Insulator pollution level detection method based on DAG-SVM

Dong Sun; Yongjian Yang; Youhua Pan; Sen Liu; Yu Ding; Guangmin Gao

doi:10.1117/12.3034064

16 October 2024 Insulator pollution level detection method based on DAG-SVM

Dong Sun, Yongjian Yang, Youhua Pan, Sen Liu, Yu Ding, Guangmin Gao

Author Affiliations +

Proceedings Volume 13291, Ninth International Symposium on Advances in Electrical, Electronics, and Computer Engineering (ISAEECE 2024); 132915J (2024) https://doi.org/10.1117/12.3034064
Event: Ninth International Symposium on Advances in Electrical, Electronics, and Computer Engineering (ISAEECE 2024), 2024, Changchun, China

Abstract

The on-line detection of pollution level of transmission line insulators is of great significance for pollution flashover prevention. Therefore, a method of insulator pollution level detection based on hyperspectral image is proposed in this paper. Initially, the original hyperspectral images are corrected using black and white correction and multiple scattering correction to enhance the characteristics of the spectral data for different contamination levels. A method for detecting insulator contamination levels based on DAG-SVM is proposed, achieving accurate detection of insulator contamination levels. The experimental results show that the method proposed in this paper achieves a detection accuracy rate of over 94% for insulators made of different substrates, meeting the needs of practical engineering applications.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Dong Sun, Yongjian Yang, Youhua Pan, Sen Liu, Yu Ding, and Guangmin Gao "Insulator pollution level detection method based on DAG-SVM", Proc. SPIE 13291, Ninth International Symposium on Advances in Electrical, Electronics, and Computer Engineering (ISAEECE 2024), 132915J (16 October 2024); https://doi.org/10.1117/12.3034064

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE