WO2023005100A1 - Power transmission line defect identification method and system based on edge computing - Google Patents

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

Info

Publication number
WO2023005100A1
WO2023005100A1 PCT/CN2021/137341 CN2021137341W WO2023005100A1 WO 2023005100 A1 WO2023005100 A1 WO 2023005100A1 CN 2021137341 W CN2021137341 W CN 2021137341W WO 2023005100 A1 WO2023005100 A1 WO 2023005100A1
Authority
WO
WIPO (PCT)
Prior art keywords
transmission line
data
line defect
defect
analysis
Prior art date
Application number
PCT/CN2021/137341
Other languages
French (fr)
Chinese (zh)
Inventor
徐海青
窦国贤
王维佳
廖逍
陈是同
白景颇
梁翀
毛舒乐
赵云龙
高亮
Original Assignee
安徽继远软件有限公司
国网信息通信产业集团有限公司
国家电网有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 安徽继远软件有限公司, 国网信息通信产业集团有限公司, 国家电网有限公司 filed Critical 安徽继远软件有限公司
Publication of WO2023005100A1 publication Critical patent/WO2023005100A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection

Definitions

  • the invention relates to the technical field of transmission line safety monitoring, in particular to a transmission line defect identification method and system based on edge computing.
  • the current online monitoring cameras of power transmission channels do not have edge computing capabilities, and can only send images back to the background for analysis and processing.
  • the background analysis load is heavy and the efficiency is low, which may easily cause key images to not be processed. To a certain extent, the quality of hidden danger monitoring has been affected.
  • the present invention provides a transmission line defect identification method and system based on edge computing.
  • edge computing capabilities on edge computing devices for online monitoring of transmission channels, the computing pressure on the cloud computing platform is effectively relieved.
  • a transmission line defect identification method based on edge computing is provided, which is applied to edge computing equipment for online monitoring of transmission channels, including:
  • Identify the monitoring task obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
  • the transmission line defects are identified, and the identified transmission line defects are classified;
  • the transmission line defect log data is generated based on the same type of transmission line defect 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 the data of different types of transmission line defects.
  • the transmission line defect log data generated based on the same type of transmission line defect is uploaded to the cloud computing platform, including:
  • the data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines that each type of defect data uploaded by the online monitoring camera is in the data according to the first parameter and the second parameter receiving the sequence in the task queue, and generating a data receiving instruction; wherein, the first parameter adopts the defect data category parameter, and the second parameter adopts the data size parameter of each category of defect data;
  • the transmission line defect log data generated based on the transmission line defect of the same category is uploaded to the cloud computing platform, and further includes:
  • the log data generation strategy corresponding to the preset data of different types of transmission line defects includes:
  • the first data for identifying the defect of the transmission line is obtained, and the first data is obtained through analysis and processing of the collected image obtained based on the image collection strategy;
  • Log data is generated based on the first data, defect category, and defect location data.
  • the analysis and processing strategy based on the collected images obtained from the cloud computing platform to obtain the first data for identifying defects in the transmission line includes:
  • the shape module Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the shape module generates the shape graph of the analysis and processing node according to the shape statement and shape logic of each analysis and processing node;
  • the transmission line defect recognition is carried out.
  • the automatic adjustment of the image acquisition strategy to the optimum based on the defect identification result includes:
  • a transmission line defect identification system based on edge computing including:
  • 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 the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
  • the monitoring task execution module is used to identify transmission line defects according to the image acquisition strategy and the analysis and processing strategy of the collected images, and classify the identified transmission line defects;
  • the monitoring task execution result upload module generates transmission line defect log data based on transmission line defects of the same type and uploads them to the cloud computing platform.
  • the transmission line defect log data is based on the log data generation strategy corresponding to the preset data of different types of transmission line defects acquired.
  • an electronic device in a third aspect, includes:
  • the processor is configured to implement the above-mentioned edge computing-based transmission line defect identification method when running the executable instructions stored in the memory.
  • a computer-readable storage medium which stores executable instructions, and when the executable instructions are executed by a processor, the above-mentioned edge computing-based transmission line defect identification method is implemented.
  • a transmission line defect identification method and system based on edge computing of the present invention has the following beneficial effects: by deploying edge computing capabilities on edge computing devices for online monitoring of power transmission channels, the computing pressure on the cloud computing platform is effectively relieved, wherein the transmission channel is online
  • the monitoring edge computing device can be an online monitoring camera for transmission channels.
  • each transmission channel online monitoring edge computing device obtains the monitoring tasks for identifying defects of transmission lines and the images required for the corresponding monitoring tasks from the cloud computing platform.
  • Analysis model so as to deploy the image analysis model to the edge computing equipment for online monitoring of transmission channels.
  • the edge computing equipment for online monitoring of transmission channels can identify transmission line defects by analyzing image acquisition strategies and image analysis and processing strategies, effectively improving the efficiency of transmission line defect identification, and further , the transmission channel online monitoring edge computing device generates transmission line defect log data and uploads it to the cloud computing platform, which avoids a large amount of invalid redundant data being uploaded to the cloud computing platform.
  • Fig. 1 is the flow chart of the transmission line defect identification method based on edge computing according to the embodiment of the present application
  • Fig. 2 is a structural diagram of a transmission line defect identification system based on edge computing in the implementation of this application.
  • the embodiment of the present application discloses a transmission line defect identification method based on edge computing, which is applied to edge computing equipment for online monitoring of power transmission channels, including:
  • Identify the monitoring task obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
  • the transmission line defects are identified, and the identified transmission line defects are classified;
  • the transmission line defect log data is generated based on the same type of transmission line defect 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 the data of different types of transmission line defects.
  • the edge computing device for online monitoring of the power transmission channel by deploying the edge computing capability on the edge computing device for online monitoring of the power transmission channel, the computing pressure on the cloud computing platform can be effectively relieved, wherein the edge computing device for online monitoring of the power transmission channel can be an online monitoring camera for the power transmission channel.
  • the edge computing device for online monitoring of each transmission channel obtains the monitoring tasks for transmission line defect identification and the image analysis model required for the corresponding monitoring tasks from the cloud computing platform, so as to deploy the image analysis model to the edge computing for online monitoring of transmission channels Equipment, online monitoring of transmission channels
  • Edge computing devices identify transmission line defects by analyzing image acquisition strategies and image analysis and processing strategies, effectively improving the efficiency of transmission line defect identification. Further, edge computing devices for online monitoring of transmission channels generate transmission line defect log data to upload To the cloud computing platform, avoiding a large amount of invalid redundant data uploaded to the cloud computing platform.
  • the above-mentioned generation of transmission line defect log data based on the same type of transmission line defect is uploaded to the cloud computing platform, including:
