Data-Driven Condition Monitoring (DaCoMo)
Auf einen Blick
- Projektleiter/in : Dr. Thilo Stadelmann
- Projektteam : Dr. Oliver Dürr, Gabriel Eyyi, Thierry Musy
- Projektvolumen : CHF 940'000
- Projektstatus : abgeschlossen
- Drittmittelgeber : KTI
- Projektpartner : mechmine LLC (Mechmine GmbH)
- Kontaktperson : Thilo Stadelmann
Beschreibung
The goal of DaCoMo is to develop a novel, totally data driven process for predictive maintenance which needs no prior knowledge of the machine itself or its components in order to detect and predict faults. This increases the efficiency of the service: neither frequency spectra need to be input nor visually inspected by experts. The challenge lies in the acquisition of data sets with representative error signatures and in learning the fault characteristics purely from data.
Publikationen
-
Braschler, Martin; Stadelmann, Thilo; Stockinger, Kurt, Hrsg.,
2019.
Applied data science : lessons learned for the data-driven business.
1. Auflage.
Cham:
Springer.
ISBN 978-3-030-11820-4.
Verfügbar unter: https://doi.org/10.1007/978-3-030-11821-1
-
Stadelmann, Thilo; Tolkachev, Vasily; Sick, Beate; Stampfli, Jan; Dürr, Oliver,
2019.
Beyond ImageNet : deep learning in industrial practice
.
In:
Braschler, Martin; Stadelmann, Thilo; Stockinger, Kurt, Hrsg.,
Applied data science : lessons learned for the data-driven business.
Cham:
Springer.
S. 205-232.
Verfügbar unter: https://doi.org/10.1007/978-3-030-11821-1_12
-
Stockinger, Kurt; Braschler, Martin; Stadelmann, Thilo,
2019.
Lessons learned from challenging data science case studies
.
In:
Braschler, Martin; Stadelmann, Thilo; Stockinger, Kurt, Hrsg.,
Applied data science : lessons learned for the data-driven business.
Cham:
Springer.
S. 447-465.
Verfügbar unter: https://doi.org/10.1007/978-3-030-11821-1_24