Data-driven fault detection in a reusable rocket engine using bivariate time-series analysis

Data-driven fault detection using a bivariate time-series analysis was done for the maintenance of reusable liquid-propellant rocket engines. This method is based on the phase plane trajectory of feature vectors extracted from two sensor data by principal component analysis, and applied to all senso...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Acta astronautica 2021-02, Vol.179, p.685-694
Hauptverfasser:	Tsutsumi, Seiji, Hirabayashi, Miki, Sato, Daiwa, Kawatsu, Kaname, Sato, Masaki, Kimura, Toshiya, Hashimoto, Tomoyuki, Abe, Masaharu
Format:	Artikel
Sprache:	eng
Schlagworte:	Bivariate analysis Bivariate time-series analysis Data analysis Fault detection Feature extraction Liquid propellant rocket engines Principal components analysis Resusable liquid-propellant rocket engine Reusable rocket engines Rocket firing Rockets Sensors Static firing Temperature sensors Time series
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!