scholarly journals Deep Reinforcement Learning Control of Cylinder Flow Using Rotary Oscillations at Low Reynolds Number

Energies ◽  
2020 ◽  
Vol 13 (22) ◽  
pp. 5920
Author(s):  
Mikhail Tokarev ◽  
Egor Palkin ◽  
Rustam Mullyadzhanov

We apply deep reinforcement learning to active closed-loop control of a two-dimensional flow over a cylinder oscillating around its axis with a time-dependent angular velocity representing the only control parameter. Experimenting with the angular velocity, the neural network is able to devise a control strategy based on low frequency harmonic oscillations with some additional modulations to stabilize the Kármán vortex street at a low Reynolds number Re=100. We examine the convergence issue for two reward functions showing that later epoch number does not always guarantee a better result. The performance of the controller provide the drag reduction of 14% or 16% depending on the employed reward function. The additional efforts are very low as the maximum amplitude of the angular velocity is equal to 8% of the incoming flow in the first case while the latter reward function returns an impressive 0.8% rotation amplitude which is comparable with the state-of-the-art adjoint optimization results. A detailed comparison with a flow controlled by harmonic oscillations with fixed amplitude and frequency is presented, highlighting the benefits of a feedback loop.

2021 ◽  
Vol 33 (7) ◽  
pp. 079902
Author(s):  
Yuexin Liu ◽  
Zonghao Zou ◽  
Alan Cheng Hou Tsang ◽  
On Shun Pak ◽  
Y.-N. Young

2021 ◽  
Vol 33 (6) ◽  
pp. 062007
Author(s):  
Yuexin Liu ◽  
Zonghao Zou ◽  
Alan Chen Hou Tsang ◽  
On Shun Pak ◽  
Y.-N. Young

2021 ◽  
Vol 143 (6) ◽  
Author(s):  
Mojtaba Forghani ◽  
Weicheng Huang ◽  
M. Khalid Jawed

Abstract In this paper, we analyze the inverse dynamics and control of a bacteria-inspired uniflagellar robot in a fluid medium at low Reynolds number. Inspired by the mechanism behind the locomotion of flagellated bacteria, we consider a robot comprising a flagellum—a flexible helical filament—connected to a spherical head. The flagellum rotates about the head at a controlled angular velocity and generates a propulsive force that moves the robot forward. When the angular velocity exceeds a threshold value, the hydrodynamic force exerted by the fluid can cause the soft flagellum to buckle, characterized by a dramatic change in its shape. In this computational study, a fluid–structure interaction model that combines Discrete Elastic Rods algorithm with Lighthill's Slender Body Theory is employed to simulate the locomotion and deformation of the robot. We demonstrate that the robot can follow a prescribed path in three-dimensional space by exploiting buckling of the flagellum. The control scheme involves only a single (binary) scalar input—the angular velocity of the flagellum. By triggering the buckling instability at the right moment, the robot can follow the path in three-dimensional space. We also show that the complexity of the dynamics of the helical filament can be captured using a deep neural network, from which we identify the input–output functional relationship between the control input and the trajectory of the robot. Furthermore, our study underscores the potential role of buckling in the locomotion of natural bacteria.


The motion of a body through a viscous fluid at low Reynolds number is considered. The motion is steady relative to axes moving with a linear velocity, U a , and rotating with an angular velocity, Ω a . The fluid motion depends on two (small) Reynolds numbers, R proportional to the linear velocity and T proportional to the angular velocity. The correction to the first approximation (Stokes flow) is a complicated function of R and T ; it is O ( R ) for T ½ ≪ R and O ( T ½ )for T ½ ≫ R . General formulae are derived for the force and couple acting on a body of arbitrary shape. From them all the terms O ( R + T ) or larger can be calculated once the Stokes problem has been solved completely. Some special cases are considered in detail.


2018 ◽  
Vol 12 (3) ◽  
pp. 255
Author(s):  
Muhammad Zal Aminullah Daman Huri ◽  
Shabudin Bin Mat ◽  
Mazuriah Said ◽  
Shuhaimi Mansor ◽  
Md. Nizam Dahalan ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document