Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers
Sensors · 27.11.2024 · 24 (23) · 7585
DOI: 10.3390/s24237585 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 27.11.2024. Verfasst von Thales W Cabral und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Communications, School of Electrical and Computer Engineering, University of Campinas, Campinas 13083-852, Brazil. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Transmissora Aliança de Energia Elétrica S.A., R&D Program of the Brazilian Electricity Regulatory Agency (ANEEL).
Abstract (Originalsprache)
Instabilities in energy supply caused by equipment failures, particularly in power transformers, can significantly impact efficiency and lead to shutdowns, which can affect the population. To address this, researchers have developed fault diagnosis strategies for oil-immersed power transformers using dissolved gas analysis (DGA) to enhance reliability and environmental responsibility. However, the fault diagnosis of oil-immersed power transformers has not been exhaustively investigated. There are gaps related to real scenarios with imbalanced datasets, such as the reliability and robustness of fault diagnosis modules. Strategies with more robust models increase the overall performance of the entire system. To address this issue, we propose a novel approach based on Kolmogorov–Arnold Network (KAN) for the fault diagnosis of power transformers. Our work is the first to employ a dedicated KAN in an imbalanced data real-world scenario, named KANDiag, while also applying the synthetic minority based on probabilistic distribution (SyMProD) technique for balancing the data in the fault diagnosis. Our findings reveal that this pioneering employment of KANDiag achieved the minimal value of Hamming loss—0.0323—which minimized the classification error, guaranteeing enhanced reliability for the whole system. This ground-breaking implementation of KANDiag achieved the highest value of weighted average F1-Score—96.8455%—ensuring the solidity of the approach in the real imbalanced data scenario. In addition, KANDiag gave the highest value for accuracy—96.7728%—demonstrating the robustness of the entire system. Some key outcomes revealed gains of 68.61 percentage points for KANDiag in the fault diagnosis. These advancements emphasize the efficiency and robustness of the proposed system.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Communications, School of Electrical and Computer Engineering, University of Campinas, Campinas 13083-852, Brazil.
- Transmissora Aliança de Energia Elétrica S.A.-TAESA, Praça Quinze de Novembro, Centro, Rio de Janeiro 20010-010, Brazil.
- Department of Hardware Design, Instituto de Pesquisa Eldorado, Campinas 13083-898, Brazil.
ORCID-Profile: Thales W Cabral, José C S S Filho, Luís G P Meloni
Förderung
- Transmissora Aliança de Energia Elétrica S.A.
- R&D Program of the Brazilian Electricity Regulatory Agency (ANEEL)
Zitieren
APA
Cabral, T. W., Gomes, F. V., de Lima, E. R., Filho, J. C. S. S., & Meloni, L. G. P. (2024). Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers. Sensors, 24(23), 7585. https://doi.org/10.3390/s24237585
Vancouver
Cabral TW, Gomes FV, de Lima ER, Filho JCSS, Meloni LGP. Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers. Sensors. 2024;24(23):7585. doi:10.3390/s24237585
BibTeX
@article{Cabral2024,
author = {Cabral, Thales W and Gomes, Felippe V and de Lima, Eduardo R and Filho, José C S S and Meloni, Luís G P},
title = {Kolmogorov–Arnold Network in the Fault Diagnosis of Oil-Immersed Power Transformers},
journal = {Sensors},
year = {2024},
volume = {24},
number = {23},
pages = {7585},
doi = {10.3390/s24237585}
}
EUVIMED