  • the data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines that each type of defect data uploaded by the online monitoring camera is in the data according to the first parameter and the second parameter receiving the sequence in the task queue, and generating a data receiving instruction; wherein, the first parameter adopts the defect data category parameter, and the second parameter adopts the data size parameter of each category of defect data;
  • the edge computing device for online monitoring of the transmission channel first sends a data upload request to the cloud computing platform, so that the cloud computing platform can rationally optimize the power transmission according to the received data upload request and the current status of the data receiving task queue of the cloud computing platform
  • the channel online monitors the data uploaded by edge computing devices, intelligently plans the sequence of uploading each type of defect data, the distribution of at least one upload time period, and the size of uploaded data in each upload time period. In this way, the efficient management of the image data collected by the transmission line and the defect identification log data between the cloud computing platform and the online monitoring edge computing device of the transmission channel is realized.
  • the above-mentioned generation of transmission line defect log data based on the same type of transmission line defect is uploaded to the cloud computing platform, which also includes:
  • the cloud computing platform intelligently plans and uploads the data upload request sent by the edge computing device for each power transmission channel based on the received data upload request and combined with the current state of the data receiving task queue of the cloud computing platform.
  • the sequence of each type of defect data, the distribution of at least one upload time period, the size of uploaded data in each upload time period, etc., so as to generate the corresponding data receiving instructions, and the online monitoring edge computing equipment of each transmission channel is based on the data received from the cloud computing platform.
  • the received data receiving instructions are sequentially uploaded to the corresponding transmission line defect log data packets, so that the cloud computing platform can optimally plan the data receiving tasks.
  • the above preset log data generation strategies corresponding to the data of different types of transmission line defects include:
  • the first data for identifying the defect of the transmission line is obtained, and the first data is obtained through analysis and processing of the collected image obtained based on the image collection strategy;
  • Log data is generated based on the first data, defect category, and defect location data.
  • the first data that best characterizes the defect of the transmission line obtained through the analysis and processing strategy process reduces the transmission line image data uploaded to the cloud computing platform .
  • the above-mentioned analysis and processing strategy based on the collected images obtained from the cloud computing platform obtains the first data for identifying the defects of the transmission line, including:
  • the shape module Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the shape module generates the shape graph of the analysis and processing node according to the shape statement and shape logic of each analysis and processing node;
  • the first data that best characterizes the defects of the transmission line is obtained in the process of analysis and processing strategy, and the analysis and processing strategy of the collected image obtained from the cloud computing platform is used to construct the shape graph, and the analysis and processing of the collected image based on the structure
  • the shape diagram corresponding to the strategy, specifically, the shape declaration and shape logic of the analysis processing node can be based on the number of network layers of each module in the image analysis model, the size of each network layer, and the data relationship between two network layers Parameters such as transmission upstream and downstream relations, data processing logic of each network layer, etc.
  • each node in the process of collecting image analysis and processing is analyzed to determine whether the output result of the current node is part of the target first data, and if so, save input into the first data storage module, so as to obtain all the first data that can best represent the defects of the transmission line, and 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, so that More important data parts in the first data are determined.
  • the transmission line defect recognition is carried out.
  • the image acquisition strategy may be adjusted based on further analysis requirements to obtain the best image representation of the current defect location.
  • the best image representation can be a short-distance high-definition image including the current defect, a global image including the current defect, or a multi-angle image collection including the current defect.
  • the image acquisition strategy is automatically adjusted to the optimum, including:
  • the central coordinates of the first image are acquired as the first coordinates
  • Moving the camera position and shooting angle to the apex of the three-dimensional space collects images for the defect positions respectively.
  • the camera For the image at the first position that does not pass the above image quality inspection, adjust the camera to take pictures at a second position away from the second coordinates, and perform image quality inspection on the image taken at the second position.
  • the second position is the same as the first position. They are two different positions.
  • the second position determines whether the distance between the second position and the second coordinate is increased or decreased compared with the first position based on the image shooting result of the first position.
  • the embodiment of the present application discloses a transmission line defect identification system based on edge computing, including:
  • 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 the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
  • the monitoring task execution module is used to identify transmission line defects according to the image acquisition strategy and the analysis and processing strategy of the collected images, and classify the identified transmission line defects;
  • the monitoring task execution result upload module generates transmission line defect log data based on transmission line defects of the same type and uploads them to the cloud computing platform.
  • the transmission line defect log data is based on the log data generation strategy corresponding to the preset data of different types of transmission line defects acquired.
  • edge computing-based transmission line defect identification system For the specific limitations of the edge computing-based transmission line defect identification system, please refer to the above-mentioned definition of the edge computing-based transmission line defect identification method, which will not be repeated here.
  • Each module in the above-mentioned edge computing-based transmission line defect identification system can be realized in whole or in part by software, hardware and a combination thereof.
  • the edge computing-based transmission line defect identification system provided by the embodiment of the present application can be realized by combining software and hardware.
  • the edge computing-based transmission line defect identification system provided by the embodiment of the present invention can be directly embodied as a
  • the combination of executed software modules, the software modules may be located in a storage medium, the storage medium is located in a memory, the processor reads the executable instructions included in the software module in the memory, and combines necessary hardware (for example, including a processor and other components connected to the bus) ) to complete the edge computing-based transmission line defect identification method provided by the embodiment of the present invention.
  • the embodiment of the present application discloses an electronic device, the electronic device includes:
  • the processor is configured to implement the above-mentioned edge computing-based transmission line defect identification method when running the executable instructions stored in the memory.
  • An electronic device provided in an embodiment of the present application includes: at least one processor, a memory, a user interface, and at least one network interface.
  • the individual components in an electronic device are coupled together via a bus system. It can be understood that a bus system is used to realize the connection communication between these components.
  • the bus system also includes a power bus, a control bus and a status signal bus.
  • the embodiment of the present application discloses a computer-readable storage medium, which stores executable instructions.
  • the executable instructions are executed by a processor, the above-mentioned edge computing-based transmission line defect identification method is implemented.
  • the computer-readable storage medium can be read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), read-only disc (compact disc read-only memory, CD-ROM) , tape, floppy disk and optical data storage nodes, etc.

