Transferable Model for Shape Optimization subject to Physical Constraints

2021-03-19 · Lukas Harsch, Johannes Burgbacher, Stefan Riedelbauch

The interaction of neural networks with physical equations offers a wide range of applications. We provide a method which enables a neural network to transform objects subject to given physical constraints. Therefore an U-Net architecture is used to learn the underlying physical behaviour of fluid flows. The network is used to infer the solution of flow simulations, which will be shown for a wide range of generic channel flow simulations. Physical meaningful quantities can be computed on the obtained solution, e.g. the total pressure difference or the forces on the objects. A Spatial Transformer Network with thin-plate-splines is used for the interaction between the physical constraints and the geometric representation of the objects. Thus, a transformation from an initial to a target geometry is performed such that the object is fulfilling the given constraints. This method is fully differentiable i.e., gradient informations can be used for the transformation. This can be seen as an inverse design process. The advantage of this method over many other proposed methods is, that the physical constraints are based on the inferred flow field solution. Thus, we have a transferable model which can be applied to varying problem setups and is not limited to a given set of geometry parameters or physical quantities.

📄 PDF Abstract BibTeX arXiv:2103.10805

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

Attention 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Residual Connection 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Adam 설명 없음

Physically-Aware Generative Network for 3D Shape Modeling

2021-06-19 · CVPR 2021 1 · Mariem Mezghanni, Malika Boulkenafed, Andre Lieutier, Maks Ovsjanikov

Shapes are often designed to satisfy structural properties and serve a particular functionality in the physical world. Unfortunately, most existing generative models focus primarily on the geometric or visual plausib…

3D Shape Modeling

Generalized Task-Driven Design of Soft Robots via Reduced-Order FEM-based Surrogate Modeling

2026-03-20 · Yao Yao, David Howard, Perla Maiolino arxiv

Task-driven design of soft robots requires models that are physically accurate and computationally efficient, while remaining transferable across actuator designs and task scenarios. However, existing modeling approaches…

Computational Efficiency Reinforcement Learning

Where Does It End? -- Reasoning About Hidden Surfaces by Object Intersection Constraints

2020-04-09 · Michael Strecke, Joerg Stueckler

Dynamic scene understanding is an essential capability in robotics and VR/AR. In this paper we propose Co-Section, an optimization-based approach to 3D dynamic scene reconstruction, which infers hidden shape information …

Object Scene Understanding

Where Does It End? - Reasoning About Hidden Surfaces by Object Intersection Constraints

2020-06-01 · CVPR 2020 6 · Michael Strecke, Jorg Stuckler

Object Scene Understanding

URBAN-SPIN: A street-level bikeability index to inform design implementations in historical city centres

2026-01-30 · Haining Ding, Chenxi Wang, Michal Gath-Morad arxiv

Cycling is reported by an average of 35\% of adults at least once per week across 28 countries, and as vulnerable road users directly exposed to their surroundings, cyclists experience the street at an intensity unmatche…