Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 795-802 |
| Seitenumfang | 8 |
| Fachzeitschrift | CIRP Journal of Manufacturing Science and Technology |
| Jahrgang | 35 |
| Frühes Online-Datum | 5 Okt. 2021 |
| Publikationsstatus | Veröffentlicht - Nov. 2021 |
Abstract
Data-based methods are capable to monitor machine components. Approaches for semi-supervised anomaly detection are trained using sensor data that describe the normal state of machine components. Thus, such approaches are interesting for industrial practice, since sensor data do not have to be labeled in a time-consuming and costly way. In this work, an ensemble approach for semi-supervised anomaly detection is used to detect anomalies. It is shown that the ensemble approach is suitable for condition monitoring of ball screws. For the evaluation of the approach, a data set of a regular test cycle of a ball screw from automotive industry is used.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Wirtschaftsingenieurwesen und Fertigungstechnik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: CIRP Journal of Manufacturing Science and Technology, Jahrgang 35, 11.2021, S. 795-802.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Data-based ensemble approach for semi-supervised anomaly detection in machine tool condition monitoring
AU - Denkena, B.
AU - Dittrich, M. A.
AU - Noske, H.
AU - Stoppel, D.
AU - Lange, D.
N1 - Funding Information: Funded by the Lower Saxony Ministry of Science and Culture under grant number ZN3489 within the Lower Saxony “Vorab” of the Volkswagen Foundation, Germany; supported by the Center for Digital Innovations (ZDIN), Germany. We also thank the Marposs Monitoring Solutions GmbH (Artis), Germany, for their support.
PY - 2021/11
Y1 - 2021/11
N2 - Data-based methods are capable to monitor machine components. Approaches for semi-supervised anomaly detection are trained using sensor data that describe the normal state of machine components. Thus, such approaches are interesting for industrial practice, since sensor data do not have to be labeled in a time-consuming and costly way. In this work, an ensemble approach for semi-supervised anomaly detection is used to detect anomalies. It is shown that the ensemble approach is suitable for condition monitoring of ball screws. For the evaluation of the approach, a data set of a regular test cycle of a ball screw from automotive industry is used.
AB - Data-based methods are capable to monitor machine components. Approaches for semi-supervised anomaly detection are trained using sensor data that describe the normal state of machine components. Thus, such approaches are interesting for industrial practice, since sensor data do not have to be labeled in a time-consuming and costly way. In this work, an ensemble approach for semi-supervised anomaly detection is used to detect anomalies. It is shown that the ensemble approach is suitable for condition monitoring of ball screws. For the evaluation of the approach, a data set of a regular test cycle of a ball screw from automotive industry is used.
KW - Ball screw
KW - Condition monitoring
KW - Failure
KW - Machine learning
KW - Maintenance
UR - http://www.scopus.com/inward/record.url?scp=85116474771&partnerID=8YFLogxK
U2 - 10.1016/j.cirpj.2021.09.003
DO - 10.1016/j.cirpj.2021.09.003
M3 - Article
AN - SCOPUS:85116474771
VL - 35
SP - 795
EP - 802
JO - CIRP Journal of Manufacturing Science and Technology
JF - CIRP Journal of Manufacturing Science and Technology
SN - 1755-5817
ER -