Deep reinforcement learning for turbulent drag reduction in channel flows

• Published in: The European physical journal. E, Soft matter and biological physics Vol. 46; no. 4; p. 27
• Main Authors: Guastoni, Luca, Rabault, Jean, Schlatter, Philipp, Azizpour, Hossein, Vinuesa, Ricardo
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2023; Springer Nature B.V
• Subjects: Algorithms; Benchmarks; Biological and Medical Physics; Biophysics; Channel flow; Complex Fluids and Microfluidics; Complex Systems; Condensed matter physics; Deep learning; Drag reduction; Flow simulation; Fluid dynamics; Fluid flow; Machine learning; Nanotechnology; Parallel processing; Physics; Physics and Astronomy; Polymer Sciences; Quantitative AI in Complex Fluids and Complex Flows: Challenges and Benchmarks; Regular - Flowing Matter; Regular Article - Flowing Matter; Reynolds number; Soft and Granular Matter; Suction; Surfaces and Interfaces; Thin Films; Turbulence; Turbulent flow

We introduce a reinforcement learning (RL) environment to design and benchmark control strategies aimed at reducing drag in turbulent fluid flows enclosed in a channel. The environment provides a framework for computationally efficient, parallelized, high-fidelity fluid simulations, ready to interfa...