Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics
Abstract The article presents the application of inductive graph machine learning surrogate models for accurate and efficient prediction of 3D flow for industrial geometries, explicitly focusing here on external aerodynamics for a motorsport case. The final aim is to build a surrogate model that can...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-03-01
|
| Series: | Advanced Modeling and Simulation in Engineering Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40323-024-00259-1 |
| _version_ | 1797247136661766144 |
|---|---|
| author | Davide Roznowicz Giovanni Stabile Nicola Demo Davide Fransos Gianluigi Rozza |
| author_facet | Davide Roznowicz Giovanni Stabile Nicola Demo Davide Fransos Gianluigi Rozza |
| author_sort | Davide Roznowicz |
| collection | DOAJ |
| description | Abstract The article presents the application of inductive graph machine learning surrogate models for accurate and efficient prediction of 3D flow for industrial geometries, explicitly focusing here on external aerodynamics for a motorsport case. The final aim is to build a surrogate model that can provide quick predictions, bypassing in this way the unfeasible computational burden of traditional computational fluid dynamics (CFD) simulations. We investigate in this contribution the usage of graph neural networks, given their ability to smoothly deal with unstructured data, which is the typical context for industrial simulations. We integrate an efficient subgraph-sampling approach with our model, specifically tailored for large dataset training. REV-GNN is the chosen graph machine learning model, that stands out for its capacity to extract deeper insights from neighboring graph regions. Additionally, its unique feature lies in its reversible architecture, which allows keeping the memory usage constant while increasing the number of network layers. We tested the methodology by applying it to a parametric Navier–Stokes problem, where the parameters control the surface shape of the industrial artifact at hand, here a motorbike. |
| first_indexed | 2024-04-24T19:53:54Z |
| format | Article |
| id | doaj.art-771a32b17ca34a52b3ee1d44b9950e96 |
| institution | Directory Open Access Journal |
| issn | 2213-7467 |
| language | English |
| last_indexed | 2024-04-24T19:53:54Z |
| publishDate | 2024-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Advanced Modeling and Simulation in Engineering Sciences |
| spelling | doaj.art-771a32b17ca34a52b3ee1d44b9950e962024-03-24T12:27:52ZengSpringerOpenAdvanced Modeling and Simulation in Engineering Sciences2213-74672024-03-0111112610.1186/s40323-024-00259-1Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamicsDavide Roznowicz0Giovanni Stabile1Nicola Demo2Davide Fransos3Gianluigi Rozza4Mathematics Area, mathLab, SISSADepartment of Pure and Applied Sciences, Informatics and Mathematics Section, University of Urbino Carlo BoMathematics Area, mathLab, SISSASauber Motorsport AGMathematics Area, mathLab, SISSAAbstract The article presents the application of inductive graph machine learning surrogate models for accurate and efficient prediction of 3D flow for industrial geometries, explicitly focusing here on external aerodynamics for a motorsport case. The final aim is to build a surrogate model that can provide quick predictions, bypassing in this way the unfeasible computational burden of traditional computational fluid dynamics (CFD) simulations. We investigate in this contribution the usage of graph neural networks, given their ability to smoothly deal with unstructured data, which is the typical context for industrial simulations. We integrate an efficient subgraph-sampling approach with our model, specifically tailored for large dataset training. REV-GNN is the chosen graph machine learning model, that stands out for its capacity to extract deeper insights from neighboring graph regions. Additionally, its unique feature lies in its reversible architecture, which allows keeping the memory usage constant while increasing the number of network layers. We tested the methodology by applying it to a parametric Navier–Stokes problem, where the parameters control the surface shape of the industrial artifact at hand, here a motorbike.https://doi.org/10.1186/s40323-024-00259-1Computational fluid dynamicsGraph machine learningExternal aerodynamicsLarge scale model3D surrogate model |
| spellingShingle | Davide Roznowicz Giovanni Stabile Nicola Demo Davide Fransos Gianluigi Rozza Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics Advanced Modeling and Simulation in Engineering Sciences Computational fluid dynamics Graph machine learning External aerodynamics Large scale model 3D surrogate model |
| title | Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics |
| title_full | Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics |
| title_fullStr | Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics |
| title_full_unstemmed | Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics |
| title_short | Large-scale graph-machine-learning surrogate models for 3D-flowfield prediction in external aerodynamics |
| title_sort | large scale graph machine learning surrogate models for 3d flowfield prediction in external aerodynamics |
| topic | Computational fluid dynamics Graph machine learning External aerodynamics Large scale model 3D surrogate model |
| url | https://doi.org/10.1186/s40323-024-00259-1 |
| work_keys_str_mv | AT davideroznowicz largescalegraphmachinelearningsurrogatemodelsfor3dflowfieldpredictioninexternalaerodynamics AT giovannistabile largescalegraphmachinelearningsurrogatemodelsfor3dflowfieldpredictioninexternalaerodynamics AT nicolademo largescalegraphmachinelearningsurrogatemodelsfor3dflowfieldpredictioninexternalaerodynamics AT davidefransos largescalegraphmachinelearningsurrogatemodelsfor3dflowfieldpredictioninexternalaerodynamics AT gianluigirozza largescalegraphmachinelearningsurrogatemodelsfor3dflowfieldpredictioninexternalaerodynamics |