Fire passage door closer abnormality detection method, system and electronic equipment

Abstract

This invention discloses a method, system, and electronic device for detecting abnormalities in fire escape door closers. The method includes: patrolling and detecting fire escape routes using a robot, acquiring and transmitting images of the door closers to a backend system; obtaining the location, confidence level, and connection relationships of key bearing points in the door closer based on the acquired image information; calculating parameters for logical judgment based on the acquired bearing key point locations, confidence levels, and connection relationships; and using a neural network model to perform logical judgments on the parameters to determine whether the door closer is abnormal. This method for detecting abnormalities in fire escape door closers reduces labor costs, improves detection efficiency, and significantly enhances the overall system's reliability.

Description

Technical Field

[0001] This invention relates to the field of fire door closer detection technology, and more specifically, to a method, system, and electronic equipment for detecting abnormalities in fire escape door closers. Background Technology

[0002] In buildings and other locations, abnormalities may occur such as damaged fire door closers or fire doors not being properly closed. In emergencies such as fires requiring immediate rescue, the ability to properly close fire doors is crucial for ensuring the safety of those escaping. Damaged door closers or doors that cannot be fully closed can exacerbate and worsen the damage caused by a fire.

[0003] Currently, security guards or other personnel conduct regular patrols and inspections of buildings and shopping malls to visually assess whether door closers are damaged and whether fire doors can be closed securely. There are currently no other methods or technologies besides human intervention for this assessment.

[0004] The current solution is labor-intensive, and human visual discrimination is prone to errors and omissions, resulting in low overall efficiency and poor timeliness. Using fixed cameras with image analysis would be limited by camera location, making the application extremely difficult. Summary of the Invention

[0005] One objective of this invention is to provide a new technical solution for detecting abnormalities in fire escape door closers, including a method, system, and electronic equipment, which can at least solve the problems of high cost, low efficiency, and difficulty in application in the prior art.

[0006] In a first aspect, the present invention provides a method for detecting abnormalities in the door closer of a fire escape route, comprising:

[0007] The robot patrols and inspects fire exits, captures information from door closers, and pushes it to the backend.

[0008] Based on the acquired camera information of the door closer, the location, confidence level, and connection relationship of the bearing key points of the door closer are obtained.

[0009] Based on the obtained bearing key point positions, confidence levels, and connection relationships of the bearing key points of the door closer, the parameters used for logical judgment are calculated.

[0010] A neural network model is used to make logical judgments on the parameters to determine whether the door closer is abnormal.

[0011] Optionally, the steps of using a robot to patrol and inspect fire exits and obtain camera information from door closers include:

[0012] Set up a robot patrol route and set up capture points along the patrol route;

[0013] The robot is controlled to patrol according to the patrol route.

[0014] Optionally, the robot is equipped with a camera to capture information when it patrols to the capture point.

[0015] Optionally, the step of obtaining the bearing key point location, confidence level, and connection relationship of the bearing key point based on the acquired image information of the door closer includes:

[0016] The position of the door closer was detected using a detector.

[0017] Based on the detected position of the door closer, determine whether the enclosure of the door closer has been detected;

[0018] Based on the detected enclosure, the bearing key points of the door closer are detected to obtain the bearing key point positions, confidence levels, and connection relationships of the bearing key points.

[0019] Optionally, in the step of performing logical judgment on the parameters, if at least half of the logically judged parameters exceed the threshold, the door closer is determined to be abnormal.

[0020] Optionally, the steps for calculating the parameters used in the logical judgment include:

[0021] Calculate the angle of the bearing connection point at the key bearing point;

[0022] Based on the angle of the bearing connection point, the pixel distance of the bearing connection point is calculated to obtain parameters for logical judgment, so as to determine whether the door closer is abnormal.

[0023] Optionally, the method for detecting abnormalities in the fire escape door closer also includes: issuing an alarm when the door closer is determined to be abnormal.