Abstract

Disclosed in the present invention is a power transmission line defect identification method and system based on edge computing. The method comprises: sending a request to a cloud computing platform, and obtaining monitoring tasks and an image analysis model corresponding to the monitoring tasks; identifying the monitoring tasks to obtain an image acquisition policy and an acquired image analysis processing policy of each monitoring task; performing power transmission line defect identification according to the image acquisition policy and the acquired image analysis processing policy, and classifying the identified power transmission line defects; and generating power transmission line defect log data on the basis of the power transmission line defects of a same category, and uploading same to the cloud computing platform. The present invention solves the problems of heavy load and low efficiency of backend analysis and low hidden danger monitoring quality in the case of large video stream access concurrency.

Description

基于边缘计算的输电线路缺陷识别方法及系统Transmission line defect identification method and system based on edge computing 技术领域technical field
本发明涉及输电线路安全监测技术领域，具体涉及基于边缘计算的输电线路缺陷识别方法及系统。The invention relates to the technical field of transmission line safety monitoring, in particular to a transmission line defect identification method and system based on edge computing.
背景技术Background technique
当前输电通道在线监控摄像头尚不具备边缘计算能力，只能将图像传回后台进行分析处理，在视频流接入并发量大的情况下，后台分析负荷重，效率低，容易造成关键影像没有处理到的情况，一定程度上影响了隐患监测质量。The current online monitoring cameras of power transmission channels do not have edge computing capabilities, and can only send images back to the background for analysis and processing. In the case of a large amount of concurrent video stream access, the background analysis load is heavy and the efficiency is low, which may easily cause key images to not be processed. To a certain extent, the quality of hidden danger monitoring has been affected.
发明内容Contents of the invention
针对上述现有技术存在的问题，本发明提供了一种基于边缘计算的输电线路缺陷识别方法及系统，通过在输电通道在线监控边缘计算设备上部署边缘计算能力，有效缓解云计算平台的计算压力，该技术方案如下：Aiming at the problems existing in the above-mentioned prior art, the present invention provides a transmission line defect identification method and system based on edge computing. By deploying edge computing capabilities on edge computing devices for online monitoring of transmission channels, the computing pressure on the cloud computing platform is effectively relieved. , the technical solution is as follows:
第一方面，提供了一种基于边缘计算的输电线路缺陷识别方法，应用于输电通道在线监控边缘计算设备，包括：In the first aspect, a transmission line defect identification method based on edge computing is provided, which is applied to edge computing equipment for online monitoring of transmission channels, including:
向云计算平台发送请求，获取监测任务以及监测任务对应的图像分析模型；Send a request to the cloud computing platform to obtain the monitoring task and the image analysis model corresponding to the monitoring task;
对监测任务进行识别，得到每个监测任务的图像采集策略以及采集图像的分析处理策略；Identify the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
根据图像采集策略和采集图像的分析处理策略进行输电线路缺陷识别，将识别出来的输电线路缺陷进行分类；According to the image acquisition strategy and the analysis and processing strategy of the collected images, the transmission line defects are identified, and the identified transmission line defects are classified;
基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，所述输电线路缺陷日志数据是基于预设不同类别输电线路缺陷的数据对应的日志数据生成策略获得的。The transmission line defect log data is generated based on the same type of transmission line defect 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 the data of different types of transmission line defects.
作为上述方案的进一步优化，基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，包括：As a further optimization of the above scheme, the transmission line defect log data generated based on the same type of transmission line defect is uploaded to the cloud computing platform, including:
向云计算平台发送数据上传请求，所述数据上传请求包括第一参数和第二参数，以使云计算平台根据所述第一参数和第二参数确定在线监控摄像头上传的每类缺陷数据在数据接收任务队列中的顺序，并生成数据接收指令；其中，所述第 一参数采用缺陷数据类别参数，第二参数采用每个类别缺陷数据的数据大小参数；Send a data upload request to the cloud computing platform, the data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines that each type of defect data uploaded by the online monitoring camera is in the data according to the first parameter and the second parameter receiving the sequence in the task queue, and generating a data receiving instruction; wherein, the first parameter adopts the defect data category parameter, and the second parameter adopts the data size parameter of each category of defect data;
接收云计算平台发送的数据接收指令。Receive data receiving instructions sent by the cloud computing platform.
作为上述方案的进一步优化，所述基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，还包括：As a further optimization of the above scheme, the transmission line defect log data generated based on the transmission line defect of the same category is uploaded to the cloud computing platform, and further includes:
基于接收的数据接收指令，将不同类别的输电线路缺陷日志数据分时上传至云计算平台。Based on the received data receiving instructions, different types of transmission line defect log data are uploaded to the cloud computing platform in time-sharing.
作为上述方案的进一步优化，所述预设不同类别输电线路缺陷的数据对应的日志数据生成策略，包括：As a further optimization of the above solution, the log data generation strategy corresponding to the preset data of different types of transmission line defects includes:
基于从云计算平台获取的采集图像的分析处理策略，获取用于识别输电线路缺陷的第一数据，所述第一数据是基于图像采集策略获取的采集图像经过分析处理得到的；Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the first data for identifying the defect of the transmission line is obtained, and the first data is obtained through analysis and processing of the collected image obtained based on the image collection strategy;
基于第一数据、缺陷类别、缺陷位置数据生成日志数据。Log data is generated based on the first data, defect category, and defect location data.
作为上述方案的进一步优化，所述基于从云计算平台获取的采集图像的分析处理策略，获取用于识别输电线路缺陷的第一数据，包括：As a further optimization of the above solution, the analysis and processing strategy based on the collected images obtained from the cloud computing platform to obtain the first data for identifying defects in the transmission line includes:
基于从云计算平台获取的采集图像的分析处理策略，形状模块根据各个分析处理节点的形状声明和形状逻辑生成所述分析处理节点的形状图；Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the shape module generates the shape graph of the analysis and processing node according to the shape statement and shape logic of each analysis and processing node;
基于所述形状图执行所述分析处理策略，并基于形状图判断当前分析处理节点的输出结果的下一输入节点是否存在输电线路缺陷识别节点；Executing the analysis and processing strategy based on the shape graph, and judging based on the shape graph whether there is a transmission line defect identification node in the next input node of the output result of the current analysis and processing node;
若是，则将当前分析处理节点的输出结果存入第一数据存储模块。If yes, store the output result of the current analysis and processing node into the first data storage module.
作为上述方案的进一步优化，所述将识别出来的输电线路缺陷进行分类之后，还包括：As a further optimization of the above scheme, after classifying the identified transmission line defects, it also includes:
基于缺陷识别结果，自动调整图像采集策略至最优；Based on the defect recognition results, automatically adjust the image acquisition strategy to the optimum;
根据最优图像采集策略下采集的图像进行输电线路缺陷识别。According to the images collected under the optimal image collection strategy, the transmission line defect recognition is carried out.
作为上述方案的进一步优化，所述基于缺陷识别结果，自动调整图像采集策略至最优，包括：As a further optimization of the above scheme, the automatic adjustment of the image acquisition strategy to the optimum based on the defect identification result includes:
若确定输电线路存在缺陷，则获取缺陷对应的位置，并调整摄像头图像采集参数，获取高清输电线路缺陷图像；If it is determined that there is a defect in the transmission line, obtain the position corresponding to the defect, and adjust the camera image acquisition parameters to obtain a high-definition transmission line defect image;
