Chemnitz University of Technology develops learning algorithm for improved car body manufacturing in BMBF-funded project
The digitization of production is currently one of the most important fields of action in the area of auto body production and its related technologies, so that Germany’s businesses in which this sector is a central branch can secure future growth and employment.
The new research project "Machine Learning for the Prognosis of Process Parameters and Component Quality in Automotive Body Manufacturing" (ML@Karoprod) is funded by the Federal Ministry of Education and Research (BMBF).
Partners in the project include the Professorship of Artificial Intelligence (Prof. Dr. Fred Hamker), the Fraunhofer Institute for Machine Tools and Forming Technology IWU in Dresden (Dr. Mathias Jäckel) as well as Scale GmbH (Dr. Ingolf Lepenies).
The project focuses on model development and the application of machine learning (ML) techniques to accelerate the initial planning and serial setup in car body manufacturing. Chemnitz University of Technology will receive € 257 000 of the total funding of roughly € 1.2 million.
The Chemnitz University of Technology schedule follows three main phases: In the first phase, a forward model is trained in order to predict the consequences of an action with unsupervised learning.
In the second phase, this trained model will be used to accelerate the model-based Deep Reinforcement Learning Algorithm. Its task will be to find a sequence of production parameters that optimizes the quality of the final product.
In the third phase, the developed algorithm is tested on the real production system, in which its robustness against missing sensory information will be tested and evaluated.
For further information, please contact Prof. Dr. Fred Hamker, Chair of Artificial Intelligence, Tel. +49 371 531-37875, E-mail firstname.lastname@example.org
(Article: Matthias Fejes / Translation: Jeffrey Karnitz)
Prof. Dr. Fred Hamker, Chair of Artificial Intelligence, Tel. +49 371 531-37875, E-mail email@example.com
Matthias Fejes | Technische Universität Chemnitz
ESJET printing technology for large area active devices awarded
11.04.2019 | Fraunhofer-Institut für Angewandte Polymerforschung IAP
9.1 million euros for trinational quantum research
07.03.2019 | Albert-Ludwigs-Universität Freiburg im Breisgau
A stellar flare 10 times more powerful than anything seen on our sun has burst from an ultracool star almost the same size as Jupiter
A localization phenomenon boosts the accuracy of solving quantum many-body problems with quantum computers which are otherwise challenging for conventional computers. This brings such digital quantum simulation within reach on quantum devices available today.
Quantum computers promise to solve certain computational problems exponentially faster than any classical machine. “A particularly promising application is the...
The technology could revolutionize how information travels through data centers and artificial intelligence networks
Engineers at the University of California, Berkeley have built a new photonic switch that can control the direction of light passing through optical fibers...
Physicists observe how electron-hole pairs drift apart at ultrafast speed, but still remain strongly bound.
Modern electronics relies on ultrafast charge motion on ever shorter length scales. Physicists from Regensburg and Gothenburg have now succeeded in resolving a...
Engineers create novel optical devices, including a moth eye-inspired omnidirectional microwave antenna
A team of engineers at Tufts University has developed a series of 3D printed metamaterials with unique microwave or optical properties that go beyond what is...
17.04.2019 | Event News
15.04.2019 | Event News
09.04.2019 | Event News
18.04.2019 | Life Sciences
18.04.2019 | Physics and Astronomy
18.04.2019 | Life Sciences