基于GPR模型的多保真气动力建模方法

罗希; 黄俊; 唐磊; 王庆凤

doi:10.7638/kqdlxxb-2024.0192

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于GPR模型的多保真气动力建模方法

研究论文 | 更新时间：2026-05-28

- 基于GPR模型的多保真气动力建模方法
- Multi-fidelity aerodynamic modeling method based on GPR model
- 空气动力学学报 2026年44卷第3期页码：22-34
- 作者机构：
  
  1. 西南科技大学计算机科学与技术学院,绵阳,621010
  2. 西南科大四川天府新区创新研究院,成都,610299
- 作者简介：
  
  罗希（2000—），女，四川泸州人，研究方向：多保真气动力建模. E-mail：luoxi_59@163.com
  黄俊*（1988—），男，四川自贡人，副教授，研究方向：气动智能. E-mail：huangjuncs@swust.edu.cn
- 基金信息：
  
  飞行器流体物理全国重点实验室开放课题（2024-APF-KFZD-06）
- DOI：10.7638/kqdlxxb-2024.0192
  中图分类号： V211.3
- 纸质出版：2026
- 稿件说明：
移动端阅览
罗希, 黄俊, 唐磊, 等. 基于GPR模型的多保真气动力建模方法[J]. 空气动力学学报, 2026, 44(3): 22−34.

Luo Xi, Huang Jun, Tang Lei, et al. Multi-fidelity aerodynamic modeling method based on GPR model[J]. 2026, 44(3): 22-34.
罗希, 黄俊, 唐磊, 等. 基于GPR模型的多保真气动力建模方法[J]. 空气动力学学报, 2026, 44(3): 22−34. DOI： 10.7638/kqdlxxb-2024.0192

Luo Xi, Huang Jun, Tang Lei, et al. Multi-fidelity aerodynamic modeling method based on GPR model[J]. 2026, 44(3): 22-34. DOI： 10.7638/kqdlxxb-2024.0192.

摘要

通过整合不同保真度的数据，多保真气动力建模能够有效提升飞行器气动特性分析的计算效率和预测精度。为了更好处理高低保真数据之间同时存在的线性和非线性的混合复杂相关性，本文在非线性自回归高斯过程（nonlinear autoregressive Gaussian process

NARGP）模型的基础上，提出了一种新的多保真高斯过程回归模型（multi-fidelity Gaussian process regressive

MFGPR）。该模型通过结合线性核函数和非线性核函数，扩展了NARGP的能力，能够同时处理多保真数据中复杂的非线性关系和线性依赖性。为验证MFGPR的有效性，本文选取两类经典解析函数进行数值测试，并与Cokriging、NARGP和MFDNN三种传统多保真方法进行了对比分析。结果表明，在处理线性相关关系时，MFGPR的预测性能与CoKriging基本一致；而在非线性相关关系建模中，MFGPR相较于其他三种方法表现出更高的预测精度，同时在建模效率方面更具优势。进一步地，本文将MFGPR应用于ONERA M6机翼的压力分布预测和NACA2414翼型的阻力系数预测问题上，验证了其在气动力建模中的应用潜力和优越性能。

Abstract

Accurate aerodynamic characterization is crucial for optimizing aircraft design and enhancing flight performance. Multi-fidelity modeling approaches improve aerodynamic prediction accuracy and computational efficiency by integrating data from various fidelity levels. To better handle the complex mixed linear and nonlinear correlations coexisting between high- and low-fidelity data

this paper proposes a new multi-fidelity Gaussian process regression (MFGPR) model based on the nonlinear autoregressive Gaussian process (NARGP) framework. By integrating linear and nonlinear kernel functions

the proposed model extends the capabilities of NARGP

enabling it to simultaneously capture complex nonlinear relationships and linear dependencies within multi-fidelity data. To validate the effectiveness of the MFGPR method

two classes of classic analytical functions were selected for numerical testing

and a comparative analysis was performed against three traditional multi-fidelity methods: Cokriging

NARGP

and MFDNN. The results indicate that in handling linear correlations

the prediction performance of MFGPR is consistent with that of CoKriging. Conversely

in modeling nonlinear correlations

MFGPR demonstrates higher prediction accuracy than the other three methods

while offering a clear advantage in modeling efficiency. Furthermore

MFGPR was applied to predict the pressure distribution of the ONERA M6 wing and the drag coefficient of the NACA2414 airfoil

verifying its potential application and superior performance in aerodynamic modeling.

