Paper
25 April 2022 Defect detection of transformer lead bushing based on deep learning
Delong Wang, Wei Wang
Author Affiliations +
Proceedings Volume 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022); 1224446 (2022) https://doi.org/10.1117/12.2635201
Event: 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 2022, Guilin, China
Abstract
The high-voltage lead bushing is the core component of the high-voltage lead insulation of a large transformer, and its operational reliability and maintenance are very important to the normal operation of its supporting power transformer.This paper proposes to use YOLOv5s as the recognition model to increase the detection accuracy by adding a small target detection layer. The proposed method mAP reaches 93.7%, which is 2.4% higher than the original YOLOv5s, which ensures the accuracy of detection.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Delong Wang and Wei Wang "Defect detection of transformer lead bushing based on deep learning", Proc. SPIE 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 1224446 (25 April 2022); https://doi.org/10.1117/12.2635201
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Lead

Target detection

Transformers

Data modeling

Defect detection

Performance modeling

Image analysis

Back to Top