Neural network model for wing strain-load relationship based on fusion of real and virtual data

Yingjie SHI; Binchao LIU; Songsong LU; Liang CHEN; Hai SHANG; Rui BAO

doi:10.7527/S1000-6893.2024.30921

ACTA AERONAUTICAET ASTRONAUTICA SINICA >

2025 , Vol. 46 >Issue 19: 530921 - 530921

DOI: https://doi.org/10.7527/S1000-6893.2024.30921

Special Issue: Aircraft Digital Twin Technology

Neural network model for wing strain-load relationship based on fusion of real and virtual data

Yingjie SHI ,
Binchao LIU ,
Songsong LU ,
Liang CHEN ,
Hai SHANG ,
Rui BAO

Expand

^1.National Key Laboratory of Strength and Structural Integrity，School of Aeronautic Science and Engineering，Beihang University，Beijing 100191，China
^2.International Innovation Institute，Beihang University，Hangzhou 311115，China
^3.AVIC Shenyang Aircraft Design and Research Institute，Shenyang 110035，China
^4.AVIC Changcheng Institute of Metrology and Measurement，Beijing 100095，China

E-mail： song_lu@buaa.edu.cn

Received date: 2024-07-09

Revised date: 2024-09-02

Accepted date: 2024-09-23

Online published: 2024-10-11

Supported by

National Key Laboratory of Strength and Structural Integrity Independent Research Project

Fold

Abstract

When establishing a strain-load relationship model for aircraft structures， ground calibration tests can obtain high-fidelity data but are trapped with limited test ranges， while finite element simulations are not limited by test ranges but the data fidelity is low. This leads to difficulties in achieving win-win situation of accuracy and applicability based solely on either ground calibration test data or finite element simulation data. To address the above issue， two multi-level neural network models fusing real and virtual data are put forward， a mapping-based model and a compensation-based model. A method for measuring the model’s cognitive degree based on the variance of base learners is established and embedded into the compensation-based model. A neural network model with high accuracy， wide applicability， and the capability to forewarn unreliable prediction results is then developed. This developed model is validated using a scaled-down wing. Compared with complete reliance on real data from ground calibration tests， the load models based on fusion of multi-source data demonstrate superior capabilities， and the compensation-based model is better than the mapping-based one. Moreover， the compensation-based model can effectively identify the data samples with poor cognitive degree of the load model and thereby provide warnings for unreliable prediction results.

Key words： strain load relationship; aircraft structure; data fusion; neural network model; base learner

Cite this article

Yingjie SHI , Binchao LIU , Songsong LU , Liang CHEN , Hai SHANG , Rui BAO . Neural network model for wing strain-load relationship based on fusion of real and virtual data[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2025 , 46(19) : 530921 -530921 . DOI: 10.7527/S1000-6893.2024.30921

