Paper
25 September 2023 An online measurement method of transformer capacity based on cyclic BP model
Bin Zhang, Meijie Liu, Linqiao Wu, Lantao Jing, Meiling Bao, Jinkuo Li, Ye Zhang, Liang Wang
Author Affiliations +
Abstract
The online detection of transformer capacity has important practical significance for the maintenance of the interests of electric power enterprises and the safe and stable operation of power grid. Due to the error of transformer operating environment, operating state or acquisition device, there is a lot of noise in the capacity detection data, which makes the on-line calculation of short-circuit impedance fluctuate and affects the capacity detection result. Based on the analysis of current data cleaning methods, a cyclic cleaning method based on BP neural network was proposed to clean historical data unsupervised and train the cleaning model synchronously. Through the trained cleaning model, online cleaning of detected data was realized. The simulation results show that the short-circuit impedance calculated by the online transformer capacity detection method based on the cyclic BP model tends to be stable, and the calculation error is maintained around 5%. Cyclic BP model is an unsupervised and intelligent data cleaning method, which can effectively improve the influence of noise data on detection results and improve the accuracy of transformer capacity detection.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Bin Zhang, Meijie Liu, Linqiao Wu, Lantao Jing, Meiling Bao, Jinkuo Li, Ye Zhang, and Liang Wang "An online measurement method of transformer capacity based on cyclic BP model", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127883L (25 September 2023); https://doi.org/10.1117/12.3004310
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Error analysis

Data analysis

Transformers

Statistical modeling

Education and training

Lithium

Back to Top