基于高清输电线路缺陷图像生成输电线路缺陷日志数据。Generation of transmission line defect log data based on high-definition transmission line defect images.
第二方面，提供了一种基于边缘计算的输电线路缺陷识别系统，包括：In the second aspect, a transmission line defect identification system based on edge computing is provided, including:
监测任务参数获取模块，用于向云计算平台发送请求，获取监测任务以及监测任务对应的图像分析模型；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;
监测任务分析模块，用于对监测任务进行识别，得到每个监测任务的图像采集策略以及采集图像的分析处理策略；The monitoring task analysis module is used to identify the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
监测任务执行模块，用于根据图像采集策略和采集图像的分析处理策略进行输电线路缺陷识别，将识别出来的输电线路缺陷进行分类；The monitoring task execution module is used to identify transmission line defects according to the image acquisition strategy and the analysis and processing strategy of the collected images, and classify the identified transmission line defects;
监测任务执行结果上传模块，基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，所述输电线路缺陷日志数据是基于预设不同类别输电线路缺陷的数据对应的日志数据生成策略获得的。The monitoring task execution result upload module generates transmission line defect log data based on transmission line defects of the same type and uploads them to the cloud computing platform. The transmission line defect log data is based on the log data generation strategy corresponding to the preset data of different types of transmission line defects acquired.
第三方面，提供了一种电子设备，所述电子设备包括：In a third aspect, an electronic device is provided, and the electronic device includes:
存储器，用于存储可执行指令；memory for storing executable instructions;
处理器，用于运行所述存储器存储的可执行指令时，实现上述的基于边缘计算的输电线路缺陷识别方法。The processor is configured to implement the above-mentioned edge computing-based transmission line defect identification method when running the executable instructions stored in the memory.
第四方面，提供了一种计算机可读存储介质，存储有可执行指令，所述可执行指令被处理器执行时实现上述的基于边缘计算的输电线路缺陷识别方法。In a fourth aspect, a computer-readable storage medium is provided, which stores executable instructions, and when the executable instructions are executed by a processor, the above-mentioned edge computing-based transmission line defect identification method is implemented.
本发明的一种基于边缘计算的输电线路缺陷识别方法及系统，具备如下有益效果：通过在输电通道在线监控边缘计算设备上部署边缘计算能力，有效缓解云计算平台的计算压力，其中输电通道在线监控边缘计算设备可以是输电通道在线监控摄像头，本申请实施例中，每个输电通道在线监控边缘计算设备从云计算平台获取对于输电线路缺陷识别的监测任务以及对应的监测任务所需调用的图像分析模型，从而将图像分析模型部署到输电通道在线监控边缘计算设备，输电通道在线监控边缘计算设备通过分析图像采集策略以及图像分析处理策略进行输电线路缺陷识别，有效提高输电线路缺陷识别效率，进一步，输电通道在线监控边缘计算设备通过生成输电线路缺陷日志数据上传至云计算平台，避免了大量无效冗余数据上传至云计算平台。A transmission line defect identification method and system based on edge computing of the present invention has the following beneficial effects: by deploying edge computing capabilities on edge computing devices for online monitoring of power transmission channels, the computing pressure on the cloud computing platform is effectively relieved, wherein the transmission channel is online The monitoring edge computing device can be an online monitoring camera for transmission channels. In the embodiment of the present application, each transmission channel online monitoring edge computing device obtains the monitoring tasks for identifying defects of transmission lines and the images required for the corresponding monitoring tasks from the cloud computing platform. Analysis model, so as to deploy the image analysis model to the edge computing equipment for online monitoring of transmission channels. The edge computing equipment for online monitoring of transmission channels can identify transmission line defects by analyzing image acquisition strategies and image analysis and processing strategies, effectively improving the efficiency of transmission line defect identification, and further , the transmission channel online monitoring edge computing device generates transmission line defect log data and uploads it to the cloud computing platform, which avoids a large amount of invalid redundant data being uploaded to the cloud computing platform.
附图说明Description of drawings
图1是本申请实施例的基于边缘计算的输电线路缺陷识别方法的流程图；Fig. 1 is the flow chart of the transmission line defect identification method based on edge computing according to the embodiment of the present application;
图2是本申请实施里的基于边缘计算的输电线路缺陷识别系统的结构图。Fig. 2 is a structural diagram of a transmission line defect identification system based on edge computing in the implementation of this application.
具体实施方式Detailed ways
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，所描述的实施例不应视为对本发明的限制，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with the accompanying drawings, and the described embodiments should not be considered as limiting the present invention, and those of ordinary skill in the art do not make any All other embodiments obtained under the premise of creative labor belong to the protection scope of the present invention.
本申请实施例公开了一种基于边缘计算的输电线路缺陷识别方法，应用于输电通道在线监控边缘计算设备，包括：The embodiment of the present application discloses a transmission line defect identification method based on edge computing, which is applied to edge computing equipment for online monitoring of power transmission channels, including:
向云计算平台发送请求，获取监测任务以及监测任务对应的图像分析模型；Send a request to the cloud computing platform to obtain the monitoring task and the image analysis model corresponding to the monitoring task;
对监测任务进行识别，得到每个监测任务的图像采集策略以及采集图像的分析处理策略；Identify the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
根据图像采集策略和采集图像的分析处理策略进行输电线路缺陷识别，将识别出来的输电线路缺陷进行分类；According to the image acquisition strategy and the analysis and processing strategy of the collected images, the transmission line defects are identified, and the identified transmission line defects are classified;
基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，所述输电线路缺陷日志数据是基于预设不同类别输电线路缺陷的数据对应的日志数据生成策略获得的。The transmission line defect log data is generated based on the same type of transmission line defect 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 the data of different types of transmission line defects.
本申请实施例中，通过在输电通道在线监控边缘计算设备上部署边缘计算能力，有效缓解云计算平台的计算压力，其中输电通道在线监控边缘计算设备可以是输电通道在线监控摄像头，本申请实施例中，每个输电通道在线监控边缘计算设备从云计算平台获取对于输电线路缺陷识别的监测任务以及对应的监测任务所需调用的图像分析模型，从而将图像分析模型部署到输电通道在线监控边缘计算设备，输电通道在线监控边缘计算设备通过分析图像采集策略以及图像分析处理策略进行输电线路缺陷识别，有效提高输电线路缺陷识别效率，进一步，输电通道在线监控边缘计算设备通过生成输电线路缺陷日志数据上传至云计算平台，避免了大量无效冗余数据上传至云计算平台。In the embodiment of the present application, by deploying the edge computing capability on the edge computing device for online monitoring of the power transmission channel, the computing pressure on the cloud computing platform can be effectively relieved, wherein the edge computing device for online monitoring of the power transmission channel can be an online monitoring camera for the power transmission channel. In this method, the edge computing device for online monitoring of each transmission channel obtains the monitoring tasks for transmission line defect identification and the image analysis model required for the corresponding monitoring tasks from the cloud computing platform, so as to deploy the image analysis model to the edge computing for online monitoring of transmission channels Equipment, online monitoring of transmission channels Edge computing devices identify transmission line defects by analyzing image acquisition strategies and image analysis and processing strategies, effectively improving the efficiency of transmission line defect identification. Further, edge computing devices for online monitoring of transmission channels generate transmission line defect log data to upload To the cloud computing platform, avoiding a large amount of invalid redundant data uploaded to the cloud computing platform.
上述基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，包括：The above-mentioned generation of transmission line defect log data based on the same type of transmission line defect is uploaded to the cloud computing platform, including:
