Research on Anomaly Detection Method of Online Monitoring Data of Dissolved Gas in Transformer Oil

Yang, Xiaohui; Guo, Chenxi; Ren, H.; Dong, Ming

doi:10.1145/3512826.3512840

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While statistical analysis can somewhat reduce the false alarm rate [9][10] , the fundamental approach is to improve the reliability of the equipment. Up to now, there have been few studies on the reliability evaluation of the devices [11] , and there is no related research on accelerated testing, let alone reports on the corresponding accelerated testing platforms.…”

Section: Introductionmentioning

confidence: 99%

On-site accelerated test method and platform for reliability evaluation of online monitoring devices for dissolved gas in insulating oil

Lian,

Zheng,

Liu

et al. 2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

The online monitoring devices for dissolved gases in insulating oil play a significant role in monitoring the operating status and pre-diagnosis of latent faults in oil-filled electrical equipment such as transformers and reactors. To quickly evaluate the reliability and long-term stability of products from different manufacturers with different detection principles and process designs, and to effectively utilize the devices' online monitoring capabilities, this article proposes a method for accelerated degradation testing of such equipment based on comprehensive research and analysis. Additionally, a corresponding on-site reliability testing platform has been established using a retired transformer at a certain substation. The method and platform proposed in this article can be used to conduct fully automatic short-cycle continuous operation (time compression), intensive stress event impact (event compression), and other accelerated degradation tests on online monitoring devices for dissolved gases in insulating oil, automatically generating various reliability indicators using statistical methods.

show abstract

Section: Introductionmentioning

confidence: 99%