An overhead line defect detection system and method

Abstract

The application belongs to the technical field of overhead line defect detection, and specifically provides an overhead line defect detection system and method, wherein the method comprises: a UAV flies along an overhead line with a front-end camera detection device; the front-end camera detection device samples data of the overhead line, compares and analyzes the collected data with historical data, and obtains defect characteristics; and a database server stores the collected data and comparison and analysis results. The scheme can improve the accuracy of overhead line defect detection, improve the reliability of overhead line defect detection operation, and ensure the safety of the overhead line.

Description

Technical Field

[0001] This invention relates to the field of overhead line defect detection technology, and more specifically, to an overhead line defect detection system and method. Background Technology

[0002] Inspection of 10kV railway lines and automatic overhead lines is essential for ensuring a continuous and stable power supply to important railway equipment. Its purpose is to detect defects and diagnose faults in power lines and other line equipment, while also observing potential hazards around the power lines.

[0003] Overhead line defect detection systems are automated devices for safety emergency response, primarily used on overhead power lines. However, when serious accidents occur on overhead lines, such as insulation damage, broken insulators, tilted crossarms, tilted poles, dense vegetation, or severe vibrations, the power supply stability of the line cannot be guaranteed.

[0004] A more reliable traditional method involves regular manual patrols along the line. This primarily involves observing the line to identify defects such as damaged insulation, broken insulators, tilted crossarms, tilted poles, excessive tree cover, and vibrations in the overhead lines. These defects are then recorded or rectified on-site. However, this method is inefficient and labor-intensive.

[0005] In addition, another method involves using drones to take aerial photographs along the line, followed by careful observation and analysis of the video footage to determine defects such as damaged insulation, broken insulators, tilted crossarms, tilted poles, excessive tree cover, and vibrations in the overhead lines. However, this method is time-consuming, has limited accuracy, and is prone to missing defects. Therefore, there is an urgent need to adopt image-based intelligent recognition technology for defect identification to ensure the safe operation of railway power lines. Summary of the Invention

[0006] This invention addresses the technical problem of low accuracy in detecting defects in traditional overhead lines, a problem present in existing technologies.

[0007] This invention provides an overhead line defect detection system, comprising:

[0008] A drone carrying a front-end camera detection device flies along an overhead power line.

[0009] The front-end camera detection device samples data from overhead lines and compares and analyzes the collected data with historical data to determine defect characteristics;

[0010] A database server is used to store the collected data and comparative analysis results.

[0011] Preferably, the drone is remotely operated to fly along an overhead route, and the flight route is recorded to form an automatic navigation route.

[0012] Preferably, the front-end camera detection device includes a memory for storing historical data according to a time schedule, the historical data including insulator defect features, power pole tower defect features, and conductor defect features.

[0013] Preferably, the insulator defect characteristics include insulator surface spontaneous explosion, insulator surface wear, insulator vibration, insulator displacement, insulator loosening, insulator overheating, insulator surface corrosion, insulator surface dirt, insulator surface bird droppings, insulator surface bird nests, and foreign matter on the insulator surface;

[0014] The defects of the power poles include wear on the surface of the power poles, tilting of the power poles, corrosion of the surface of the power poles, loosening of the power poles, flooding of the power poles, and exposed steel bars on the surface of the power poles;

[0015] The defects in the conductors include spontaneous breakage, wear, vibration, misalignment, loosening, overheating, corrosion, dirt, bird droppings, bird nests, and foreign objects.

[0016] Preferably, the front-end camera detection device includes an analysis module, which performs sample deep learning based on a neural network on historical data of overhead lines to match insulator defect features, power pole tower defect features and conductor defect features, and then stores them in a memory.

[0017] Preferably, the front-end camera detection device acquires image data of the conductor and conductor crossarm, and the analysis module compares and analyzes each image data with historical data of the same period to obtain the conductor inclination angle change and conductor crossarm deformation, and then calculates the conductor crossarm tension and conductor tension magnitude.

[0018] Preferably, the wind deflection angle of the conductor changes with the month by the camera of the front-end camera detection device, and a time-wind deflection angle change curve is plotted; the analysis module performs deep training on the data in the historical change curve to obtain standard data of conductor tilt angle and conductor crossarm deformation at different periods; then the standard data is compared and analyzed with the real-time collected data to determine whether there are conductor defect characteristics.

[0019] The present invention also provides a method for detecting defects in overhead lines, wherein the system is used to implement the overhead line defect detection system, comprising:

[0020] The drone, carrying a front-end camera detection device, flew along the overhead power line;

[0021] The front-end camera detection device samples data from the overhead line and compares and analyzes the collected data with historical data to determine the defect characteristics;

[0022] The database server stores the collected data and comparative analysis results.

