Power transmission line defect identification method and system based on edge computing

Abstract

The application discloses a power transmission line defect identification method and system based on edge calculation, and the method comprises the following steps: sending a request to a cloud computing platform, obtaining a monitoring task and an image analysis model corresponding to the monitoring task; identifying the monitoring task to obtain an image acquisition strategy of each monitoring task and an analysis and processing strategy of the acquired image; identifying the power transmission line defects according to the image acquisition strategy and the analysis and processing strategy of the acquired image, classifying the identified power transmission line defects; and uploading power transmission line defect log data generated based on the same category of power transmission line defects to the cloud computing platform. The application solves the problems of heavy background analysis load, low efficiency and low hidden danger monitoring quality in the case of large video stream access concurrency.

Description

Technical Field

[0001] This invention relates to the field of power transmission line safety monitoring technology, specifically to a method and system for identifying power transmission line defects based on edge computing. Background Technology

[0002] Currently, the online monitoring cameras in power transmission channels do not have edge computing capabilities. They can only transmit images back to the backend for analysis and processing. When the concurrent access of video streams is high, the backend analysis load is heavy and the efficiency is low. This can easily lead to situations where key images are not processed, which to some extent affects the quality of hazard monitoring. Summary of the Invention

[0003] To address the problems existing in the prior art, this invention provides a method and system for identifying transmission line defects based on edge computing. By deploying edge computing capabilities on edge computing devices for online monitoring of transmission channels, the computational pressure on cloud computing platforms is effectively alleviated. The technical solution is as follows:

[0004] Firstly, a method for identifying transmission line defects based on edge computing is provided, applied to edge computing equipment for online monitoring of transmission channels, including:

[0005] Send a request to the cloud computing platform to obtain the monitoring task and the corresponding image analysis model;

[0006] The monitoring tasks are identified, and the image acquisition strategy and image analysis and processing strategy for each monitoring task are obtained.

[0007] Based on the image acquisition strategy and the image analysis and processing strategy, the transmission line defects are identified and classified.

[0008] Transmission line defect log data is generated based on the same category of transmission line defects and uploaded to the cloud computing platform. The transmission line defect log data is obtained based on the preset log data generation strategy corresponding to different categories of transmission line defects.

[0009] As a further optimization of the above solution, transmission line defect log data based on the same category of transmission line defects is generated and uploaded to the cloud computing platform, including:

[0010] A data upload request is sent to the cloud computing platform. The data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines the order of each type of defect data uploaded by the online monitoring camera in the data receiving task queue according to the first parameter and the second parameter, and generates a data receiving instruction. The first parameter is a defect data category parameter, and the second parameter is a data size parameter for each type of defect data.

[0011] Receive data receiving instructions sent by the cloud computing platform.

[0012] As a further optimization of the above solution, the step of generating transmission line defect log data based on the same category of transmission line defects and uploading it to the cloud computing platform also includes:

[0013] Based on the received data receiving instructions, different categories of transmission line defect log data are uploaded to the cloud computing platform in time-sharing manner.

[0014] As a further optimization of the above scheme, the log data generation strategy corresponding to the preset data of different categories of transmission line defects includes:

[0015] Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, first data for identifying transmission line defects is obtained. The first data is obtained by analyzing and processing the acquired images based on the image acquisition strategy.

[0016] Log data is generated based on the first data, defect category, and defect location data.

[0017] As a further optimization of the above solution, the analysis and processing strategy based on the acquired images obtained from the cloud computing platform to obtain the first data for identifying transmission line defects includes:

[0018] Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, the shape module generates the shape map of the analysis and processing node according to the shape declaration and shape logic of each analysis and processing node;

[0019] The analysis and processing strategy is executed based on the shape diagram, and the next input node of the output result of the current analysis and processing node is determined based on the shape diagram to determine whether there is a transmission line defect identification node.

[0020] If so, the output of the current analysis and processing node will be stored in the first data storage module.

[0021] As a further optimization of the above scheme, after classifying the identified transmission line defects, the method further includes:

[0022] Based on the defect identification results, the image acquisition strategy is automatically adjusted to the optimal level.

[0023] Transmission line defects are identified based on images acquired using the optimal image acquisition strategy.

[0024] As a further optimization of the above scheme, the automatic adjustment of the image acquisition strategy to the optimal level based on the defect identification results includes:

[0025] If a defect is determined in the transmission line, the location of the defect is obtained, and the camera image acquisition parameters are adjusted to obtain a high-definition image of the transmission line defect.

