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 paper focuses on developing a deep reinforcement learning (DRL) controlstrategy to mitigate aerodynamic forces acting on a three dimensional (3D)square cylinder under high Reynolds number flow conditions. Four jets situatedat the corners of the square cylinder are used as actuators and pressure probeson the cylinder surface are employed as feedback observers. The SoftActor-Critic (SAC) algorithm is deployed to identify an effective controlscheme. Additionally, we pre-train the DRL agent using a two dimensional (2D)square cylinder flow field at a low Reynolds number (Re =1000), followed bytransferring it to the 3D square cylinder at Re =22000. To address the issue ofstate dimension mismatch in transfer learning from 2D to 3D case, a statedimension mismatch transfer learning method is developed to enhance the SACalgorithm, named SDTL-SAC. The results demonstrate transfer learning acrossdifferent state spaces achieves the same control policy as the SAC algorithm,resulting in a significant improvement in training speed with a training costreduction of 51.1%. Furthermore, the SAC control strategy leads to a notable52.3% reduction in drag coefficient, accompanied by substantial suppression oflift fluctuations. These outcomes underscore the potential of DRL in activeflow control, laying the groundwork for efficient, robust, and practicalimplementation of this control technique in practical engineering.

Deep reinforcement transfer learning for active flow control of a 3D square cylinder under state dimension mismatch