Institutional Repository of Coll Energy & Power Engn
Improved Deep Learning Algorithm for Reproduction of Airfoil Flow Field | |
Yang, Congxin1; Ling, Zuguang1; Wang, Yan2; Qian, Chen1; Zhao, Bin1; Zhou, Nannan1 | |
2021-03-10 | |
发表期刊 | Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University |
ISSN | 0253-987X |
卷号 | 55期号:3页码:20-28 |
摘要 | In order to overcome the disadvantages of the computational fluid dynamics (CFD) method such as high computational cost and the inability to reuse the computational results, a steady prediction model of pressure and velocity fields for NACA0018 airfoil in α=2°-8°, Re=0.1×106-1.6×106 is established based on deep-learning method using 132 sets of two-dimensional flow data. The energy conservation equation of incompressible flow at low velocity is used as the constraint condition. Considering the correlation between lift drag and surface pressure, an activation function is proposed. The results show that for pressure field prediction the average error of the traditional neural network is about 2.77%, but for velocity field prediction that of the traditional neural network is 11% and the maximum is 26.993%, while the average error of the improved neural network is only 2.77%. Compared with the traditional activation function, the improved activation function neural network is more accurate in predicting airfoil velocity field and the flow field transition is more uniform. Compared with the traditional CFD method, the neural network can obtain the flow field in a few seconds, which can greatly reduce the calculation time. © 2021, Editorial Office of Journal of Xi'an Jiaotong University. All right reserved. |
关键词 | Airfoils Cell proliferation Chemical activation Computational fluid dynamics Deep learning Flow fields Forecasting Incompressible flow Learning algorithms Learning systems Predictive analytics Transpiration Velocity Activation functions Computational costs Computational fluid dynamics methods Computational results Constraint conditions Energy conservation equations Surface pressures Two-dimensional flow |
DOI | 10.7652/xjtuxb202103003 |
收录类别 | EI |
语种 | 中文 |
出版者 | Xi'an Jiaotong University |
EI入藏号 | 20211310141439 |
EI主题词 | Neural networks |
EI分类号 | 461.9 Biology ; 631.1 Fluid Flow, General ; 652.1 Aircraft, General ; 723.5 Computer Applications ; 804 Chemical Products Generally |
引用统计 | 无
|
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/148402 |
专题 | 能源与动力工程学院 |
作者单位 | 1.College of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou; 730050, China; 2.Nuclear Power Institute of China, Chengdu; 610000, China |
第一作者单位 | 能源与动力工程学院 |
第一作者的第一单位 | 能源与动力工程学院 |
推荐引用方式 GB/T 7714 | Yang, Congxin,Ling, Zuguang,Wang, Yan,et al. Improved Deep Learning Algorithm for Reproduction of Airfoil Flow Field[J]. Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University,2021,55(3):20-28. |
APA | Yang, Congxin,Ling, Zuguang,Wang, Yan,Qian, Chen,Zhao, Bin,&Zhou, Nannan.(2021).Improved Deep Learning Algorithm for Reproduction of Airfoil Flow Field.Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University,55(3),20-28. |
MLA | Yang, Congxin,et al."Improved Deep Learning Algorithm for Reproduction of Airfoil Flow Field".Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University 55.3(2021):20-28. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论