[0026] Transmission line defect log data is generated based on high-definition images of transmission line defects.

[0027] Secondly, a transmission line defect identification system based on edge computing is provided, including:

[0028] The monitoring task parameter acquisition module is used to send a request to the cloud computing platform to obtain the monitoring task and the image analysis model corresponding to the monitoring task;

[0029] The monitoring task analysis module is used to identify monitoring tasks and obtain the image acquisition strategy and image analysis and processing strategy for each monitoring task.

[0030] The monitoring task execution module is used to identify transmission line defects based on the image acquisition strategy and the image analysis and processing strategy, and to classify the identified transmission line defects.

[0031] The monitoring task execution result upload module generates transmission line defect log data based on the same category of transmission line defects and uploads it to the cloud computing platform. The transmission line defect log data is obtained based on the preset log data generation strategy corresponding to different categories of transmission line defects.

[0032] Thirdly, an electronic device is provided, the electronic device comprising:

[0033] Memory, used to store executable instructions;

[0034] When the processor runs the executable instructions stored in the memory, it implements the above-described edge computing-based transmission line defect identification method.

[0035] Fourthly, a computer-readable storage medium is provided, storing executable instructions that, when executed by a processor, implement the aforementioned edge computing-based transmission line defect identification method.

[0036] The edge computing-based method and system for identifying transmission line defects of the present invention has the following beneficial effects: By deploying edge computing capabilities on the online monitoring edge computing device of the transmission channel, the computing pressure on the cloud computing platform is effectively alleviated. The online monitoring edge computing device of the transmission channel can be an online monitoring camera of the transmission channel. In this embodiment, each online monitoring edge computing device of the transmission channel obtains the monitoring task for identifying transmission line defects and the corresponding image analysis model required by the monitoring task from the cloud computing platform, thereby deploying the image analysis model to the online monitoring edge computing device of the transmission channel. The online monitoring edge computing device of the transmission channel identifies transmission line defects by analyzing the image acquisition strategy and the image analysis processing strategy, effectively improving the efficiency of transmission line defect identification. Furthermore, the online monitoring edge computing device of the transmission channel generates transmission line defect log data and uploads it to the cloud computing platform, avoiding the uploading of a large amount of invalid and redundant data to the cloud computing platform. Attached Figure Description

[0037] Figure 1 This is a flowchart of the transmission line defect identification method based on edge computing according to an embodiment of this application;

[0038] Figure 2 This is a structural diagram of the edge computing-based transmission line defect identification system implemented in this application. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] This application discloses a method for identifying defects in transmission lines based on edge computing, applied to an edge computing device for online monitoring of transmission channels, including:

[0041] Send a request to the cloud computing platform to obtain the monitoring task and the corresponding image analysis model;

[0042] The monitoring tasks are identified, and the image acquisition strategy and image analysis and processing strategy for each monitoring task are obtained.

[0043] Based on the image acquisition strategy and the image analysis and processing strategy, the transmission line defects are identified and classified.

[0044] Transmission line defect log data is generated based on the same category of transmission line defects and uploaded to the cloud computing platform. The transmission line defect log data is obtained based on the preset log data generation strategy corresponding to different categories of transmission line defects.

[0045] In this embodiment, by deploying edge computing capabilities on the online monitoring edge computing device of the power transmission channel, the computing pressure on the cloud computing platform is effectively alleviated. The online monitoring edge computing device can be a power transmission channel online monitoring camera. In this embodiment, each online monitoring edge computing device obtains the monitoring task for power transmission line defect identification and the corresponding image analysis model required by the monitoring task from the cloud computing platform. The image analysis model is then deployed to the online monitoring edge computing device. The online monitoring edge computing device identifies power transmission line defects by analyzing image acquisition and image analysis processing strategies, effectively improving the efficiency of power transmission line defect identification. Furthermore, the online monitoring edge computing device generates power transmission line defect log data and uploads it to the cloud computing platform, avoiding the uploading of a large amount of invalid and redundant data to the cloud computing platform.

