Constellation, le dépôt institutionnel de l'Université du Québec à Chicoutimi

Identification and application of machine learning algorithms for transformer dissolved gas analysis

Ungarala Mohan Rao, Fofana Issouf, Rajesh K. N. V. P. S. et Picher Patrick. (2021). Identification and application of machine learning algorithms for transformer dissolved gas analysis. IEEE Transactions on Dielectrics and Electrical Insulation, 28, (5), p. 1828-1835.

[thumbnail of Identification_and_Application_of_Machine_Learning_Algorithms_for_Transformer_Dissolved_Gas_Analysis.pdf] PDF - Version soumise
Administrateurs seulement

919kB

URL officielle: http://dx.doi.org/doi:10.1109/TDEI.2021.009770

Résumé

Power transformers represent one of the most abundant and expensive components in the electric power industry. Dissolved gas analysis (DGA) of transformer is the most widely accepted diagnostic tool across the globe to understand insulation incipient failures. Nevertheless, DGA fault gas interpretation is a remarkable challenge for transformer owners and utility engineers. Several computational techniques have been adopted for DGA fault classification along with offline methods. However, limited data availability, high ambiguity in DGA interpretation, suitability, and model accuracy are critical challenges in the DGA fault classification using computational techniques. In this work, highly diverse and large DGA data samples of in-service transformer fleets from five different utilities have been used to develop an efficient fault classification methodology. A total of 4580 DGA samples and IEC TC 10 database are used for training and testing, respectively, for various machine learning algorithms. Discussions on performance indicators and evaluation of several algorithms to verify the most suitable class algorithms are also the focus of this work. Furthermore, a best-performing model is identified based on various performance indicators. The hyperparameters of the best model are further tuned to achieve a most precise fault classification. It is inferred that non-parametric methods and non-linear SVM are best suitable for transformer DGA fault classification. Importantly, the rankings in the present study suggest that transformer DGA fault prediction is better with ensemble learning methods.

Type de document:Article publié dans une revue avec comité d'évaluation
Volume:28
Numéro:5
Pages:p. 1828-1835
Version évaluée par les pairs:Oui
Date:1 Novembre 2021
Sujets:Sciences naturelles et génie > Génie
Sciences naturelles et génie > Génie > Génie des matériaux et génie métallurgique
Sciences naturelles et génie > Sciences appliquées
Département, module, service et unité de recherche:Départements et modules > Département des sciences appliquées > Module d'ingénierie
Unités de recherche > Centre international de recherche sur le givrage atmosphérique et l’ingénierie des réseaux électriques (CENGIVRE) > Vieillissement de l’appareillage installé sur les lignes à haute tension (ViAHT)
Mots-clés:support vector machines, learning systems, industries, training, machine learning algorithms, dissolved gas analysis, tools, machines vectorielles de support, systèmes d'apprentissage, formation, algorithmes d'apprentissage automatique, analyse de gaz dissous, outils, transformers, insulation liquids, DGA, fault diagnosis
Déposé le:15 nov. 2021 19:58
Dernière modification:25 janv. 2022 16:17
Afficher les statistiques de telechargements

Éditer le document (administrateurs uniquement)

Creative Commons LicenseSauf indication contraire, les documents archivés dans Constellation sont rendus disponibles selon les termes de la licence Creative Commons "Paternité, pas d'utilisation commerciale, pas de modification" 2.5 Canada.

Bibliothèque Paul-Émile-Boulet, UQAC
555, boulevard de l'Université
Chicoutimi (Québec)  CANADA G7H 2B1
418 545-5011, poste 5630