Finite operator learning: Bridging neural operators and numerical methods for efficient parametric solution and optimization of pdes

S Rezaei, RN Asl, K Taghikhani, A Moeineddin… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce a method that combines neural operators, physics-informed machine learning,
and standard numerical methods for solving PDEs. The proposed approach extends each of …

[HTML][HTML] Investigation of physics-informed deep learning for the prediction of parametric, three-dimensional flow based on boundary data

P Heger, D Hilger, M Full, N Hosters - Computers & Fluids, 2024 - Elsevier
The placement of temperature sensitive and safety-critical components is crucial in the
automotive industry. It is therefore inevitable, even at the design stage of new vehicles, that …

Geometric improvement of the sheet/film extrusion die using Rabinowitsch-Mooney analysis

A Razeghiyadaki, D Wei, A Perveen… - The International Journal of …, 2024 - Springer
Abstract The well-known Winter-Fritz horseshoe die introduced in the 1980s has been used
in polymer sheet/film extrusion die and coating die industries with success. The geometric …

A model hierarchy for predicting the flow in stirred tanks with physics-informed neural networks

V Trávníková, D Wolff, N Dirkes, S Elgeti… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper explores the potential of Physics-Informed Neural Networks (PINNs) to serve as
Reduced Order Models (ROMs) for simulating the flow field within stirred tank reactors …

Reduced-order modeling for plastics profile extrusion

D Hilger, M Behr, SN Elgeti - 2024 - publications.rwth-aachen.de
Kurzfassung Die numerische Modellierung und Analyse hat sich in den vergangenen
Jahrzehnten zu einem wichtigen Werkzeug zur effizienten und wirtschaftlichen …

Shape Optimization of CAD-Compliant Boundary-Conforming Microstructured Geometries

JM Zwar - 2024 - repositum.tuwien.at
Recent developments in additive manufacturing have opened up a vast field of new design
possibilities that cannot be fully exploited by traditional engineering methods. These …