|
|
论文:2024,Vol:42,Issue(2):328-334 |
|
|
引用本文： |
|
|
朱星谕, 梅立泉. 基于复合神经网络的多源气动数据建模[J]. 西北工业大学学报 |
|
|
ZHU Xingyu, MEI Liquan. Multi-fidelity aerodynamic data analysis by using composite neural network[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 基于复合神经网络的多源气动数据建模 |
|
| 朱星谕, 梅立泉 |
|
| 西安交通大学 数学与统计学院, 陕西 西安 710049 |
| 摘要: |
| 将深度学习方法应用至气动数据建模,能够解决传统建模方法效率低、代价高的问题,具有重要的现实意义。基于复合神经网络模型对多源气动数据进行学习,利用低精度数据辅助高精度数据进行预测。与不同网络模型进行对比,验证了文中提出的复合神经网络在气动数据建模中表现优良,且泛化能力较好。 |
| 关键词:
气动数据建模
深度神经网络
复合神经网络
|
|
| Multi-fidelity aerodynamic data analysis by using composite neural network |
|
| ZHU Xingyu, MEI Liquan |
|
| School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an 710049, China |
| Abstract: |
| Applying deep learning to aerodynamic data modeling has important practical significance. In this paper, the composite neural network is applied to the aerodynamics, making full use of the different characteristics of high and low-fidelity aerodynamic data. Multi-fidelity analysis technique is also used to analyze the correlation between the two types of data so as to establish the composite neural network. The experimental results show that the learning of multi-fidelity aerodynamic data based on the composite neural network model can better capture the mapping relationship between the aerodynamic input and the output data. And after comparing with the single neural network, it is verified that the present model has excellent performance in the regression modeling of aerodynamic data. |
| Key words:
aerodynamic data modeling
deep neural network
composite neural network
|
|
| 收稿日期: 2023-03-02
修回日期:
|
| DOI: 10.1051/jnwpu/20244220328 |
| 基金项目: 国家自然科学基金(12171385)资助 |
| 通讯作者: 梅立泉(1969—),教授 e-mail:lqmei@mail.xjtu.edu.cn
Email：lqmei@mail.xjtu.edu.cn |
| 作者简介: 朱星谕(1999—),硕士研究生
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] IOANNIS G T, DIMITRIS G, EURIPIDIS G. Solving differential equations with constructed neural networks[J]. Neurocomputing, 2009, 72(10/11/12): 2385-2391
[2] MALL S, CHAKRAVERTY S. Comparison of artificial neural network architecture in solving ordinary differential equations[J]. Advances in Artificial Neural Systems, 2013, 2013: 12
[3] DENNIS J L, ROBERT F S. Identification of aerodynamic coefficients using computational neural networks[J]. Journal of Guidance, Control, and Dynamics, 1993, 16(6): 1018-1025
[4] WILLIAM E F, SCOTT J S. Neural networks: applications and opportunities in aeronautics[J]. Progress in Aerospace Sciences, 1996, 32(5): 433-456
[5] 陈海, 钱炜祺, 何磊. 基于深度学习的翼型气动系数预测[J]. 空气动力学学报, 2018, 36(2): 294-299 CHEN Hai, QIAN Weiqi, HE Lei. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2): 294-299 (in Chinese)
[6] 李轶. 基于CNN的流场特征可视化方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2018 LI Yi, Research on visualization method of flow field feature based on convolution neural network[D]. Harbin: Harbin Engineering University, 2018 (in Chinese)
[7] MENG Xuhui, HESSAM B, GEORGE E K. Multi-fidelity bayesian neural networks: algorithms and applications[J]. Journal of Computational Physics, 2021, 438: 110361
[8] ALEXANDER I J F, ANDRÁS S, ANDY J K. Multi-fidelity optimization via surrogate modelling[J]. Proceedings of the Royal Society A Mathematical Physical & Engineering Sciences, 2007, 463(2088): 3251-3269
[9] MAZIAR R, GEORGE K. Deep multi-fidelity Gaussian processes[J]. (2016-04-26)[2023-01-05]. https://arxiv.org/abs/1604.07484.07484
[10] PERDIKARIS P, RAISSI M, DAMIANOU A, et al. 2017 Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling[J]. Proceedings of the Royal Society, Mathematical, Physical and Engineering Sciences,2017,473(2198):20160751
[11] ELDRED M. Recent advances in non-intrusive polynomial chaos and stochastic collocation methods for uncertainty analysis and design[C]//50th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 2009
[12] PANG Guofei, LIU Yang, GEORGE E, et al. Neural-net-induced gaussian process regression for function approximation and PDE solution[J]. Journal of Computational Physics, 2019(384): 270-288
[13] NHU-VAN N, SEOK-MIN C, WAN-SUB K, et al. Multidisciplinary unmanned combat air vehicle system design using multi-fidelity model[J]. Aerospace Science and Technology, 2013, 26(1): 200-210
[14] LU Chuan, ZHU Xueyu. Bifidelity data-assisted neural networks in nonintrusive reduced-order modeling[J]. Science of Computer Programming, 2021, 87(1): 1-30
[15] CHEN Chi, ZUO Yunxing, YE Weike, et al. Learning properties of ordered and disordered materials from multi-fidelity data[J]. Nature Computational Science, 2021, 1(1): 46-53
[16] MENG Xuhui, GEORGE E K. A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems[J]. Journal of Computational Physics, 2020(401): 109020
[17] 吕召阳, 聂雪媛, 赵奥博. 基于CNN机翼气动系数预测[J]. 北京航空航天大学学报, 2023, 49(3): 674-680 LYU Zhaoyang, NIE Xueyuan, ZHAO Aobo. Prediction of wing aerodynamic coefficient based on CNN[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(3): 674-680 (in Chinese) |
|
|
|
|
|
|
|
