Anomaly detection and diagnosis for wind turbines using long short-term memory-based stacked denoising autoencoders and XGBoost

•An anomaly detection and diagnosis method for wind turbines.•Abnormal data recognition algorithm based on LOF and adaptive K-means.•Normal behavior model based on LSTM-SDAE.•Anomaly location by contribution analysis and XGBoost. An anomaly detection and diagnosis method for wind turbines using long...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Reliability engineering & system safety Jg. 222; S. 108445
Hauptverfasser:	Zhang, Chen, Hu, Di, Yang, Tao
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Barking Elsevier Ltd 01.06.2022 Elsevier BV
Schlagworte:	Abnormalities Algorithms Anomalies Anomaly detection and diagnosis Confidence intervals Diagnosis Feature extraction Long short-term memory Long short-term memory (LSTM) Mahalanobis distance (MD) Noise reduction Outliers (statistics) Reliability engineering Stacked denoising autoencoders (SDAE) Statistical analysis Turbines Wind farms Wind power Wind turbine Wind turbines XGBoost Stacked denoising autoencoders (SDAE) Mahalanobis distance (MD) Anomaly detection and diagnosis Wind turbine Long short-term memory (LSTM) XGBoost
ISSN:	0951-8320, 1879-0836
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!