A detection algorithm for opening and closing states of high-voltage isolation switches based on deep learning

被引：0
|
作者：
Du Y. [1 ,2 ]
Xie J. [1 ]
Liu Z. [1 ]
Yu H. [2 ]
Zhou S. [2 ]
Lin J. [3 ]
机构：
[1] Faculty of Electric Power Engineering, Kunming University of Science and Technology, Kunming
[2] Electric Power Research Institute of Yunnan Power Grid Co., Ltd., Kunming
[3] Wenshan Power Supply Bureau of Yunnan Power Grid Co., Ltd., Wenshan
来源：
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | 2023年 / 51卷 / 19期
关键词：
deep learning; isolated switches; light weighting of models; neural networks; target detection;
D O I：
10.19783/j.cnki.pspc.230248
中图分类号：
学科分类号：
摘要：
Normal operation of high-voltage disconnect switches is a prerequisite for the stable operation of power systems. To correctly identify the breaking and closing states of disconnect switches, a lightweight improved YOLOv5s target detection algorithm is proposed. First, the anchor frame parameters are reacquired using a quadratic optimized K-means++ clustering algorithm for the disconnecting switch dataset. Then, the loss function in the model is replaced from CIOU to EIOU with stronger convergence performance to accelerate the convergence speed of model training. Finally, a CBAM attention module is added to the last layer of the model backbone feature extraction network to strengthen the model feature extraction capability. The improved model is lightened using the channel sparsification pruning method to reduce the model size and arithmetic power consumption. The experimental results show that the average accuracy of the improved model reaches 97.4% and the model's size is 3.92 MB after the light weighting process, making the model easier to deploy to mobile devices for real-time detection. © 2023 Power System Protection and Control Press. All rights reserved.
引用
收藏
页码：114 / 123
页数：9
相关论文
共 33 条
  • [1] PANG Xiaofeng, MA Jinwei, WANG Liuhuo, Et al., Study on wind load and mechanical properties of high voltage disconnector under strong wind, High Voltage Apparatus, 58, 6, pp. 205-211, (2022)
  • [2] ZHENG Keqin, LU Wangyan, NIE Ming, Et al., Analysis on corrosion and protection of contact materials of outdoors high voltage disconnectors, Guangdong Electric Power, 32, 7, pp. 124-133, (2019)
  • [3] CHENG Lin, ZHANG Hongye, YI Tongqiang, Et al., Insulation defect detection method for disconnecting switches based on time-frequency analysis of 3D electric fields, High Voltage Engineering, 46, 4, pp. 1417-1423, (2020)
  • [4] ZHANG Saipeng, FENG Shitao, ZHAO Chunming, Et al., Study on reliability of high voltage disconnector based on Weibull distribution and Monte Carlo method, High Voltage Apparatus, 57, 6, pp. 86-93, (2021)
  • [5] CHEN Lei, DENG Xinyi, CHEN Hongkun, Et al., Review of the assessment and improvement of power system resilience, Power System Protection and Control, 50, 13, pp. 11-22, (2022)
  • [6] LI Xianfeng, HU Chengang, GAO Zhenyu, Et al., Evaluation method of contact state of GIS disconnector based on multi-feature fusion, Thermal Power Generation, 52, 5, pp. 22-28, (2023)
  • [7] LI Zhongxiang, SONG Jiancheng, On-line temperature measurement system for contacts in HV switchgear, High Voltage Apparatus, 45, 2, pp. 11-13, (2009)
  • [8] CHENG Lin, XU Hui, LIU Yufei, Et al., Mechanical state detection method of horizontal folding arm disconnector based on torque-angle curve, High Voltage Apparatus, 56, 4, pp. 192-198, (2020)
  • [9] ZHANG Zhaoyu, HU Yidan, SONG Yanfeng, Et al., Development and application of mechanical vibration-ultrasound combined sensor for power equipment, Proceedings of the CSEE, 43, 14, pp. 5713-5722, (2023)
  • [10] QIU Zhibin, RUAN Jiangjun, HUANG Daochun, Et al., Mechanical fault diagnosis of high voltage disconnector based on motor current detection, Proceedings of the CSEE, 35, 13, pp. 3459-3466, (2015)
1234