Metraipolis › archive › dc_877f0abb2668
Learning Stiffness Dependent Fluid Structure Dynamics from Coarse Flow Representations — arXiv:2609.26816
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26816
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T09:11:47.117Z
- SHA-256 of the archived text
128760845c5fd0b13db611c203381a3e60e36bdf7e07cbd8d4cb9c04c584ddf9- Stable URL of this page
https://metraipolis.com/documento/dc_877f0abb2668
How to cite
Learning Stiffness Dependent Fluid Structure Dynamics from Coarse Flow Representations — arXiv:2609.26816 — arXiv (en), https://arxiv.org/abs/2609.26816 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_877f0abb2668 (Metraipolis archive dc_877f0abb2668, sha256 128760845c5fd0b13db611c203381a3e60e36bdf7e07cbd8d4cb9c04c584ddf9)
BibTeX
@misc{dc877f0abb2668,
title = {Learning Stiffness Dependent Fluid Structure Dynamics from Coarse Flow Representations — arXiv:2609.26816},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26816},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_877f0abb2668; sha256 128760845c5fd0b13db611c203381a3e60e36bdf7e07cbd8d4cb9c04c584ddf9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26816. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper develops a data-driven framework for long-term prediction of fluid--structure interaction (FSI) dynamics, focusing on the flow-induced vibration (FIV) of a flexible plate. A stiffness-conditioned neural evolution operator jointly represents the Eulerian flow field and Lagrangian structural state. The plate is represented by 101 ordered structural tokens carrying nodal coordinates and velocities, with nondimensional bending stiffness as a global conditioning variable. Bidirectional cross-attention couples fluid and structural representations within a hybrid CNN-Transformer architecture. Trained with staged multi-step autoregressive rollouts and symmetry-reflected trajectories, a single operator captures three stiffness-dependent response regimes: deflected--flapping, deflected, and flapping. The predicted trajectories preserve the principal flow structures, structural oscillations, and dominant frequencies, while blind 1000-step rollouts remain bounded. The operator also interpolates to stiffness values excluded from training. To reduce sensitivity to under-resolved near-wall gradients in force reconstruction, we develop a differentiable aerodynamic-force module based on the derivative-moment transformation (DMT). Conventional wall-stress surface integrals are replaced by an enclosed 2D curve integral around the core vortex region, enabling accurate reconstruction of lift and drag. A Signed Distance Function (SDF) and smoothed Dirac-delta formulation make the integration fully differentiable while preserving gradient flow. The proposed framework provides an accurate and differentiable surrogate for stiffness-dependent FSI dynamics, enabling efficient parameter studies and future stiffness optimization for flow-energy-harvesting applications. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI). Categorie arXiv: Fluid Dynamics (physics.flu-dyn) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.26816 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T08:13:26.567Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).