Title: Reinforcement-learning-based control of confined cylinder

Reporter: Dr. Mengqi Zhang

Time: 30th July 2021. 8:30-12:00

Location: Conference room A310 in School of Aeronautics

Abstract: 

In this talk, I will introduce our recent work where we test the application of a reinforcement-learning-based(RL) flow control strategy to the flow past a cylinder confined between two walls in order to suppress its vortex shedding. The control action is blowing and suction of two synthetic jets on the cylinder, We aim to embed some useful flow information in the design of the RL algorithm. First, flow (linear) stability and sensitivity analyses based on the time-mean flow and the steady flow (which is a solution to the Navier-Stokes equations) have been conducted in a range of blockage ratios and Reynolds numbers. Then, in utilizing these physical results in the development of the RL-based control policy, we found that the controlled wake flow converges to the unstable steady base flow and the vortex shedding can be successfully suppressed in this case.

Introduction of Dr. Mengqi Zhang:

Dr. Mengqi Zhang is an assistant professor in the Department of Mechanics Engineering, National University of Singapore since 2018. He received his Ph.D. in Universite de Poitiers, France in 2016. His research interest includes numerical analysis and simulations of various flow problems, such as non-Newtonian flows and electrohydrodynamic flows. He is also interested in flow control and reduced-order modelling of complex flows, including machine-learning-aided flow manipulation.