基于数字孪生的飞机起落架健康管理技术

doi:10.7527/S1000-6893.2022.27629

Abstract

Abstract:

Traditional health management methods for aircraft landing gear systems face the problems of inadequate knowledge， unbalanced data， and rigidified models. This paper explores the application of the digital twin-driven health management technology， and proposes a digital twin health management framework based on self-updating models to reliably complete diagnostic and prediction tasks. The digital twin model is established from physical and behavior dimensions to realize the digital mapping of real systems. The reinforcement learning algorithm is used to update the parameters of the digital twin model to ensure real-time tracking and reflection of the entity health status by the twin model. Further， event-based fault diagnosis and particle filter scheme-based fault prediction are designed. In the validation experiment with the retraction/extension as an example， our method exhibits better performance in terms of real-time， accuracy and robustness than traditional methods.

Key words: landing gear, digital twin, health management, event-based fault diagnosis, model tracking, fault prediction

CLC Number:

Chenghao GUO, Jinsong YU, Yue SONG, Qi YIN, Jiaxuan LI. Application of digital twin⁃based aircraft landing gear health management technology[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(11): 227629-227629.

Figures/Tables 24

Fig. 1

Fig. 2

Algorithm 1 Reinforcement learning AC algorithm

算法强化学习AC算法

输入：学习率等超参数

输出：网络结构与控制策略 $π$

1. $f o r e a c h i t e r a t i o n d o :$

2. $S a m p l e s 0 a c c o r d i n g t o ρ$

3. $f o r e a c h t i m e s t e p d o :$

4. $S a m p l e a t f r o m π s a n d s t e p f o r w a r d$

5. $O b s e r v e s t + 1, π t$

6. $S t o r e s t, a t, r t, s t + 1 i n D M$

7. $e n d f o r$

8. $f o r e a c h u p d a t e s t e p d o :$

9. $S a m p l e m i n i b a t c h e s o f t r a n s i t i o n s f r o m D M$

10. $U p d a t e π w i t h g r a d i e n t s$

11. $U p d a t e n e t w o r k s w i t h s o f t r e p l a c e m e n t$

12. $e n d f o r$

13. $e n d f o r$

Fig. 3

Table 1

Landing gear retraction system failure event signature

故障	$q p$	$p p u m p$	$p 1$	$F i n f l o w 1$	$v$	$x$	信号优先级（Measurement Orderings）
泵泄漏	$+ 0$	$- -$	$- 0$	$- -$	$- 0$	$- -$	$p p u m p < q p$
作动筒泄漏	$+ +$	$- -$	$- +$	$- +$	$+ 0$	$+ -$	$F i n f l o w 1 < v < x, p 1$
节流阀阻塞	$- 0$	$- +$	$+ 0$	$- 0$	$- 0$	$- -$
油滤污染	$+ -$	$- -$	$- 0$	$- 0$	$+ -$	$- 0$
作动筒磨损	$00$	$00$	$+ 0$	$- 0$	$+ -$	$- 0$	$F i n f l o w 1 < v < x, p 1$

Table 1

Fig. 4

Algorithm 2 Fuzzy matching fault isolation algorithm based on levenshtein distance

