Scholarlink

<p>The real power of artificial intelligence appears in reinforcement learning, which is more sophisticated due to its dynamic nature. This paper will add rotation to the cylinder alongside the deep reinforcement learning (DRL) algorithm, which uses multiple controlled jets to reach the maximum possible drag suppression. Characteristics of the code, including controlling parameters, their limitations, and optimization of the DRL network for use with rotation will be presented. This work will focus on optimizing the number and positions of the jets, the sensor’s location, and the maximum allowed flow rate to jets in the form of the maximum allowed flow rate of each actuation and the total number of them per episode. It is found that combining the rotation and DRL is promising since it suppresses the vortex shedding, stabilizes the Karman vortex street, and reduces the drag coefficient by up to 49.75%. Also, it will be shown that having more sensors at more locations is not always a good choice and the sensor number and location should be determined based on the need of the user and corresponding configuration. Also, allowing the agent to have access to higher flow rates, mostly reduces the performance, except when the cylinder rotates.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Implementation of deep reinforcement learning for control of flow over rotating cylinder with multiple jets

  • 期刊论文

  • 发表日期：

    2026年2月12日

查看全文
  • Kamyar Dobakhti,
  • Jafar Ghazanfarian

摘要

The real power of artificial intelligence appears in reinforcement learning, which is more sophisticated due to its dynamic nature. This paper will add rotation to the cylinder alongside the deep reinforcement learning (DRL) algorithm, which uses multiple controlled jets to reach the maximum possible drag suppression. Characteristics of the code, including controlling parameters, their limitations, and optimization of the DRL network for use with rotation will be presented. This work will focus on optimizing the number and positions of the jets, the sensor’s location, and the maximum allowed flow rate to jets in the form of the maximum allowed flow rate of each actuation and the total number of them per episode. It is found that combining the rotation and DRL is promising since it suppresses the vortex shedding, stabilizes the Karman vortex street, and reduces the drag coefficient by up to 49.75%. Also, it will be shown that having more sensors at more locations is not always a good choice and the sensor number and location should be determined based on the need of the user and corresponding configuration. Also, allowing the agent to have access to higher flow rates, mostly reduces the performance, except when the cylinder rotates.