Reducing flow fluctuation using deep reinforcement learning with a CNN-based flow feature model

doi:10.1016/j.oceaneng.2024.118089

IMECH-IR > 流固耦合系统力学重点实验室

	Reducing flow fluctuation using deep reinforcement learning with a CNN-based flow feature model
	Ye SR(叶舒然); Zhang, Zhen; Wang YW(王一伟); Huang CG(黄晨光)
通讯作者	Wang, Yiwei([email protected])
发表期刊	OCEAN ENGINEERING
	2024-08-15
卷号	306 页码:10
ISSN	0029-8018
摘要	Flow control and shape optimisation are fundamental problems in fluid mechanics, particularly in certain scenarios involving ocean engineering. Attempts to manage the flow field via reinforcement learning are based on newly developed deep -learning techniques. By utilising an adaptive optimisation process in the flow around two square cylinders (the main square cylinder with a smaller square cylinder in the front) for the position of the front square cylinder, the flow state that minimises the oscillation of the flow field in the wake can be obtained through deep reinforcement learning. Furthermore, as the training process for this reinforcement learning is time consuming, the flow simulation component of the process is replaced with a feature detection model based on a convolutional neural network, which effectively accelerates the training process. This approach to simulating the optimal position -finding procedure with acceleration can be extended to other similar situations and practical engineering projects.
关键词	Deep reinforcement learning Flow feature detection Flow around two square cylinders Position optimisation Deep learning
DOI	10.1016/j.oceaneng.2024.118089
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:001240669700001
关键词[WOS]	SQUARE CYLINDER
WOS研究方向	Engineering ; Oceanography
WOS类目	Engineering, Marine ; Engineering, Civil ; Engineering, Ocean ; Oceanography
资助项目	National Natural Science Foundation of China (NSFC)[12302514] ; National Natural Science Foundation of China (NSFC)[12202291]
项目资助者	National Natural Science Foundation of China (NSFC)
论文分区	一类
力学所作者排名	1
RpAuthor	Wang, Yiwei
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://dspace.imech.ac.cn/handle/311007/95561
专题	流固耦合系统力学重点实验室
推荐引用方式 GB/T 7714	Ye SR,Zhang, Zhen,Wang YW,et al. Reducing flow fluctuation using deep reinforcement learning with a CNN-based flow feature model[J]. OCEAN ENGINEERING,2024,306:10.Rp_Au:Wang, Yiwei
APA	叶舒然,Zhang, Zhen,王一伟,&黄晨光.(2024).Reducing flow fluctuation using deep reinforcement learning with a CNN-based flow feature model.OCEAN ENGINEERING,306,10.
MLA	叶舒然,et al."Reducing flow fluctuation using deep reinforcement learning with a CNN-based flow feature model".OCEAN ENGINEERING 306(2024):10.