[0024] A second aspect of the present invention provides a system for detecting abnormalities in the door closer of a fire escape route, applied to the method for detecting abnormalities in the door closer of a fire escape route described in the above embodiments, the system comprising:

[0025] The first acquisition module is used to patrol and detect fire exits with a robot, acquire the camera information of the door closer, and push it to the background.

[0026] The second acquisition module is used to acquire the bearing key point position, confidence level and connection relationship of the bearing key point based on the acquired shooting information of the door closer;

[0027] The calculation module is used to calculate parameters for logical judgment based on the obtained bearing key point positions, confidence levels and connection relationships of the bearing key points of the door closer.

[0028] The judgment module uses a neural network model to perform logical judgments on the parameters in order to determine whether the door closer is abnormal.

[0029] A third aspect of the present invention provides an electronic device comprising: a processor and a memory, wherein computer program instructions are stored in the memory, wherein when the computer program instructions are executed by the processor, the processor causes the processor to perform the steps of the fire escape door closer abnormal detection method described in the above embodiments.

[0030] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the fire escape door closer anomaly detection method described in the above embodiments.

[0031] The present invention discloses a method for detecting abnormalities in fire escape door closers. This method utilizes a robot for patrol and inspection, acquiring photographic information about the closer, obtaining the location, confidence level, and connection relationships of key bearing points, and calculating parameters for logical judgment to determine whether the closer and fire door are closing properly. This method reduces labor costs, improves detection efficiency, and significantly enhances the overall system's reliability.

[0032] Other features and advantages of the invention will become clear from the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings. Attached Figure Description

[0033] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments of the invention and, together with their description, serve to explain the principles of the invention.

[0034] Figure 1 This is a method for detecting abnormalities in the door closer of a fire escape route according to an embodiment of the present invention;

[0035] Figure 2 This is a logic block diagram of a fire escape door closer malfunction detection method according to an embodiment of the present invention;

[0036] Figure 3 This is a schematic diagram of robot inspection according to an embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram illustrating the calculation of the bearing key point positions of the door closer according to an embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of the working principle of an electronic device according to an embodiment of the present invention.

[0039] Figure label:

[0040] Robot 10;

[0041] Fire door 20;

[0042] 30 capture points;

[0043] Door closer 40;

[0044] Processor 201;

[0045] Memory 202; Operating System 2021; Application Program 2022;

[0046] Network interface 203;

[0047] Input device 204;

[0048] Hard drive 205;

[0049] Display device 206. Detailed Implementation

[0050] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0051] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0052] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0053] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0054] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0055] The following describes in detail, with reference to the accompanying drawings, a method for detecting abnormalities in the fire escape door closer 40 according to an embodiment of the present invention.

[0056] like Figure 1As shown, the method for detecting abnormalities in the fire escape door closer 40 according to an embodiment of the present invention includes:

[0057] S1. The robot 10 patrols and inspects the fire exit, obtains the camera information from the door closer 40, and pushes it to the backend.

[0058] S2. Based on the captured information of the door closer 40, obtain the bearing key point position, confidence level and connection relationship of the bearing key point of the door closer 40.

[0059] S3. Based on the obtained bearing key point positions, confidence levels, and connection relationships of the bearing key points of the door closer 40, calculate the parameters used for logical judgment.

[0060] S4. Use a neural network model to make logical judgments on the parameters to determine whether the door closer 40 is abnormal.

[0061] In other words, in the abnormal detection method of the fire escape door closer 40 in this embodiment of the invention, firstly, see... Figure 1 The robot 10 can patrol and inspect the fire exit, acquiring images of the door closer 40 and pushing them to the backend. The robot 10's back-and-forth patrols collect relevant data, improving patrol efficiency and saving labor costs. Then, based on the acquired images of the door closer 40, the location, confidence level, and connection relationships of the bearing key points of the door closer 40 can be obtained. Next, parameters for logical judgment can be calculated based on these parameters. Finally, a neural network model can be used to perform logical judgments on the parameters to determine whether the door closer 40 is malfunctioning.

