Reinforcement learning for bluff body active flow control in experiments and simulations

D Fan, L Yang, Z Wang… - Proceedings of the …, 2020 - National Acad Sciences
We have demonstrated the effectiveness of reinforcement learning (RL) in bluff body flow
control problems both in experiments and simulations by automatically discovering active …

Deep reinforcement transfer learning of active control for bluff body flows at high Reynolds number

Z Wang, D Fan, X Jiang, MS Triantafyllou… - Journal of Fluid …, 2023 - cambridge.org
We demonstrate how to accelerate the computationally taxing process of deep
reinforcement learning (DRL) in numerical simulations for active control of bluff body flows at …

Illuminating the complex role of the added mass during vortex induced vibration

Z Wang, D Fan, MS Triantafyllou - Physics of Fluids, 2021 - pubs.aip.org
The role of the added mass coefficient in vortex induced vibration (VIV) of the bluff body is
complex and elusive. It is certain that decoding the relationship between the added mass …

Solution multiplicity and effects of data and eddy viscosity on Navier-Stokes solutions inferred by physics-informed neural networks

Z Wang, X Meng, X Jiang, H Xiang… - arXiv preprint arXiv …, 2023 - arxiv.org
Physics-informed neural networks (PINNs) have emerged as a new simulation paradigm for
fluid flows and are especially effective for inverse and hybrid problems. However, vanilla …

Mapping the properties of the vortex-induced vibrations of flexible cylinders in uniform oncoming flow

D Fan, Z Wang, MS Triantafyllou… - Journal of Fluid …, 2019 - cambridge.org
Flexible structures placed within an oncoming flow exhibit far more complex vortex-induced
dynamics than flexibly mounted rigid cylinders, because they involve the distributed …

A large-eddy simulation study on the similarity between free vibrations of a flexible cylinder and forced vibrations of a rigid cylinder

Z Wang, D Fan, MS Triantafyllou… - Journal of Fluids and …, 2021 - Elsevier
The strip theory in hydrodynamics has been widely used for predicting complex vortex
induced vibrations (VIV) behind bluff bodies, but the question of how accurate such …

An entropy viscosity method for large eddy simulation of turbulent thermal flow in a rotor–stator cavity

Q Du, Y Xie, Z Wang, X Jiang, L Xie - Physics of Fluids, 2023 - pubs.aip.org
Turbulent flow and heat transfer in a rotor–stator cavity have fundamental importance in both
academia of turbulence research and the industry of rotating turbomachinery. The main …

Inferring vortex induced vibrations of flexible cylinders using physics-informed neural networks

E Kharazmi, D Fan, Z Wang, MS Triantafyllou - Journal of Fluids and …, 2021 - Elsevier
We develop a robust computational framework to infer the motion of a flexible cylinder
undergoing vortex induced vibration. Given scattered data in space–time on displacement …

An artificial viscosity augmented physics-informed neural network for incompressible flow

Y He, Z Wang, H Xiang, X Jiang, D Tang - Applied Mathematics and …, 2023 - Springer
Physics-informed neural networks (PINNs) are proved methods that are effective in solving
some strongly nonlinear partial differential equations (PDEs), eg, Navier-Stokes equations …

Active-and transfer-learning applied to microscale-macroscale coupling to simulate viscoelastic flows

L Zhao, Z Li, Z Wang, B Caswell, J Ouyang… - Journal of …, 2021 - Elsevier
Active-and transfer-learning are applied to microscale dynamics of polymer flows for the
multiscale discovery of effective constitutive approximations required in viscoelastic flow …