Early weak anomaly detection and uncertainty quantification of equipment based on multi-task and multi-domain temporal memory autoencoder

To avoid severe malfunctions of industrial equipment, it is necessary to perform accurate detection in the early stages of abnormal occurrences. However, early anomalies are usually weak, difficult to model anomalous features, and affected by data uncertainty and training uncertainty. To address the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Engineering applications of artificial intelligence Jg. 162; S. 112735
Hauptverfasser:	Li, Chuanrui, Ma, Liyong
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 26.12.2025
Schlagworte:	Autoencoder Early weak anomaly detection Multi-task learning Uncertainty Early weak anomaly detection Uncertainty Autoencoder Multi-task learning
ISSN:	0952-1976
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!