关键词

Keywords

references

Goovaerts P. Ordinary cokriging revisited[J]. Mathematical Geology, 1998, 30(1): 21−42. doi: 10.1023/A:1021757104135

Stein A, Corsten L C A. Universal Kriging and cokriging as a regression procedure[J]. Biometrics, 1991, 47(2): 575. doi: 10.2307/2532147

Stein A, Staritsky I G, Bouma J, et al. Simulation of moisture deficits and areal interpolation by universal cokriging[J]. Water Resources Research, 1991, 27(8): 1963−1973. doi: 10.1029/91wr00505

Geng M X, Huang D N, Yang Q J, et al. 3D inversion of airborne gravity-gradiometry data using cokriging[J]. Geophysics, 2014, 79(4): G37−G47. doi: 10.1190/geo2013-0393.1

Kennedy M, O'Hagan A. Predicting the output from a complex computer code when fast approximations are available[J]. Biometrika, 2000, 87(1): 1−13. doi: 10.1093/biomet/87.1.1

Han Z H, Zimmermann R, Goretz S. A new cokriging method for variable-fidelity surrogate modeling of aerodynamic data[C]// 48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition, Orlando, Florida. AIAA, 2010: AIAA 2010-1225. doi: 10.2514/6.2010-1225

Han Z H, Görtz S. Hierarchical Kriging model for variable-fidelity surrogate modeling[J]. AIAA Journal, 2012, 50(9): 1885−1896. doi: 10.2514/1.j051354

Zhang Xi, Yang Xixiang, Zhang Weihua, et al. An improved CoKriging modeling method and its application[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2021, 60(4): 10 (in Chinese) . doi: 10.13471/j.cnki.acta.snus.2020.09.10.2020B90

Peng X H, Kou J Q, Zhang W W. Multi-fidelity nonlinear unsteady aerodynamic modeling and uncertainty estimation based on Hierarchical Kriging[J]. Applied Mathematical Modelling, 2023, 122: 1−21. doi: 10.1016/j.apm.2023.05.031

Ulaganathan S, Couckuyt I, Ferranti f, et al. Performance study of multi-fidelity gradient enhanced Kriging[J]. Structural and Multidisciplinary Optimization, 2015, 51(5): 1017−1033. doi: 10.1007/s00158-014-1192-x

Deng Y, Lin G, Yang X. Multifidelity data fusion via gradient-enhanced Gaussian process regression[J]. arXiv preprint arXiv:2008.01066, 2020. doi: 10.4208/cicp.oa-2020-0151

Lin Q, Hu D W, Hu J X, et al. A screening-based gradient-enhanced Gaussian process regression model for multi-fidelity data fusion[J]. Advanced Engineering Informatics, 2021, 50: 101437. doi: 10.1016/j.aei.2021.101437

Perdikaris P, Raissi M, Damianou A, et al. Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2017, 473(2198): 20160751. doi: 10.1098/rspa.2016.0751

Meng X H, Karniadakis G E. 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. doi: 10.1016/j.jcp.2019.109020

Zhang X, Xie F, Ji T, et al. Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization[J]. Computer Methods in Applied Mechanics and Engineering, 2021, 373: 113485. doi: 10.1016/j.cma.2020.113485

Ning Chenjia, Wu Jifei, Li Guoshuai, et al. Research on few-shot aerodynamic modeling methods for civil aircraft model with wide-range high Reynolds number[J]. Acta Aerodynamica Sinica, 2024, 42(8): 60−76 (in Chinese). doi: 10.7638/kqdlxxb-2023.0208

Chen Baining, Xie Fangfang, Meng Xuhui. Adaptive multi-fidelity composite deep neural networks[J]. Physics of Gases, 2024, 9(4): 1−8 (in Chinese).

Keane A, Forrester A, Sobester A. Engineering design via surrogate modelling: A practical guide[M]. Washington, DC: AIAA, Inc. , 2008. doi: 10.2514/4.479557

Perdikaris P, Raissi M, Damianou A, et al. Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling[J]. Proceedings Mathematical, Physical, and Engineering Sciences, 2017, 473(2198): 20160751. doi: 10.1098/rspa.2016.0751

Schmitt V, Charpin F. Pressure distributions on the ONERA-M6-wing at transonic Mach numbers[R]. AGARD-AR-138, 1979.

Slater J W, Dudek J C, Tatum K E. The NPARC alliance verification and validation archive[C]// Fluids Engineering Division summer meeting, vol. 1. Finite element applications in fluid dynamics ; Turbulent flows ; Laminar flows. No. NASA/TM-2000-209946. 2000.

Selig M S, Guglielmo J J, Broeren A P, et al. Summary of low speed airfoil data[M]. SoarTech Publications, 1995.

Zhang Junjie, Huang Jun, Liu Zhiqin, et al. Variable confidence aerodynamic modeling method based on transfer learning[J]. Experimental Considerations Fluid Mechanics, 2025, 39(4): 93−103 (in Chinese). doi: 10.11729/syltlx20220058

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

考虑近距离海洋下垫面影响的对称风机翼型静气动特性

翼尖链翼组合式无人机气动特性研究

基于透气结构的海鸥仿生翼型气动特性

湍流工况涡流发生器对风力机翼型气动特性影响的试验研究

基于BP神经网络的弹射座椅姿态控制律设计