Detection Method for Bolt Missing Pins of Transmission Line Based on Improved SSD Network
DOI:
https://doi.org/10.54097/2r4jz792Keywords:
Missing pins; SSD; FPN; SE module; Focal Loss.Abstract
The bolt pin structure plays a role in connecting and fixing various components in transmission lines, and the pins are prone to detachment, which may lead to the disintegration of key components and cause serious consequences. The bolt pin target size in the transmission line inspection image is small, the background is complex, and the detection effect using traditional object detection algorithms is poor. This article proposes a method for detecting missing bolts in transmission lines based on an improved SSD (Single Shot MultiBox Detector) network. Using the traditional SSD network as the foundation, a feature fusion module is first added to the network to enrich the semantic information of low-level feature maps and the detail information of high-level feature maps through the mutual fusion of high-level and low-level feature maps. Secondly, embedding a channel attention mechanism module enhances the channel features corresponding to the bolt pin structure and suppresses channel features that are irrelevant to the background; At the same time, the introduction of Focal Loss loss function reduces the unevenness of positive and negative sample classification. Finally, experiments were conducted on the collected bolt missing pin detection dataset, and the results showed that the method proposed in this paper has good performance in detecting missing pins, and the detection accuracy has been significantly improved.
References
[1] Zhao Zhenbing, Zhang Wei, Zhai Yongjie, Zhao Wenqing, Zhang Ke. “The Concept, Research Status and Prospect of Electric Power Vision Technology”, Electric Power Science and Engineering, Vol.1, pp. 1-8, 2020. https://doi.org/10.3969/j.ISSN.1672-0792.2020.01.001
[2] Liu Zhiying, Miao Xiren, Chen Jing, Jiang Hao. “Overview of Research on Intelligent Processing of Visible Light Images for Overhead Line Inspection”, Power System Technology, Vol. 3, pp. 1057-1069, 2020. https://doi.org/10.13335/j.1000-3673.pst.2019.0349
[3] Xiao Xiaohui, Wu Liyuan, Bi Jiangang, Yang Yuan, Gong Yanpeng. “UAV Integrated Inspection Technology for Overhead Transmission Lines in Distribution Network”, China Electric Power, Vol. 1, pp. 97-101, 2018.
[4] Hou Chunping, Zhang Hengguang, Zhang Wei, Yang Yang, Zhang Guifeng, Tian Zhiren. “Identification Method of Spontaneous Explosion Defect of Transmission Line Insulator”, Journal of Electric Power System and Automation, Vol. 6, pp. 1-6, 2019. https://doi.org/10.19635/j.cnki.csu-epsa.000064
[5] Tang Yu, Han Jun, Wei Wenli, Ding Jian, Peng Xinjun. “Research on Component Recognition and Defect Detection in Transmission Lines by Deep Learning”, Electronic Measurement Technology, Vol.6, pp. 60-65, 2018. https://doi.org/10.19651/j.cnki.emt.1701266
[6] Zhang Ji, Yu Juan, Wang Jinli, Tan Shoubiao. “Image Recognition Technology for Transmission Line External Damage Based on Deep Learning”, Computer System Applications, Vol.8, pp. 176-179, 2018. https://doi.org/10.15888/j.cnki.csa.006458
[7] Zhang Shu, Wang Haotian, Dong Xiaochong, Li Yurong, Li Ye. “Transmission Line Bolt Detection Technology Based on Deep Learning”, Power grid technology, Vol.7, pp.2821-2829, 2021. https://doi.org/10.13335/j.1000-3673.pst.2020.1336
[8] Li Xuefeng, Liu Haiying, Liu Gaohua, Su Hansong. “Transmission Line Pin Defect Detection Based on Deep Learning”, Power grid technology, Vol.8, pp.2988-2995, 2021. https://doi.org/10.13335/j.1000-3673.pst.2020.1028
[9] Zhao Zhenbing, Zhang Shuai, Jiang Wei, Wu Peng. “The Detection Method of Transmission Line Bolt Shortage Based on DBSCAN-FPN”, China Electric Power, Vol.3, pp. 45-54, 2021.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Minfu Xu, Zhixiang Zhuang, Junjun Wu

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