[0062] This invention uses deep learning to obtain relevant information and then judges the image. The entire image analysis process can be summarized into three main steps: detection of the door closer 40, detection of key points of the door closer 40, and comprehensive logical judgment. In deep learning, the YOLOv5 method is used to locate the door closer 40 on the fire door 20 in the image. To reduce the detection time, this invention modifies the original YOLOv5 backbone network to a lightweight network like Mobilenetv3. Part of the model's training data comes from open-source networks, and the other part is collected and labeled by ourselves. To improve the model's universality and detection capability, the focus structure in YOLOv5 can be removed, and the image input for model training and inference can be changed to a video resolution ratio of 4:3 for multiscale training. Through the detector, we can initially determine whether the door closer 40 is abnormal. If the door closer 40 cannot be detected, there is a high probability that the fire safety door does not have the door closer 40 installed, i.e., it is judged as abnormal.

[0063] Therefore, the fire escape door closer 40 anomaly detection method according to an embodiment of the present invention utilizes a robot 10 for patrol inspection, acquires image information of the closer 40, obtains the bearing key point positions, confidence levels, and connection relationships of the bearing key points of the closer 40, and calculates parameters for logical judgment to determine whether the closer 40 and the fire door 20 are closing normally. This fire escape door closer 40 anomaly detection method reduces labor costs, improves detection efficiency, and greatly enhances the overall system's reliability.

[0064] According to one embodiment of the present invention, the step of using a robot 10 to patrol and inspect fire exits and obtain image information from the door closer 40 includes:

[0065] Set up a patrol route for robot 10 and set up capture points 30 along the patrol route;

[0066] Control robot 10 to patrol according to the patrol route.

[0067] Robot 10 is equipped with a camera, which captures information when it patrols to the capture point 30.

[0068] In other words, such as Figure 3 As shown, during the process of the robot 10 patrolling and inspecting the fire escape and obtaining image information from the door closer 40, a patrol route for the robot 10 can be set, and capture points 30 can be set along the patrol route. Then, the robot 10 can be controlled to patrol according to the patrol route. The robot 10 is equipped with a camera, which acquires image information when the robot 10 patrols to the capture point 30.

[0069] The detection method of this invention is based on an inspection robot 10, with a camera positioned on the head of the robot 10. It continuously inspects points set up along the fire escape route and collects video footage in real time, which is then pushed to a background algorithm server for image analysis. The image analysis primarily uses target detection and key point detection to determine anomalies in the fire door 20 and door closer 40.

[0070] When robot 10 patrols a fixed environment, it follows a circular path, repeatedly circling the scene. The patrol route can be manually set (and must pass through the fire door 20 area). During the patrol, robot 10 captures images at preset points. Specifically, it stops at fixed points and uses a camera mounted on its head to capture video streams of the fire escape route. The video is then transmitted via a network module to a backend algorithm server for analysis and early warning.

[0071] In some specific embodiments of the present invention, the step of obtaining the bearing key point position, confidence level, and connection relationship of the bearing key point based on the acquired imaging information of the door closer 40 includes:

[0072] The position of the door closer 40 was detected using a detector.

[0073] Based on the detected position of the door closer 40, determine whether the enclosure of the door closer 40 has been detected.

[0074] Based on the detected enclosure, the key bearing points of the door closer 40 are detected to obtain the location, confidence level, and connection relationship of the key bearing points of the door closer 40.

[0075] In the step of making logical judgments on the parameters, if at least half of the logically judged parameters exceed the threshold, the door closer 40 is determined to be abnormal.

[0076] The steps for calculating the parameters used in logical judgments include:

[0077] Calculate the angle of the bearing connection point, a key point of the bearing.

[0078] Based on the angle of the bearing connection point, the pixel distance of the bearing connection point is calculated to obtain the parameters used for logical judgment, so as to determine whether the door closer 40 is abnormal.

