Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture

•State-of-the-art results on the C-MAPSS dataset.•Genetic algorithm effectively tunes hyper-parameters in deep architectures.•Unsupervised pre-training extracts degradation related features.•Semi-supervised learning improves the remaining useful life prediction accuracy. In recent years, research ha...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Reliability engineering & system safety Jg. 183; S. 240 - 251
Hauptverfasser:	Listou Ellefsen, André, Bjørlykhaug, Emil, Æsøy, Vilmar, Ushakov, Sergey, Zhang, Houxiang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Barking Elsevier Ltd 01.03.2019 Elsevier BV
Schlagworte:	Algorithms Architecture Artificial neural networks C-MAPSS Datasets Deep learning Degradation Experiments Feature extraction Genetic algorithm Genetic algorithms Long short-term memory Machine learning Neural networks Predictions Prognostics and health management Reliability engineering Remaining useful life Semi-supervised learning Training Turbofan engines Deep learning Remaining useful life C-MAPSS Genetic algorithm Semi-supervised learning Prognostics and health management
ISSN:	0951-8320, 1879-0836
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!