基于数据合成的飞行器结构损伤状态快速识别方法

doi:10.12305/j.issn.1001-506X.2024.11.19

摘要/Abstract

摘要：

针对当前飞行器结构健康监测过程中存在的识别流程复杂、识别准确度低的问题, 提出一种基于数据合成的飞行器结构损伤状态快速识别方法。建立数字孪生结构损伤快速识别模型构建流程, 构建飞行器结构数字模型。基于数据合成思想, 提出一种对传感器数据的可信度评价方法, 建立具有可解释性的生成-判别模型, 解决了因样本数据不足导致的学习准确率低的问题。引入分类边界模糊化方法, 使用判别模型确定模糊化区域以提升神经网络识别的稳定性。最后, 以某无人机为例, 对所提识别方法进行验证。结果表明, 该方法能够高效构建结构损伤状态数据库并提升识别泛化能力和稳定性, 对损伤状态的识别准确率超过99%。

关键词: 数字孪生, 结构健康监测, 损伤检测, 数据合成, 神经网络

Abstract:

In response to the complexity of the identification process and the low accuracy of identification in the current health monitoring process of aircraft structures, a rapid identification method for aircraft structural damage patterns based on data synthesis is proposed. A digital twin structure damage rapid identification model construction process is established to construct a digital model of aircraft structure. Based on the idea of data synthesis, a credibility evaluation method for sensor data is proposed, and an interpretable generative-discriminative model is established to solve the problem of low learning accuracy due to insufficient sample data. The method of fuzzy classification boundary is introduced, and the discriminative model is used to determine the fuzzy area to improve the stability of neural network identification. Finally, the proposed identification method is verified with a certain drone as an example. The results show that this method can efficiently build a structural damage pattern database and improve the generalization ability and stability of identification, with an identification accuracy rate of over 99% for damage patterns.

Key words: digital twin, structural health monitoring, damage detection, data synthesis, neural network

中图分类号:

王浩渊, 粟华, 李鹏, 龚春林. 基于数据合成的飞行器结构损伤状态快速识别方法[J]. 系统工程与电子技术, 2024, 46(11): 3774-3783.

Haoyuan WANG, Hua SU, Peng LI, Chunlin GONG. Rapid identification method for aircraft structural damage patterns based on data synthesis[J]. Systems Engineering and Electronics, 2024, 46(11): 3774-3783.

