6 papers
The HydroGym Reinforcement Learning Platform for Fluid Dynamics
Christian Lagemann, Sajeda Mokbel, Miro Gondrum +18
Modeling and controlling fluids is critical across science and engineering. Effective flow control can increase lift, reduce drag, enhance mixing, and attenuate noise, potentially…
A fully GPU-based workflow for building physics emulators of hypersonic flows
Fabian Paischer, Dylan Rubini, Deniz A. Bezgin +6
The ability to resolve complex physical phenomena with high fidelity and at low computational cost is central to addressing key challenges in modern engineering. A prime example li…
Data-driven shape inference in three-dimensional steady state supersonic flows using ODIL and JAX-Fluids
Aaron B. Buhendwa, Deniz A. Bezgin, Petr Karnakov +2
We present a novel data- and first-principles-driven method for inferring the shape of a solid obstacle and its flow field in three-dimensional steady-state supersonic flows. The m…
A thermodynamically consistent and robust four-equation model for multi-phase multi-component compressible flows using ENO-type schemes including interface regularization
Henry Collis, Deniz A. Bezgin, Shahab Mirjalili +1
In this work, a concise and robust computational framework is proposed to simulate compressible multi-phase multi-component flows. To handle both shocks and material interfaces, a…
Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme
Shantanu Shahane, Sheide Chammas, Deniz A. Bezgin +8
Conventional WENO3 methods are known to be highly dissipative at lower resolutions, introducing significant errors in the pre-asymptotic regime. In this paper, we employ a rational…
JAX-based differentiable fluid dynamics on GPU and end-to-end optimization
Wenkang Wang, Xuanwei Zhang, Deniz Bezgin +3
This project aims to advance differentiable fluid dynamics for hypersonic coupled flow over porous media, demonstrating the potential of automatic differentiation (AD)-based optimi…