Details
| Original language | English |
|---|---|
| Pages (from-to) | 1010-1015 |
| Number of pages | 6 |
| Journal | Procedia CIRP |
| Volume | 118 |
| Early online date | 18 Jul 2023 |
| Publication status | Published - 2023 |
| Event | 16th CIRP Conference on Intelligent Computation in Manufacturing Engineering 2022 - Naples, Italy Duration: 13 Jul 2022 → 15 Jul 2022 |
Abstract
With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.
Keywords
- computer vision, predictive maintenance, prognostic health management
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Engineering(all)
- Industrial and Manufacturing Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Procedia CIRP, Vol. 118, 2023, p. 1010-1015.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Introduction to deep degradation metric in smart production ecosystems
AU - Adhisantoso, Yeremia Gunawan
AU - Xuan, Quy Le
AU - Munderloh, Marco
AU - Ostermann, Jörn
AU - Kellerman, Christoph
N1 - Funding Information: The authors acnk oledw ge the inf ancial support by the Federal Ministry of r Economic Afaf irs and Climate Action of Germany (BWMK) in the rf ameow r k of IIP -Ecosphere project (project number 01MK20006A ). We ow uld also lie k to thank Gerresheimer Bnü de GmbH for providing the materials in this work.
PY - 2023
Y1 - 2023
N2 - With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.
AB - With the advent of Industry 4.0, more data is exploited to improve efficiency in production and to enable a cost-effective maintenance approach called predictive maintenance. In a production ecosystem, assets are maintained based on their corresponding internal condition. Often, there is no known ground truth or label for the internal condition of the components, especially for high-dimensional data. Furthermore, the initial degradation condition of the assets differs from each other. We present a novel approach to learns a degradation metric implicitly (with minimal information). The approach can take the initial condition of the asset into consideration.
KW - computer vision
KW - predictive maintenance
KW - prognostic health management
UR - http://www.scopus.com/inward/record.url?scp=85173576129&partnerID=8YFLogxK
U2 - 10.1016/j.procir.2023.06.173
DO - 10.1016/j.procir.2023.06.173
M3 - Conference article
AN - SCOPUS:85173576129
VL - 118
SP - 1010
EP - 1015
JO - Procedia CIRP
JF - Procedia CIRP
SN - 2212-8271
T2 - 16th CIRP Conference on Intelligent Computation in Manufacturing Engineering 2022
Y2 - 13 July 2022 through 15 July 2022
ER -