English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present a novel application of neural networks to design improved mixingelements for single-screw extruders. Specifically, we propose to use neuralnetworks in numerical shape optimization to parameterize geometries. Geometryparameterization is crucial in enabling efficient shape optimization as itallows for optimizing complex shapes using only a few design variables. Recentapproaches often utilize CAD data in conjunction with spline-based methodswhere the spline's control points serve as design variables. Consequently,these approaches rely on the same design variables as specified by the humandesigner. While this choice is convenient, it either restricts the design tosmall modifications of given, initial design features - effectively prohibitingtopological changes - or yields undesirably many design variables. In thiswork, we step away from CAD and spline-based approaches and construct anartificial, feature-dense yet low-dimensional optimization space using agenerative neural network. Using the neural network for the geometryparameterization extends state-of-the-art methods in that the resulting designspace is not restricted to user-prescribed modifications of certain basisshapes. Instead, within the same optimization space, we can interpolate betweenand explore seemingly unrelated designs. To show the performance of this newapproach, we integrate the developed shape parameterization into our numericaldesign framework for dynamic mixing elements in plastics extrusion. Finally, wechallenge the novel method in a competitive setting against current free-formdeformation-based approaches and demonstrate the method's performance even atthis early stage.

Neural Networks vs. Splines: Advances in Numerical Extruder Design