire control center in real time, and receive the remote control instruction synchronously.

Images