[0046] The above-mentioned generation of transmission line defect log data based on the same category of transmission line defects and uploading it to the cloud computing platform includes:

[0047] A data upload request is sent to the cloud computing platform. The data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines the order of each type of defect data uploaded by the online monitoring camera in the data receiving task queue according to the first parameter and the second parameter, and generates a data receiving instruction. The first parameter is a defect data category parameter, and the second parameter is a data size parameter for each type of defect data.

[0048] Receive data receiving instructions sent by the cloud computing platform.

[0049] In this application, the edge computing device for online monitoring of power transmission channels first sends a data upload request to the cloud computing platform. The cloud computing platform, based on the received data upload request and the current status of its data receiving task queue, can rationally optimize the data upload scheme of the edge computing device for online monitoring of power transmission channels. This includes intelligently planning the order of uploading each type of defect data, the distribution of at least one upload time period, and the size of the data uploaded in each upload time period. This achieves efficient management of image data collected from power transmission lines and defect identification log data between the cloud computing platform and the edge computing device for online monitoring of power transmission channels.

[0050] The above-mentioned generation of transmission line defect log data based on the same category of transmission line defects and uploading it to the cloud computing platform also includes:

[0051] Based on the received data receiving instructions, different categories of transmission line defect log data are uploaded to the cloud computing platform in time-sharing manner.

[0052] In this embodiment, the cloud computing platform, based on the received data upload requests and the current status of the data receiving task queue, intelligently plans the order of uploading each type of defect data, the distribution of at least one upload time period, and the size of the data uploaded in each upload time period for each data upload request sent by the online monitoring edge computing device of the power transmission channel. This generates corresponding data receiving instructions. Each online monitoring edge computing device of the power transmission channel sequentially uploads the corresponding power transmission line defect log data packet based on the data receiving instructions received from the cloud computing platform, enabling the cloud computing platform to optimally plan the data receiving task.

[0053] The aforementioned log data generation strategies corresponding to different categories of transmission line defects include:

[0054] Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, first data for identifying transmission line defects is obtained. The first data is obtained by analyzing and processing the acquired images based on the image acquisition strategy.

[0055] Log data is generated based on the first data, defect category, and defect location data.

[0056] In this embodiment of the application, the original images of power transmission lines collected by the edge computing device for online monitoring of power transmission channels are processed by analyzing the first data that best represents the defects of the power transmission lines, thereby reducing the amount of power transmission line image data uploaded to the cloud computing platform.

[0057] The above-mentioned analysis and processing strategy based on images acquired from a cloud computing platform obtains first data for identifying transmission line defects, including:

[0058] Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, the shape module generates the shape map of the analysis and processing node according to the shape declaration and shape logic of each analysis and processing node;

[0059] The analysis and processing strategy is executed based on the shape diagram, and the next input node of the output result of the current analysis and processing node is determined based on the shape diagram to determine whether there is a transmission line defect identification node.

[0060] If so, the output of the current analysis and processing node will be stored in the first data storage module.

[0061] In this embodiment, the first data that best characterizes the transmission line defects is obtained during the analysis and processing strategy process. A shape graph is constructed based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform. Specifically, the shape declaration and shape logic of the analysis and processing node can be determined based on parameters such as the number of network layers in each module of the image analysis model, the size of each network layer, the upstream and downstream relationship of data transmission between two network layers, and the data processing logic of each network layer. Each node in the image acquisition analysis and processing process is analyzed to determine whether the output result of the current node is part of the target first data. If so, it is stored in the first data storage module, thereby obtaining all the first data that best characterizes the transmission line defects. For the first data in the first data storage module, the importance weight ratio of each part of the first data can be further analyzed to determine the more important data parts in the first data.

[0062] After classifying the identified transmission line defects as described above, the following also applies:

[0063] Based on the defect identification results, the image acquisition strategy is automatically adjusted to the optimal level.

[0064] Transmission line defects are identified based on images acquired using the optimal image acquisition strategy.

[0065] In this embodiment of the application, after determining that a defect exists in the current transmission line image, the image acquisition strategy can be adjusted based on further analysis requirements to obtain the optimal image representation of the current defect location. This optimal image representation can be a close-up high-definition image including the current defect, a global image including the current defect, or a set of multi-angle images including the current defect.

[0066] The above-mentioned automatic adjustment of the image acquisition strategy to the optimal level based on the defect identification results includes:

[0067] If a defect is determined in the transmission line, the location of the defect is obtained, and the camera image acquisition parameters are adjusted to obtain a high-definition image of the transmission line defect.

