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. 力学研究所
  3. 中国科学院力学研究所
  4. 非线性力学国家重点实验室
Developing a Silicon Beam Emulator Using Graph Attention Networks

文献类型：期刊论文

作者Lv, Siyuan3; Cheng, Qianxi3; Gong, Haojie3; Gao, Hao2; Zhou D(周东)1; Zheng, Duanmu3
刊名IEEE ACCESS
出版日期2024
卷号12页码:179119-179129
关键词Micromechanical devices Silicon Emulation Attention mechanisms Vectors Graph neural networks Computational modeling Numerical models Material properties graph attention networks MEMS silicon beams finite element analysis augmented graph generation augmented graph generation
ISSN号2169-3536
DOI10.1109/ACCESS.2024.3505603
通讯作者Zhou, Dong(zhoudong@imech.ac.cn) ; Zheng, Duanmu(ariesdmz@bistu.edu.cn)
英文摘要This study pioneers the application of Graph Attention Networks (GAT) and Graph Neural Networks (GNN), to the emulation of MEMS silicon beams under external loadings, representing a significant advancement in MEMS simulation. The novel augmented graph generation technique employed in this research enhances model performance and computational efficiency compared to traditional GNN message passing, particularly in data augmentation for training robust GAT. Silicon beam simulations were conducted under varying pressure conditions, and the results were found to be consistent with the theoretical solution, which can be a complementary roles of structural analysis combined with traditional finite element analysis (FEA). The trained GAT achieved a remarkable accuracy, with over 91% of predictions exhibiting an error no more than 3%, while the computation time for a single graph remained under 2 milliseconds. In the testing phase, the GAT-based computational simulation demonstrated a significant speed advantage, over 20 times faster than conventional FEA. The successful application of GAT in this context promises to reshape multiple aspects of technology development and optimization, paving the way for more efficient and accurate simulations across a wide range of disciplines.
分类号二类
资助项目National Key Research and Development Program of China[2021YFB3201705]
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:001373800700006
资助机构National Key Research and Development Program of China
其他责任者Zhou, Dong ; Zheng, Duanmu
源URL[http://dspace.imech.ac.cn/handle/311007/97807]  
专题力学研究所_非线性力学国家重点实验室
作者单位1.Chinese Acad Sci, Inst Mech, Beijing 100190, Peoples R China
2.Univ Glasgow, Sch Math & Stat, Glasgow City G12 8QQ, Scotland;
3.Beijing Informat Sci & Technol Univ, Sch Instrument Sci & Optoelect Engn, Beijing 100085, Peoples R China;
推荐引用方式
GB/T 7714		 Lv, Siyuan,Cheng, Qianxi,Gong, Haojie,et al. Developing a Silicon Beam Emulator Using Graph Attention Networks[J]. IEEE ACCESS,2024,12:179119-179129.
APA Lv, Siyuan,Cheng, Qianxi,Gong, Haojie,Gao, Hao,周东,&Zheng, Duanmu.(2024).Developing a Silicon Beam Emulator Using Graph Attention Networks.IEEE ACCESS,12,179119-179129.
MLA Lv, Siyuan,et al."Developing a Silicon Beam Emulator Using Graph Attention Networks".IEEE ACCESS 12(2024):179119-179129.

入库方式： OAI收割

来源：力学研究所

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。