算法基于编辑距离的模糊匹配故障隔离算法

输入：系统响应特征向量 $V m e a s u r e = S f + M O$

故障事件信号特征向量 $V s i g n a t u r e = S f + M O$

输出：模糊匹配近似度 $f u z z y m a t c h i n g s c o r e s$

1. $n = l e n V m e a s u r e$ ， $m = l e n V s i g n a t u r e$

2. $i n i t i a l i z e m a t r i x D m × n$

3. $t e m p = 0 V m e a s u r e i = = V s i g n a t u r e 1 其他$

4. $i n s e r t : D i - 1 . j + 1$

5. $d e l e t e : D i . j - 1 + 1$

6. $s w a p : D i - 1 . j - 1 + t e m p$

7. $f o r i, j i n D :$

8. $D i, j = m i n i n s e r t, d e l e t e, s w a p$

9. $D i s t a n c e = d n m$

10. $f u z z y m a t c h i n g s c o r e s = 1 - D i s t a n c e m a x n, m$

Fig. 5

Algorithm 3 Sampling importance resampling

算法重要性重采样（SIR）

1. 输入： ${(x k - 1 i, θ k - 1 i), ω k - 1 i} i = 1 N, u k - 1 : k, y k$

2. 输出： ${(x k j, θ k j), ω k j} i = 1 N$

3. 初始状态随机游走，分配粒子权重

$f o r i i n 1, N :$

$θ k i = θ k - 1 i + ξ k - 1 i, ξ k - 1 i ∼ N μ, σ 2$

$x k i = p f x k - 1 i, θ k - 1 i, u k - 1$

$ω k i = p h x k i, θ k i, u k$

$e n d f o r$

$n o r m a l i z e ω k i$

4. 旧粒子集中重采样得到新粒子集

$i ← 1$

$u 1 ~ U C D F (0,1 / N)$

$f o r j i n 1, N :$

$u ← u 1 + (j + 1) / N$

$w h i l e u > C D F i d o :$

$i ← i + 1$

$e n d w h i l e$

$x k j, θ k j, ω k j ← x k i, θ k j, 1 N$

$e n d f o r$

Fig. 6

Table 2

Fig. 7

Fig. 8

Fig. 9

Table 3

Fig. 10

Table 4

Network hyperparameter settings

超参数	数值
批尺寸（Batch Size）	256
Actor网络学习率（Learning Rate）/10^-4	2
Critic网络学习率（Learning Rate）/10^-4	2
折扣因子 $γ$	0.995
衰减率（网络软更新）/10^-3	1~5

Table 4

Fig. 11

Fig. 12

Fig. 13

Table 5

Model tracking algorithm comparison

算法

准确性

实时性

鲁棒性

RMSE/（10⁵

L ⋅ m i n - 1 ⋅ P a - 1

）

训练速度/s

部署速度/（10^-3 s）

在60 dB信噪比下的RMSE

/（10⁵ $L ⋅ m i n - 1 ⋅ P a - 1$ ）

0.167

24 000

1.37

0.204

DNN

0.243

100

1.68

0.276

Table 5

Fig. 14

Table 6

Prediction algorithm experiment results

粒子数	随机游走方差相乘系数	RMSE_ $x a 1 / m$	RMSE_ $F i n f l o w_a 1 /$ （L·min^-1）
100	1	2.17×10^-2	0.922
100	10	3.48×10^-2	1.050
1 000	1	5.81×10^-3	0.721
1 000	10	2.31×10^-2	1.540