[0079] The method also includes issuing an alarm when the door closer 40 is found to be malfunctioning.

[0080] In other words, based on the inspection robot 10, the camera is placed on the head of the robot 10. It continuously inspects the points set up in the fire escape route and collects video in real time after the points are fixed, which is then pushed to the backend algorithm server for image analysis. The image analysis mainly uses target detection and key point detection to determine the anomalies of the fire door 20 and the door closer 40.

[0081] The robot 10 patrols specific fire exits or areas with fire safety doors in parks, shopping malls, and buildings, and collects fixed-point video streams in real time and pushes them to the backend for analysis.

[0082] When robot 10 patrols a fixed environment, it follows a circular path, repeatedly circling the scene. The patrol route can be manually set (and must pass through the fire door 20 area). During the patrol, robot 10 captures images at preset points. Specifically, it stops at fixed points and uses a camera mounted on its head to capture video streams of the fire escape route. The video is then transmitted via a network module to a backend algorithm server for analysis and early warning.

[0083] The process involves acquiring real-time video images, using deep learning to obtain relevant information, and then judging the information within the image. The entire image analysis process can be summarized in three main steps: detection of the door closer 40, detection of key points in the door closer 40, and comprehensive logical judgment.

[0084] (1) Detection of door closer 40

[0085] This invention uses the YOLOv5 method in deep learning to locate the door closer 40 on a fire door 20 in an image. To reduce detection time, the original YOLOv5 backbone network was modified to a lightweight network like MobileNetv3. Part of the training data for the model comes from open-source networks, while the other part was collected and labeled by ourselves. To improve the model's generality and detection capability, we removed the focus structure from YOLOv5 and changed the image input for training and inference to a 4:3 video resolution ratio for multiscale training. Using the detector, we can initially determine whether the door closer 40 is abnormal. If the door closer 40 is not detected, there is a high probability that the fire safety door is not equipped with the door closer 40, thus indicating an anomaly.

[0086] (2). Key point detection of door closer 40

[0087] For ease of subsequent logical judgment, a neural network model is used to detect the key point positions of the three bearings on the door closer 40. This invention uses the Heatmap method in OpenPose deep learning to locate the key points of the bearing nodes of the door closer 40. Through the neural network, we can obtain the bearing key point positions, confidence levels, and bearing connection relationships for each bearing of the door closer 40 in each frame. To reduce processing time, ShuffleNetV2 is used as the backbone model of the neural network. Part of the model's training data is obtained through web crawling, and the other part is collected and labeled by ourselves. To improve the model's accuracy, the downsampling factor is changed to 2, and the input image resolution is changed to 256*256, with a 1:1 aspect ratio approximating the actual width and height ratio of the door closer 40.

[0088] Based on the obtained key point locations, parameters for logical judgment can be derived through certain calculations. Finally, logical judgment can determine whether the door closer 40 is functioning properly or whether the fire door 20 is tightly closed. The specific calculation method is as follows:

[0089] See Figure 4 To calculate the angle alpha at the bearing connection point: we can calculate the angle between line segments CD and DE, denoted as alpha; and calculate the angle between AB and CD, denoted as beta. We use the vector dot product formula to assist in the angle calculation:

[0090] A·B=|A|*|B|*cos(alpha)

[0091] Calculating the pixel distance d between bearing connection points: The distance between line segments CD can be calculated and denoted as d1; the distance between AB can be calculated and denoted as d2; the distance between DE can be calculated and denoted as d3. The formula for calculating the distance is the Euclidean distance in a two-dimensional plane.

[0092] Based on the actual performance of the door closer 40, it can be observed that if the fire door 20 is open, the wider it is opened, the larger the alpha angle and the smaller the beta angle; and the ratios d1 / d2 and d3 / d2 will both increase. Based on this characteristic, we can determine whether the door closer 40 is abnormally damaged or whether the fire door 20 is open by setting certain thresholds. Specifically, the abnormality judgment logic is as follows: if at least two of the following four conditions are met—alpha > 60°, beta < 60°, d1 / d2 < 1.1, and d2 / d2 < 0.9—the door closer 40 is considered abnormal, or the fire door 20 is not closing properly.

