Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the 20th International Conference of the European Society for Precision Engineering and Nanotechnology |
| Untertitel | EUSPEN 2020 |
| Seiten | 263-266 |
| Seitenumfang | 4 |
| ISBN (elektronisch) | 9780995775176 |
| Publikationsstatus | Veröffentlicht - 2020 |
| Veranstaltung | 20th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2020 - Geneva, Virtual, Österreich Dauer: 8 Juni 2020 → 12 Juni 2020 |
Abstract
Mechanical polishing is an important step within the process chain of manufacturing workpieces with high requirements regarding the surface quality, e.g. for optical components. The resulting surface quality depends on several parameters, e.g. the process parameters, the workpiece material, the initial surface roughness and the tool condition. Thus, finding process parameters that lead to the desired surface roughness can be regarded as a complex optimization problem. For this purpose, an artificial neural network (ANN) has been designed and trained with data from polishing experiments. Using a dreaming network approach, the ANN has been enabled to suggest appropriate process parameters under consideration of the initial roughness of the workpiece and the tool condition. The validation experiments showed that the process parameters suggested by the neural network led in 72% to the target roughness within a standard deviation.
ASJC Scopus Sachgebiete
- Physik und Astronomie (insg.)
- Instrumentierung
- Ingenieurwesen (insg.)
- Wirtschaftsingenieurwesen und Fertigungstechnik
- Werkstoffwissenschaften (insg.)
- Umweltwissenschaften (insg.)
- Environmental engineering
- Ingenieurwesen (insg.)
- Maschinenbau
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 20th International Conference of the European Society for Precision Engineering and Nanotechnology: EUSPEN 2020. 2020. S. 263-266.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung
}
TY - GEN
T1 - Dreaming neural networks for adaptive polishing
AU - Dittrich, Marc André
AU - Rosenhahn, Bodo
AU - Magnor, Marcus
AU - Denkena, Berend
AU - Malek, Talash
AU - Munderloh, Marco
AU - Kassubeck, Marc
N1 - Funding information: [ This research has been funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122, Project ID 390833453).
PY - 2020
Y1 - 2020
N2 - Mechanical polishing is an important step within the process chain of manufacturing workpieces with high requirements regarding the surface quality, e.g. for optical components. The resulting surface quality depends on several parameters, e.g. the process parameters, the workpiece material, the initial surface roughness and the tool condition. Thus, finding process parameters that lead to the desired surface roughness can be regarded as a complex optimization problem. For this purpose, an artificial neural network (ANN) has been designed and trained with data from polishing experiments. Using a dreaming network approach, the ANN has been enabled to suggest appropriate process parameters under consideration of the initial roughness of the workpiece and the tool condition. The validation experiments showed that the process parameters suggested by the neural network led in 72% to the target roughness within a standard deviation.
AB - Mechanical polishing is an important step within the process chain of manufacturing workpieces with high requirements regarding the surface quality, e.g. for optical components. The resulting surface quality depends on several parameters, e.g. the process parameters, the workpiece material, the initial surface roughness and the tool condition. Thus, finding process parameters that lead to the desired surface roughness can be regarded as a complex optimization problem. For this purpose, an artificial neural network (ANN) has been designed and trained with data from polishing experiments. Using a dreaming network approach, the ANN has been enabled to suggest appropriate process parameters under consideration of the initial roughness of the workpiece and the tool condition. The validation experiments showed that the process parameters suggested by the neural network led in 72% to the target roughness within a standard deviation.
KW - Control loop
KW - Deep learning
KW - Mechanical polishing
KW - Neural network
KW - Process planning
UR - http://www.scopus.com/inward/record.url?scp=85091553318&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85091553318
SP - 263
EP - 266
BT - Proceedings of the 20th International Conference of the European Society for Precision Engineering and Nanotechnology
T2 - 20th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2020
Y2 - 8 June 2020 through 12 June 2020
ER -