基于飞参-载荷-寿命数字孪生模型的飞机结构健康管理方法

doi:10.7527/S1000-6893.2025.32382

Abstract

Abstract:

Aimed at the urgent needs of high-precision real-time life prediction and intelligent operation and maintenance in aircraft structural health management， this paper proposes an aircraft structural health management approach based on flight parameter-load-life digital twin models. First， measured data of flight parameters and loads in structural key parts are used to train flight parameter-load digital twin models based on the incremental learning eXtreme Gradient Boosting （XGBoost）， so as to realize high-precision dynamic mapping of the loads of the key parts. Second， simulated data of parametric models are used to train load-stress field digital twin models based on the non-intrusive reduced-order technique to realize high-precision dynamic reconstruction of the stress field of the key parts. Furthermore， the fatigue life estimation model is constructed based on the Detail Fatigue Rating （DFR） method. The parameters of the fatigue life estimation model are calculated from the prediction results of the above digital twin models， and the life consumption is estimated to realize the high-accuracy dynamic prediction of the remaining life， forming a flight parameter-load-life digital twin model. On this basis， fleet maintenance and flight task multi-objective planning models are constructed respectively， and solution sets of historical planning problems are formed by intelligent optimization algorithm. Then， based on clustering center distance and coefficient of determination metrics， similarity between historical planning （source-domain） problems and new planning （target-domain） problem in terms of solution set distribution and feature space is quantified. Finally， the highly similar source-domain problem solutions are transferred to the initial population of the target-domain problems to form an intelligent planning method for fleet maintenance and flight task based on transfer learning of historical information， which realizes the intelligent and efficient management of fleet life. The results of a typical flight-testing example show that this method can dynamically predict the loads and remaining life of the structural key parts with a load prediction error of 5.30% and a life prediction error of -7.19%. Meanwhile， for the complex maintenance and flight task planning problems of 20 aircraft， the efficiency of the proposed method is improved by 33.9% and 14.5%， respectively， compared with the direct optimization method， which verifies the effectiveness of the proposed method.

Key words: structural health management, digital twin, reduced-order model, fatigue life prediction, flight and maintenance planning

CLC Number:

V215.2

Lei HUANG, Cong GUO, Xiaobo ZHANG, Liangchen SUN, Yinghui ZUO, Bo WANG, Kuo TIAN. Aircraft structural health management method based on flight parameter-load-life digital twin models[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(21): 532382.

Figures/Tables 17

Fig.1

Table 1

Primary hyperparameters of flight parameter-key part load mapping model

超参数名称	符号	取值范围
n_estimators：决策树数量	K	［50，500］
max_depth：树最大深度	d_max	［3，15］
learning_rate：学习率	$η$	［0.01，1］
gamma：叶子节点数惩罚系数	$γ$	［0，1］
reg_alpha：L1正则化系数	$α$	［0，10］
reg_lambda：L2正则化系数	$λ$	［0，10］
min_child_weight：子节点样本的最小权重和	w_min	［1，8］
subsample：样本采样率	S_sub	［0.5，1］
colsample_bytree：特征采样率	S_col	［0.5，1］
freq：训练集数据均匀采样间隔	Q	［1，320］

