Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers
Thales W Cabral, Felippe V Gomes, Eduardo R de Lima, José C S S Filho, Luís G P Meloni, Jongmyon Kim · 2024
Read Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers by Thales W Cabral, Felippe V Gomes, Eduardo R de Lima, José C S S Filho, Luís G P Meloni, Jongmyon Kim (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644399.txt.
Description
Thales Cabral and co-authors apply a new network type to power grid faults in a 2024 paper. Oil-filled transformers fail in ways that gas tests on their oil can reveal. Real fault data are lopsided, with rare faults starved of examples, which weakens diagnosis models. The team pairs a Kolmogorov-Arnold network with a data balancing trick.
Their system posted the best scores the authors found for error rate, balanced class score, and accuracy, near ninety-seven percent on the last. Gains over rivals ran large on some measures. Readers in power systems get a robust option for catching transformer faults before outages spread.
Catalog record
| CREATOR | Thales W Cabral, Felippe V Gomes, Eduardo R de Lima, José C S S Filho, Luís G P Meloni, Jongmyon Kim |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |