English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This work studies the application of a reinforcement-learning-based (RL) flowcontrol strategy to the flow past a cylinder confined between two walls inorder to suppress vortex shedding. The control action is blowing and suction oftwo synthetic jets on the cylinder. The theme of this study is to investigatehow to use and embed physical information of the flow in the RL-based control.First, global linear stability and sensitivity analyses based on the time-meanflow and the steady flow (which is a solution to the Navier-Stokes equations)are conducted in a range of blockage ratios and Reynolds numbers. It is foundthat the most sensitive region in the wake extends itself when either parameterincreases in the parameter range we investigated here. Then, we utilise thesephysical results to help design RL-based control policies. We find that thecontrolled wake converges to the unstable steady base flow, where the vortexshedding can be successfully suppressed. A persistent oscillating control seemsnecessary to maintain this unstable state. The RL algorithm is able tooutperform a gradient-based optimisation method (optimised in a certain periodof time) in the long run. Furthermore, when the flow stability information isembedded in the reward function to penalise the instability, the controlledflow may become more stable. Finally, according to the sensitivity analyses,the control is most efficient when the probes are placed in the most sensitiveregion. The control can be successful even when few probes are properly placedin this manner.

Reinforcement-learning-based control of confined cylinder wakes with stability analyses