A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions

•A novel method called DRHRML is proposed for bearing fault diagnosis with small samples under different working conditions.•Improved sparse denoising autoencoder (ISDAE) is proposed to preprocess the raw vibration data.•Two novel task datasets are constructed for verifying the proposed method. Rece...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Mechanical systems and signal processing 2022-04, Vol.169, p.108765, Article 108765
Hauptverfasser:	Su, Hao, Xiang, Ling, Hu, Aijun, Xu, Yonggang, Yang, Xin
Format:	Artikel
Sprache:	eng
Schlagworte:	Bearing Data reconstruction Fault diagnosis Intelligent fault diagnosis Learning Meta-learning Reconstruction Small sample learning Working conditions
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!