Aerodynamic data fusion method under epistemic uncertainty in flight tests

QIU Jingxuan; SI Haiqing; GAO Xinrui; CAO Jiufa; WU Xiaojun; ZHAO Wei; ZHANG Peihong

doi:10.7638/kqdlxxb-2024.0109

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Aerodynamic data fusion method under epistemic uncertainty in flight tests

更新时间：2026-05-28

- Aerodynamic data fusion method under epistemic uncertainty in flight tests
- Vol. 42, Issue 10, Pages: 69-83(2024)
- 作者机构：
  
  1. 南京航空航天大学通用航空与飞行学院,南京,211106
  2. 中国空气动力研究与发展中心计算空气动力研究所,绵阳,621000
- 作者简介：
- 基金信息：
- DOI：10.7638/kqdlxxb-2024.0109
  CLC： V211.3;TP18
- Published：2024
- 稿件说明：
移动端阅览
仇静轩, 司海青, 高昕睿, 等. 面向飞行试验认知不确定性的气动数据融合方法[J]. 空气动力学学报, 2024, 42(10): 69−83.

QIU Jingxuan, SI Haiqing, GAO Xinrui, et al. Aerodynamic data fusion method under epistemic uncertainty in flight tests[J]. 2024, 42(10): 69-83.
仇静轩, 司海青, 高昕睿, 等. 面向飞行试验认知不确定性的气动数据融合方法[J]. 空气动力学学报, 2024, 42(10): 69−83. DOI： 10.7638/kqdlxxb-2024.0109

QIU Jingxuan, SI Haiqing, GAO Xinrui, et al. Aerodynamic data fusion method under epistemic uncertainty in flight tests[J]. 2024, 42(10): 69-83. DOI： 10.7638/kqdlxxb-2024.0109.

摘要

在飞机设计领域中，不同的气动数据获取手段各有利弊，仅靠单一手段难以精确预测飞机的气动特性。因此，在实际工程应用中通常需要融合多种来源的数据，以获得更为准确和全面的气动特性描述。针对这一需求，以典型喷气式飞机为例，采用真实飞行数据、模拟飞行数据以及计算流体力学（CFD）仿真数据，结合深度神经网络，提出了一种认知不确定性的气动数据双层深度证据融合算法。该算法通过引入两种标准的置信分配方法，并将深度神经网络的输出与变分狄利克雷分布参数相结合，来表达和量化模型融合过程中的认知不确定性，并借助Dempster-Shafer理论有效地融合不同来源的数据及其不确定性。研究结果表明，该算法有效地融合了多源气动数据，所得结果不仅更加符合物理规律，而且提供了更高精度和更全面的气动数据，相比于单一数据源具有明显优势。

Abstract

In the field of aircraft design

various methods for obtaining aerodynamic data have their own advantages and disadvantages

making it a challenge to accurately predict an aircraft's aerodynamic characteristics using a single approach. Therefore

in practical engineering applications

it is often necessary to fuse data from multiple sources to achieve a more accurate and comprehensive description of aerodynamic characteristics. In response to this need

this study takes the typical jet aircraft as an example and employs real flight data

simulated flight data

and Computational Fluid Dynamics (CFD) data. By combining these with deep neural networks

we propose a dual-level deep evidential fusion algorithm for aerodynamic data under epistemic uncertainty. In this algorithm

two standard confidence distribution methods are introduced

and the output of deep neural networks is combined with variational Dirichlet distribution parameters to express and quantify epistemic uncertainty during the model fusion process. Utilizing the Dempster-Shafer theory

this algorithm effectively fuses data from different sources and their associated uncertainties. The results indicate that this algorithm successfully fuses multi-source aerodynamic data

producing outcomes that not only conform to physical laws but also provide more accurate and comprehensive aerodynamic data

which demonstrate significant advantages over single-source data methods.

关键词

Keywords

references

KOU J Q, ZHANG W W . Data-driven modeling for unsteady aerodynamics and aeroelasticity[J ] . Progress in Aerospace Sciences, 2021 , 125 : 100725 .

ZHANG W W, KOU J Q, LIU Y L . Prospect of artificial intelligence empowered fluid mechanical[J ] . Acta Aeronautica et Astronautica Sinica, 2021 , 42 ( 04 ): 524689: 1 − 46 (in Chinese).

ZHANG Q. Development of a data fusion framework for the aerodynamic analysis of launchers[D]. Delft, The Netherlands: Delft University of Technology , 2017.

RENGANATHAN S A, HARADA K, MAVRIS D N . Aerodynamic data fusion toward the digital twin paradigm[J ] . AIAA Journal, 2020 , 58 ( 9 ): 3902 − 3918 .

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 .

HE K F, QIAN W Q, WANG Q, et al . Application of data fusion technique in aerodynamics studies[J ] . Acta Aerodynamica Sinica, 2014 , 32 ( 6 ): 777 − 782 (in Chinese).

