SOURCE-LINKED INTELLIGENCE

Sparse Measurement-Based Reduced-Order Models of Fluid-Structure-Interactions

CORDIS · observation · Publication date unknown

, which will bring a deep understanding and efficient prediction of FSI. A low-dimensional subspace of the FSI will be extracted using modal analysis through Variational Autoencoders (VAE) based on deep learning (DL) of FSI data. The FSI data will be obtained by performing high-fidelity computational fluids dynamics (CFD) simulations of classic FSI problems. The ROMs are developed by both physics-informed mapping of governing equations onto the low-dimensional subspace and data-driven techniques to deal with nonlinear and unresolved parts of the FSI. Physical constrains are incorporated and sparse measurements of the FSI will be used in building the ROMs. Dynamics and future states of the FSI, hydro- or aerodynamic loads on the structures and structural responses can be predicted based on the ROMs. SMARTFLUIDS will provide an innovative and systematic view of FSI by focusing on a few dominant features and enrich the knowledge of FSI physics by adopting latest DL techniques. The project will bring a novel solution to reduce time and cost of CFD and experiments in predicting FSI dyna

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

1499159

unit

EUR