Unlock instant, AI-driven research and patent intelligence for your innovation.

A stock-bridge damper deformation detection method based on the LSD algorithm and machine learning

A machine learning and detection method technology, applied in instruments, measuring devices, optical devices, etc., can solve the problems of easy omission of key information, easy omission and misreporting of key information, etc., to enhance the management level, reduce the accident rate, The effect of improving utilization

Inactive Publication Date: 2016-12-14
STATE GRID FUJIAN ELECTRIC POWER CO LTD +3
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the amount of images or video data obtained during the aerial inspection is very large. If the manual screening, manual analysis and judgment are used to directly process the huge video and picture information, it is undoubtedly very hard work and very difficult. It is easy to miss key information; if manual online monitoring, real-time judgment and detection of abnormalities in power transmission and transformation lines are used, it will be more difficult work, and it is easier to miss and misreport key information

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
  • A stock-bridge damper deformation detection method based on the LSD algorithm and machine learning
  • A stock-bridge damper deformation detection method based on the LSD algorithm and machine learning
  • A stock-bridge damper deformation detection method based on the LSD algorithm and machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0017] A method for detecting the deformation of an anti-vibration hammer based on the LSD algorithm and machine learning is implemented by the following steps:

[0018] (1) A large number of images are taken from the transmission line (such as 220KV transmission line) by drone, and the image is reduced to 80% of the original size, and then the gradient value and gradient magnitude of each pixel of the image are calculated separately, and the calculation formula Expressed as follows:

[0019]

[0020]

[0021] In formula (1)-(2): g x (x, y) and g y (x, y) represent the gradient value of the pixel point in the X direction and the Y direction; G(x, y) represents the gradient magnitude of the pixel point; i(x, y) is the coordinate center pixel point [i, j] the gray value of;

[0022] Then use the pixel with the largest gradient magnitude as the seed point, and sort each pixel of the image from small to large, thereby obtaining a sorted list; then use an unused pixel in 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 stock-bridge damper deformation detection method based on the LSD algorithm and machine learning. According to the invention, computer vision analysis technology with the significance of artificial intelligence is introduced to make existing detection systems possess human eye recognition and human brain analysis ability, and through the visual analysis, monitoring and analyzing potential threat events such as deformation of fittings on a transmission line are carried out so as to effectively monitor key equipment in the transmission line; real-time early warning of the reliability of the equipment is realized; and further condition maintenance of distribution-network-related equipment and the management level of a demand side are enhanced to improve asset utilization and reduce the accident rate.

Description

technical field [0001] The invention relates to a method for detecting deformation of an anti-vibration hammer, in particular to a method for detecting deformation of an anti-vibration hammer based on LSD algorithm and machine learning. Background technique [0002] At present, my country's transmission lines are still dominated by overhead lines. High-voltage and ultra-high-voltage transmission lines are distributed in many points and wide areas. The terrain is complex and the natural environment is harsh. Cause damage to the foundation of power transmission lines, especially power facilities such as towers, lead to the toppling of towers or equipment damage, and directly damage the transmission lines. The transmission line built in the mining area may cause the foundation of the tower to sink suddenly due to changes in the mining area, resulting in damage to the transmission line. Therefore, for the transmission lines in such dangerous areas, it is necessary to observe and...

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): G01B11/16
CPCG01B11/16
Inventor 汤明文詹仁俊戴礼豪黄宇淇王力群
Owner STATE GRID FUJIAN ELECTRIC POWER CO LTD