What is it about?
As we move towards experimental discovery guided by machines, we show that reinforcement learning can discover optimal control strategies to actively reduce drag in the notoriously difficult problem of bluff body drag that is associated with the formation of a Karman street, without human intervention and at a fraction of the effort needed in past studies.
Featured Image
Photo by S. on Unsplash
Why is it important?
Applying machine learning methods in experimental fluid mechanics is only in its beginning, but the rewards can be very significant as shown in this paper.
Perspectives
Having spent many years in the laboratory and knowing the long time it takes to conduct systematic experiments for exploring the physics of a problem, AI methods are shown offer unique ways to shorten considerably the time to discovery in multi-parameter problems.
Professor Michael S Triantafyllou
Massachusetts Institute of Technology
Read the Original
This page is a summary of: Reinforcement learning for bluff body active flow control in experiments and simulations, Proceedings of the National Academy of Sciences, October 2020, Proceedings of the National Academy of Sciences,
DOI: 10.1073/pnas.2004939117.
You can read the full text:
Contributors
The following have contributed to this page
