Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911984042115072 |
|---|---|
| author | Schmöcker, Robin Henkes, Alexander Roth, Julian Wick, Thomas |
| author_facet | Schmöcker, Robin Henkes, Alexander Roth, Julian Wick, Thomas |
| contents | This works investigates the generalization capabilities of MeshGraphNets (MGN) [Pfaff et al. Learning Mesh-Based Simulation with Graph Networks. ICML 2021] to unseen geometries for fluid dynamics, e.g. predicting the flow around a new obstacle that was not part of the training data. For this purpose, we create a new benchmark dataset for data-driven computational fluid dynamics (CFD) which extends DeepMind's flow around a cylinder dataset by including different shapes and multiple objects. We then use this new dataset to extend the generalization experiments conducted by DeepMind on MGNs by testing how well an MGN can generalize to different shapes. In our numerical tests, we show that MGNs can sometimes generalize well to various shapes by training on a dataset of one obstacle shape and testing on a dataset of another obstacle shape. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06101 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics Schmöcker, Robin Henkes, Alexander Roth, Julian Wick, Thomas Machine Learning Artificial Intelligence Numerical Analysis Fluid Dynamics This works investigates the generalization capabilities of MeshGraphNets (MGN) [Pfaff et al. Learning Mesh-Based Simulation with Graph Networks. ICML 2021] to unseen geometries for fluid dynamics, e.g. predicting the flow around a new obstacle that was not part of the training data. For this purpose, we create a new benchmark dataset for data-driven computational fluid dynamics (CFD) which extends DeepMind's flow around a cylinder dataset by including different shapes and multiple objects. We then use this new dataset to extend the generalization experiments conducted by DeepMind on MGNs by testing how well an MGN can generalize to different shapes. In our numerical tests, we show that MGNs can sometimes generalize well to various shapes by training on a dataset of one obstacle shape and testing on a dataset of another obstacle shape. |
| title | Generalization capabilities of MeshGraphNets to unseen geometries for fluid dynamics |
| topic | Machine Learning Artificial Intelligence Numerical Analysis Fluid Dynamics |
| url | https://arxiv.org/abs/2408.06101 |