[0068] Transmission line defect log data is generated based on high-definition images of transmission line defects.

[0069] The above-mentioned steps for obtaining the location of the defect and adjusting the camera image acquisition parameters include:

[0070] Based on the image used to determine the presence of defects in the transmission line as the first image, the center coordinates of the first image are obtained as the first coordinates;

[0071] The center coordinates of the defect location on the first image are used as the second coordinates.

[0072] The camera is adjusted to a first position at a distance from the second coordinate to take a picture, and the image captured at the first position is subjected to image quality detection.

[0073] For the first position image that passes the image quality detection, obtain a three-dimensional space with the first position as the vertex and the second coordinate as the centroid;

[0074] The camera position and shooting angle are moved to the vertices of the three-dimensional space to capture images of the defect locations.

[0075] For the first position image that fails the above image quality detection, the camera is adjusted to take a picture at a second position at a distance from the second coordinate. The image taken at the second position is then subjected to image quality detection. This second position is different from the first position. Of course, the second position is determined based on the result of the first position image to determine whether the distance between the second position and the second coordinate is increased or decreased compared to the first position.

[0076] This application discloses a transmission line defect identification system based on edge computing, including:

[0077] The monitoring task parameter acquisition module is used to send a request to the cloud computing platform to obtain the monitoring task and the image analysis model corresponding to the monitoring task;

[0078] The monitoring task analysis module is used to identify monitoring tasks and obtain the image acquisition strategy and image analysis and processing strategy for each monitoring task.

[0079] The monitoring task execution module is used to identify transmission line defects based on the image acquisition strategy and the image analysis and processing strategy, and to classify the identified transmission line defects.

[0080] The monitoring task execution result upload module generates transmission line defect log data based on the same category of transmission line defects and uploads it to the cloud computing platform. The transmission line defect log data is obtained based on the preset log data generation strategy corresponding to different categories of transmission line defects.

[0081] Specific limitations regarding the edge computing-based transmission line defect identification system can be found in the limitations of the edge computing-based transmission line defect identification method described above, and will not be repeated here. Each module in the aforementioned edge computing-based transmission line defect identification system can be implemented entirely or partially through software, hardware, or a combination thereof. The edge computing-based transmission line defect identification system provided in this application embodiment can be implemented using a combination of software and hardware. As an example, the edge computing-based transmission line defect identification system provided in this embodiment can be directly embodied as a combination of software modules executed by a processor. The software modules can be located in a storage medium, which is located in a memory. The processor reads the executable instructions included in the software modules from the memory and combines them with necessary hardware (e.g., including the processor and other components connected to the bus) to complete the edge computing-based transmission line defect identification method provided in this embodiment.

[0082] This application discloses an electronic device, which includes:

[0083] Memory, used to store executable instructions;

[0084] When the processor runs the executable instructions stored in the memory, it implements the above-described edge computing-based transmission line defect identification method.

[0085] The electronic device provided in this application includes at least one processor, a memory, a user interface, and at least one network interface. The various components in the electronic device are coupled together via a bus system. It is understood that the bus system is used to implement communication between these components. In addition to a data bus, the bus system also includes a power bus, a control bus, and a status signal bus.

[0086] This application discloses a computer-readable storage medium storing executable instructions. When these executable instructions are executed by a processor, they implement the aforementioned edge computing-based transmission line defect identification method. It is understood that the computer-readable storage medium can be a read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, or optical data storage node, etc.

[0087] This invention is not limited to the specific embodiments described above. Any modifications made by those skilled in the art based on the above concept without creative effort are within the scope of protection of this invention.

