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

Non-contact detection method of insulator pollution degree based on hyperspectral technology

A detection method and insulator technology, applied in the direction of optical testing flaws/defects, etc., can solve the problems of manpower, material and manual interference, easy to cause errors, and inability to carry out on-site live detection.

Active Publication Date: 2021-08-10
SOUTHWEST JIAOTONG UNIV
View PDF19 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional salt and ash density detection process is cumbersome, and on-site live detection cannot be carried out. It is necessary to disassemble the insulator by climbing a pole and scrubbing to dissolve all the dirt on the surface of the insulator. After measuring the conductivity, it needs to be filtered, dried, and weighed to measure the ash density. Personnel technology and experience, easy to cause errors in the measurement process
If it is necessary to measure the pollution degree of each part of the insulator, it is necessary to repeat the above operation, which consumes manpower and material resources, and there are many manual interferences, resulting in large dispersion of measurement results.
[0004] To sum up, the traditional salt and ash density detection has great limitations in field application. In view of this, it is necessary to provide an effective, reliable, non-contact live detection method for insulator pollution degree

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
  • Non-contact detection method of insulator pollution degree based on hyperspectral technology
  • Non-contact detection method of insulator pollution degree based on hyperspectral technology
  • Non-contact detection method of insulator pollution degree based on hyperspectral technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Please refer to figure 1 , this embodiment discloses a non-contact detection method for insulator pollution degree based on hyperspectral technology, including the following steps:

[0040] S1. Obtain the hyperspectral image set of the polluted insulator, and correct and transform the hyperspectral image set, and divide the processed hyperspectral image set into two parts, namely the first hyperspectral image set and the second hyperspectral image set image collection;

[0041] S2. Obtain the salt-ash ratio I and the total amount of pollution I of the polluted insulator area corresponding to the first hyperspectral image set;

[0042] S3. Extracting texture features and hyperspectral spectral lines of the first hyperspectral image set, wherein the corresponding label of the texture feature of the first hyperspectral image set is salt-gray ratio I, and the corresponding label of the hyperspectral spectral line of the first hyperspectral image set is The total amount of...

Embodiment 2

[0053] For step S1 in Embodiment 1, it is to select a hyperspectral image set to be acquired in the same pollution type area of ​​the polluted insulator.

[0054] In this embodiment, the area of ​​the same pollution type refers to the assumption that the soluble components and proportions of the same pollution amount on the surface of the insulator in this area are the same.

Embodiment 3

[0056] For step S1 in Example 1, the method for obtaining the hyperspectral image set of polluted insulators is as follows: after the UAV carries a hyperspectral instrument to fly to the line tower and hovers, use the hyperspectral instrument to acquire the hyperspectral image set of polluted insulators.

[0057] In this embodiment, the hyperspectral image set of polluted insulators is usually obtained on sunny days after fog. Therefore, at this time, the dirt on the insulators will precipitate salt crystals after being wet, making the distribution of pollution on the surface of the insulators more obvious.

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 non-contact detection method for the contamination degree of insulators based on hyperspectral technology, and relates to the technical field of operation state maintenance of power transmission and transformation equipment. The method includes: acquiring a first hyperspectral image set and a second hyperspectral image set of a contaminated insulator; extracting hyperspectral data of the first hyperspectral image set, and using a part of the data as a training set and the other part of the data as a test set, Establish a multi-parameter detection model of contamination degree, and use the test set to optimize the model; extract the hyperspectral data of several local areas in the second hyperspectral image set, and identify it through the optimized multi-parameter detection model of contamination degree, so as to obtain the salt The ash ratio II and the total amount of pollution II are used to calculate the pollution equivalent salt density II and pollution ash density II of the insulator. The method has high recognition accuracy and is suitable for on-site live detection. It can realize the detection of contamination in each local area of ​​the insulator, and provides a technical reference for formulating a targeted insulator cleaning plan.

Description

technical field [0001] The invention relates to the field of maintenance of the running state of power transmission and transformation equipment, in particular to a non-contact detection method for pollution degree of insulators based on hyperspectral technology. Background technique [0002] Insulator pollution flashover accidents can easily cause the system to lose stability and lead to long-term and large-scale power outages. With the increase of severe weather conditions such as smog and salt spray, and the increase of the voltage level of transmission lines, insulators exposed to the atmospheric environment are facing more serious pollution accumulation problems, and the prevention and control of pollution flashover accidents will also face greater challenges. At present, the recommendations of GB / T 16434, GB / T5582 and other standards, as well as the basis for the classification of pollution areas of various power grid companies and the configuration of external insulat...

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): G01N21/94
CPCG01N21/94
Inventor 吴广宁邱彦郭裕钧张血琴刘凯高国强杨泽锋魏文赋
Owner SOUTHWEST JIAOTONG UNIV
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