A state detection method for high voltage distribution network equipment based on improved YOLOv5

Qiwen Zhang; Kai Li; Jianfeng Guo; Peiqin Zhan; Junyong Cui

doi:10.1117/12.3030633

5 June 2024 A state detection method for high voltage distribution network equipment based on improved YOLOv5

Qiwen Zhang, Kai Li, Jianfeng Guo, Peiqin Zhan, Junyong Cui

Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131635D (2024) https://doi.org/10.1117/12.3030633
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China

Abstract

In this study, an improved YOLOv5 algorithm is proposed for the task of high-voltage distribution network equipment status detection, aiming to enhance the performance and flexibility of the detection network by introducing a decoupled detection head design. To achieve this, we collected a diverse dataset of high-voltage distribution network equipment, taking into account various influencing factors such as different states, environmental conditions, and shooting angles. Experimental results confirm that our model exhibits significant advantages in the performance of high-voltage distribution network equipment status detection compared to traditional models, especially in terms of accuracy and robustness, providing an efficient and accurate solution for the automation of high-voltage distribution network equipment in power systems.

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

Citation Download Citation

Qiwen Zhang, Kai Li, Jianfeng Guo, Peiqin Zhan, and Junyong Cui "A state detection method for high voltage distribution network equipment based on improved YOLOv5", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131635D (5 June 2024); https://doi.org/10.1117/12.3030633

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

Includes PDF, HTML & Video, when available