DENG C, CHEN G, WANG W Z, et al. Research on the data fusion algorithm based on flight test data and wind tunnel test data[J]. Acta Aerodynamica Sinica, 2022, 40(6): 45−50(in Chinese).

WANG X, NING C G /J /Q, 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 (in Chinese).

YANG H, CHEN S S, GAO Z H, et al . Rotor aerodynamic data fusion based on Bayesian framework[J ] . Acta Aeronautica et Astronautica Sinica, 2024 , 45 ( 8 ): 133 − 145 (in Chinese).

LIU L, LIU J C, YE Y, et al . Ultra-short-term wind power forecasting based on deep Bayesian model with uncertainty[J ] . Renewable Energy, 2023 , 205 : 598 − 607 .

GUO Z, WAN Z L, ZHANG Q S, et al . A survey on uncertainty reasoning and quantification in belief theory and its application to deep learning[J ] . Information Fusion, 2024 , 101 : 101987 .

TIAN X L, MA J S, LI L, et al . Development of prospect theory in decision making with different types of fuzzy sets: A state-of-the-art literature review[J ] . Information Sciences, 2022 , 615 : 504 − 528 .

TONG Z, XU P, DENŒUX T . An evidential classifier based on Dempster-Shafer theory and deep learning[J ] . Neurocomputing, 2021 , 450 : 275 − 293 .

DENG Y . Random permutation set[J ] . International Journal of Computers Communications Control, 2022 , 17 ( 1 ).

XIAO F Y . A distance measure for intuitionistic fuzzy sets and its application to pattern classification problems[J ] . IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021 , 51 ( 6 ): 3980 − 3992 .

XIAO F Y . CED: A distance for complex mass functions[J ] . IEEE Transactions on Neural Networks and Learning Systems, 2021 , 32 ( 4 ): 1525 − 1535 .

XIAO F Y, PEDRYCZ W . Negation of the quantum mass function for multisource quantum information fusion with its application to pattern classification[J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 , 45 ( 2 ): 2054 − 2070 .

XIAO F Y, CAO Z H, LIN C T . A complex weighted discounting multisource information fusion with its application in pattern classification[J ] . IEEE Transactions on Knowledge and Data Engineering, 2023 , 35 ( 8 ): 7609 − 7623 .

WANG H F, DENG X Y, JIANG W, et al . A new belief divergence measure for Dempster–Shafer theory based on belief and plausibility function and its application in multi-source data fusion[J ] . Engineering Applications of Artificial Intelligence, 2021 , 97 : 104030 .

LI H W, XIAO F Y . A method for combining conflicting evidences with improved distance function and Tsallis entropy[J ] . International Journal of Intelligent Systems, 2020 , 35 ( 11 ): 1814 − 1830 .

SHANG Q Y, LI H W, DENG Y, et al . Compound credibility for conflicting evidence combination: An autoencoder- K -means approach[J ] . IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022 , 52 ( 9 ): 5602 − 5610 .

BRUNTON S L, NOACK B R, KOUMOUTSAKOS P . Machine learning for fluid mechanics[J ] . Annual Review of Fluid Mechanics, 2020 , 52 : 477 − 508 .

LE CLAINCHE S, FERRER E, GIBSON S, et al . Improving aircraft performance using machine learning: A review[J ] . Aerospace Science and Technology, 2023 , 138 : 108354 .

SHAO Z M, DOU W B, PAN Y . Dual-level deep evidential fusion: Integrating multimodal information for enhanced reliable decision-making in deep learning[J ] . Information Fusion, 2024 , 103 : 102113 .

ANNA-KATHRIN K, BERTRAND C, DANIEL Z, et al. Evaluating robustness of predictive uncertainty estimation: Are Dirichlet-based models reliable? [C] // International Conference on Machine Learning, 2021.

HEIN M, ANDRIUSHCHENKO M, BITTERWOLF J. Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem[C]//Proc of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. IEEE, 2019: 41−50.

SENSOY M, KAPLAN L, KANDEMIR M. Evidential deep learning to quantify classification uncertainty[C] // Advances in Neural Information Processing Systems, 2018.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Numerical simulation analysis of rainwater contamination on vehicle side windows

Multi-source aerodynamic data fusion modeling with XGBoost

Research progress on the fusion of data obtained by high-speed wind tunnels, CFD and model flight

Flight tests and predictions of sonic boom signature for supersonic aircraft

Intelligent fusion method of multi-source aerodynamic data for flight tests

Related Author

GAO Jing

ZHAO Peng

MEI Liquan

HAI Chunlong

LIN Feng

YUAN Xianxu

Tang Zhigong

QIAN Weiqi

Related Institution

NIO lnc., Shanghai

School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an

University of Electronic Science and Technology, Chengdu

State Key Laboratory of Aerodynamics, Mianyang

China Aerodynamics Research and Development Center, Mianyang

AI问答

⁰