[0093] This invention uses a robot 10 to perform image analysis on the door closer 40 and the fire safety door, thereby determining whether there are any abnormalities in the closing of the door closer 40 and the fire safety door. This breaks away from the traditional method of using security personnel for inspection, resulting in higher overall efficiency and significantly reducing problems such as false alarms and missed alarms caused by manual inspection.

[0094] According to a second aspect of the present invention, a system for detecting anomalies in fire escape door closers 40 is provided, applied to the fire escape door closer 40 anomaly detection method described in the above embodiments. The system includes a first acquisition module, a second acquisition module, a calculation module, and a judgment module. Specifically, the first acquisition module is used to patrol and detect the fire escape route using a robot 10, acquire photographic information of the closers 40, and push it to the background. The second acquisition module is used to acquire the bearing key point positions, confidence levels, and connection relationships of the closers 40 based on the acquired photographic information of the closers 40. The calculation module is used to calculate parameters for logical judgment based on the acquired bearing key point positions, confidence levels, and connection relationships of the closers 40. The judgment module uses a neural network model to perform logical judgment on the parameters to determine whether the closers 40 are abnormal.

[0095] This invention uses a robot 10 to perform image analysis on the door closer 40 and the fire safety door, thereby determining whether there are any abnormalities in the closing of the door closer 40 and the fire safety door. This breaks away from the traditional method of using security personnel for inspection, resulting in higher overall efficiency and significantly reducing problems such as false alarms and missed alarms caused by manual inspection.

[0096] According to a third aspect of the present invention, an electronic device is also provided, comprising: a processor 201 and a memory 202, wherein computer program instructions are stored in the memory 202, wherein when the computer program instructions are executed by the processor 201, the processor 201 causes the processor 201 to perform the steps of the abnormal detection method for the fire escape door closer 40 in the above embodiments.

[0097] Furthermore, such as Figure 5 As shown, the electronic device also includes a network interface 203, an input device 204, a hard disk 205, and a display device 206.

[0098] The various interfaces and devices described above can be interconnected via a bus architecture. The bus architecture can include any number of interconnecting buses and bridges. Specifically, various circuits of one or more central processing units 201 (CPUs), represented by processor 201, and one or more memories 202, represented by memory 202, are connected together. The bus architecture can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. It is understood that the bus architecture is used to implement communication between these components. In addition to the data bus, the bus architecture also includes a power bus, a control bus, and a status signal bus, which are well known in the art and therefore will not be described in detail herein.

[0099] The network interface 203 can be connected to a network (such as the Internet, local area network, etc.), obtain relevant data from the network, and save it to the hard disk 205.

[0100] Input device 204 can receive various instructions input by the operator and send them to processor 201 for execution. Input device 204 may include a keyboard or clicking device (e.g., mouse, trackball, touchpad, or touch screen).

[0101] Display device 206 can display the results obtained by the processor 201 executing instructions.

[0102] The memory 202 is used to store the programs and data necessary for the operation of the operating system 2021, as well as intermediate results and other data during the calculation process of the processor 201.

[0103] It is understood that the memory 202 in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. The memory 202 of the apparatus and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory 202.

[0104] In some implementations, memory 202 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating system 2021 and application 2022.

[0105] The operating system 2021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 2022 includes various applications, such as a browser, used to implement various application functions. Programs implementing the methods of this embodiment can be included in the application program 2022.

[0106] When the processor 201 calls and executes the application program 2022 and data stored in the memory 202, specifically the program or instructions stored in the application program 2022, it executes the steps of the abnormal detection method of the fire escape door closer 40 according to the above embodiment.

