An insulator recognition and detection method based on multi-feature information fusion technology

An insulator identification and detection method technology, applied in character and pattern recognition, image analysis, image enhancement, etc., can solve the problems of high-altitude operation environment, low work efficiency, and high risk

Active Publication Date: 2019-03-26
西安金源电气股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional method of checking the operation status of insulators is regular power outages or live manual inspections. These operations not only require boarding poles to inspect pieces one by one, but also high-altitude operations are greatly affected by the environment, high risk, and low work efficiency.

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
  • An insulator recognition and detection method based on multi-feature information fusion technology
  • An insulator recognition and detection method based on multi-feature information fusion technology
  • An insulator recognition and detection method based on multi-feature information fusion technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0151] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0152] The invention provides an insulator identification and detection method based on multi-feature information fusion technology, such as figure 1 As shown, the specific steps are as follows:

[0153] Step 1, using the image signal of the insulator on the transmission line collected by a fixed-focus camera with a pan-tilt installed on the iron tower or iron pole on site;

[0154] Step 2, preprocessing the image collected in step 1, the specific steps are: use the optimal entropy threshold method (OET) to segment the image, and find the optimal threshold by analyzing the entropy of the image gray histogram, the specific steps are :

[0155] In step 2.1, record the gray scale range of the image collected in step 1 as {0, 1, 2, ... L-1}.

[0156] In step 2.2, set the area formed by pixels with a gray level lower than t as the target area A...

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 method for identifying and detecting insulators based on multi-feature information fusion technology, which is specifically implemented according to the following steps: Step 1, using a fixed-focus camera with a pan-tilt mounted on an iron tower or an iron pole to collect the insulators on a transmission line Image signal; step 2, preprocessing the image collected in step 1; step 3, extracting the texture feature vector of the insulator from the preprocessed image; step 4, extracting the color feature vector of the insulator to be identified, and collecting the insulator in step 1 The HSV color space of the insulator image is non-equally spaced; Step 5, using the Hu moment algorithm in the region description method to extract the shape features of the insulator; Step 6, extracting the three features of the insulator in Step 3, Step 4, and Step 5 After fusion, the method of the present invention can simply, reliably, quickly and automatically detect the operating state of the insulator, thereby preventing the failure of the power system caused by the breakage of the insulator.

Description

technical field [0001] The invention belongs to the field of online monitoring of power systems, and relates to an insulator identification and detection method based on multi-feature information fusion technology. Background technique [0002] With the proposal of the theoretical concept of the Global Energy Internet, with the UHV grid as the backbone grid and the strong smart grid as the basis, strengthening the real-time monitoring, safety maintenance and operation management of transmission lines is the top priority. In high-voltage transmission lines, poor insulation is the main cause of accidents, and accidents caused by broken insulators currently rank first in the failure rate of power systems. The long-term operation of the insulator outdoors, the interference of various pollutants in the atmosphere and other factors may easily cause internal cracks, surface damage, insulation strength reduction and pollution flashover of the insulator. When there are low-value or ...

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 Patents(China)
IPC IPC(8): G06T7/136G06T7/90G06K9/46
CPCG06T2207/30108G06T2207/20221G06T2207/10004G06V10/462
Inventor 黄新波邢晓强朱永灿纪超张烨李菊清刘新慧张慧莹
Owner 西安金源电气股份有限公司
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