Table 6

Fig. 15

References 36

1	EASA. Annual safety review 2021［R］. Germany： European Union Aviation Safety Agency， 2021.
2	陈新霞，刘煜原，黄加阳，等. 基于贝叶斯网络推理的起落架系统故障诊断技术研究［J］. 计算机测量与控制， 2016， 24（10）： 24-27.
	CHEN X X， LIU Y Y， HUANG J Y， et al. Fault diagnosis of landing gear system based on Bayesian network inference［J］. Computer Measurement & Control， 2016， 24（10）： 24-27 （in Chinese）.
3	PHILLIPS P， DISTON D， STARR A. Perspectives on the commercial development of landing gear health monitoring systems［J］. Transportation Research Part C： Emerging Technologies， 2011， 19（6）： 1339-1352.
4	ZHANG H G， KANG R， PECHT M. A hybrid prognostics and health management approach for condition-based maintenance［C］∥2009 IEEE International Conference on Industrial Engineering and Engineering Management. Piscataway： IEEE Press， 2010： 1165-1169.
5	AHMADI A， FRANSSON T， CRONA A， et al. Integration of RCM and PHM for the next generation of aircraft［C］∥2009 IEEE Aerospace Conference. Piscataway： IEEE Press， 2009： 1-9.
6	CHEN J， CHEN S Y， LIU Z B， et al. Health monitoring of landing gear retraction/extension system based on optimized fuzzy C-means algorithm［J］. IEEE Access， 2020， 8： 219611-219621.
7	YANG Y. Aircraft landing gear extension and retraction control system diagnostics， prognostics and health management［D］. Bedfordshire： Cranfield University， 2012.
8	HOLMES G， SARTOR P， REED S， et al. Prediction of landing gear loads using machine learning techniques［J］. Structural Health Monitoring， 2016， 15（5）： 568-582.
9	BYINGTON C S， WATSON M， EDWARDS D. Data-driven neural network methodology to remaining life predictions for aircraft actuator components［C］∥ 2004 IEEE Aerospace Conference Proceedings. Piscataway： IEEE Press， 2004： 3581-3589.
10	DZIENDZIKOWSKI M， KURNYTA A， REYMER P， et al. Application of operational load monitoring system for fatigue estimation of main landing gear attachment frame of an aircraft［J］. Materials， 2021， 14（21）： 6564.
11	SARTOR P， SCHMIDT R K. Aircraft landing gear structural health monitoring using a loads monitoring approach［J］. Revue Internationale de la Croix-Rouge et Bulletin international des Sociétés de la Croix-Rouge， 2008， 33（387）： f1-f10.
12	LI C Z， MAHADEVAN S， LING Y， et al. Dynamic Bayesian network for aircraft wing health monitoring digital twin［J］. AIAA Journal， 2017， 55（3）， doi： 10.2514/1.J055201 .
13	TAO F， ZHANG M， LIU Y S， et al. Digital twin driven prognostics and health management for complex equipment［J］. CIRP Annals， 2018， 67（1）： 169-172.
14	LI W H， RENTEMEISTER M， BADEDA J， et al. Digital twin for battery systems： Cloud battery management system with online state-of-charge and state-of-health estimation［J］. Journal of Energy Storage， 2020， 30： 101557.
15	HE B， LIU L， ZHANG D. Digital twin-driven remaining useful life prediction for gear performance degradation： a review［J］. Journal of Computing and Information Science in Engineering， 2021， 21（3）： 030801.
16	WANG Y C， TAO F， ZHANG M， et al. Digital twin enhanced fault prediction for the autoclave with insufficient data［J］. Journal of Manufacturing Systems， 2021， 60： 350-359.
17	YE Y M， YANG Q， YANG F， et al. Digital twin for the structural health management of reusable spacecraft： a case study［J］. Engineering Fracture Mechanics， 2020， 234： 107076.
18	PILTAN F， TOMA R N， SHON D， et al. Strict-feedback backstepping digital twin and machine learning solution in AE signals for bearing crack identification［J］. Sensors， 2022， 22（2）： 539.
19	NASA. 2020 NASA technology taxonomy［R］. Washington D.C.： NASA， 2020.
20	MOSTERMAN P J， BISWAS G. A theory of discontinuities in physical system models［J］. Journal of the Franklin Institute， 1998， 355（3）： 401-439.
21	DAIGLE M J， ROYCHOUDHURY I， BISWAS G， et al. A comprehensive diagnosis methodology for complex hybrid systems： a case study on spacecraft power distribution systems［J］. IEEE Transactions on Systems， Man， and Cybernetics - Part A： Systems and Humans， 2010， 40（5）： 917-931.
22	DAIGLE M J， KOUTSOUKOS X D， BISWAS G. A qualitative event-based approach to continuous systems diagnosis［J］. IEEE Transactions on Control Systems Technology， 2009， 17（4）： 780-793.
23	ROYCHOUDHURY I， DAIGLE M， BREGON A， et al. A structural model decomposition framework for systems health management［C］∥ 2013 IEEE Aerospace Conference. Piscataway： IEEE Press， 2013： 1-12.
24	LILLEY D S， MATHÉ P， SCHLOßHAUE V. Calibration and uncertainty quantification of gas turbine performance models［C］∥ASME Turbo Expo 2015： Turbine Technical Conference and Exposition. New York： AMSE， 2015， doi： 10.1115/GT2015-42392 .
25	BORGUET S. Variations on the Kalman filter for enhanced performance monitoring of gas turbine engines［D］. Liège： University of Liège， 2012.
26	RUTTER C M， MIGLIORETTI D L， SAVARINO J E. Bayesian calibration of microsimulation models［J］. Journal of the American Statistical Association， 2009， 104（488）： 1338-1350.
27	LIU S Q， BOROVYKH A， GRZELAK L A， et al. A neural network-based framework for financial model calibration［J］. Journal of Mathematics in Industry， 2019， 9（1）： 9.
28	TIAN Y， CHAO M A， KULKARNI C， et al. Real-time model calibration with deep reinforcement learning［DB/OL］. arXiv preprint： 2006.04001， 2020.
29	MOSTERMAN P J， BISWAS G. Diagnosis of continuous valued systems in transient operating regions［J］. IEEE Transactions on Systems， Man， and Cybernetics - Part A： Systems and Humans， 1999， 29（6）： 554-565.
30	DAIGLE M J， KOUTSOUKOS X D， BISWAS G. An event-based approach to integrated parametric and discrete fault diagnosis in hybrid systems［J］. Transactions of the Institute of Measurement and Control， 2010， 32（5）： 487-510.
31	BISWAS G， SIMON G， MAHADEVAN N， et al. A robust method for hybrid diagnosis of complex systems［J］. IFAC Proceedings Volumes. 2003， 36（5）： 1023-1028.
32	SAHA B， GOEBEL K. Modeling Li-ion battery capacity depletion in a particle filtering framework［C］∥Annual Conference of the PHM Society. 2009.
33	DAIGLE M J， GOEBEL K. A model-based prognostics approach applied to pneumatic valves［J］. International Journal of Prognostics and Health Management， 2011， 2（2）， doi： 10.36001/ijphm.2011.v2i2.1359 .
34	DAIGLE M， GOEBEL K. Multiple damage progression paths in model-based prognostics［C］∥ 2011 Aerospace Conference. Piscataway： IEEE Press， 2011： 3621-3630.
35	胡晓青，马存宝，和麟，等. 飞机起落架收放系统建模与故障仿真［J］. 计算机工程与科学， 2016， 38（6）： 1286-1293.
	HU X Q， MA C B， HE L， et al. Modeling and fault simulation of the landing gear extension and retraction system［J］. Computer Engineering & Science， 2016， 38（6）： 1286-1293 （in Chinese）.
36	DEB S， GHOSHAL S， MATHUR A， et al. Multisignal modeling for diagnosis， FMECA， and reliability［C］∥ SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems， Man， and Cybernetics. Piscataway： IEEE Press， 2002： 3026-3031.