[0023] The present invention also provides an electronic device, including a memory and a processor, wherein the processor is used to implement the steps of the overhead line defect detection method when executing a computer management program stored in the memory.

[0024] The present invention also provides a computer-readable storage medium storing a computer management program thereon, which, when executed by a processor, implements the steps of an overhead line defect detection method.

[0025] Beneficial Effects: This invention provides an overhead power line defect detection system and method. The method includes: a drone carrying a front-end camera detection device flies along the overhead power line; the front-end camera detection device samples data from the overhead power line and compares and analyzes the collected data with historical data to obtain defect characteristics; a database server stores the collected data and the comparison and analysis results. This solution can improve the accuracy of overhead power line defect detection, improve the reliability of overhead power line defect detection operation, and ensure the safety of overhead power lines. Attached Figure Description

[0026] Figure 1 A schematic diagram of an overhead line defect detection system provided by the present invention;

[0027] Figure 2 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0028] Figure 3 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention;

[0029] Figure 4 A comparative analysis diagram of conductor defects provided by the present invention. Detailed Implementation

[0030] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0031] Figure 1 The present invention provides an overhead line defect detection system, comprising:

[0032] The drone, carrying a front-end camera detection device, flies along the overhead power line. The front-end camera detection device captures and collects image data of the overhead power line in real time, including image acquisition of key objects such as conductors, insulators, and power poles.

[0033] The front-end camera inspection device samples data from overhead lines and compares the collected data with historical data to determine defect characteristics. Historical data, including images of key objects under normal conditions and detected defect information, is stored. If the currently collected image differs from historical data, defect characteristics can be determined.

[0034] The database server stores the collected data and comparative analysis results. Staff can query historical data and detected defect data.

[0035] In a preferred embodiment, the drone is remotely operated to fly along an overhead line, and the flight path is recorded to form an automatic navigation route. For different overhead lines, the drone is first controlled to fly along the line to obtain the automatic navigation route and the attitude information of the camera on the front-end camera detection device. The real-time attitude of the camera is highly matched with the automatic navigation route. During automatic navigation, the camera is aimed at key objects such as power lines, power poles, and insulators in real time to collect image data. The camera is mounted on a gimbal, and the gimbal is automatically controlled to lock onto key objects for image sampling.

[0036] In a preferred embodiment, the front-end camera detection device includes a memory for storing historical data according to a timeline. This historical data includes insulator defect features, power pole tower defect features, and conductor defect features. The memory stores the historical data, including insulator defect features, power pole tower defect features, and conductor defect features. When conductor data is sampled during imaging, the conductor data is compared and analyzed with the conductor defect features. If the similarity reaches a certain level, it indicates that a defect exists in the conductor.

[0037] The defects include: Insulator defects such as spontaneous explosion, surface wear, vibration, displacement, loosening, overheating, corrosion, contamination, bird droppings, bird nests, and foreign objects. Power pole defects include surface wear, tilting, rust, loosening, flooding, and exposed reinforcing steel. Conductor defects include spontaneous explosion, wear, vibration, displacement, loosening, overheating, corrosion, contamination, bird droppings, bird nests, and foreign objects.

[0038] In a preferred embodiment, the front-end camera detection device includes an analysis module. This module performs deep learning on historical data of overhead lines using a neural network to match insulator defect features, power pole tower defect features, and conductor defect features, which are then stored in a memory. By training on historical data, using a portion as a training set and a portion as a validation set, defect feature detection models for different key objects are obtained. During detection, real-time collected data is input into the defect feature detection model to output whether defect features are present.

[0039] In a preferred embodiment, a front-end camera detection device acquires image data of the conductor and its crossarm. An analysis module compares these image data with historical data from the same period to obtain changes in the conductor's inclination angle and crossarm deformation. Then, it calculates the crossarm tension and the conductor's tensile force. By storing historical data on the conductor's inclination angle and crossarm posture from the same period, and comparing the current inclination angle and crossarm posture with those from the same historical period, the changes in conductor inclination angle and crossarm deformation can be obtained. The tensile force can then be calculated based on the deformation. If the tensile force exceeds a certain limit, it indicates a defect.

[0040] In a preferred embodiment, the front-end camera detection device collects the wind deflection angle of the conductor as it changes monthly, plotting a time-wind deflection angle variation curve. The analysis module performs deep training on the data from the historical variation curve to obtain standard data on the conductor tilt angle and crossarm deformation at different times. Then, the standard data is compared and analyzed with the real-time acquired data to determine whether conductor defects exist. Figure 4 The above describes the use of neural networks for deep training; collecting the wind deflection angle of overhead lines as they change month by month; Series 1 is long-term collected data, showing that the wind force may vary with the month, exhibiting regular fluctuations; while Series 2 shows that the wind deflection angle remains constant after October. After deep training and comparison, it can be seen that wind force causes permanent faults in overhead lines that cannot be restored to their original state, such as spontaneous explosion, wear, vibration, displacement, loosening, overheating, and corrosion.

