Echo state kernel recursive least squares algorithm for machine condition prediction

•A combination of reservoir computing and kernel adaptive filter.•The fixed reservoir facilitates the capability of performing long-term prediction.•The novel online learning method still maintains the simplicity of the training process.•A online prognostic method based on KAF and a Bayesian techniq...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Mechanical systems and signal processing Jg. 111; S. 68 - 86
Hauptverfasser:	Zhou, Haowen, Huang, Jinquan, Lu, Feng, Thiyagalingam, Jeyarajan, Kirubarajan, Thia
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Berlin Elsevier Ltd 01.10.2018 Elsevier BV
Schlagworte:	Adaptive algorithms Adaptive filters Algorithms Bayesian analysis Convexity Data points Dependence Dynamic characteristics Kernel adaptive filter Least squares Life prediction Long-term prediction Machine learning Mathematical models Neural networks Numerical analysis Principal components analysis Prognostics Remaining useful lifeprediction Reservoir computing Signal processing Time series Turbofan engines Kernel adaptive filter Remaining useful lifeprediction Reservoir computing Prognostics Long-term prediction
ISSN:	0888-3270, 1096-1216
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!