CASIA OpenIR  > 复杂系统认知与决策实验室  > 群体决策智能团队
Learn to flap: foil non-parametric path planning via deep reinforcement learning
Wang, Zhipeng1; Lin, Runji2; Zhao, Zhiyu2; Chen, Xu3; Guo, Pengming1; Yang, Ning2; Wang,Zhicheng4; Fan, Dixia1
Source PublicationJournal of Fluid Mechanics
2024
Volume984Pages:A9
Abstract

To optimize flapping foil performance, in the current study we apply deep reinforcement learning (DRL) to plan foil non-parametric motion, as the traditional control techniques

and simplified motions cannot fully model nonlinear, unsteady and high-dimensional

foil–vortex interactions. Therefore, a DRL training framework is proposed based on the proximal policy optimization algorithm and the transformer architecture, where the policy

is initialized from the sinusoidal expert display. We first demonstrate the effectiveness of the proposed DRL-training framework, learning the coherent foil flapping motion to generate thrust. Furthermore, by adjusting reward functions and action thresholds, DRL-optimized foil trajectories can gain significant enhancement in both thrust and efficiency compared with the sinusoidal motion. Last, through visualization of wake morphology and instantaneous pressure distributions, it is found that DRL-optimized foil can adaptively adjust the phases between motion and shedding vortices to improve hydrodynamic performance. Our results give a hint of how to solve complex fluid manipulation problems using the DRL method.

DOI10.1017/jfm.2023.1096
Indexed BySCI
Language英语
Sub direction classification决策智能理论与方法
planning direction of the national heavy laboratory其他
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57325
Collection复杂系统认知与决策实验室_群体决策智能团队
Corresponding AuthorGuo, Pengming; Yang, Ning; Wang,Zhicheng
Affiliation1.Westlake University
2.Institute of Automation, Chinese Academy of Sciences
3.Taihu Laboratory of Deepsea Technological Science
4.Dalian University of Technology
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wang, Zhipeng,Lin, Runji,Zhao, Zhiyu,et al. Learn to flap: foil non-parametric path planning via deep reinforcement learning[J]. Journal of Fluid Mechanics,2024,984:A9.
APA Wang, Zhipeng.,Lin, Runji.,Zhao, Zhiyu.,Chen, Xu.,Guo, Pengming.,...&Fan, Dixia.(2024).Learn to flap: foil non-parametric path planning via deep reinforcement learning.Journal of Fluid Mechanics,984,A9.
MLA Wang, Zhipeng,et al."Learn to flap: foil non-parametric path planning via deep reinforcement learning".Journal of Fluid Mechanics 984(2024):A9.
Files in This Item: Download All
File Name/Size DocType Version Access License
learn-to-flap-foil-n(1892KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Zhipeng]'s Articles
[Lin, Runji]'s Articles
[Zhao, Zhiyu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Zhipeng]'s Articles
[Lin, Runji]'s Articles
[Zhao, Zhiyu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Zhipeng]'s Articles
[Lin, Runji]'s Articles
[Zhao, Zhiyu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: learn-to-flap-foil-non-parametric-path-planning-via-deep-reinforcement-learning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.