Application progress of deep learning in power equipment defect identification
ZANG Guoqiang1,2 , LIU Xiaoli3 , XU Yingfei1,2 , CHEN Yulu4 , LI Wenbo1
1. Hefei Institute of Physical Science, Chinese Academy of Sciences, Hefei 230031;
Abstract Deep learning can be used to identify defects in power equipment images intelligently, efficiently and accurately in power equipment defect recognition. In this paper, the substance and the background of defect recognition is described at first. Then several dominant deep learning models of defect recognition are sketched and the improvement and optimization of these models are introduced. The applications of the models in current market are summarized, and the challenges and difficulties faced in these applications are analyzed. Finally, the future trend of deep learning in power equipment defect recognition is discussed in terms of automatic machine learning, sample database construction and power knowledge mapping.
Key words ：
deep learning
defect recognition
power equipment
intelligent inspection
Received: 22 November 2021
Cite this article:
ZANG Guoqiang,LIU Xiaoli,XU Yingfei等. Application progress of deep learning in power equipment defect identification[J]. Electrical Engineering, 2022, 23(6): 1-7.
URL:
https://dqjs.cesmedia.cn/EN/Y2022/V23/I6/1
[1] 李宗. 电力系统及电力设备的可靠性[J]. 甘肃科技纵横, 2018, 47(10): 49-51, 86.
2022, Vol. 23 
