Active flow control with rotating cylinders by an artificial neural network trained by deep reinforcement learning

• Published in: Journal of hydrodynamics. Series B Vol. 32; no. 2; pp. 254 - 258
• Main Authors: Xu, Hui, Zhang, Wei, Deng, Jian, Rabault, Jean
• Format: Journal Article
• Language: English
• Published: Singapore Springer Singapore 01.04.2020
• Subjects: Engineering; Engineering Fluid Dynamics; Hydrology/Water Resources; Numerical and Computational Physics; Simulation; Special Column on the International Symposium on High-Fidelity Computational Methods and Applications 2019 (Guest Editors Hui Xu; Wei Zhang; rotating cylinders; Artificial neural network (ANN); flow control; deep reinforcement learning (DRL)

In this paper, an artificial neural network (ANN) trained through a deep reinforcement learning (DRL) agent is used to perform flow control. The target is to look for the wake stabilization mechanism in an active way. The flow past a 2-D cylinder with a Reynolds number 240 is addressed with and with...