DRL policies equipped with spatial convolution and temporal memory achieve cell coalescence in Rayleigh-Bénard convection at Ra=10,000, reducing Nu by 26% in single-agent setups, and discover adaptive travelling-wave actuation in double-diffusive convection.
Improving turbulence control through explainable deep learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Turbulent-flow control aims to develop strategies that effectively manipulate fluid systems, such as the reduction of drag in transportation and enhancing energy efficiency, both critical steps towards reducing global CO$_2$ emissions. Deep reinforcement learning (DRL) offers novel tools to discover flow-control strategies, which we combine with our knowledge of the physics of turbulence. We integrate explainable deep learning (XDL) to objectively identify the coherent structures containing the most informative regions in the flow, with a DRL model trained to reduce them. The model trained with XDL targets the most relevant regions in the flow to sustain turbulence and produces a drag reduction which is higher than that of a model specifically trained to reduce the drag, resulting in a $18.1\%$ better net-energy saving. The XDL-based control remains the most effective control strategy when generalizing across Reynolds numbers and geometries. This demonstrates that combining DRL with XDL can produce causal control strategies that precisely target the most influential features of turbulence. By directly addressing the core mechanisms that sustain turbulence, our approach offers a powerful pathway towards its efficient control, which is a long-standing challenge in physics with profound implications for energy systems, climate modeling and aerodynamics.
verdicts
UNVERDICTED 5representative citing papers
A combined SHAP-guided MARL strategy using U-net predictions of skin-friction and wall pressure achieves 34.44% drag reduction and 34.01% net energy saving with 0.43% normalized input power in turbulent channel flow.
Policy-DRIFT combines conditional flow matching with terminal reward guidance and decoupled DRL to achieve 49% drag reduction in Re_tau=180 channel flow, 16% above DRL benchmarks and with 37 times less actuation energy.
Zero-shot RL control trained on matched channel flows reduces skin-friction drag 28.7% and total drag 10.7% on a NACA4412 wing, outperforming opposition control.
VIVALDy is a hybrid β-VAE-GAN plus bidirectional transformer framework that reconstructs and predicts turbulent flow around a one-degree-of-freedom moving cylinder using only cylinder displacement as input.
citing papers explorer
-
Deep reinforcement learning with spatial and temporal awareness for active boundary control of buoyancy-driven convection
DRL policies equipped with spatial convolution and temporal memory achieve cell coalescence in Rayleigh-Bénard convection at Ra=10,000, reducing Nu by 26% in single-agent setups, and discover adaptive travelling-wave actuation in double-diffusive convection.
-
Explainable deep reinforcement learning reveals energy-efficient control strategies for turbulent drag reduction
A combined SHAP-guided MARL strategy using U-net predictions of skin-friction and wall pressure achieves 34.44% drag reduction and 34.01% net energy saving with 0.43% normalized input power in turbulent channel flow.
-
Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
Policy-DRIFT combines conditional flow matching with terminal reward guidance and decoupled DRL to achieve 49% drag reduction in Re_tau=180 channel flow, 16% above DRL benchmarks and with 37 times less actuation energy.
-
Physics-guided surrogate learning enables zero-shot control of turbulent wings
Zero-shot RL control trained on matched channel flows reduces skin-friction drag 28.7% and total drag 10.7% on a NACA4412 wing, outperforming opposition control.
-
VIVALDy: A Hybrid Generative Reduced-Order Model for Turbulent Flows, Applied to Vortex-Induced Vibrations
VIVALDy is a hybrid β-VAE-GAN plus bidirectional transformer framework that reconstructs and predicts turbulent flow around a one-degree-of-freedom moving cylinder using only cylinder displacement as input.