Table 1

Fig.2

Table 2

Table 3

Fig.3

Fig.4

Table 4

Fig.5

Fig. 6

Table 5

Table 6

Table 7

Fig.7

Table 8

Table 9

Fig.8

References 40

[1]	张彦军，王斌团，宁宇，等. 基于健康监测的飞机结构寿命预测技术［J］. 航空工程进展， 2024， 15（1）： 1-14.
	ZHANG Y J， WANG B T， NING Y， et al. Life prediction technology of aircraft structures based on structural health monitoring［J］. Advances in Aeronautical Science and Engineering， 2024， 15（1）： 1-14 （in Chinese）.
[2]	魏元雷，高飞鹏. 民用飞机结构健康监测系统的设计方法［J］. 计算机测量与控制， 2022， 30（8）： 38-43.
	WEI Y L， GAO F P. Architecture design method for structural health monitoring system （SHM） of civil aircraft［J］. Computer Measurement & Control， 2022， 30（8）： 38-43 （in Chinese）.
[3]	董雷霆，周轩，赵福斌，等. 飞机结构数字孪生关键建模仿真技术［J］. 航空学报， 2021， 42（3）： 113-141.
	DONG L T， ZHOU X， ZHAO F B， et al. Key technologies for modeling and simulation of airframe digital twin［J］. Acta Aeronautica et Astronautica Sinica， 2021， 42（3）： 113-141 （in Chinese）.
[4]	谢克诚，周轩，董雷霆. 基于长短期记忆网络与小波变换的直升机飞参-载荷预测［J］. 航空科学技术， 2024， 35（11）： 51-57.
	XIE K C， ZHOU X， DONG L T. Flight-parameter-based load prediction of helicopter using LSTM network and wavelet transform［J］. Aeronautical Science & Technology， 2024， 35（11）： 51-57 （in Chinese）.
[5]	CANDON M， ESPOSITO M， FAYEK H， et al. Advanced multi-input system identification for next generation aircraft loads monitoring using linear regression， neural networks and deep learning［J］. Mechanical Systems and Signal Processing， 2022， 171： 108809.
[6]	兑红娜，王勇军，董江，等. 基于飞行参数的飞机结构载荷最优回归模型［J］. 航空学报， 2018， 39（11）： 80-89.
	DUI H N， WANG Y J， DONG J， et al. Optimal regression model for aircraft structural load based on flight data［J］. Acta Aeronautica et Astronautica Sinica， 2018， 39（11）： 80-89 （in Chinese）.
[7]	李文龙，杨美娟，唐宁，等. 某型飞机关键部位结构应变预测［J］. 应用力学学报， 2021， 38（2）： 649-654.
	LI W L， YANG M J， TANG N， et al. Structural strain prediction of key parts of an aircraft［J］. Chinese Journal of Applied Mechanics， 2021， 38（2）： 649-654 （in Chinese）.
[8]	顾宇轩，隋福成，宋恩鹏. 神经网络技术在单机应变寿命监控中的应用研究［J］. 装备环境工程， 2018， 15（12）： 74-77.
	GU Y X， SUI F C， SONG E P. Application of neural network technique in individual strain life monitoring［J］. Equipment Environmental Engineering， 2018， 15（12）： 74-77 （in Chinese）.
[9]	WANG S， LAI X N， HE X W， et al. Building a trustworthy product-level shape-performance integrated digital twin with multifidelity surrogate model［J］. Journal of Mechanical Design， 2022， 144（3）： 031703.
[10]	NOVAIS H C， SILVA S DA， FIGUEIREDO E. Co-Kriging strategy for structural health monitoring of bridges［J］. Structural Health Monitoring， 2024： 14759217241265375.
[11]	LIU L X， SONG X G， ZHANG C， et al. GAN-MDF： An enabling method for multifidelity data fusion［J］. IEEE Internet of Things Journal， 2022， 9（15）： 13405-13415.
[12]	田阔，孙志勇，李增聪. 面向结构静力试验监测的高精度数字孪生方法［J］. 航空学报， 2024， 45（7）： 288-299.
	TIAN K， SUN Z Y， LI Z C. High-precision digital twin method for structural static test monitoring［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（7）： 288-299 （in Chinese）.
[13]	WANG B， LI Z C， XU Z Y， et al. Digital twin modeling for structural strength monitoring via transfer learning-based multi-source data fusion［J］. Mechanical Systems and Signal Processing， 2023， 200： 110625.
[14]	XU Z Y， GAO T H， LI Z C， et al. Digital twin modeling method for hierarchical stiffened plate based on transfer learning［J］. Aerospace， 2023， 10（1）： 66.
[15]	黄熠玮，耿一斌，高天贺，等. 数字孪生驱动的结构全场变形高精度反演方法［J/OL］. 航空学报，（2024-10-16）［2025-08-23］. .
	HUANG Y W， GENG Y B， GAO T H， et al. Digital twin driven high precision reconstruction method for full-field deformation of structure［J/OL］. Acta Aeronautica et Astronautica Sinica，（2024-10-16）［2025-08-23］. （in Chinese）.
[16]	HUANG L， XU Z Y， GAO T H， et al. Digital twin-based non-destructive testing method for ultimate load-carrying capacity prediction［J］. Thin-Walled Structures， 2024， 204： 112223.
[17]	郭聪，毕清洁，张澍，等. 面向空间压紧堆叠结构的数字孪生模态试验方法［J］. 中国空间科学技术（中英文）， 2024， 44（6）： 72-80.
	GUO C， BI Q J， ZHANG S， et al. Digital twin modal testing method for space compressed stacking structures［J］. Chinese Space Science and Technology， 2024， 44（6）： 72-80 （in Chinese）.
[18]	HARTMANN D， HERZ M， WEVER U. Model order reduction a key technology for digital twins［M］. Reduced-Order Modeling （ROM） for Simulation and Optimization： Powerful Algorithms as Key Enablers for Scientific Computing. Cham： Springer International Publishing， 2018： 167-179.
