Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Optimisation of manufacturing process parameters using deep neural networks as surrogate models

: Pfrommer, J.; Zimmerling, C.; Liu, J.; Kärger, L.; Henning, F.; Beyerer, J.

Postprint urn:nbn:de:0011-n-5036846 (968 KByte PDF)
MD5 Fingerprint: 90c950bf19981e68c4239bbd8f379a9b
Erstellt am: 26.7.2018

Procedia CIRP 72 (2018), S.426-431
ISSN: 2212-8271
Conference on Manufacturing Systems (CMS) <51, 2018, Stockholm>
Zeitschriftenaufsatz, Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
Artificial intelligence in manufacturing; modelling; simulation; optimisation; Process Parameter Optimisation; machine learning; deep learning; composite textile draping

Optimisation of manufacturing process parameters requires resource-intensive search in a high-dimensional parameter space. In some cases, physics-based simulations can replace actual experiments. But they are computationally expensive to evaluate. Surrogate-based optimisation uses a simplified model to guide the search for optimised parameter combinations, where the surrogate model is iteratively improved with new observations. This work applies surrogate-based optimisation to a composite textile draping process. Numerical experiments are conducted with a Finite Element (FE) simulation model. The surrogate model, a deep artificial neural network, is trained to predict the shear angle of more than 24,000 textile elements. Predicting detailed process results instead of a single performance scalar improves the model quality, as more relevant data from every experiment can be used for training. For the textile draping case, the approach is shown to reduce the number of resource-intensive FE simulations required to find optimised parameter configurations. It also improves on the best-known overall solution.