[0107] The methods disclosed in the above embodiments of the present invention can be applied to processor 201, or implemented by processor 201. Processor 201 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 201 or by instructions in the form of software. The processor 201 may be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor, or processor 201 may be any conventional processor 201, etc. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of hardware decoding processor, or executed by a combination of hardware and software modules in decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 202. The processor 201 reads the information in memory 202 and, in conjunction with its hardware, completes the steps of the above method.

[0108] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions of this application, or combinations thereof.

[0109] For software implementation, the techniques described herein can be implemented through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory 202 and executed by processor 201. Memory 202 can be implemented in processor 201 or external to processor 201.

[0110] Specifically, the processor 201 is also used to read the computer program and perform the following steps: predicting and outputting the answer to the user's question regarding the charging method for the charging pile.

[0111] According to a fourth aspect of the present invention, a computer-readable storage medium is also provided, which stores a computer program. When the computer program is run by a processor 201, the processor 201 performs the steps of the abnormal detection method for the fire escape door closer 40 described in the above embodiments.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0113] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0114] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute certain steps of the transmission and reception methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0115] While specific embodiments of the invention have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for detecting abnormalities in the door closer of a fire escape route, characterized in that, include: The robot patrols and inspects fire exits, captures information from door closers, and pushes it to the backend. Based on the acquired camera information of the door closer, the location, confidence level, and connection relationship of the bearing key points of the door closer are obtained. Based on the obtained bearing key point positions, confidence levels, and connection relationships of the bearing key points of the door closer, the parameters used for logical judgment are calculated. A neural network model is used to make logical judgments on the parameters in order to determine whether the door closer is abnormal. The step of obtaining the bearing key point location, confidence level, and connection relationship of the bearing key point based on the acquired image information of the door closer includes: The position of the door closer was detected using a detector. Based on the detected position of the door closer, determine whether the enclosure of the door closer has been detected; Based on the detected enclosure box, the bearing key points of the door closer are detected to obtain the bearing key point positions, confidence levels, and connection relationships of the bearing key points of the door closer. In the step of performing logical judgment on the parameters, if at least half of the logically judged parameters exceed the threshold, the door closer is determined to be abnormal. The steps for calculating the parameters used in the logical judgment include: Calculate the angle of the bearing connection point at the key bearing point; Based on the angle of the bearing connection point, the pixel distance of the bearing connection point is calculated to obtain parameters for logical judgment, so as to determine whether the door closer is abnormal.

2. The method for detecting abnormalities in the door closer of a fire escape route according to claim 1, characterized in that, The steps for using robots to patrol and inspect fire exits and obtain information from door closers include: Set up a robot patrol route and set up capture points along the patrol route; The robot is controlled to patrol according to the patrol route.

3. The method for detecting abnormalities in the door closer of a fire escape route according to claim 2, characterized in that, The robot is equipped with a camera, which captures information when the robot patrols to the capture point.

4. The method for detecting abnormalities in the door closer of a fire escape route according to claim 1, characterized in that, Also includes: An alarm is triggered when the door closer is detected to be malfunctioning.

5. A fire escape door closer malfunction detection system, applied to the fire escape door closer malfunction detection method according to any one of claims 1-4, characterized in that, The system includes: The first acquisition module is used to patrol and detect fire exits with a robot, acquire the camera information of the door closer, and push it to the background. The second acquisition module is used to acquire the bearing key point position, confidence level and connection relationship of the bearing key point based on the acquired shooting information of the door closer; The calculation module is used to calculate parameters for logical judgment based on the obtained bearing key point positions, confidence levels and connection relationships of the bearing key points of the door closer. The judgment module uses a neural network model to perform logical judgments on the parameters in order to determine whether the door closer is abnormal.

6. An electronic device, characterized in that, include: A processor and a memory, wherein computer program instructions are stored in the memory, wherein when the computer program instructions are executed by the processor, the processor causes the processor to perform the steps of the fire escape door closer abnormal detection method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the steps of the fire escape door closer abnormal detection method according to any one of claims 1-4.

Images