[19]	ABADÍA-HEREDIA R， LÓPEZ-MARTÍN M， CARRO B， et al. A predictive hybrid reduced order model based on proper orthogonal decomposition combined with deep learning architectures［J］. Expert Systems with Applications， 2022， 187： 115910.
[20]	崔凯，杨靖，常思源，等. 基于POD和代理模型的高压捕获翼表面流场快速预测方法［J］. 力学学报， 2025， 57（4）： 883-894.
	CUI K， YANG J， CHANG S Y， et al. Rapid prediction method for high-pressure capturing wing surface flow field based on proper orthogonal decomposition and surrogate model［J］. Chinese Journal of Theoretical and Applied Mechanics， 2025， 57（4）： 883-894 （in Chinese）.
[21]	VIZZACCARO A， GIVOIS A， LONGOBARDI P， et al. Non-intrusive reduced order modelling for the dynamics of geometrically nonlinear flat structures using three-dimensional finite elements［J］. Computational Mechanics， 2020， 66（6）： 1293-1319.
[22]	刘斌超，鲁嵩嵩，曾苇鹏，等. 从金属材料疲劳性能的力学描述到飞机结构疲劳寿命评定：现状与展望［J］. 固体力学学报， 2023， 44（4）： 417-457.
	LIU B C， LU S S， ZENG W P， et al. From mechanical description for metal fatigue properties to service life evaluation of aircraft structural components： status and challenges［J］. Chinese Journal of Solid Mechanics， 2023， 44（4）： 417-457 （in Chinese）.
[23]	ELATTAR H M， ELMINIR H K， RIAD A M. Prognostics： A literature review［J］. Complex & Intelligent Systems， 2016， 2（2）： 125-154.
[24]	WANG H K， HAYNES R， HUANG H Z， et al. The use of high-performance fatigue mechanics and the extended Kalman/particle filters， for diagnostics and prognostics of aircraft structures［J］. CMES-Computer Modeling in Engineering and Sciences， 2015， 105（1）： 1-24.
[25]	BARTRAM G， MAHADEVAN S. Integration of heterogeneous information in SHM models［J］. Structural Control and Health Monitoring， 2014， 21（3）： 403-422.
[26]	ZHANG Q， LIU Y， XIAHOU T， et al. A heuristic maintenance scheduling framework for a military aircraft fleet under limited maintenance capacities［J］. Reliability Engineering & System Safety， 2023， 235： 109239.
[27]	CHA G， PARK J， MOON I. Military aircraft flight and maintenance planning model considering heterogeneous maintenance tasks［J］. Reliability Engineering & System Safety， 2023， 239： 109497.
[28]	JIANG M， HUANG Z Q， QIU L M， et al. Transfer learning-based dynamic multiobjective optimization algorithms［J］. IEEE Transactions on Evolutionary Computation， 2018， 22（4）： 501-514.
[29]	LIM R， GUPTA A， ONG Y S， et al. Non-linear domain adaptation in transfer evolutionary optimization［J］. Cognitive Computation， 2021， 13（2）： 290-307.
[30]	CHEN T Q， GUESTRIN C. XGBoost： A scalable tree boosting system［C］∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2016.
[31]	SHEKHAR S， BANSODE A， SALIM A. A comparative study of hyper-parameter optimization tools［C］∥ 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering （CSDE）. Piscataway： IEEE Press， 2021.
[32]	LI L S， JAMIESON K， DESALVO G， et al. Hyperband： A novel bandit-based approach to hyperparameter optimization［J］. Journal of Machine Learning Research， 2018， 18（185）： 1-52.
[33]	陶雪菲，王瑞，高玉魁，等. 基于DFR法的螺栓连接件疲劳性能研究［J］. 民用飞机设计与研究， 2021（4）： 28-36.
	TAO X F， WANG R， GAO Y K， et al. Investigation of fatigue properties of bolted connectors based on detail fatigue rating［J］. Civil Aircraft Design & Research， 2021（4）： 28-36 （in Chinese）.
[34]	刘庆刚，魏青，韩伟信，等. 基于有限元法的V型缺口平板应力集中系数研究［J］. 河北工业科技， 2019， 36（4）： 240-245.
	LIU Q G， WEI Q， HAN W X， et al. Study of the stress concentration factors of a V-notched plate by using finite element method［J］. Hebei Journal of Industrial Science and Technology， 2019， 36（4）： 240-245 （in Chinese）.
[35]	MA H P， ZHANG Y J， SUN S Y， et al. A comprehensive survey on NSGA-II for multi-objective optimization and applications［J］. Artificial Intelligence Review， 2023， 56（12）： 15217-15270.
[36]	HUANG L， ZUO Y H， GUO C， et al. AirLoadBench： An original dataset for flight parameter-based structural load prediction［DB/OL］. Zenodo： 14917880， 2025.
[37]	HU J C， SZYMCZAK S. A review on longitudinal data analysis with random forest［J］. Briefings in Bioinformatics， 2023， 24（2）： 1-11.
[38]	SALEEM R， YUAN B， KURUGOLLU F， et al. Explaining deep neural networks： A survey on the global interpretation methods［J］. Neurocomputing， 2022， 513： 165-180.
[39]	VAN HOUDT G， MOSQUERA C， NÁPOLES G. A review on the long short-term memory model［J］. Artificial Intelligence Review， 2020， 53（8）： 5929-5955.
[40]	顾宇轩，陈亮，董一飞，等. 数字孪生驱动的机群寿命精细化管理研究［J/OL］. 航空学报，（2025-02-26）［2025-08-23］. .
	GU Y X， CHEN L， DONG Y F， et al. Research on the refined management of fleet life driven by digital twins［J/OL］. Acta Aeronautica et Astronautica Sinica，（2025-02-26）［2025-08-23］. （in Chinese）.

