Flashover Characteristics of Composite Insulators with Different Levels of Guano Adhesion and Detection Based on Hyperspectral Technique

In recent years, with the enhancement of people's environmental awareness, the number of birds is increasing, bird damage faults of transmission lines become one of important types of transmission line operation faults. The degree of guano adhesion affects the flashover characteristics of insulators, so it is necessary to test the degree of guano adhesion of insulators. The traditional detection methods such as equivalent salt deposit density method, surface dirt conductivity method, leakage current method are more complex and not conducive to field application. Hyperspectral technology can collect insulator spectrum information non-contactly, which can be applied to insulator detection. Therefore, this paper carried out experiments to study the flashover characteristics of insulators under different guano adhesion degrees, and proposed a method based on hyperspectral technology to detect guano adhesion degrees of composite insulators. The results showed that the more guano attached, the lower the flashover voltage. Then hyperspectral images of insulators with different degrees of adhesion were taken, and the degree of adhesion was divided according to the equivalent salt deposit density and non-soluble deposit density. Then the original data collected were preprocessed and corrected to remove noise interference. Then, a support vector machine (SVM) classification model was established based on the differences of the spectral lines of different bird feces adhesion degrees to achieve the classification of the degree of bird feces adhesion of the samples, and the accuracy can reach 100%. Finally, the principal component analysis (PCA) was used to reduce the dimension of the sample spectral line data to remove redundant information, and the classification accuracy can still be maintained after being reduced to 4 dimensions compared with the classification accuracy before dimension reduction, which realizes effective dimension reduction and provides reference for bird damage prevention of transmission lines in areas with frequent bird activities and prominent bird feces adherence.

Authors

Institutions

Publication Details

Published
2024-09-27
DOI
https://doi.org/10.1145/3702879.3702930
Primary Topic
Image Enhancement Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Flashover Characteristics of Composite Insulators with Different Levels of Guano Adhesion and Detection Based on Hyperspectral Technique

Minghui Jia, Long Tian, Bin Yao, Xiaolong Wang et al.
Image Enhancement Techniques
article

Flashover Characteristics of Composite Insulators with Different Levels of Guano Adhesion and Detection Based on Hyperspectral Technique

Minghui Jia, Long Tian, Bin Yao, Xiaolong Wang, Wei Meng, Ping Wang, Hao Zhang, Yanli Jin, Lin Huang
article en

Abstract

In recent years, with the enhancement of people's environmental awareness, the number of birds is increasing, bird damage faults of transmission lines become one of important types of transmission line operation faults. The degree of guano adhesion affects the flashover characteristics of insulators, so it is necessary to test the degree of guano adhesion of insulators. The traditional detection methods such as equivalent salt deposit density method, surface dirt conductivity method, leakage current method are more complex and not conducive to field application. Hyperspectral technology can collect insulator spectrum information non-contactly, which can be applied to insulator detection. Therefore, this paper carried out experiments to study the flashover characteristics of insulators under different guano adhesion degrees, and proposed a method based on hyperspectral technology to detect guano adhesion degrees of composite insulators. The results showed that the more guano attached, the lower the flashover voltage. Then hyperspectral images of insulators with different degrees of adhesion were taken, and the degree of adhesion was divided according to the equivalent salt deposit density and non-soluble deposit density. Then the original data collected were preprocessed and corrected to remove noise interference. Then, a support vector machine (SVM) classification model was established based on the differences of the spectral lines of different bird feces adhesion degrees to achieve the classification of the degree of bird feces adhesion of the samples, and the accuracy can reach 100%. Finally, the principal component analysis (PCA) was used to reduce the dimension of the sample spectral line data to remove redundant information, and the classification accuracy can still be maintained after being reduced to 4 dimensions compared with the classification accuracy before dimension reduction, which realizes effective dimension reduction and provides reference for bird damage prevention of transmission lines in areas with frequent bird activities and prominent bird feces adherence.

North China Electric Power University (CN)
Affordable and clean energy
Openalex Percentile: Top 77%
Image Enhancement Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.