向云计算平台发送数据上传请求，所述数据上传请求包括第一参数和第二参数，以使云计算平台根据所述第一参数和第二参数确定在线监控摄像头上传的每类缺陷数据在数据接收任务队列中的顺序，并生成数据接收指令；其中，所述第一参数采用缺陷数据类别参数，第二参数采用每个类别缺陷数据的数据大小参 数；Send a data upload request to the cloud computing platform, the data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines that each type of defect data uploaded by the online monitoring camera is in the data according to the first parameter and the second parameter receiving the sequence in the task queue, and generating a data receiving instruction; wherein, the first parameter adopts the defect data category parameter, and the second parameter adopts the data size parameter of each category of defect data;
接收云计算平台发送的数据接收指令。Receive data receiving instructions sent by the cloud computing platform.
本申请中，输电通道在线监控边缘计算设备先向云计算平台发送数据上传请求，从而云计算平台可以根据接收到的数据上传请求，结合云计算平台当前的数据接收任务队列的状态，合理优化输电通道在线监控边缘计算设备的上传数据的方案，智能规划上传每类缺陷数据的先后顺序、至少一个上传时间段的分布、每个上传时间段上传数据的大小等。从而实现云计算平台和输电通道在线监控边缘计算设备之间对输电线路采集图像数据以及缺陷识别日志数据的高效管理。In this application, the edge computing device for online monitoring of the transmission channel first sends a data upload request to the cloud computing platform, so that the cloud computing platform can rationally optimize the power transmission according to the received data upload request and the current status of the data receiving task queue of the cloud computing platform The channel online monitors the data uploaded by edge computing devices, intelligently plans the sequence of uploading each type of defect data, the distribution of at least one upload time period, and the size of uploaded data in each upload time period. In this way, the efficient management of the image data collected by the transmission line and the defect identification log data between the cloud computing platform and the online monitoring edge computing device of the transmission channel is realized.
上述基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，还包括：The above-mentioned generation of transmission line defect log data based on the same type of transmission line defect is uploaded to the cloud computing platform, which also includes:
基于接收的数据接收指令，将不同类别的输电线路缺陷日志数据分时上传至云计算平台。Based on the received data receiving instructions, different types of transmission line defect log data are uploaded to the cloud computing platform in time-sharing.
本申请实施例中，云计算平台根据根据接收到的数据上传请求，结合云计算平台当前的数据接收任务队列的状态，针对每个输电通道在线监控边缘计算设备发送的数据上传请求，智能规划上传每类缺陷数据的先后顺序、至少一个上传时间段的分布、每个上传时间段上传数据的大小等，从而生成对应的数据接收指令，每个输电通道在线监控边缘计算设备基于从云计算平台接收到的数据接收指令依次上传对应的输电线路缺陷日志数据包，使得云计算平台对数据接收任务进行最佳规划。In this embodiment of the application, the cloud computing platform intelligently plans and uploads the data upload request sent by the edge computing device for each power transmission channel based on the received data upload request and combined with the current state of the data receiving task queue of the cloud computing platform. The sequence of each type of defect data, the distribution of at least one upload time period, the size of uploaded data in each upload time period, etc., so as to generate the corresponding data receiving instructions, and the online monitoring edge computing equipment of each transmission channel is based on the data received from the cloud computing platform. The received data receiving instructions are sequentially uploaded to the corresponding transmission line defect log data packets, so that the cloud computing platform can optimally plan the data receiving tasks.
上述预设不同类别输电线路缺陷的数据对应的日志数据生成策略，包括：The above preset log data generation strategies corresponding to the data of different types of transmission line defects include:
基于从云计算平台获取的采集图像的分析处理策略，获取用于识别输电线路缺陷的第一数据，所述第一数据是基于图像采集策略获取的采集图像经过分析处理得到的；Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the first data for identifying the defect of the transmission line is obtained, and the first data is obtained through analysis and processing of the collected image obtained based on the image collection strategy;
基于第一数据、缺陷类别、缺陷位置数据生成日志数据。Log data is generated based on the first data, defect category, and defect location data.
本申请实施例中，对于输电通道在线监控边缘计算设备采集的输电线路原始图像，通过分析处理策略过程获取的最能表征输电线路缺陷的第一数据，缩减上传至云计算平台的输电线路图像数据。In the embodiment of the present application, for the original image of the transmission line collected by the edge computing device for online monitoring of the transmission channel, the first data that best characterizes the defect of the transmission line obtained through the analysis and processing strategy process reduces the transmission line image data uploaded to the cloud computing platform .
上述基于从云计算平台获取的采集图像的分析处理策略，获取用于识别输电线路缺陷的第一数据，包括：The above-mentioned analysis and processing strategy based on the collected images obtained from the cloud computing platform obtains the first data for identifying the defects of the transmission line, including:
基于从云计算平台获取的采集图像的分析处理策略，形状模块根据各个分析处理节点的形状声明和形状逻辑生成所述分析处理节点的形状图；Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the shape module generates the shape graph of the analysis and processing node according to the shape statement and shape logic of each analysis and processing node;
基于所述形状图执行所述分析处理策略，并基于形状图判断当前分析处理节点的输出结果的下一输入节点是否存在输电线路缺陷识别节点；Executing the analysis and processing strategy based on the shape graph, and judging based on the shape graph whether there is a transmission line defect identification node in the next input node of the output result of the current analysis and processing node;
若是，则将当前分析处理节点的输出结果存入第一数据存储模块。If yes, store the output result of the current analysis and processing node into the first data storage module.
本申请实施例中，在分析处理策略过程获取最能表征输电线路缺陷的第一数据，通过对从云计算平台获取的采集图像的分析处理策略进行形状图构造，基于构造的与采集图像分析处理策略对应的形状图，具体的，分析处理节点的形状声明和形状逻辑可以是基于图像分析模型中每一模块的网络层的层数、每个网络层的大小以及两个网络层之间数据的传输上下游关系、每个网络层的数据处理逻辑等参数确定，在采集图像分析处理过程中的每个节点进行分析，确定当前节点的输出结果是否为目标第一数据的一部分，若是，则存入第一数据存储模块，从而获取全部的最能表征输电线路缺陷的第一数据，对于第一数据存储模块内的第一数据，可以进一步分析第一数据的每一部分的重要性权重比例，从而确定第一数据中较为重要的数据部分。In the embodiment of the present application, the first data that best characterizes the defects of the transmission line is obtained in the process of analysis and processing strategy, and the analysis and processing strategy of the collected image obtained from the cloud computing platform is used to construct the shape graph, and the analysis and processing of the collected image based on the structure The shape diagram corresponding to the strategy, specifically, the shape declaration and shape logic of the analysis processing node can be based on the number of network layers of each module in the image analysis model, the size of each network layer, and the data relationship between two network layers Parameters such as transmission upstream and downstream relations, data processing logic of each network layer, etc. are determined, and each node in the process of collecting image analysis and processing is analyzed to determine whether the output result of the current node is part of the target first data, and if so, save input into the first data storage module, so as to obtain all the first data that can best represent the defects of the transmission line, and 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, so that More important data parts in the first data are determined.
上述将识别出来的输电线路缺陷进行分类之后，还包括：After the above classification of identified transmission line defects, it also includes:
基于缺陷识别结果，自动调整图像采集策略至最优；Based on the defect recognition results, automatically adjust the image acquisition strategy to the optimum;
根据最优图像采集策略下采集的图像进行输电线路缺陷识别。According to the images collected under the optimal image collection strategy, the transmission line defect recognition is carried out.
