Extra-high voltage converter station protection system panoramic monitoring image reconstruction and transmission method

A panoramic monitoring and protection system technology, applied in image data processing, graphic image conversion, neural learning methods, etc., can solve problems such as poor real-time performance of reconstructed communication networks, blurred panoramic monitoring images, and congestion of panoramic monitoring data transmission, etc. Achieve the best structural similarity and peak signal-to-noise ratio performance, reduce the difficulty of training, and promote the effect of reuse

Pending Publication Date: 2022-04-05
STATE GRID ANHUI ELECTRIC POWER CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to design a panoramic monitoring image reconstruction and transmission method for the UHV converter station protection system, so as to solve the blurring and low resolution of the panoramic monitoring image of the current UHV converter station protection system, and the When the network fails, the real-time performance and low reliability of the reconstructed communication network are caused by the congestion of panoramic monitoring data transmission.

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
  • Extra-high voltage converter station protection system panoramic monitoring image reconstruction and transmission method
  • Extra-high voltage converter station protection system panoramic monitoring image reconstruction and transmission method
  • Extra-high voltage converter station protection system panoramic monitoring image reconstruction and transmission method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as figure 1 As shown, the ultra-high voltage converter station protection system panoramic surveillance image super-resolution reconstruction method includes the following steps:

[0050] 1. Super-resolution reconstruction of panoramic surveillance images

[0051] 1.1. Establish a deep multi-scale residual network model on the edge side

[0052] 1.1.1, Deep Multi-scale residual network (Deep Multi-scale residual network, DMRN)

[0053] figure 1 It is a deep multi-scale residual network architecture, which consists of convolutional layers, k multi-scale convolution blocks (Multi-scale convolution block, MC block) and skip connections. The stacking of k multi-scale convolution blocks is used to obtain greater depth. At the same time, the convolution operation of the convolution block using small kernels of different scales is improved to extract the detailed features of the image at different scales for fusion, which improves the network's ability to Input the reco...

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 panoramic monitoring image reconstruction and transmission method for an extra-high voltage converter station protection system, belongs to the technical field of panoramic monitoring of extra-high voltage converter stations, and solves the problems that the panoramic monitoring image of the conventional extra-high voltage converter station protection system is blurred and low in resolution, and the panoramic monitoring data transmission is congested when a network fails. Multi-scale convolution blocks are adopted in a deep multi-scale residual network model to construct low-order and high-order features of a multi-scale extraction image, the phenomenon of incomplete extraction of image details is avoided, a residual learning mechanism is adopted to reserve low-order rough features and promote reuse of the features, and then the reconstruction capability of the image is improved; according to the topological optimization, a topological structure of a heterogeneous network is constructed, a framework combining deep reinforcement learning and Monte Carlo tree search is adopted, and the network is sequentially constructed according to a predefined topological rule; the search result of the Monte Carlo tree enhances the learning of the deep convolutional neural network, so that more accurate prediction can be obtained in the next iteration.

Description

technical field [0001] The invention belongs to the technical field of panoramic monitoring of UHV converter stations, and relates to a method for reconstructing and transmitting panoramic monitoring images of a protection system of UHV converter stations. Background technique [0002] With the development of the power grid, the interconnection scale of the power grid is continuously increasing, and the electrical connection within the network is closer. The safe and reliable operation of the UHV converter station plays an important role in the safe and stable operation of the power grid. Therefore, in the daily operation and maintenance of UHV, manual inspection and troubleshooting of equipment failures are required to ensure the safety and stability of the system. . However, this manual inspection mode has high work intensity, and the inspection performance is easily affected by the experience and responsibility of personnel. In order to improve the efficiency of the ope...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06N3/04G06N3/08G06Q50/06H04L12/44
Inventor 谢民邵庆祝章昊汪伟俞斌于洋张骏叶远波程晓平丁津津孙辉张峰许旵鹏刘之奎张军
Owner STATE GRID ANHUI ELECTRIC POWER CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products