图/表 17

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

表1

表2

表3

表4

参考文献 33

1	张卫红, 唐长红. 航空航天装备的轻量化: 挑战与未来[J]. 航空学报, 2024, 45 (5): 9-15, 4.
	ZHANG W H , TANG C H . Lightweighting of aerospace and aeronautical equipment: challenges and perspectives[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45 (5): 9-15, 4.
2	王博, 郝鹏, 田阔, 等. 航空航天结构轻量化设计与实验方法研究进展[J]. 宇航学报, 2023, 44 (4): 596- 606.
	WANG B , HAO P , TIAN K , et al. Research progress on lightweight design and experimental methods for aerospace structures[J]. Journal of Astronautics, 2023, 44 (4): 596- 606.
3	VAN D W T , DENG Q , SANTOS B F . Robust long-term aircraft heavy maintenance check scheduling optimization under uncertainty[J]. Computers & Operations Research, 2022, 141, 105667.
4	YANG Z Y , YANG H J , TIAN T , et al. A review in guided-ultrasonic-wave-based structural health monitoring: from fundamental theory to machine learning techniques[J]. Ultrasonics, 2023, 133, 107014. doi: 10.1016/j.ultras.2023.107014
5	FIGUEIREDO E , BROWNJOHN J . Three decades of statistical pattern recognition paradigm for SHM of bridges[J]. Structural Health Monitoring, 2022, 21 (6): 3018- 3054. doi: 10.1177/14759217221075241
6	MONTAZERIAN H , RASHIDI A . Integrated sensors in advanced composites: a critical review[J]. Critical Reviews in Solid State and Materials Sciences, 2020, 45 (3): 187- 238. doi: 10.1080/10408436.2019.1588705
7	JU M , DOU Z , LI J W , et al. Piezoelectric materials and sensors for structural health monitoring: fundamental aspects, current status, and future perspectives[J]. Sensors, 2023, 23 (1): 543. doi: 10.3390/s23010543
8	SIMON J , KURIN T , MOLL J , et al. Embedded radar networks for damage detection in wind turbine blades: validation in a full-scale fatigue test[J]. Structural Health Monitoring, 2023, 22 (6): 4252- 4263. doi: 10.1177/14759217231152815
9	何存富, 郑明方, 吕炎, 等. 超声导波检测技术的发展、应用与挑战[J]. 仪器仪表学报, 2016, 37 (8): 1713- 1735. doi: 10.3969/j.issn.0254-3087.2016.08.004
	HE C F , ZHENG M F , LYU Y , et al. Development, applications and challenges in ultrasonic guided waves testing technology[J]. Chinese Journal of Scientific Instrument, 2016, 37 (8): 1713- 1735. doi: 10.3969/j.issn.0254-3087.2016.08.004
10	REN Y Q , QIU L , YUAN S F , et al. A diagnostic imaging approach for online characterization of multi-impact in aircraft composite structures based on a scanning spatial-wavenumber filter of guided wave[J]. Mechanical Systems and Signal Processing, 2017, 90, 44- 63. doi: 10.1016/j.ymssp.2016.12.005
11	REN B Y , LISSENDEN C J . PVDF multielement lamb wave sensor for structural health monitoring[J]. IEEE Trans.on Ultrasonics, Ferroelectrics, and Frequency Control, 2016, 63 (1): 178- 185. doi: 10.1109/TUFFC.2015.2496423
12	PAK C G . Wing shape sensing from measured strain[J]. American Institute of Aeronautics and Astronautics, 2016, 54 (3): 1068- 1077. doi: 10.2514/1.J053986
13	杜飞, 徐超, 鱼则行. 可重复使用运载器结构健康监测技术研究进展[J]. 宇航学报, 2019, 40 (10): 1177- 1186. doi: 10.3873/j.issn.1000-1328.2019.10.008
	DU F , XU C , YU Z X . Research progress on structural health monitoring technology for reusable launch vehicles[J]. Journal of Astronautics, 2019, 40 (10): 1177- 1186. doi: 10.3873/j.issn.1000-1328.2019.10.008
14	梁栋, 袁慎芳, 常琦, 等. 基于黑板协作的多区域冲击监测[J]. 系统工程与电子技术, 2011, 33 (3): 700- 706. doi: 10.3969/j.issn.1001-506X.2011.03.46
	LIANG D , YUAN S F , CHANG Q , et al. Multi-region impact monitoring based on blackboard coordination[J]. Systems Engineering and Electronics, 2011, 33 (3): 700- 706. doi: 10.3969/j.issn.1001-506X.2011.03.46
15	ERIC U . Fiber optic smart structures[J]. Proceedings of the IEEE, 1996, 84 (6): 884- 894. doi: 10.1109/5.503144
16	李鹏, 潘凯, 刘小川. 美国空军机体数字孪生计划的回顾与启示[J]. 航空科学技术, 2020, 31 (9): 1- 10.