本申请实施例中，在确定当前输电线路图像中存在缺陷后，可以基于进一步分析要求，调整图像采集策略，获取当前缺陷位置的最佳图像表示。该最佳图像表示，可以是包括当前缺陷在内的近距离高清图像，可以是包括当前缺陷在内的全局图像，也可以是包括当前缺陷在内的多角度图像集合。In the embodiment of the present application, after it is determined that there is a defect in the current transmission line image, the image acquisition strategy may be adjusted based on further analysis requirements to obtain the best image representation of the current defect location. The best image representation can be a short-distance high-definition image including the current defect, a global image including the current defect, or a multi-angle image collection including the current defect.
上述基于缺陷识别结果，自动调整图像采集策略至最优，包括：Based on the result of defect recognition, the image acquisition strategy is automatically adjusted to the optimum, including:
若确定输电线路存在缺陷，则获取缺陷对应的位置，并调整摄像头图像采集参数，获取高清输电线路缺陷图像；If it is determined that there is a defect in the transmission line, obtain the position corresponding to the defect, and adjust the camera image acquisition parameters to obtain a high-definition transmission line defect image;
基于高清输电线路缺陷图像生成输电线路缺陷日志数据。Generation of transmission line defect log data based on high-definition transmission line defect images.
上述述获取缺陷对应的位置，并调整摄像头图像采集参数，包括：Obtain the position corresponding to the above-mentioned defect, and adjust the camera image acquisition parameters, including:
基于用于确定输电线路存在缺陷的图像作为第一图像，获取第一图像的中心坐标为第一坐标；Based on the image used to determine the defect of the transmission line as the first image, the central coordinates of the first image are acquired as the first coordinates;
获取第一图像上的缺陷位置的中心坐标为第二坐标；Obtaining the center coordinates of the defect position on the first image as the second coordinates;
将调整摄像头在距离所述第二坐标的第一位置进行拍摄，对所述第一位置拍摄图像进行图像质量检测；Adjusting the camera to take pictures at a first position away from the second coordinates, and performing image quality inspection on images taken at the first position;
对于通过图像质量检测的第一位置图像，获取以第一位置为顶点，以第二坐标为质心的立体空间；For the first position image passing the image quality detection, obtain a stereo space with the first position as the vertex and the second coordinate as the center of mass;
移动摄像头位置和拍摄角度至所述立体空间的顶点分别对所述缺陷位置采集图像。Moving the camera position and shooting angle to the apex of the three-dimensional space collects images for the defect positions respectively.
对于未通过上述图像质量检测的第一位置图像，调整摄像头在距离所述第二坐标的第二位置进行拍摄，对所述第二位置拍摄图像进行图像质量检测，该第二位置与第一位置是不同的两个位置，当然，该第二位置基于第一位置图像拍摄结果来确定是第二位置相比于第一位置和所述第二坐标的距离是增大还是减小。For the image at the first position that does not pass the above image quality inspection, adjust the camera to take pictures at a second position away from the second coordinates, and perform image quality inspection on the image taken at the second position. The second position is the same as the first position. They are two different positions. Of course, the second position determines whether the distance between the second position and the second coordinate is increased or decreased compared with the first position based on the image shooting result of the first position.
本申请实施例公开了基于边缘计算的输电线路缺陷识别系统，包括：The embodiment of the present application discloses a transmission line defect identification system based on edge computing, including:
监测任务参数获取模块，用于向云计算平台发送请求，获取监测任务以及监测任务对应的图像分析模型；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;
监测任务分析模块，用于对监测任务进行识别，得到每个监测任务的图像采集策略以及采集图像的分析处理策略；The monitoring task analysis module is used to identify the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
监测任务执行模块，用于根据图像采集策略和采集图像的分析处理策略进行输电线路缺陷识别，将识别出来的输电线路缺陷进行分类；The monitoring task execution module is used to identify transmission line defects according to the image acquisition strategy and the analysis and processing strategy of the collected images, and classify the identified transmission line defects;
监测任务执行结果上传模块，基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，所述输电线路缺陷日志数据是基于预设不同类别输电线路缺陷的数据对应的日志数据生成策略获得的。The monitoring task execution result upload module generates transmission line defect log data based on transmission line defects of the same type and uploads them to the cloud computing platform. The transmission line defect log data is based on the log data generation strategy corresponding to the preset data of different types of transmission line defects acquired.
关于基于边缘计算的输电线路缺陷识别系统的具体限定可以参见上文中对于基于边缘计算的输电线路缺陷识别方法的限定，在此不再赘述。上述基于边缘计算的输电线路缺陷识别系统中的各个模块可全部或部分通过软件、硬件及其组合来实现。本申请实施例提供的基于边缘计算的输电线路缺陷识别系统可以采用软硬件结合的方式实现，作为示例，本发明实施例所提供的基于边缘计算的输电线路缺陷识别系统可以直接体现为由处理器执行的软件模块组合，软件模块可以位于存储介质中，存储介质位于存储器，处理器读取存储器中软件模块包括的可执行指令，结合必要的硬件(例如，包括处理器以及连接到总线的其他组件)完 成本发明实施例提供的基于边缘计算的输电线路缺陷识别方法。For the specific limitations of the edge computing-based transmission line defect identification system, please refer to the above-mentioned definition of the edge computing-based transmission line defect identification method, which will not be repeated here. Each module in the above-mentioned edge computing-based transmission line defect identification system can be realized in whole or in part by software, hardware and a combination thereof. The edge computing-based transmission line defect identification system provided by the embodiment of the present application can be realized by combining software and hardware. As an example, the edge computing-based transmission line defect identification system provided by the embodiment of the present invention can be directly embodied as a The combination of executed software modules, the software modules may be located in a storage medium, the storage medium is located in a memory, the processor reads the executable instructions included in the software module in the memory, and combines necessary hardware (for example, including a processor and other components connected to the bus) ) to complete the edge computing-based transmission line defect identification method provided by the embodiment of the present invention.
本申请实施例公开了一种电子设备，该电子设备包括：The embodiment of the present application discloses an electronic device, the electronic device includes:
存储器，用于存储可执行指令；memory for storing executable instructions;
处理器，用于运行所述存储器存储的可执行指令时，实现上述的基于边缘计算的输电线路缺陷识别方法。The processor is configured to implement the above-mentioned edge computing-based transmission line defect identification method when running the executable instructions stored in the memory.
本申请实施例提供的电子设备包括：至少一个处理器、存储器、用户接口和至少一个网络接口。电子设备中的各个组件通过总线系统耦合在一起。可以理解，总线系统用于实现这些组件之间的连接通信。总线系统除包括数据总线之外，还包括电源总线、控制总线和状态信号总线。An electronic device provided in an embodiment of the present application includes: at least one processor, a memory, a user interface, and at least one network interface. The individual components in an electronic device are coupled together via a bus system. It can be understood that a bus system is used to realize the connection communication between these components. In addition to the data bus, the bus system also includes a power bus, a control bus and a status signal bus.
本申请实施例公开了一种计算机可读存储介质，存储有可执行指令，所述可执行指令被处理器执行时实现上述的基于边缘计算的输电线路缺陷识别方法。可以理解，可计算机可读存储介质以是只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、只读光盘(compact disc read-only memory，CD-ROM)、磁带、软盘和光数据存储节点等。The embodiment of the present application discloses a computer-readable storage medium, which stores executable instructions. When the executable instructions are executed by a processor, the above-mentioned edge computing-based transmission line defect identification method is implemented. It can be understood that the computer-readable storage medium can be read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), read-only disc (compact disc read-only memory, CD-ROM) , tape, floppy disk and optical data storage nodes, etc.
本发明不局限于上述具体的实施方式，本领域的普通技术人员从上述构思出发，不经过创造性的劳动，所做出的种种变换，均落在本发明的保护范围之内。The present invention is not limited to the above-mentioned specific implementation manners, and various transformations made by those skilled in the art starting from the above-mentioned ideas without creative work all fall within the scope of protection of the present invention.

