基于 XGBoost 的多源气动数据融合建模

林枫; 海春龙; 梅立泉

doi:10.7638/kqdlxxb-2023.0066

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 XGBoost 的多源气动数据融合建模

研究论文 | 更新时间：2026-07-27

- 基于 XGBoost 的多源气动数据融合建模
- Multi-source aerodynamic data fusion modeling with XGBoost
- 空气动力学学报 2024年42卷第7期页码：27-34
- 作者机构：
  
  西安交通大学数学与统计学院,西安,710049
- 作者简介：
  
  林枫（1998—），男，江西新余人，硕士研究生，研究方向：气动数据建模与数据挖掘. E-mail：llinmaple@163.com
  梅立泉*（1969—），男，教授，研究方向：偏微分方程数值解与计算物理. E-mail：lqmei@mail.xjtu.edu.cn
- 基金信息：
- DOI：10.7638/kqdlxxb-2023.0066
  中图分类号： V211.3
- 纸质出版：2024
- 稿件说明：
移动端阅览
林枫, 海春龙, 梅立泉. 基于 XGBoost 的多源气动数据融合建模[J]. 空气动力学学报, 2024, 42(7): 27−34.

LIN Feng, HAI Chunlong, MEI Liquan. Multi-source aerodynamic data fusion modeling with XGBoost[J]. 2024, 42(7): 27-34.
林枫, 海春龙, 梅立泉. 基于 XGBoost 的多源气动数据融合建模[J]. 空气动力学学报, 2024, 42(7): 27−34. DOI： 10.7638/kqdlxxb-2023.0066

LIN Feng, HAI Chunlong, MEI Liquan. Multi-source aerodynamic data fusion modeling with XGBoost[J]. 2024, 42(7): 27-34. DOI： 10.7638/kqdlxxb-2023.0066.

摘要

飞行试验和计算流体力学（CFD）是气动数据获取的两种常用手段，其中，通过飞行试验获取的气动数据精度高，但成本高昂，而通过CFD获取气动数据成本低，数据量丰富。因此，为了以尽可能低的成本获取精度更高的气动数据，本文利用数据融合方法，提出了一种可以融合大量的由CFD获取的气动数据与少量由飞行试验获取的气动数据的嫁接XGBoost （eXtreme Gradient Boosting）集成模型框架。首先，利用充足的CFD气动数据建模，作为融合框架中的低精度模型；然后，将少量飞行试验参数输入低精度模型得到相应的气动输出；最后，结合飞行试验气动数据的其他特征进行二次建模，实现对真实气动参数的预测。为了证明所提算法的有效性，本文设置了相关的对比实验，结果表明：1）多源气动数据融合建模较单源气动数据建模具有更高的预测精度；2）集成学习模型比传统的机器学习模型具有更强的泛化性能，其中XGBoost 模型泛化能力最强，能够实现对气动参数的准确预测。

Abstract

Flight tests and CFD (Computational Fluid Dynamics) are frequently used to obtain aerodynamic data. The aerodynamic data obtained by flight tests are usually highly accurate but expensive

while those obtained by CFD are relatively less accurate

but cheap and abundant in data. Therefore

to obtain aerodynamic parameters with higher accuracy at the lowest possible cost

this paper proposes a grafted XGBoost (eXtreme Gradient Boosting) integrated model framework

combining aerodynamic data obtained by CFD and flight tests for fusion modeling. First

a large amount of CFD aerodynamic data are used to establish a low-precision model in the fusion modeling framework regarding the trend of aerodynamic data. Then

a small number of design variables of flight tests are put into the low-precision model to obtain the corresponding aerodynamic output. Finally

the secondary modeling is carried out by integrating the information from other flight test aerodynamic data characteristics to predict the exact aerodynamic output. In order to verify the effectiveness of the proposed algorithm

relevant comparative experiments are conducted. The results show that: 1) Multi-source aerodynamic data fusion modeling has higher prediction accuracy than its single-source counterparts; 2) The integrated learning model has a better generalization performance than traditional machine learning models

among which the XGBoost model has the best generalization ability and can realize the accurate prediction of aerodynamic parameters.

关键词

Keywords

references

PALACIOS F, ECONOMON T D, ALONSO J J. Large-scale aircraft design using SU2[C]// 53rd AIAA Aerospace Sciences Meeting, Kissimmee, Florida. Reston, Virginia: AIAA, 2015: 1946. doi: 10.2514/6.2015-1946

BUSAN R C, MURPHY P C, HATKE D B, et al. Wind tunnel testing techniques for a tandem tilt-wing, distributed electric propulsion VTOL aircraft[C]// AIAA Scitech 2021 Forum, VIRTUAL EVENT. Reston, Virginia: AIAA, 2021: 1189. doi: 10.2514/6.2021-1189

SONI B, ALIABADI S. Large-scale CFD simulations of airflow and particle deposition in lung airway[J]. Computers Fluids, 2013, 88: 804-812. DOI: 10.1016/j.compfluid.2013.06.015

HU L W, XIANG Y, ZHANG J, et al. Aerodynamic data predictions based on multi-task learning[J]. Applied Soft Computing, 2022, 116: 108369. DOI: 10.1016/j.asoc.2021.108369

SHI Z F. Research on aerodynamic data modeling method based on deep neural network[D]. Chengdu: University of Electronic Science and Technology of China, 2020(in Chinese).