[0041] This invention also provides a method for detecting defects in overhead lines. The system is used to implement an overhead line defect detection system, comprising:

[0042] The drone, carrying a front-end camera detection device, flew along the overhead power line;

[0043] The front-end camera detection device samples data from the overhead line and compares and analyzes the collected data with historical data to determine the defect characteristics;

[0044] The database server stores the collected data and comparative analysis results.

[0045] Please see Figure 2 This is a schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 2 As shown, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, it performs the following steps: the drone carrying the front-end camera detection device flies along the overhead line.

[0046] The front-end camera detection device samples data from the overhead line and compares and analyzes the collected data with historical data to determine the defect characteristics;

[0047] The database server stores the collected data and comparative analysis results.

[0048] Please see Figure 3 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by the present invention. (See diagram below.) Figure 3 As shown, this embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, it performs the following steps: the drone carrying the front-end camera detection device flies along the overhead line;

[0049] The front-end camera detection device samples data from the overhead line and compares and analyzes the collected data with historical data to determine the defect characteristics;

[0050] The database server stores the collected data and comparative analysis results.

[0051] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0052] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0057] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An overhead line defect detection system, characterized in that, include: A drone carrying a front-end camera detection device flies along an overhead power line. The drone is remotely operated to fly along an overhead line and record the flight path to form an automatic navigation route. Specifically, for different overhead lines, the drone is controlled to fly along the overhead line to obtain the automatic navigation route and the attitude information of the camera of the front-end camera detection device. The real-time attitude of the camera is highly matched with the automatic navigation route. During automatic navigation, the camera is aimed at key objects such as power lines, power poles and insulators in real time to collect image data. The camera is mounted on a gimbal, and the gimbal is automatically controlled to lock onto key objects for shooting and sampling. The front-end camera detection device samples data from overhead lines and compares and analyzes the collected data with historical data to determine defect characteristics; The front-end camera detection device includes a memory for storing historical data according to a time schedule. The historical data includes insulator defect features, power pole tower defect features, and conductor defect features. Power pole tower defect features include surface wear, tilting, corrosion, loosening, flooding, and exposed rebar. Conductor defect features include spontaneous explosion, wear, vibration, misalignment, loosening, overheating, corrosion, dirt, bird droppings, bird nests, and foreign objects. The front-end camera detection device includes an analysis module for performing deep learning on historical data of overhead lines using a neural network to match insulator defect features, power pole tower defect features, and conductor defect features, which are then stored in the memory. By training on historical data, using a portion as a training set and a portion as a validation set, defect feature detection models for different key objects are obtained. During detection, real-time collected data is input into the memory. The defect feature detection model can output whether there are defect features by performing detection within the model. The front-end camera detection device collects image data of the conductor and conductor crossarm. The analysis module compares and analyzes each image data with historical data of the same period to obtain the conductor tilt angle change and conductor crossarm deformation, and then calculates the conductor crossarm tension and conductor tension. By storing historical data of conductor tilt angle and conductor crossarm posture of the same period, and comparing and analyzing the current conductor tilt angle and conductor crossarm posture with the historical conductor tilt angle and conductor crossarm posture of the same period, the conductor tilt angle change and conductor crossarm deformation can be obtained. The tension can be calculated based on the deformation. If the tension exceeds the limit value, it indicates that there is a defect. The camera of the front-end camera detection device collects the wind deflection angle of the conductor as the month changes and draws a time-wind deflection angle change curve. The analysis module performs deep training on the data in the historical change curve to obtain standard data of conductor tilt angle and conductor crossarm deformation at different periods. Then, by comparing and analyzing the standard data with the real-time acquired data, it can be determined whether there are any wire defect characteristics. A database server is used to store the collected data and comparative analysis results.

2. A method for detecting defects in overhead power lines, characterized in that, The method is used to implement the overhead line defect detection system as described in claim 1, comprising: The drone, carrying a front-end camera detection device, flew along the overhead power line; The front-end camera detection device samples data from the overhead line and compares and analyzes the collected data with historical data to determine the defect characteristics; The database server stores the collected data and comparative analysis results.

3. An electronic device, characterized in that, It includes a memory and a processor, wherein the processor is used to execute computer management programs stored in the memory to implement the steps of the overhead line defect detection method as described in claim 2.

4. A computer-readable storage medium, characterized in that, It stores a computer management program, which, when executed by a processor, implements the steps of the overhead line defect detection method as described in claim 2.

Images