Details
| Original language | English |
|---|---|
| Pages (from-to) | 224-232 |
| Number of pages | 9 |
| Journal | CIRP Journal of Manufacturing Science and Technology |
| Volume | 31 |
| Early online date | 19 Jun 2020 |
| Publication status | Published - Nov 2020 |
Abstract
This article presents an approach for a self-optimizing compensation of tool load induced surface deviations in 5-axis ball-end milling. In order to predict the surface deviation independently from the workpiece geometry, the tool deflection is modelled as a function of the tool engagement using a machine learning approach. For that purpose, a novel description of the cutting conditions in ball-end milling is introduced. The selected features are derived from a process-parallel simulation. Subsequently, the learning behavior, the transferability of process knowledge to other shapes and the feasible compensation are investigated experimentally. It is shown that the developed approach can reduce the shape error by over 70%.
Keywords
- Adaptive manufacturing, Ball-end milling, Compensation, Computer aided manufacturing (CAM), Machine learning
ASJC Scopus subject areas
- Engineering(all)
- Industrial and Manufacturing Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: CIRP Journal of Manufacturing Science and Technology, Vol. 31, 11.2020, p. 224-232.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Self-optimizing compensation of surface deviations in 5-axis ball-end milling based on an enhanced description of cutting conditions
AU - Dittrich, Marc-André
AU - Uhlich, Florian
N1 - Funding information: The authors would like to thank the Leibniz Universität Hannover for its funding within the program “Wege in die Forschung II”. Moreover, the authors would like to thank Berend Denkena for his support.
PY - 2020/11
Y1 - 2020/11
N2 - This article presents an approach for a self-optimizing compensation of tool load induced surface deviations in 5-axis ball-end milling. In order to predict the surface deviation independently from the workpiece geometry, the tool deflection is modelled as a function of the tool engagement using a machine learning approach. For that purpose, a novel description of the cutting conditions in ball-end milling is introduced. The selected features are derived from a process-parallel simulation. Subsequently, the learning behavior, the transferability of process knowledge to other shapes and the feasible compensation are investigated experimentally. It is shown that the developed approach can reduce the shape error by over 70%.
AB - This article presents an approach for a self-optimizing compensation of tool load induced surface deviations in 5-axis ball-end milling. In order to predict the surface deviation independently from the workpiece geometry, the tool deflection is modelled as a function of the tool engagement using a machine learning approach. For that purpose, a novel description of the cutting conditions in ball-end milling is introduced. The selected features are derived from a process-parallel simulation. Subsequently, the learning behavior, the transferability of process knowledge to other shapes and the feasible compensation are investigated experimentally. It is shown that the developed approach can reduce the shape error by over 70%.
KW - Adaptive manufacturing
KW - Ball-end milling
KW - Compensation
KW - Computer aided manufacturing (CAM)
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85087066370&partnerID=8YFLogxK
U2 - 10.1016/j.cirpj.2020.05.013
DO - 10.1016/j.cirpj.2020.05.013
M3 - Article
VL - 31
SP - 224
EP - 232
JO - CIRP Journal of Manufacturing Science and Technology
JF - CIRP Journal of Manufacturing Science and Technology
SN - 1755-5817
ER -