Claims (10)

  1. 一种基于边缘计算的输电线路缺陷识别方法，应用于输电通道在线监控边缘计算设备，其特征在于，包括：A transmission line defect identification method based on edge computing, applied to edge computing equipment for online monitoring of transmission channels, characterized in that it includes:
    向云计算平台发送请求，获取监测任务以及监测任务对应的图像分析模型；Send a request to the cloud computing platform to obtain the monitoring task and the image analysis model corresponding to the monitoring task;
    对监测任务进行识别，得到每个监测任务的图像采集策略以及采集图像的分析处理策略；Identify the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
    根据图像采集策略和采集图像的分析处理策略进行输电线路缺陷识别，将识别出来的输电线路缺陷进行分类；According to the image acquisition strategy and the analysis and processing strategy of the collected images, the transmission line defects are identified, and the identified transmission line defects are classified;
    基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，所述输电线路缺陷日志数据是基于预设不同类别输电线路缺陷的数据对应的日志数据生成策略获得的。The transmission line defect log data is generated based on the same type of transmission line defect 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 the data of different types of transmission line defects.
  2. 根据权利要求1所述的基于边缘计算的输电线路缺陷识别方法，其特征在于，所述基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，包括：The transmission line defect identification method based on edge computing according to claim 1, wherein the generation of transmission line defect log data based on the same type of transmission line defect is uploaded to the cloud computing platform, including:
    向云计算平台发送数据上传请求，所述数据上传请求包括第一参数和第二参数，以使云计算平台根据所述第一参数和第二参数确定在线监控摄像头上传的每类缺陷数据在数据接收任务队列中的顺序，并生成数据接收指令；其中，所述第一参数采用缺陷数据类别参数，第二参数采用每个类别缺陷数据的数据大小参数；Send a data upload request to the cloud computing platform, the data upload request includes a first parameter and a second parameter, so that the cloud computing platform determines that each type of defect data uploaded by the online monitoring camera is in the data according to the first parameter and the second parameter receiving the sequence in the task queue, and generating a data receiving instruction; wherein, the first parameter adopts the defect data category parameter, and the second parameter adopts the data size parameter of each category of defect data;
    接收云计算平台发送的数据接收指令。Receive data receiving instructions sent by the cloud computing platform.
  3. 根据权利要求2所述的基于边缘计算的输电线路缺陷识别方法，其特征在于，所述基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，还包括：The transmission line defect identification method based on edge computing according to claim 2, wherein the generation of transmission line defect log data based on the same type of transmission line defect is uploaded to the cloud computing platform, and further includes:
    基于接收的数据接收指令，将不同类别的输电线路缺陷日志数据分时上传至云计算平台。Based on the received data receiving instructions, different types of transmission line defect log data are uploaded to the cloud computing platform in time-sharing.
  4. 根据权利要求1所述的基于边缘计算的输电线路缺陷识别方法，其特征在于，所述预设不同类别输电线路缺陷的数据对应的日志数据生成策略，包括：The edge computing-based transmission line defect identification method according to claim 1, wherein the log data generation strategy corresponding to the preset data of different types of transmission line defects includes:
    基于从云计算平台获取的采集图像的分析处理策略，获取用于识别输电线路缺陷的第一数据，所述第一数据是基于图像采集策略获取的采集图像经过分析处理得到的；Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the first data for identifying the defect of the transmission line is obtained, and the first data is obtained through analysis and processing of the collected image obtained based on the image collection strategy;
    基于第一数据、缺陷类别、缺陷位置数据生成日志数据。Log data is generated based on the first data, defect category, and defect location data.
  5. 根据权利要求4所述的基于边缘计算的输电线路缺陷识别方法，其特征在于，所述基于从云计算平台获取的采集图像的分析处理策略，获取用于识别输电线路缺陷的第一数据，包括：According to the edge computing-based transmission line defect identification method according to claim 4, it is characterized in that the analysis and processing strategy based on the collected images obtained from the cloud computing platform is to obtain the first data for identifying transmission line defects, including :
    基于从云计算平台获取的采集图像的分析处理策略，形状模块根据各个分析处理节点的形状声明和形状逻辑生成所述分析处理节点的形状图；Based on the analysis and processing strategy of the collected image obtained from the cloud computing platform, the shape module generates the shape graph of the analysis and processing node according to the shape statement and shape logic of each analysis and processing node;
    基于所述形状图执行所述分析处理策略，并基于形状图判断当前分析处理节点的输出结果的下一输入节点是否存在输电线路缺陷识别节点；Executing the analysis and processing strategy based on the shape graph, and judging based on the shape graph whether there is a transmission line defect identification node in the next input node of the output result of the current analysis and processing node;
    若是，则将当前分析处理节点的输出结果存入第一数据存储模块。If yes, store the output result of the current analysis and processing node into the first data storage module.
  6. 根据权利要求1所述的基于边缘计算的输电线路缺陷识别方法，其特征在于，所述将识别出来的输电线路缺陷进行分类之后，还包括：The transmission line defect identification method based on edge computing according to claim 1, characterized in that, after classifying the identified transmission line defects, further comprising:
    基于缺陷识别结果，自动调整图像采集策略至最优；Based on the defect recognition results, automatically adjust the image acquisition strategy to the optimum;
    根据最优图像采集策略下采集的图像进行输电线路缺陷识别。According to the images collected under the optimal image collection strategy, the transmission line defect recognition is carried out.
  7. 根据权利要求6所述的基于边缘计算的输电线路缺陷识别方法，其特征在于，所述基于缺陷识别结果，自动调整图像采集策略至最优，包括：The edge computing-based transmission line defect identification method according to claim 6, wherein the automatic adjustment of the image acquisition strategy to the optimum based on the defect identification result includes:
    若确定输电线路存在缺陷，则获取缺陷对应的位置，并调整摄像头图像采集参数，获取高清输电线路缺陷图像；If it is determined that there is a defect in the transmission line, obtain the position corresponding to the defect, and adjust the camera image acquisition parameters to obtain a high-definition transmission line defect image;
    基于高清输电线路缺陷图像生成输电线路缺陷日志数据。Generation of transmission line defect log data based on high-definition transmission line defect images.
  8. 一种基于边缘计算的输电线路缺陷识别系统，其特征在于，包括：A transmission line defect identification system based on edge computing, characterized in that it includes:
    监测任务参数获取模块，用于向云计算平台发送请求，获取监测任务以及监测任务对应的图像分析模型；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;
    监测任务分析模块，用于对监测任务进行识别，得到每个监测任务的图像采集策略以及采集图像的分析处理策略；The monitoring task analysis module is used to identify the monitoring task, obtain the image acquisition strategy of each monitoring task and the analysis and processing strategy of the collected image;
    监测任务执行模块，用于根据图像采集策略和采集图像的分析处理策略进行输电线路缺陷识别，将识别出来的输电线路缺陷进行分类；The monitoring task execution module is used to identify transmission line defects according to the image acquisition strategy and the analysis and processing strategy of the collected images, and classify the identified transmission line defects;
    监测任务执行结果上传模块，基于同一类别的输电线路缺陷生成输电线路缺陷日志数据上传至云计算平台，所述输电线路缺陷日志数据是基于预设不同类别输电线路缺陷的数据对应的日志数据生成策略获得的。The monitoring task execution result upload module generates transmission line defect log data based on transmission line defects of the same type and uploads them to the cloud computing platform. The transmission line defect log data is based on the log data generation strategy corresponding to the preset data of different types of transmission line defects acquired.
  9. 一种电子设备，其特征在于，所述电子设备包括：An electronic device, characterized in that the electronic device comprises:
    存储器，用于存储可执行指令；memory for storing executable instructions;
    处理器，用于运行所述存储器存储的可执行指令时，实现权利要求1至7任一项所述的基于边缘计算的输电线路缺陷识别方法。The processor is configured to implement the edge computing-based transmission line defect identification method according to any one of claims 1 to 7 when running the executable instructions stored in the memory.
  10. 一种计算机可读存储介质，存储有可执行指令，其特征在于，所述可执行指令被处理器执行时实现权利要求1至7任一项所述的基于边缘计算的输电线路缺陷识别方法。A computer-readable storage medium storing executable instructions, wherein when the executable instructions are executed by a processor, the edge computing-based transmission line defect identification method according to any one of claims 1 to 7 is implemented.
PCT/CN2021/137341 2021-07-30 2021-12-13 Power transmission line defect identification method and system based on edge computing WO2023005100A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110872816.3 2021-07-30
CN202110872816.3A CN113850285A (en) 2021-07-30 2021-07-30 Power transmission line defect identification method and system based on edge calculation