	LI P , PAN K , LIU X C . Retrospect and enlightenment of the AFRL airframe digital twin program[J]. Aeronautical Science & Technology, 2020, 31 (9): 1- 10.
17	LI L N , SOHAIB A , ANDREW W , et al. Digital twin in aerospace industry: a gentle introduction[J]. IEEE Access, 2021, 10, 9543- 9562.
18	TAO F , XIAO B , QI Q L , et al. Digital twin modeling[J]. Journal of Manufacturing Systems, 2022, 64, 372- 389. doi: 10.1016/j.jmsy.2022.06.015
19	DANG H V , TATIPAMULA M , NGUYEN H X . Cloud-based digital twinning for structural health monitoring using deep learning[J]. IEEE Trans.on Industrial Informatics, 2021, 18 (6): 3820- 3830.
20	YE Y M , YANG Q A , YANG F , et al. Digital twin for the structural health management of reusable spacecraft: a case study[J]. Engineering Fracture Mechanics, 2020, 234, 107076. doi: 10.1016/j.engfracmech.2020.107076
21	KAPTEYN M G , KNEZEVIC D J , HUYNH D B P , et al. Data-driven physics-based digital twins via a library of component-based reduced-order models[J]. International Journal for Numerical Methods in Engineering, 2022, 123 (13): 2986- 3003. doi: 10.1002/nme.6423
22	王子一, 粟华, 龚春林, 等. 数字孪生机翼损伤模式快速识别与监测方法[J]. 航空动力学报, 2024, 39 (6): 112- 120.
	WANG Z Y , SU H , GONG C L , et al. Rapid identification and monitors of digital twin wings damage patterns[J]. Journal of Aerospace Power, 2024, 39 (6): 112- 120.
23	WANG J Y , LIU K X , ZHANG Y C , et al. Recent advances of few-shot learning methods and applications[J]. Science China Technological Sciences, 2023, 66 (4): 920- 944. doi: 10.1007/s11431-022-2133-1
24	刘建伟, 刘媛, 罗雄麟. 半监督学习方法[J]. 计算机学报, 2015, 38 (8): 1592- 1617.
	LIU J W , LIU Y , LUO X L . Semi-supervised learning methods[J]. Chinese Journal of Computers, 2015, 38 (8): 1592- 1617.
25	RAMIREZ-SANZ J M , MAESTRO- PRIETO J A , ARNAIZ-GONZALEZ A , et al. Semi-supervised learning for industrial fault detection and diagnosis: a systemic review[J]. ISA Transactions, 2023, 143, 255- 270. doi: 10.1016/j.isatra.2023.09.027
26	LIU B, WANG X D, DIXIT M, et al. Feature space transfer for data augmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 9090-9098.
27	王钰清, 陆文凯, 刘金林, 等. 基于数据增广和CNN的地震随机噪声压制[J]. 地球物理学报, 2019, 62 (1): 421- 433.
	WANG Y Q , LU W K , LIU J L , et al. Random seismic noise attenuation based on data augmentation and CNN[J]. Chinese Journal of Geophysics, 2019, 62 (1): 421- 433.
28	GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proc. of the Advances in Neural Information Processing Systems, 2014: 2672-2680.
29	JIANG Y F, CHANG S Y, WANG Z Y. TransGAN: two pure transformers can make one strong GAN, and that can scale up[C]//Proc. of the Advances in Neural Information Processing Systems, 2021: 14745-14758.
30	王鹏, 杨妹, 祝建成, 等. 面向数字孪生的动态数据驱动建模与仿真方法[J]. 系统工程与电子技术, 2020, 42 (12): 2779- 2786. doi: 10.3969/j.issn.1001-506X.2020.12.14
	WANG P , YANG M , ZHU J C , et al. Dynamic data driven modeling and simulation method for digital twin[J]. Systems Engineering and Electronics, 2020, 42 (12): 2779- 2786. doi: 10.3969/j.issn.1001-506X.2020.12.14
31	方伟光, 聂兆伟, 刘宸宁, 等. 数字孪生驱动的武器装备智能保障技术研究[J]. 系统工程与电子技术, 2023, 45 (4): 1247- 1260. doi: 10.12305/j.issn.1001-506X.2023.04.35
	FANG W G , NIE Z W , LIU C N , et al. Research on digital twin driven intelligent weaponry support technology[J]. Systems Engineering and Electronics, 2023, 45 (4): 1247- 1260. doi: 10.12305/j.issn.1001-506X.2023.04.35
32	韩忠华. Kriging模型及代理优化算法研究进展[J]. 航空学报, 2016, 37 (11): 3197- 3225.
	HAN Z H . Kriging surrogate model and its application to design optimization: a review of recent progress[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37 (11): 3197- 3225.
33	ALTMAN N S . An introduction to kernel and nearest-neighbor nonparametric regression[J]. The American Statistician, 1992, 46 (3): 175- 185. doi: 10.1080/00031305.1992.10475879

