Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen: https://doi.org/10.21256/zhaw-25296
Publikationstyp: Konferenz: Paper
Art der Begutachtung: Peer review (Publikation)
Titel: Uncertainty informed anomaly scores with deep learning : robust fault detection with limited data
Autor/-in: Zgraggen, Jannik
Pizza, Gianmarco
Goren Huber, Lilach
et. al: No
DOI: 10.36001/phme.2022.v7i1.3342
10.21256/zhaw-25296
Tagungsband: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022
Herausgeber/-in des übergeordneten Werkes: Do, Phuc
Michau, Gabriel
Ezhilarasu, Cordelia
Band(Heft): 7
Heft: 1
Seite(n): 530
Seiten bis: 540
Angaben zur Konferenz: 7th European PHM, Turin, Italy, 6-8 July 2022
Erscheinungsdatum: 4-Jul-2022
Reihe: PHM Society European Conference
Reihenzählung: 7
Verlag / Hrsg. Institution: PHM Society
Verlag / Hrsg. Institution: State College
ISBN: 978-1-936263-36-3
Sprache: Englisch
Schlagwörter: Deep learning; Anomaly detection; Predictive maintenance; Wind turbines; Uncertainty quantification; Condition based maintenance; Machine learning
Fachgebiet (DDC): 006: Spezielle Computerverfahren
Zusammenfassung: Quantifying the predictive uncertainty of a model is an important ingredient in data-driven decision making. Uncertainty quantification has been gaining interest especially for deep learning models, which are often hard to justify or explain. Various techniques for deep learning based uncertainty estimates have been developed primarily for image classification and segmentation, but also for regression and forecasting tasks. Uncertainty quantification for anomaly detection tasks is still rather limited for image data and has not yet been demonstrated for machine fault detection in PHM applications. In this paper we suggest an approach to derive an uncertainty-informed anomaly score for regression models trained with normal data only. The score is derived using a deep ensemble of probabilistic neural networks for uncertainty quantification. Using an example of wind-turbine fault detection, we demonstrate the superiority of the uncertainty-informed anomaly score over the conventional score. The advantage is particularly clear in an "out-of-distribution" scenario, in which the model is trained with limited data which does not represent all normal regimes that are observed during model deployment.
Weitere Angaben: Best Paper Award Lizenzangabe: CC BY 3.0 United States
URI: https://digitalcollection.zhaw.ch/handle/11475/25296
Volltext Version: Publizierte Version
Lizenz (gemäss Verlagsvertrag): CC BY 3.0: Namensnennung 3.0 Unported
Departement: School of Engineering
Organisationseinheit: Institut für Datenanalyse und Prozessdesign (IDP)
Publiziert im Rahmen des ZHAW-Projekts: Machine Learning Based Fault Detection for Wind Turbines
Enthalten in den Sammlungen:Publikationen School of Engineering

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
2022_Zgraggen-Pizza-Goren-Huber_Uncertainty-informed_ProPHME22.pdf3.56 MBAdobe PDFMiniaturbild
Öffnen/Anzeigen
Zur Langanzeige


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.