β-Variational autoencoders and transformers for reduced-order modelling of fluid flows
A Solera-Rico, C Sanmiguel Vila… - Nature …, 2024 - nature.com
Variational autoencoder architectures have the potential to develop reduced-order models
for chaotic fluid flows. We propose a method for learning compact and near-orthogonal …
for chaotic fluid flows. We propose a method for learning compact and near-orthogonal …
Reconstruction of missing flow field from imperfect turbulent flows by machine learning
Obtaining reliable flow data is essential for the fluid mechanics analysis and control, and
various measurement techniques have been proposed to achieve this goal. However …
various measurement techniques have been proposed to achieve this goal. However …
A deep learning framework for reconstructing experimental missing flow field of hydrofoil
Hydrofoils play a crucial role in enhancing the efficiency of fluid machinery designed for
ocean environments, reducing lift-induced drag and contributing to improved overall …
ocean environments, reducing lift-induced drag and contributing to improved overall …
A comparison of machine learning methods for recovering noisy and missing 4D flow MRI data
Experimental blood flow measurement techniques are invaluable for a better understanding
of cardiovascular disease formation, progression, and treatment. One of the emerging …
of cardiovascular disease formation, progression, and treatment. One of the emerging …
Adaptive restoration and reconstruction of incomplete flow fields based on unsupervised learning
Y Sha, Y Xu, Y Wei, C Wang - Physics of Fluids, 2023 - pubs.aip.org
Due to experimental limitations and data transmission constraints, we often encounter
situations where we can only obtain incomplete flow field data. However, even with …
situations where we can only obtain incomplete flow field data. However, even with …
[HTML][HTML] Spatial prediction of the turbulent unsteady von Kármán vortex street using echo state networks
M Sharifi Ghazijahani, F Heyder, J Schumacher… - Physics of …, 2023 - pubs.aip.org
The spatial prediction of the turbulent flow of the unsteady von Kármán vortex street behind
a cylinder at Re= 1000 is studied. For this, an echo state network (ESN) with 6000 neurons …
a cylinder at Re= 1000 is studied. For this, an echo state network (ESN) with 6000 neurons …
A reduced order modeling-based machine learning approach for wind turbine wake flow estimation from sparse sensor measurements
A comprehensive understanding of wind turbine wake characteristics is vital, particularly in
the context of expanding large offshore wind farms. Existing wake measurement techniques …
the context of expanding large offshore wind farms. Existing wake measurement techniques …
Reconstructing multiphase flow fields with limited pressure observations based on an improved transformer model
Y Xu, Y Sha, C Wang, H Cui, Y Wei - Ocean Engineering, 2024 - Elsevier
In practical applications, the implementation of active cavitation control can significantly
enhance the hydrodynamic performance of underwater vehicles. However, the sparsity of …
enhance the hydrodynamic performance of underwater vehicles. However, the sparsity of …
Adaptive estimation model: Robust full-state prediction through sparse observations with variable layout and quantity
Y Xu, Y Sha, C Wang, Y Wei - Ocean Engineering, 2024 - Elsevier
Recovering the full-state from limited observation data is crucial because it provides a
reliable reference for active control. Advances in deep learning technology further enable …
reliable reference for active control. Advances in deep learning technology further enable …
Sparse learning model with embedded RIP conditions for turbulence super-resolution reconstruction
Q Huang, W Zhu, F Ma, Q Liu, J Wen, L Chen - Computer Methods in …, 2024 - Elsevier
In practical engineering scenarios, constraints arising from sensor placement, quantity, and
the limitations of current testing technologies often lead to turbulence data characterized by …
the limitations of current testing technologies often lead to turbulence data characterized by …