References

[1]	闫中午，宗宁，任文广，等. 飞行载荷发展综述［J］. 航空工程进展， 2020， 11（6）： 873-886.
	YAN Z W， ZONG N， REN W G， et al. Development overview of flight loads［J］. Advances in Aeronautical Science and Engineering， 2020， 11（6）： 873-886 （in Chinese）.
[2]	蒋祖国，田丁栓，周占廷. 飞机结构载荷/环境谱［M］. 北京：电子工业出版社， 2012： 260-267.
	JIANG Z G， TIAN D S， ZHOU Z T. Aircraft structural load/environment spectrum［M］. Beijing： Publishing House of Electronics Industry， 2012： 260-267 （in Chinese）.
[3]	张海涛，余建虎，李志蕊，等. T型尾翼布局的垂尾载荷测量技术［J］. 航空学报， 2019， 40（3）： 122074.
	ZHANG H T， YU J H， LI Z R， et al. Measuring technology for vertical fin load of T-shaped empennage layout［J］. Acta Aeronautica et Astronautica Sinica， 2019， 40（3）： 122074 （in Chinese）.
[4]	曹景涛. 飞机全动式鸭翼载荷飞行测量技术［J］. 航空学报， 2015， 36（4）： 1135-1141.
	CAO J T. Aircraft all movable canard load flight measurement technology［J］. Acta Aeronautica et Astronautica Sinica， 2015， 36（4）： 1135-1141 （in Chinese）.
[5]	兑红娜，刘栋梁，张志贤，等. 基于应变测量的结构载荷分布反演方法［J］. 航空学报， 2021， 42（5）： 524337.
	DUI H N， LIU D L， ZHANG Z X， et al. Distributed load recovery approach based on strain measurements［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（5）： 524337 （in Chinese）.
[6]	闫楚良. 飞机载荷谱实测技术与编制原理［M］. 北京：航空工业出版社， 2011： 96-102.
	YAN C L. Measurement technology and compilation principle of aircraft load spectrum［M］. Beijing： Aviation Industry Press， 2011： 96-102 （in Chinese）.
[7]	段垚奇，刘克格，赵丽娜，等. 飞机翼面标定试验中加载点载荷优化分配算法［J］. 计量与测试技术， 2022， 49（7）： 75-78.
	DUAN Y Q， LIU K G， ZHAO L N， et al. The optimization algorithm of loading-points load allocation during calibration test of the aircraft wings［J］. Metrology & Measurement Technique， 2022， 49（7）： 75-78 （in Chinese）.
[8]	阎楚良，张书明，卓宁生，等. 飞机机翼结构载荷测量试验力学模型与数据处理［J］. 航空学报， 2000， 21（1）： 56-59.
	YAN C L， ZHANG S M， ZHUO N S， et al. Mechanical model and data processing of load measurement test for the airplane’s wing structure［J］. Acta Aeronautica et Astronautica Sinica， 2000， 21（1）： 56-59 （in Chinese）.
[9]	刘佳玮，于明鑫，祝连庆，等. 基于深度学习的机翼蒙皮载荷计算方法［J］. 电子测量与仪器学报， 2022， 36（4）： 1-8.
	LIU J W， YU M X， ZHU L Q， et al. Calculation method of wing skin load based on deep learning［J］. Journal of Electronic Measurement and Instrumentation， 2022， 36（4）： 1-8 （in Chinese）.
[10]	杨全伟，舒成辉，赵华. 飞机机翼载荷校准试验的有限元仿真方法［J］. 系统仿真学报， 2008， 20（23）： 6569-6571.
	YANG Q W， SHU C H， ZHAO H. Technology of FEM simulation in aircraft wing loads calibration test［J］. Journal of System Simulation， 2008， 20（23）： 6569-6571 （in Chinese）.
[11]	COOPER S B， DIMAIO D. Static load estimation using artificial neural network： application on a wing rib［J］. Advances in Engineering Software， 2018， 125： 113-125.
[12]	孟敏，吴波，李俊. 飞机载荷校准虚拟试验建模方法研究［J］. 现代机械， 2020（1）： 51-54.
	MENG M， WU B， LI J. Modeling method for aircraft load calibration virtual test［J］. Modern Machinery， 2020（1）： 51-54 （in Chinese）.
[13]	唐吉运，张赐宝，滕申科. 基于BP神经网络的三角机翼飞行载荷模型研究［J］. 工程与试验， 2014， 54（3）： 5-8.
	TANG Y J， ZHANG C B， TENG S K. Study on flight load model for delta wing based on BP neural network［J］. Engineering & Test， 2014， 54（3）： 5-8 （in Chinese）.
[14]	郝云霄，闫楚良，刘克格. 基于支持向量机的机翼载荷模型研究［J］. 科学技术与工程， 2013， 13（25）： 7432-7437.
	HAO Y X， YAN C L， LIU K G. Modeling aircraft wing loads based on support vector machine［J］. Science Technology and Engineering， 2013， 13（25）： 7432-7437 （in Chinese）.
[15]	尚琳，何发东，杨华保，等. 基于神经网络的垂尾飞行载荷模型研究［J］. 强度与环境， 2011， 38（5）： 49-53.
	SHANG L， HE F D， YANG H B， et al. Research on flight loads model of vertical tail based on neural networks［J］. Structure & Environment Engineering， 2011， 38（5）： 49-53 （in Chinese）.
[16]	陈高颖，刘清惓，丁仁惠，等. 基于数据融合降低气温测量辐射误差的仿真分析与试验研究［J］. 气象科学， 2021， 41（3）： 404-409.
	CHEN G Y， LIU Q Q， DING R H， et al. Simulation analysis and experimental study of reducing temperature measurement radiation error based on data fusion［J］. Journal of the Meteorological Sciences， 2021， 41（3）： 404-409 （in Chinese）.
[17]	王旋，狄鹏. 基于虚实试验数据融合的装备测试性评估方法［J］. 舰船电子工程， 2021， 41（6）： 131-134.
	WANG X， DI P. Testability evaluation method of equipment based on data fusion for virtual and real test data fusion［J］. Ship Electronic Engineering， 2021， 41（6）： 131-134 （in Chinese）.
[18]	GAWLIKOWSKI J， TASSI C R N， ALI M， et al. A survey of uncertainty in deep neural networks［J］. Artificial Intelligence Review， 2023， 56（1）： 1513-1589.
[19]	YANG J K， ZHOU K Y N， LI Y X， et al. Generalized out-of-distribution detection： a survey［DB/OL］. arXiv preprint： 2110.11334， 2024.
[20]	DEVRIES T， TAYLOR G W. Learning confidence for out-of-distribution detection in neural networks［DB/OL］. arXiv preprint： 1802.04865， 2018.
[21]	LEE K， LEE H， LEE K， et al. training confidence-calibrated classifiers for detecting out-of-distribution samples［DB/OL］. arXiv preprint： 1711.09325， 2018.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References