Issue |
MATEC Web Conf.
Volume 408, 2025
44th Conference of the International Deep Drawing Research Group (IDDRG 2025)
|
|
---|---|---|
Article Number | 01013 | |
Number of page(s) | 6 | |
Section | Full Papers | |
DOI | https://doi.org/10.1051/matecconf/202540801013 | |
Published online | 07 May 2025 |
Introduction and validation of a surrogate model for warm forming and cathodic dip treatment of EN AW-7075-T6
Leibniz University Hannover, Institute of Forming Technology and Machines,
30823
Garbsen, Germany
* Corresponding author: jepkens@ifum.uni-hannover.de
For the production of safety-relevant automotive components, aluminium alloy EN AW-7075 is a promising substitute characterised by its high specific strength. Due to its low formability at room temperature, warm forming within the temperature range of 150 to 300 °C is carried out to enhance formability. Additionally, warm forming is an energy saving alternative to hot forming due to lower forming temperatures. After forming, the components undergo cathodic dip coating (CDC), causing artificial ageing to achieve final mechanical properties. This paper introduces and validates an experimental-numerical method to model the warm forming and CDC process chain. The method combines a validated finite element (FE) model of warm forming with a random forest regressor to predict post-CDC properties. Training, validation, and testing of the regressor is conducted utilising experimental data. Miniaturised uniaxial tensile specimens were preconditioned with variations in true strain, strain rate, forming temperature and cooling rate, then CDC-treated and destructively tested. To validate the surrogate model approach, tensile specimens were taken from an industrial demonstrator with an analogous thermo-mechanical process chain and destructively tested. A comparison of tensile strength and uniform strain shows good agreement for forming histories within the experimental training data limits.
Key words: Warm forming / FE simulation / Machine learning / Artificial intelligence
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.