序号	数据集参数名称	参数含义	序号	数据集参数名称	参数含义
0	Relative_Time	相对时间（不作为输入）	20	R_Eng_Start	右发起动
1	Nz	法向过载	21	L_Throttle_Pos	左发油门杆位置
2	Nx	纵向过载	22	R_Throttle_Pos	右发油门杆位置
3	Roll_Angle	横滚角	23	L_Eng_N1	左发低压转子转速
4	Pitch_Angle	俯仰角	24	R_Eng_N1	右发低压转子转速
5	True_AOA	真迎角	25	L_Eng_N2	左发高压转子转速
6	True_Sideslip	真侧滑角	26	R_Eng_N2	右发高压转子转速
7	FPA	航迹角	27	L_Gear_Down	左起落架放下
8	True_Heading	真航向	28	R_Gear_Down	右起落架放下
9	CAS	校正空速	29	N_Gear_Down	前起落架放下
10	TAS	真空速	30	L_Flaperon_Pos	左副襟翼位置
11	Mach	马赫数	31	R_Flaperon_Pos	右副襟翼位置
12	SAT	总温	32	L_LEF_Pos	左前缘襟翼位置
13	Baro_Alt	气压高度	33	R_LEF_Pos	右前缘襟翼位置
14	Roll_Rate	横滚角速率	34	L_Rudder_Pos	左方向舵位置
15	Pitch_Rate	俯仰角速率	35	L_Stab_Pos	左平尾位置
16	Heading_Rate	航向角速率	36	R_Stab_Pos	右平尾位置
17	Fuel_Qty1	燃油油量1	37	Stick_Pitch	操纵杆俯仰位置
18	Fuel_Qty2	燃油油量2	38	Stick_Roll	操纵杆倾斜位置
19	L_Eng_Start	左发起动	39	Pedal_Pos	脚蹬位置

模型	E_NRMSE/%	训练耗时/s
GPR （1 000样本点）	7.91	11
GPR （10 000样本点）	7.00	2 371
决策树	9.09	544
RF	6.70	36 882
DNN	5.97	4 453
LSTM	5.65	155 983
XGBoost	5.50	267
XGBoost-IL	5.30	12 504

测试工况	R²	E_NRMSE
1	0.999 9	5.46×10^-4
2	1.000 0	1.60×10^-4
3	0.999 7	8.17×10^-4
4	0.999 9	3.29×10^-4
5	0.999 8	6.97×10^-4
6	1.000 0	2.78×10^-4
7	0.998 4	2.15×10^-3
8	0.999 8	5.76×10^-4
9	0.999 8	6.10×10^-4
10	0.999 4	1.12×10^-3

