Details
Original language | English |
---|---|
Pages (from-to) | 341-344 |
Number of pages | 4 |
Journal | CIRP annals |
Volume | 70 |
Issue number | 1 |
Early online date | 19 May 2021 |
Publication status | Published - 2021 |
Abstract
On the way to fully autonomous machine tools it is essential to independently select suitable process parameters and adapt them on-the-fly to the appropriate process conditions in a self-controlled manner. Such systems require complex physical process models and are usually limited to feed and spindle speed adaption during the milling process. This paper introduces a new approach enabling machines during the milling process to learn which parameters lead to a stable process with maximum productivity and to adjust them autonomously. It is shown that this approach enables the machine tool to independently find stable process parameters with maximum productivity.
Keywords
- Chatter, Machine Learning, Machine tool
ASJC Scopus subject areas
- Engineering(all)
- Mechanical Engineering
- Engineering(all)
- Industrial and Manufacturing Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: CIRP annals, Vol. 70, No. 1, 2021, p. 341-344.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Online adaption of milling parameters for a stable and productive process
AU - Bergmann, Benjamin
AU - Reimer, Svenja
N1 - Funding Information: The authors thank the German Research Foundation (DFG) for its financial and organizational support of the project DE 447/156-1.
PY - 2021
Y1 - 2021
N2 - On the way to fully autonomous machine tools it is essential to independently select suitable process parameters and adapt them on-the-fly to the appropriate process conditions in a self-controlled manner. Such systems require complex physical process models and are usually limited to feed and spindle speed adaption during the milling process. This paper introduces a new approach enabling machines during the milling process to learn which parameters lead to a stable process with maximum productivity and to adjust them autonomously. It is shown that this approach enables the machine tool to independently find stable process parameters with maximum productivity.
AB - On the way to fully autonomous machine tools it is essential to independently select suitable process parameters and adapt them on-the-fly to the appropriate process conditions in a self-controlled manner. Such systems require complex physical process models and are usually limited to feed and spindle speed adaption during the milling process. This paper introduces a new approach enabling machines during the milling process to learn which parameters lead to a stable process with maximum productivity and to adjust them autonomously. It is shown that this approach enables the machine tool to independently find stable process parameters with maximum productivity.
KW - Chatter
KW - Machine Learning
KW - Machine tool
UR - http://www.scopus.com/inward/record.url?scp=85106384880&partnerID=8YFLogxK
U2 - 10.1016/j.cirp.2021.04.086
DO - 10.1016/j.cirp.2021.04.086
M3 - Article
AN - SCOPUS:85106384880
VL - 70
SP - 341
EP - 344
JO - CIRP annals
JF - CIRP annals
SN - 0007-8506
IS - 1
ER -