中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Real-time feedback control of β p based on deep reinforcement learning on EAST

文献类型：期刊论文

作者Zhang, Y. C.1,2; Wang, S.2; Yuan, Q. P.2; Xiao, B. J.1,2; Huang, Y.2
刊名PLASMA PHYSICS AND CONTROLLED FUSION
出版日期2024-05-01
卷号66
关键词deep reinforcement learning beta control EAST tokamak real-world implementation controller design
ISSN号0741-3335
DOI10.1088/1361-6587/ad3749
通讯作者Wang, S.(sen.wang@ipp.ac.cn) ; Yuan, Q. P.(qpyuan@ipp.ac.cn)
英文摘要Recently, with the advancement of the AI field, reinforcement learning (RL) has increasingly been applied to plasma control on tokamak devices. However, possibly due to the generally high training costs of reinforcement learning based on first-principle physical models and the uncertainty in ensuring simulation results align perfectly with tokamak experiments, feedback control experiments using reinforcement learning specifically for plasma kinetic parameters on tokamaks remain scarce. To address this challenge, this work proposes a novel design scheme including the development of a low computational cost environment. This environment is derived from EAST modulation experiments data through system identification. To tackle issues of noise and actuator limitations encountered in experiments, data preprocessing methods were employed. During training, the agent collected data across multiple plasma scenarios to update its strategy, and the performance of the RL controller was fine-tuned by adjusting the weight of the integral term of the error in the reward function. The effectiveness and robustness of the proposed design were then validated in a simulated environment. Finally, the scheme was successfully implemented on EAST, effectively tracking the beta p target with lower hybrid wave (LHW) at 4.6 GHz as the actuator, and providing reference for implementing feedback control based on reinforcement learning in tokamaks.
资助项目Comprehensive Research Facility for Fusion Technology Program of China[2018-000052-73-01-001228] ; National Nature Science Foundation of China[12075285] ; Provincial and ministerial joint funding for the postdoctoral international exchange program[E35E0D19]
WOS研究方向Physics
语种英语
WOS记录号WOS:001195725500001
出版者IOP Publishing Ltd
资助机构Comprehensive Research Facility for Fusion Technology Program of China ; National Nature Science Foundation of China ; Provincial and ministerial joint funding for the postdoctoral international exchange program
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/136839]  
专题中国科学院合肥物质科学研究院
通讯作者Wang, S.; Yuan, Q. P.
作者单位1.Univ Sci & Technol China, Hefei 230026, Anhui, Peoples R China
2.Chinese Acad Sci, Inst Plasma Phys, Hefei Inst Phys Sci, Hefei 230031, Anhui, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Y. C.,Wang, S.,Yuan, Q. P.,et al. Real-time feedback control of β p based on deep reinforcement learning on EAST[J]. PLASMA PHYSICS AND CONTROLLED FUSION,2024,66.
APA Zhang, Y. C.,Wang, S.,Yuan, Q. P.,Xiao, B. J.,&Huang, Y..(2024).Real-time feedback control of β p based on deep reinforcement learning on EAST.PLASMA PHYSICS AND CONTROLLED FUSION,66.
MLA Zhang, Y. C.,et al."Real-time feedback control of β p based on deep reinforcement learning on EAST".PLASMA PHYSICS AND CONTROLLED FUSION 66(2024).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。