Publikationstyp: Konferenz: Sonstiges
Art der Begutachtung: Keine Angabe
Titel: Scaling-up deep learning based predictive maintenance for commercial machine fleets : a case study
Autor/-in: Goren Huber, Lilach
et. al: No
Angaben zur Konferenz: 9th Swiss Conference on Data Science (SDS), Lucerne, Switzerland, 22.-23. Juni 2022
Erscheinungsdatum: 23-Jun-2022
Sprache: Englisch
Schlagwörter: Predictive maintenance; Deep learning; Scalability; Transfer learning; Fleet PHM; Condition based maintenance; Multi-component system
Fachgebiet (DDC): 006: Spezielle Computerverfahren
620: Ingenieurwesen
Zusammenfassung: Developing predictive maintenance algorithms for industrial systems is a growing trend in numerous application fields. Whereas applied research methods have been rapidly advancing, implementations in commercial systems are still lagging behind. One of the main reasons for this delay is the fact that most methodological advances have been focusing on development of data driven algorithms for fault detection, diagnosis or prognosis, ignoring some of the crucial aspects that are required for scaling these algorithms to large fleets of multi-component heterogeneous machines under varying operating conditions, and making sure that their implementation is technically feasible. In this talk I summarize results of an extensive project, developing a deep learning based fault detection scheme for wind farms. I emphasize the elements of this scheme that enabled scaling it up for commercial implementation which took place recently.
Weitere Angaben: Best Presentation Award
URI: https://digitalcollection.zhaw.ch/handle/11475/25291
Volltext Version: Publizierte Version
Lizenz (gemäss Verlagsvertrag): Lizenz gemäss Verlagsvertrag
Departement: School of Engineering
Organisationseinheit: Institut für Datenanalyse und Prozessdesign (IDP)
Enthalten in den Sammlungen:Publikationen School of Engineering

Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.
Zur Langanzeige


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