测试集飞行工况	真实疲劳损伤/10^-5	对应疲劳寿命/次数	预测疲劳损伤/10^-5	对应疲劳寿命/次数
第10组	37.70	2 652	32.34	3 092
第23组	13.16	7 601	20.30	4 925
第26组	31.25	3 199	37.75	2 648
第36组	15.58	6 418	14.87	6 726
4次飞行合计	97.69	4 094	105.26	3 800

飞机	M_T/h	飞机	M_T/h
1	156	11	15 085
2	1 674	12	16 309
3	3 438	13	17 934
4	4 592	14	19 283
5	5 979	15	20 969
6	7 552	16	22 252
7	9 269	17	23 809
8	10 545	18	25 305
9	12 066	19	26 782
10	13 447	20	28 229

Aircraft structural health management method based on flight parameter-load-life digital twin models

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 40

Related Articles 15

Recommended Articles

Metrics

Comments

源域问题	I_sim	R²
1	0.88	-0.86
2	0.85	0.99
3	0.91	0.97
4	0.90	-0.83
5	0.87	0.84
6	0.94	0.98
7	0.87	-0.81

[1]	Yiwei HUANG, Yibin GENG, Tianhe GAO, Xuanwei HU, Yuan WANG, Hongyan MA, Kuo TIAN. Digital twin driven high precision reconstruction method for full-field deformation of structure [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 530967-530967.
[2]	Dingqiang DAI, Xuan ZHOU, Leiting DONG, Xiasheng SUN. Research progress and prospects of digital engineering and digital twin in field of aeronautical fatigue and structural integrity [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531022-531022.
[3]	Shangyu LI, Hang FENG, Junquan CHEN, Bin CHEN, Dan MEI. A design architecture and conceptual modeling approach for digital twins [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531118-531118.
[4]	Junqi LEI, Yuehua CHENG, Bin JIANG, Cheng XU, Guili XU, Tianyu SUN. Digital-twin’s modelling and dynamic adjustment mechanism of rudder-loop-system under fault conditions [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531273-531273.
[5]	Liang CHEN, Lei HUANG, Yuxuan GU, Cong GUO, Kexin LIN, Yu GUAN, Jian SONG. Twinning technology of key part load based on flight parameters [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531292-531292.
[6]	Yuxuan GU, Cong GUO, Lei HUANG, Yifei DONG, Hongda DONG, Zhilun DENG. Refined management of fleet life driven by digital twins [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531290-531290.
[7]	Yinxuan ZHANG, Qi ZHANG, Zhenyong XU, Linshu MENG. Predicting method of aircraft mechanical response based on residual neural networks [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531295-531295.
[8]	Ruoyao XIAO, Lianyu ZHENG, Jian ZHOU, Siru ZHAO, Jieru ZHANG, Yuwu CHEN. Online optimization method for positioning accuracy in cylindrical components aligning based on digital twins [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531978-531978.
[9]	Jialiang HU, Jiangpeng WU, Sixu HUO, Yidi GAO, Hua ZHENG. Modal parameter estimation based on reconstruction of digital twin sweep data in flutter flight test [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 531602-531602.
[10]	Pengfei WANG, Lifang ZENG, Xueming SHAO, Jun LI. Multi-source data fusion modeling method for aerodynamic load of aircraft wing based on pre-training and fine-tuning [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532297-532297.
[11]	Yifei WANG, Geyong CAO, Yang CAO, Xiaojun WANG. Uncertainty technologies in aircraft digital strength twins [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532408-532408.
[12]	Liang CHEN, Fanxing MENG, Chengbo WANG, Yinxuan ZHANG, Linshu MENG. Development and application of digital twins technology in aircraft strength design [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532252-532252.
[13]	Ran ZHUO, Chuliang YAN. A key component in digital twin of aircraft structures: Multi-dimensional flight parameter measurements [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532375-532375.
[14]	Lin LIN, Shiwei SUO, Dan LIU, Yinxuan ZHANG, Lingyu YUE, Sihao ZHANG, Yikun LIU, Song FU. A deep feature fusion network based on multi-scale kernel construction for filling wing stress field data [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(19): 532343-532343.
[15]	Chao AN, Rui ZHAO, Changchuan XIE, Chao YANG. Reduced-order modeling and aeroelastic analysis of geometrically nonlinear structures of large flexible wings [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730569-730569.

飞机	任务1	任务2	任务4	任务6	任务7	任务10
4	\	\	\	1	1	\
6	\	\	1	\	\	1
11	1	\	\	\	\	\
13	\	1	\	\	1	1
19	\	\	1	\	\	\