A novel remaining useful life prediction method based on gated attention mechanism capsule neural network

•The gating mechanism of the proposed GAM can effectively minimize the effect of noise in the sensor data and improve the anti-interference ability of the model. Moreover, the GAM enables the model to pay more attention to important features.•The CapsNet is employed to extract features from the weig...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Measurement : journal of the International Measurement Confederation 2022-02, Vol.189, p.110637, Article 110637
Hauptverfasser:	Zhao, Chengying, Huang, Xianzhen, Li, Yuxiong, Li, Shangjie
Format:	Artikel
Sprache:	eng
Schlagworte:	Capsule neural network (CapsNet) Datasets Feature extraction Gated attention mechanism (GAM) Life prediction Maintenance management Neural networks Prediction uncertainty Predictions Reliability Remaining useful life (RUL) Turbine engines Uncertainty Useful life Wear
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!