Details
| Translated title of the contribution | ANN development in semi-hot forming |
|---|---|
| Original language | German |
| Pages (from-to) | 407-412 |
| Number of pages | 6 |
| Journal | WT Werkstattstechnik |
| Volume | 113 |
| Issue number | 10 |
| Publication status | Published - 2023 |
Abstract
The numerical representation of thermomechanical forming processes requires high computing power. This can be reduced by combining FE simulation and artificial neural networks (KNN), especially for processes involving forming and heat treatment. The article presents the development of a KNN to be used for predicting the material properties of an EN AW-7075 T6 alloy after cathodic dip painting depending on the forming history.
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Engineering(all)
- Automotive Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: WT Werkstattstechnik, Vol. 113, No. 10, 2023, p. 407-412.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - KNN-Entwicklung in der Halbwarmumformung
AU - Ramirez, D. Vasquez
AU - Wester, H.
AU - Uhe, J.
AU - Behrens, B. A.
N1 - Funding Information: Die Autoren bedanken sich bei den Forschungsförderer, dem Bundesministerium für Wirtschaft und Energie. Die Finanzierung wurde von der Arbeitsgemeinschaft industrieller Forschungsvereinigungen (AiF) im Rahmen eines Programms für industrielle Gemeinschaftsforschung (IGF) unter der Förder-kennziffer 21645N organisiert.
PY - 2023
Y1 - 2023
N2 - The numerical representation of thermomechanical forming processes requires high computing power. This can be reduced by combining FE simulation and artificial neural networks (KNN), especially for processes involving forming and heat treatment. The article presents the development of a KNN to be used for predicting the material properties of an EN AW-7075 T6 alloy after cathodic dip painting depending on the forming history.
AB - The numerical representation of thermomechanical forming processes requires high computing power. This can be reduced by combining FE simulation and artificial neural networks (KNN), especially for processes involving forming and heat treatment. The article presents the development of a KNN to be used for predicting the material properties of an EN AW-7075 T6 alloy after cathodic dip painting depending on the forming history.
UR - http://www.scopus.com/inward/record.url?scp=85177428837&partnerID=8YFLogxK
U2 - 10.37544/1436-4980-2023-10-29
DO - 10.37544/1436-4980-2023-10-29
M3 - Artikel
AN - SCOPUS:85177428837
VL - 113
SP - 407
EP - 412
JO - WT Werkstattstechnik
JF - WT Werkstattstechnik
SN - 1436-5006
IS - 10
ER -