Claims

1. A method for identifying transmission line defects based on edge computing, applied to edge computing equipment for online monitoring of transmission channels, characterized in that, include: Send a request to the cloud computing platform to obtain the monitoring task and the corresponding image analysis model; The monitoring tasks are identified, and the image acquisition strategy and image analysis and processing strategy for each monitoring task are obtained. Based on the image acquisition strategy and the image analysis and processing strategy, the transmission line defects are identified and classified. Transmission line defect log data is generated based on the same category of transmission line defects and uploaded to the cloud computing platform. The transmission line defect log data is obtained based on the preset log data generation strategy corresponding to different categories of transmission line defects. Based on the received data receiving instructions, different categories of transmission line defect log data are uploaded to the cloud computing platform in time-sharing manner; The process of generating transmission line defect log data based on the same category of transmission line defects and uploading it to the cloud computing platform includes: A data upload request is sent to the cloud computing platform. The data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines the order of each type of defect data uploaded by the online monitoring camera in the data receiving task queue according to the first parameter and the second parameter, and generates a data receiving instruction. The first parameter is a defect data category parameter, and the second parameter is a data size parameter for each type of defect data. Receive data receiving instructions sent by the cloud computing platform; The preset log data generation strategy for different categories of transmission line defects includes: Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, first data for identifying transmission line defects is obtained. The first data is obtained by analyzing and processing the acquired images based on the image acquisition strategy. Log data is generated based on the initial data, defect category, and defect location data. The analysis and processing strategy based on the acquired images obtained from the cloud computing platform obtains first data for identifying transmission line defects, including: Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, the shape module generates the shape map of the analysis and processing node according to the shape declaration and shape logic of each analysis and processing node; The analysis and processing strategy is executed based on the shape diagram, and the next input node of the output result of the current analysis and processing node is determined based on the shape diagram to determine whether there is a transmission line defect identification node. If so, the output of the current analysis and processing node will be stored in the first data storage module.

2. The method for identifying transmission line defects based on edge computing according to claim 1, characterized in that, After classifying the identified transmission line defects, the process also includes: Based on the defect identification results, the image acquisition strategy is automatically adjusted to the optimal level. Transmission line defects are identified based on images acquired using the optimal image acquisition strategy.

3. The method for identifying transmission line defects based on edge computing according to claim 2, characterized in that, The automatic adjustment of the image acquisition strategy to the optimal level based on the defect identification results includes: If a defect is determined in the transmission line, the location of the defect is obtained, and the camera image acquisition parameters are adjusted to obtain a high-definition image of the transmission line defect. Transmission line defect log data is generated based on high-definition images of transmission line defects.

4. A transmission line defect identification system based on edge computing, characterized in that, include: The monitoring task parameter acquisition module is used to send a request to the cloud computing platform to obtain the monitoring task and the image analysis model corresponding to the monitoring task; The monitoring task analysis module is used to identify monitoring tasks and obtain the image acquisition strategy and image analysis and processing strategy for each monitoring task. The monitoring task execution module is used to identify transmission line defects based on the image acquisition strategy and the image analysis and processing strategy, and to classify the identified transmission line defects. The monitoring task execution result upload module generates transmission line defect log data based on the same category of transmission line defects and uploads it to the cloud computing platform. The transmission line defect log data is obtained based on the preset log data generation strategy corresponding to different categories of transmission line defects. Based on the received data receiving instructions, different categories of transmission line defect log data are uploaded to the cloud computing platform in time-sharing manner; The process of generating transmission line defect log data based on the same category of transmission line defects and uploading it to the cloud computing platform includes: A data upload request is sent to the cloud computing platform. The data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines the order of each type of defect data uploaded by the online monitoring camera in the data receiving task queue according to the first parameter and the second parameter, and generates a data receiving instruction. The first parameter is a defect data category parameter, and the second parameter is a data size parameter for each type of defect data. Receive data receiving instructions sent by the cloud computing platform; The preset log data generation strategy for different categories of transmission line defects includes: Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, first data for identifying transmission line defects is obtained. The first data is obtained by analyzing and processing the acquired images based on the image acquisition strategy. Log data is generated based on the initial data, defect category, and defect location data. The analysis and processing strategy based on the acquired images obtained from the cloud computing platform obtains first data for identifying transmission line defects, including: Based on the analysis and processing strategy of the acquired images obtained from the cloud computing platform, the shape module generates the shape map of the analysis and processing node according to the shape declaration and shape logic of each analysis and processing node; The analysis and processing strategy is executed based on the shape diagram, and the next input node of the output result of the current analysis and processing node is determined based on the shape diagram to determine whether there is a transmission line defect identification node. If so, the output of the current analysis and processing node will be stored in the first data storage module.

5. An electronic device, characterized in that, The electronic device includes: Memory, used to store executable instructions; The processor, when running the executable instructions stored in the memory, implements the edge computing-based transmission line defect identification method according to any one of claims 1 to 3.

6. A computer-readable storage medium storing executable instructions, characterized in that, When the executable instructions are executed by the processor, they implement the edge computing-based transmission line defect identification method according to any one of claims 1 to 3.

Images