Home Journals Articles Updates About
CN
image
收藏切换
Study on object recognition method of multi-source PD diagrams in oil-immersed power transformer
收藏切换
PDF
Yanbo WANG1, 2, Wei WANG1, 2, Dawei WANG1, 2, Yajun ZOU1, 2, Dingge CHANG3, Guanjun ZHANG3
Insulating Materials | 2023, 56(4) : 85 - 92
Less
收藏切换
Insulating Materials | 2023, 56(4): 85-92
• Test and Analysis •
Study on object recognition method of multi-source PD diagrams in oil-immersed power transformer
Full
Yanbo WANG1, 2, Wei WANG1, 2, Dawei WANG1, 2, Yajun ZOU1, 2, Dingge CHANG3, Guanjun ZHANG3
Affiliations
  • 1Global Energy Interconnection Co., Ltd., Beijing 100031, China
  • 2Global Energy Interconnection Development and Cooperation Organization, Beijing 100031, China
  • 3Xi′an Jiaotong University, Xi′an 710049, China
Published: 2023-04-20 doi: 10.16790/j.cnki.1009-9239.im.2023.04.014
Outline
收藏切换

Partial discharge (PD) phenomenon in power transformer is not only the main cause of insulation deterioration, but also the characteristic parameter to characterize the insulation condition. It is of great significance to accurately recognize the type of PD for the diagnosis of transformer insulation condition. A new method for identifying the type of multi-source PD spectrum based on Faster-RCNN algorithm was proposed in this paper, which can detect different types of PD clusters from multi-source spectrum. The results show that the average recognition accuracy of multi-source PD reaches 72.1% when the proposed algorithm was applied to the PD spectrum obtained from 35 kV transformer. Because the air gap defect has dense PD points and obvious characteristics, its missed and false detection rates are lower than other defects, leading to there be good discrimination for the air gap defect. Because the tip defect has the characteristics of intermittent discharge and high initial discharge voltage, its missed detection rate is high.

power transformer  /  pattern recognition  /  partial discharge  /  RCNN
Yanbo WANG, Wei WANG, Dawei WANG, Yajun ZOU, Dingge CHANG, Guanjun ZHANG. Study on object recognition method of multi-source PD diagrams in oil-immersed power transformer[J]. Insulating Materials, 2023 , 56 (4) : 85 -92 . DOI: 10.16790/j.cnki.1009-9239.im.2023.04.014
Appendix
Less
Year 2023 volume 56 Issue 4
PDF
171
80
Cite this Article
BibTeX
Article Info
doi: 10.16790/j.cnki.1009-9239.im.2023.04.014
  • Receive Date：2022-03-30
  • Online Date：2025-11-21
  • Published：2023-04-20
Article Data
Affiliations
History
  • Received：2022-03-30
  • Revised：2022-05-26
Affiliations
    1Global Energy Interconnection Co., Ltd., Beijing 100031, China
    2Global Energy Interconnection Development and Cooperation Organization, Beijing 100031, China
    3Xi′an Jiaotong University, Xi′an 710049, China
References
Share
https://castjournals.cast.org.cn/joweb/jycl/EN/10.16790/j.cnki.1009-9239.im.2023.04.014
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62199257
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House