Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Power transmission line monitoring system and method and recognition system and method for cloud-side cooperation

A transmission line and monitoring system technology, applied in character and pattern recognition, circuit devices, neural learning methods, etc., can solve problems such as difficult on-site fault diagnosis, insufficient timeliness of information processing, and difficult information transmission, so as to avoid image and The transmission of large amount of video data, significant application value, and the effect of solving insufficient efficiency

Pending Publication Date: 2022-04-15
CHINA ELECTRIC POWER RES INST +2
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical solution of the present invention aims at many problems such as insufficient timeliness of on-site sensor information processing, difficult information transmission, and difficult implementation of on-site fault diagnosis under the cloud computing architecture mode, and proposes a cloud-edge collaborative transmission line monitoring system and method, identification system and method, using the edge-side recognition technology to identify the target object, only transmitting the label information and recognition results, avoiding the transmission of large amounts of image and video data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Power transmission line monitoring system and method and recognition system and method for cloud-side cooperation
  • Power transmission line monitoring system and method and recognition system and method for cloud-side cooperation
  • Power transmission line monitoring system and method and recognition system and method for cloud-side cooperation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] An intelligent computing framework for cloud-edge collaborative architecture, such as figure 1 Shown is the five-layer power Internet of Things architecture of "intelligent cloud, pipe, edge and end", based on the cloud-edge collaborative architecture, which includes the five-layer architecture of "intelligence, cloud, management, edge, and end";

[0085] Among them, intelligence refers to intelligent applications, and intelligent applications corresponding to "cloud, pipe, edge, and end" are described as cloud intelligence, network intelligence, edge intelligence, and terminal intelligence;

[0086] The cloud layer takes the cloud platform as the core, including the main functional entities such as the operation management platform, the IoT management platform, and the enterprise middle platform. For different scales of the Internet of Things, choose to deploy public cloud, private cloud or hybrid cloud. "Cloud" is the main station platform of cloudification, and there...

Embodiment 2

[0099] The specific implementation process includes: the transmission line perception layer image monitoring device and the video camera device generate picture data and video data, including two schemes:

[0100] Solution 1 is to form sample data that can be used for training after preprocessing and labeling directly on the sensing terminal, and then gather and upload to the cloud (or directly upload to the cloud) through the edge IoT agent, and access it through the IoT management platform. Collected into the sample bank;

[0101] The second option is to form sample data that can be used for training after preprocessing and labeling on the edge IoT agent, upload it to the cloud, access it through the IoT management platform, and collect it into the sample library.

[0102] The artificial intelligence platform (that is, the cloud platform is equipped with an artificial intelligence training module) can use the sample data in the sample library to organize model training, and ...

Embodiment 4

[0123] As a preferred embodiment, the intelligent recognition of the edge side of the transmission line is realized by using a deep learning network model. The specific algorithm includes using MobileNetv2 for the head network to extract features; using YOLOv3 for the main network to deepen target classification and target detection based on the features extracted by the head network. Based on this basic network structure, a high-performance identification algorithm for the transmission line edge side is established. The network structure of MobileNetv2+YOLOv3 adopted in the present invention, depth separable convolution is introduced in the calculation of input eigenvalues ​​of YOLOv3, so that YOLOv3 can match with MobileNetv2, and the amount of parameters and calculations are greatly reduced. Because MobileNetv2 is a lightweight network structure, compared with other popular structures such as VGG and ResNet, MobileNetv2 effectively reduces storage and computing overhead at t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a power transmission line monitoring system and method and a recognition system and method oriented to cloud edge collaboration. The monitoring system comprises a sensing layer which comprises a state sensing and execution control main body in the power Internet of Things and is used for monitoring, collecting and sensing power system equipment data to obtain sensing data; the edge layer comprises an edge internet-of-things proxy terminal and is used for preprocessing the sensing data at an edge computing node; the network layer comprises a remote communication channel and a local access channel and is used for gathering and transmitting the preprocessed sensing data; and the cloud is used for carrying out data storage, data classification, data exchange and data distribution on the sensing data which are gathered and transmitted, and sending execution instructions to the network layer, the edge layer and the sensing layer in sequence. According to the invention, many problems of insufficient timeliness of field sensor information processing, high information transmission difficulty, difficult implementation of field fault diagnosis and the like in a cloud computing architecture mode are solved.

Description

technical field [0001] The invention relates to the field of electric power internet of things, in particular to a transmission line monitoring system and method for cloud-edge collaboration, and an identification system and method. Background technique [0002] The power Internet of Things provides information and data support for all aspects of power system energy production, transmission, distribution, etc., which greatly promotes the optimization of power grid operation, reduces management costs, improves economic benefits, and improves service quality. [0003] In order to effectively improve data sharing capabilities and improve the level of information management, information value mining, big data and artificial intelligence analysis, cloud computing architecture is currently used to upload perception layer data to the cloud platform for centralized processing and application. However, in the context of massive data, there are the following problems: on the one hand,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H02J13/00G06N3/04G06N3/08G06V20/40G06V20/52
CPCY02E60/00Y04S10/50Y04S40/128
Inventor 雷煜卿谈元鹏仝杰彭国政
Owner CHINA ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com