A Fault Diagnosis Method for Mechanical Rotating Components Based on Automatic Learning of Pseudo Labels

To address the problem that existing fully supervised learning methods cannot utilize massive unlabeled samples and semi-supervised learning methods are still inadequate in terms of the accuracy of fault diagnosis models, this paper proposes a quasi-fully supervised fault diagnosis method based on A...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2021 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) S. 1 - 6
Hauptverfasser:	Yin, Shuangyan, Yang, Jingli, Yang, Cheng
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 21.10.2021
Schlagworte:	adversarial autoencoder Classification algorithms constrained seed k-means Data analysis Data models Fault diagnosis mechanical rotating components Semisupervised learning Supervised learning Tagging
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!