Conditional feature disentanglement learning for anomaly detection in machines operating under time-varying conditions

•Data-driven AD of machines under time-varying operating conditions is considered in this paper.•A feature disentanglement learning is proposed to solve entanglement between OCs and health states.•A Conditional VAE network combined with PCA is developed to realize the feature disentanglement and AD....

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Mechanical systems and signal processing Jg. 191; S. 110139
Hauptverfasser:	Zhou, Haoxuan, Lei, Zihao, Zio, Enrico, Wen, Guangrui, Liu, Zimin, Su, Yu, Chen, Xuefeng
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 15.05.2023 Elsevier
Schlagworte:	Anomaly detection Bearing Business administration Engineering Sciences Feature disentanglement learning Humanities and Social Sciences Machines Time-varying operating conditions Variational autoencoder Feature disentanglement learning Variational autoencoder Time-varying operating conditions Machines Anomaly detection Bearing Condition monitoring Learning systems Feature extraction
ISSN:	0888-3270, 1096-1216
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!