Publications (1)

Publication Number Publication Date
WO2023005100A1 true WO2023005100A1 (en) 2023-02-02

Family

ID=78975231

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137341 WO2023005100A1 (en) 2021-07-30 2021-12-13 Power transmission line defect identification method and system based on edge computing

Country Status (2)

Country Link
CN (1) CN113850285A (en)
WO (1) WO2023005100A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117081237A (en) * 2023-07-19 2023-11-17 珠海市深瑞智联科技有限公司 Method and system for identifying hidden danger of power transmission line based on radar scanning and image acquisition
CN116865430B (en) * 2023-05-31 2024-05-17 河南水利与环境职业学院 Online intelligent electricity safety identification system and method based on edge calculation

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116054414B (en) * 2023-03-06 2023-07-28 广东电网有限责任公司佛山供电局 Line defect hidden danger monitoring method, device, computer equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109870461A (en) * 2019-03-29 2019-06-11 深圳市阿赛姆电子有限公司 A kind of electronic component quality detection system
CN110730327A (en) * 2019-09-03 2020-01-24 华为技术有限公司 Method for monitoring power transmission line and acquisition front end
WO2020029682A1 (en) * 2018-08-07 2020-02-13 腾讯科技（深圳）有限公司 Panel defect analysis method and apparatus, storage medium and network device
US20210034044A1 (en) * 2019-05-23 2021-02-04 Wangsu Science & Technology Co., Ltd. Method for quality controling of target object and edge computing device
CN212846883U (en) * 2020-04-22 2021-03-30 北京智芯微电子科技有限公司 Monitoring system for power transmission line

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020029682A1 (en) * 2018-08-07 2020-02-13 腾讯科技（深圳）有限公司 Panel defect analysis method and apparatus, storage medium and network device
CN109870461A (en) * 2019-03-29 2019-06-11 深圳市阿赛姆电子有限公司 A kind of electronic component quality detection system
US20210034044A1 (en) * 2019-05-23 2021-02-04 Wangsu Science & Technology Co., Ltd. Method for quality controling of target object and edge computing device
CN110730327A (en) * 2019-09-03 2020-01-24 华为技术有限公司 Method for monitoring power transmission line and acquisition front end
CN212846883U (en) * 2020-04-22 2021-03-30 北京智芯微电子科技有限公司 Monitoring system for power transmission line

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116865430B (en) * 2023-05-31 2024-05-17 河南水利与环境职业学院 Online intelligent electricity safety identification system and method based on edge calculation
CN117081237A (en) * 2023-07-19 2023-11-17 珠海市深瑞智联科技有限公司 Method and system for identifying hidden danger of power transmission line based on radar scanning and image acquisition
CN117081237B (en) * 2023-07-19 2024-04-02 珠海市深瑞智联科技有限公司 Method and system for identifying hidden danger of power transmission line based on radar scanning and image acquisition

Also Published As

Publication number Publication date
CN113850285A (en) 2021-12-28

Similar Documents

Publication Publication Date Title
WO2023005100A1 (en) Power transmission line defect identification method and system based on edge computing
EP3836077A2 (en) Product defect detection method and apparatus, electronic device, storage medium and program
WO2020199834A1 (en) Object detection method and apparatus, and network device and storage medium
Ali et al. Edge enhanced deep learning system for large-scale video stream analytics
CN112087522B (en) Edge cloud collaborative flow arrangement system for industrial robot data processing
CN112732450B (en) Robot knowledge graph generation system and method under end-edge-cloud cooperative framework
CN105005521B (en) Method of testing and device
CN111131379A (en) Distributed flow acquisition system and edge calculation method
CN113408087B (en) Substation inspection method based on cloud side system and video intelligent analysis
CN112162863B (en) Edge unloading decision method, terminal and readable storage medium
CN104079885A (en) Nobody-monitored and linkage-tracked network camera shooting method and device
US11551447B2 (en) Real-time video stream analysis system using deep neural networks
WO2015090099A1 (en) Algorithm configuration method and system
JP2020530125A (en) Display screen peripheral circuit detection method, display screen peripheral circuit detection device, electronic devices and storage media
CN103020590A (en) Vehicle identification system and method based on three-dimensional model and image matching
Wette et al. DCT2Gen: A traffic generator for data centers
CN114499979A (en) SDN abnormal flow cooperative detection method based on federal learning
CN115277574A (en) Data center network load balancing method under SDN architecture
CN111061911B (en) Target detection and tracking method, device and equipment for multi-video monitoring data
CN105608411A (en) Image classification method and apparatus for preset tour camera
CN114172809B (en) Video computing cloud edge collaborative task scheduling method based on target tracking
Zhang et al. End-to-end latency optimization of multi-view 3D reconstruction for disaster response
TWI766237B (en) Object at sea distance measuring system
WO2017054515A1 (en) Method and system for detecting pornographic image
Pankov et al. Model studies of systems with diagnostics based on fault simulation

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE