Distribution transformer mechanical faults diagnosis method incorporating cross-domain feature extraction and recognition of unknown-type faults

•An improved CAE algorithm is introduced, which integrates frequency spectral sequences into the output reconstruction phase. This innovative approach allows the model to dynamically extract information from the vibration signals across both the time and frequency domains, thereby providing a more c...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Measurement : journal of the International Measurement Confederation Jg. 238; S. 115270
Hauptverfasser:	Huang, Haiyan, Gao, Wei, Yang, Gengjie
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.10.2024
Schlagworte:	Cross-domain fusion multi-scale convolutional autoencoder (CFMS-CAE) Distribution transformer Mechanical faults Open-set domain adaptation classifier(OSDA-C) Vibration signals Cross-domain fusion multi-scale convolutional autoencoder (CFMS-CAE) Open-set domain adaptation classifier(OSDA-C) Distribution transformer Vibration signals Mechanical faults
ISSN:	0263-2241
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!