区块	0、1等级边界	1、2等级边界	2、3等级边界	3、4等级边界
1	0.204 5	0.405 8	0.604 3	0.797 3
2	0.208 5	0.405 7	0.604 6	0.798 2
3	0.207 8	0.402 1	0.599 6	0.799 7
4	0.205 4	0.401 8	0.599 6	0.799 3
5	0.216 8	0.405 2	0.601 7	0.797 9
6	0.204 3	0.401 5	0.600 9	0.798 8

区块	0、1等级边界	1、2等级边界	2、3等级边界	3、4等级边界
1	0.019 2	0.034 4	0.044 6	0.049 5
2	0.034 2	0.049 3	0.054 2	0.055 5
3	0.054 4	0.057 1	0.057 3	0.057 7
4	0.054 1	0.057 2	0.057 7	0.057 6
5	0.045 9	0.055 2	0.056 2	0.057 0
6	0.040 1	0.048 3	0.051 5	0.053 8

区块	无边界模糊化识别准确率	使用边界模糊化识别准确率
1	97.2	99.2
2	94.3	99.6
3	94.0	99.4
4	93.2	99.2
5	96.7	99.8
6	97.1	100.0

区块	无边界模糊化识别准确率	使用边界模糊化识别准确率
1	99.7	100.0
2	99.0	100.0
3	98.1	100.0
4	96.3	100.0
5	96.9	100.0
6	99.3	100.0

[1]	张天骐, 杨宗方, 邹涵, 马焜然. 基于编码矩阵估计的极化码参数盲识别算法[J]. 系统工程与电子技术, 2024, 46(9): 3221-3230.
[2]	王磊, 张劲, 叶秋炫. LDACS系统基于循环谱和残差神经网络的频谱感知方法[J]. 系统工程与电子技术, 2024, 46(9): 3231-3238.
[3]	张瑞斌, 朱梦韬, 李云杰. 对调制识别网络隐身的雷达发射信号生成方法[J]. 系统工程与电子技术, 2024, 46(7): 2256-2268.
[4]	齐兵, 程建华, 赵砚驰, 汪籽粒. 基于微形变分析的电容式MEMS加速度计温漂误差精密估计方法[J]. 系统工程与电子技术, 2024, 46(7): 2437-2445.
[5]	吴巍屹, 贾云献, 姜相争, 史宪铭, 刘洁, 刘彬, 董恩志, 朱曦. 面向阶段任务的携行器材品种确定方法[J]. 系统工程与电子技术, 2024, 46(6): 2054-2064.
[6]	庆豪, 方志耕, 王育红, 邱玺睿. 基于灰色-神经网络的民机需求组合预测[J]. 系统工程与电子技术, 2024, 46(5): 1665-1672.
[7]	杨宗方, 张天骐, 马焜然, 邹涵. 基于深层神经网络的信道编码类型盲识别[J]. 系统工程与电子技术, 2024, 46(5): 1820-1829.
[8]	何通, 卢青, 周军, 郭宗易. 带有神经网络干扰观测器的视线角约束制导[J]. 系统工程与电子技术, 2024, 46(4): 1372-1382.
[9]	周红进, 宋辉, 范文良, 王苏, 谷东亮. 基于贝叶斯神经网络的船用惯导定位修正方法[J]. 系统工程与电子技术, 2024, 46(4): 1393-1400.
[10]	孟宪鹏, 刘利民, 董健, 王力, 胡文华. 基于双胞循环神经网络的雷达捷变频行为识别[J]. 系统工程与电子技术, 2024, 46(3): 898-905.
[11]	于蕾, 邓秋月, 郑丽颖, 吴昊宇. 二阶逐层特征融合网络的图像超分辨重建[J]. 系统工程与电子技术, 2024, 46(2): 391-400.
[12]	王坤, 段欣然, 陈征, 黎军. 过载和攻击时间约束下的非线性最优制导方法[J]. 系统工程与电子技术, 2024, 46(2): 649-657.
[13]	肖博文, 马泽远, 鲁天宇, 夏群利. 平台式导引头隔离度模型在线辨识方法[J]. 系统工程与电子技术, 2024, 46(11): 3595-3604.
[14]	雷刚, 赖灿辉, 李云舒, 罗炜. 机动发射条件下电子干扰策略快速计算方法[J]. 系统工程与电子技术, 2024, 46(11): 3648-3657.
[15]	崔永生, 詹亚锋, 陈泰伊, 方鑫. 基于DNN的低复杂度联合解调译码迭代同步算法[J]. 系统工程与电子技术, 2024, 46(11): 3893-3900.