EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Application of an Initial Neural Network Model for Validation of Partial Discharge Classification on Stator Coils

Ľubomír Pallaj, Jaroslav Petráš, Ardian Hyseni

Acta Electrotechnica et Informatica · 01.06.2026 · 26 (2) · 46-54

DOI: 10.2478/aei-2026-0010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Electrotechnica et Informatica, online erschienen am 17.06.2026. Verfasst von Ľubomír Pallaj und 2 weiteren Autor:innen. Die Arbeit nennt 7 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents the application of an initial neural network model for the validation of partial discharge classification in stator coils. The aim is to verify the model’s ability to distinguish between different types of partial discharges in a stator coil based on signal processing and their representation using scalograms. The results highlight the potential of artificial neural networks in the classification of insulation systems of electrical machines, with the proposed model serving as a foundation for further development and optimization of more accurate classification methods.

Zitieren

APA

Pallaj, Ľ., Petráš, J., & Hyseni, A. (2026). Application of an Initial Neural Network Model for Validation of Partial Discharge Classification on Stator Coils. Acta Electrotechnica et Informatica, 26(2), 46-54. https://doi.org/10.2478/aei-2026-0010

Vancouver

Pallaj Ľ, Petráš J, Hyseni A. Application of an Initial Neural Network Model for Validation of Partial Discharge Classification on Stator Coils. Acta Electrotechnica et Informatica. 2026;26(2):46-54. doi:10.2478/aei-2026-0010

BibTeX
@article{Pallaj2026,
  author = {Pallaj, Ľubomír and Petráš, Jaroslav and Hyseni, Ardian},
  title = {Application of an Initial Neural Network Model for Validation of Partial Discharge Classification on Stator Coils},
  journal = {Acta Electrotechnica et Informatica},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {46--54},
  doi = {10.2478/aei-2026-0010}
}
Kostenlos starten →