Surrogate Model Based Process Parameters Optimization of Textile Forming: Unterschied zwischen den Versionen
(Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Aleksandr Eismont |email=ukqln@student.kit.edu |vortragstyp=Proposal |betreuer=Bela Böhnke |termin=Institutsseminar/2023-03-31-IPD-Boe…“) |
(kein Unterschied)
|
Version vom 19. März 2023, 19:54 Uhr
Vortragende(r) | Aleksandr Eismont | |
---|---|---|
Vortragstyp | Proposal | |
Betreuer(in) | Bela Böhnke | |
Termin | Fr 31. März 2023 | |
Vortragsmodus | in Präsenz | |
Kurzfassung | Manufacturing optimization is crucial for organizations to remain competitive in the market. However, optimizing complex processes, such as textile forming, can be challenging and resource-intensive. Surrogate-based optimization can efficiently optimize manufacturing process parameters by using simplified models to guide the search for optimal parameter combinations. Moreover, using a Bayesian deep neural network allows for incorporation of uncertainty estimates into the model, which can speed up the optimization process. In this work, the surrogate model, a Bayesian deep convolutional neural network, is proposed to train with all available process parameters to predict the shear angle of a textile element. It is believed that predicting detailed process results incorporating background information into the surrogate model can lead to greater efficiency and increased product quality. |