HE L, QIAN W Q, ZHAO T, et al. Multi-fidelity aerodynamic data fusion with a deep neural network modeling method[J]. Entropy, 2020, 22(9): 1022. DOI: 10.3390/e22091022

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

ZHANG M M, BARTOLI N, JUNGO A, et al. Enhancing the handling qualities analysis by collaborative aerodynamics surrogate modelling and aero-data fusion[J]. Progress in Aerospace Sciences, 2020, 119: 100647. DOI: 10.1016/j.paerosci.2020.100647

PHAM V, KIM M, TYAN M, et al. Numerical experience with variable-fidelity metamodeling for aerodynamic data fusion problems[J]. Journal of Defense Acquisition and Technology, 2019, 1(1): 1-8. DOI: 10.33530/jdaat.2019.1.1.1

KOU J Q, ZHANG W W. Multi-fidelity modeling framework for nonlinear unsteady aerodynamics of airfoils[J]. Applied Mathematical Modelling, 2019, 76: 832-855. DOI: 10.1016/j.apm.2019.06.034

WANG X, NING C J, WANG W Z, et al. Intelligent fusion method of multi-source aerodynamic data for flight tests[J]. Acta Aerodynamica Sinica, 2023, , 41(2): 12-20, I0001(in Chinese).

BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. DOI: 10.1023/A:1010933404324

DENG C, CHEN G, WANG W Z, et al. Aerodynamic data fusion algorithms based on aerodynamic model and uncertainly[J]. Acta Aerodynamica Sinica, 2022, 40(4)117-123 (in Chinese).

CHEN H, QIAN W Q, HE L. Aerodynamic coefficient prediction of airfoils based on deep learning[J]. Acta Aerodynamica Sinica, 2018, 36(2)294-299(in Chinese).

WANG W Z, ZHENG K P, CHEN G, et al. Application research of data-mining method to flight test data analysis and aerodynamic parameter identification[J]. Acta Aerodynamica Sinica, 2016, 34(6): 778-782(in Chinese).

WEBB G I, ZHENG Z. Multistrategy ensemble learning: reducing error by combining ensemble learning techniques[J]. IEEE Transactions on Knowledge and Data Engineering, 2004, 16(8): 980-991. DOI: 10.1109/TKDE.2004.29

DU P F, ZHANG S, ALPHONES A, et al. Faster deployment for indoor visible light positioning using xgboost algorithms in industrial Internet-of-things[C]//IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, Toronto, ON, Canada. IEEE, 2021: 1−7. doi: 10.1109/IECON48115.2021.9589151

ABBASIMEHR H, PAKI R, BAHRINI A. A novel XGBoost-based featurization approach to forecast renewable energy consumption with deep learning models[J]. Sustainable Computing: Informatics and Systems, 2023, 38: 100863. DOI: 10.1016/j.suscom.2023.100863

KIANGALA S K, WANG Z H. An effective adaptive customization framework for small manufacturing plants using extreme gradient boosting-XGBoost and random forest ensemble learning algorithms in an Industry 4.0 environment[J]. Machine Learning With Applications, 2021, 4: 100024. DOI: 10.1016/j.mlwa.2021.100024

WU T W, HE P J, LAN D Y, et al. Application of XGBoost for fast identification of typical industrial organic waste samples with near-infrared hyperspectral imaging[J]. ACS EST Engineering, 2023, 3(6): 841-850. DOI: 10.1021/acsestengg.2c00426

GUMUS M, KIRAN M S. Crude oil price forecasting using XGBoost[C]// 2017 International Conference on Computer Science and Engineering (UBMK), Antalya, Turkey. IEEE, 2017: 1100-1103. doi: 10.1109/UBMK.2017.8093500

CHEN T Q, GUESTRIN C. Xgboost: A scalable tree boosting system[C]// 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. 2016: 785-794. doi: 10.1145/2939672.2939785

BROWNE M W. Cross-validation methods[J]. Journal of Mathematical Psychology, 2000, 44(1): 108-132. DOI: 10.1006/jmps.1999.1279

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

基于多精度深度神经网络的汽车气动外形优化设计方法

面向飞行试验认知不确定性的气动数据融合方法

面向民机标模的宽域高雷诺数小样本气动建模方法研究

基于物理信息神经网络的气动数据融合方法

高速空气动力学三大手段数据融合研究进展