Jaremenko C, Huang X, Affronti E, Merklein M, Maier A (2017)
Publication Type: Conference contribution
Publication year: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Edited Volumes: Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
Pages Range: 100-103
Conference Proceedings Title: Proceedings of the 15th IAPR International Conference on Machine Vision Applications
ISBN: 9784901122160
URI: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2017/Jaremenko17-SMF.pdf
DOI: 10.23919/MVA.2017.7986814
Forming limit diagrams are used to evaluate the formability of metal sheets and describe the maximum strain to failure in terms of major and minor strain. The main idea is the detection of the onset of necking in limited areas of the investigated sheet metals. Current methods introduce location-or time-dependency or may require user interaction. Within this contribution we interpret the onset of necking as classification problem and show that a support vector machine performs comparable to a human experts group. Best results reach up to 87.5 % avg. precision and 84.9 % avg. recall, using all available 2D-information, while being time- and location-independent.
APA:
Jaremenko, C., Huang, X., Affronti, E., Merklein, M., & Maier, A. (2017). Sheet metal forming limits as classification problem. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications (pp. 100-103). Nagoya, JP: Institute of Electrical and Electronics Engineers Inc..
MLA:
Jaremenko, Christian, et al. "Sheet metal forming limits as classification problem." Proceedings of the Machine Vision Applications, Nagoya Institute of Electrical and Electronics Engineers Inc., 2017. 100-103.
BibTeX: Download