元件模型	参数	数值
液压马达	轴转速/（r·min^-1）	5 000
油滤	孔径/mm	6
	临界流数	2 320
	最大流量系数	0.7
上位锁	活塞直径/mm	25
	活塞杆直径/mm	12
	活塞行程/mm	55
主起收放作动筒	活塞直径/mm	85.55
	活塞杆直径/mm	36.449
	活塞行程/mm	219.4
	运动部件等效质量/kg	2.8
溢流阀	阀开启压力/MPa	21
溢流阀	阀流量压力梯度/（L·min^-1·MPa^-1）	200

故障模式	多信号流图		因果图
故障模式	故障候选集	推理时间/s	故障候选集	置信度分数	推理时间/s
作动筒泄漏	｛作动筒泄漏，油滤污染｝	0.07	｛作动筒泄漏，泵泄漏｝	｛88，86｝	0.001
节流阀堵塞	｛节流阀堵塞，作动筒磨损｝	0.03	｛节流阀堵塞｝	｛91｝	0.001

[1]	Fangli WANG, Kai LIU, Wei PAN, Mingbo TONG. Application and development of green structure maintenance for civil aircraft [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(11): 25851-025851.
[2]	CAO Ming, HUANG Jinquan, ZHOU Jian, CHEN Xuefeng, LU Feng, WEI Fang. Current status, challenges and opportunities of civil aero-engine diagnostics & health management Ⅰ: Diagnosis and prognosis of engine gas path, mechanical and FADEC [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 625573-625573.
[3]	CAO Ming, WANG Peng, ZUO Hongfu, ZENG Haijun, SUN Jianzhong, YANG Weidong, WEI Fang, CHEN Xuefeng. Current status, challenges and opportunities of civil aero-engine diagnostics & health management Ⅱ: Comprehensive off-board diagnosis, life management and intelligent condition based MRO [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(9): 625574-625574.
[4]	ZHAO Kun, LIANG Junbiao, Ivan BELYAEV, Victor KOPIEV, Gareth BENNETT. Review of civil airplane landing gear noise study and its control approaches [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 26996-026996.
[5]	DU Xiaoqiong, LI Bin, LUO Linyin. Braking vibration behavior of high strut landing gear of amphibious aircraft [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 526199-526199.
[6]	LIU Xiaochuan, LIU Chongchong, MOU Rangke. Research progress on shimmy dynamics of aircraft landing gear systems [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 527063-527063.
[7]	LI Yueming, LI Xiaoyun, CHAI Yijun, YANG Xiongwei. Dynamic response analysis of nose landing gear in aircraft new towing and taxiing mode [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 526915-526915.
[8]	LI Yueming, LI Xiaoyun, CHAI Yijun, YANG Xiongwei. Dynamic response analysis of nose landing gear in aircraft new towing and taxiing mode [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(6): 526915-526915.
[9]	YUE Caixu, ZHANG Juntao, LIU Xianli, CHEN Zhitao, Steven Y. LIANG, Lihui WANG. Research progress on machining deformation of thin-walled parts in milling process [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(4): 525164-525164.
[10]	YAN Rong, HE Yiwen, LI Kaixiang, LI Peng, MU Rangke, SHI Aiming. Improved formula for prediction of self-sustained oscillation frequencies of bay-opening cabin with landing gear [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(12): 226140-226140.
[11]	YUAN Li, WANG Shuyi. A review on development of intelligent health management technology for spacecraft control systems [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(4): 525044-525044.
[12]	DONG Leiting, ZHOU Xuan, ZHAO Fubin, HE Shuangxin, LU Zhiyuan, FENG Jianmin. Key technologies for modeling and simulation of airframe digital twin [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(3): 23981-023981.
[13]	MENG Songhe, YE Yumei, YANG Qiang, HUANG Zhen, XIE Weihua. Digital twin and its aerospace applications [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(9): 23615-023615.
[14]	ZHANG Lixin, ZHONG Shunlu, LIU Xiaodong, FU Huanbing, DUI Hongna, LIU Dongliang, JING Luyun, MOU Binjie, SHI Shanglu. Development and application of strength design technology of high performance fighter [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(6): 523480-523480.
[15]	YANG Yixin, YIN Yin, NIE Hong, WEI Xiaohui. Strut locking mechanism design for landing gear based on bifurcation theory [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(11): 223958-223958.

Application of digital twin⁃based aircraft landing gear health management technology

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 24

References 36

Related Articles 15

Recommended Articles

Metrics

Comments