基于机理增强条件生成对抗的民机运行可靠性评估方法

doi:10.7527/S1000-6893.2025.32483

Abstract

Abstract:

To address the scarcity of abnormal samples and the challenges in operational reliability modeling for civil aircraft， this paper proposes an operational reliability assessment method based on a Mechanism-Enhanced Conditional Generative Adversarial Network （ME-CGAN）. Within the ME-CGAN framework， CGAN is employed to generate failure data samples. System failure mechanisms are analyzed to construct a fault logic diagram， which associates faults with Quick Access Recorder （QAR） parameters. A Multi-Layer Perceptron （MLP） is then utilized to establish a logical verification model for operational data. This logical verification model is placed after the CGAN discriminator to perform anomaly validation on the generated samples using fault logic， while also providing a new backpropagation mechanism for network hyperparameter optimization. The engineering applicability of the ME-CGAN method is demonstrated through two case studies involving the LG lever disagreement and HYD 1 ACMP failure. Moreover， the modeling and simulation performance of the ME-CGAN method is evaluated through comparisons with various mathematical approaches. Experimental results indicate that the ME-CGAN method achieves high efficiency in generating failure samples and can effectively enhance the accuracy of operational reliability modeling and solution processes for civil aircraft.

Key words: civil aircraft, fault logic graph, failure mechanism, conditional generative adversarial network, operational reliability

CLC Number:

V240.2

Yunwen FENG, Wanyi LIU, Qianyun KE, Cheng LU, Rui WANG. Operational reliability evaluation method for civil aircraft based on mechanism-enhanced conditional generative adversarial[J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(6): 232483.

Figures/Tables 27

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 1

Table 2

Fig.8

Fig.9

Fig.10

Table 3

Fig.11

Fig.12

Fig.13

Table 4

Fig.14

Table 5

Fig.15

Table 6

Fig.16

Table 7

Fig.17

Fig.18

Fig.19

Table 8

References 29

[1]	陈保家，邱光银，肖文荣，等. 航空发动机转子轴承运行可靠性评估方法［J］. 西安交通大学学报， 2018， 52（10）： 41-48.
	CHEN B J， QIU G Y， XIAO W R， et al. An evaluation method of operational reliability for aero-engine rotor bearings［J］. Journal of Xi’an Jiaotong University， 2018， 52（10）： 41-48 （in Chinese）.
[2]	LIU H， SUN Y C， WANG X Y， et al. Operating condition feature representation-based Fourier graph network for civil aircraft state estimation［J］. Reliability Engineering & System Safety， 2025， 261： 111085.
[3]	DY L R I， MOTT J H. Evaluating near midair collision reporting systems using aircraft surveillance data： A case study at a university airport［J］. Journal of Safety Research， 2024， 91： 201-209.
[4]	SONG Z C， FENG Y W， LU C. Superimposable neural network for health monitoring of aircraft hydraulic system［J］. Engineering Failure Analysis， 2024， 160： 108063.
[5]	FU X Y， LUO H， ZHONG S S， et al. Aircraft engine fault detection based on grouped convolutional denoising autoencoders［J］. Chinese Journal of Aeronautics， 2019， 32（2）： 296-307.
[6]	汪磊，张楠，高杉. 基于QAR数据与关联规则的着陆阶段超限风险评估［J］. 北京航空大学学报， 2025， 51（6）： 1907-1915.
	WANG L， ZHANG N， GAO S. Risk assessment of landing phase exceedance based on QAR data and association rule［J］. Journal of Beijing University of Aeronautics and Astronautics， 2025， 51（6）： 1907-1915 （in Chinese）.
[7]	刘佳奇，冯蕴雯，路成，等. 基于智能神经网络的航空发动机运行安全分析［J］. 航空学报， 2022， 43（9）： 625375.
	LIU J Q， FENG Y W， LU C， et al. Safety analysis of aero-engine operation based on intelligent neural network［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（9）： 625375 （in Chinese）.
[8]	WANG B， ZOU R Y， MAO J F， et al. Developing an aircraft takeoff mass estimation model based on the hybrid KMI-DNN-BI model using quick access recorder （QAR） data［J］. Aerospace Science and Technology， 2025， 158： 109918.
[9]	MAGRYTA P， PIETRYKOWSKI K. Failure analysis of transmission gear in aircraft opposed piston Diesel engine using FEM method［J］. Engineering Failure Analysis， 2025， 175： 109569.
[10]	LIN C Y， KONG Y， HUANG G Y， et al. Generalization classification regularization generative adversarial network for machinery fault diagnostics under data imbalance［J］. Reliability Engineering & System Safety， 2025， 256： 110791.
[11]	石旭东，蒋贵嘉，张宇，等. 基于联合仿真的飞机空调系统故障影响［J］. 航空学报， 2020， 41（8）： 323647.
	SHI X D， JIANG G J， ZHANG Y， et al. Fault impact of aircraft air conditioning system based on joint simulation［J］. Acta Aeronautica et Astronautica Sinica， 2020， 41（8）： 323647 （in Chinese）.
[12]	PANG H， YU T X， SONG B F. Failure mechanism analysis and reliability assessment of an aircraft slat［J］. Engineering Failure Analysis， 2016， 60： 261-279.
[13]	SHEN X K， FENG K X， XU H M， et al. Reliability analysis of bending fatigue life of hydraulic pipeline［J］. Reliability Engineering & System Safety， 2023， 231： 109019.
[14]	庄子波，张春辉，陈星，等. 基于DCGAN的终端区激光雷达晴空湍流识别［J］. 航空学报， 2024， 45（16）： 329748.
	ZHUANG Z B， ZHANG C H， CHEN X， et al. Clear⁃air turbulence recognition by Doppler⁃wind⁃lidar in terminalarea based on DCGAN［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（16）： 329748 （in Chinese）.
[15]	WANG J， LI R Z， HE C， et al. An inverse design method for supercritical airfoil based on conditional generative models［J］. Chinese Journal of Aeronautics， 2022， 35（3）： 62-74.
[16]	MA Z H， SUN Y W， YIN F L， et al. Few-shot reliability evaluation of tribopairs degradation based on active learning supported generative adversarial network［J］. Engineering Failure Analysis， 2024， 165： 108772.
[17]	DOU Y L， ZHOU Z， WANG R. Dynamic behavior recognition in aerial deployment of multi-segmented foldable-wing drones using variational autoencoders［J］. Chinese Journal of Aeronautics， 2025， 38（6）： 103397.
[18]	甘纪强，王小平. 基于虚拟样本生成的铺丝表面缺陷检测［J］. 航空学报， 2024， 45（1）： 428624.
	GAN J Q， WANG X P. Surface defect detection of fiber placement based on virtual sample generation［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（1）： 428624 （in Chinese）.
[19]	吴明雨，陈志华，邱志明，等. 条件生成对抗网络的翼型反设计方法［J］. 宇航学报， 2023， 44（10）： 1512-1521.
	WU M Y， CHEN Z H， QIU Z M， et al. An inverse design method of airfoil using conditional generative adversarial network［J］. Journal of Astronautics， 2023， 44（10）： 1512-1521 （in Chinese）.
[20]	WANG Z L， XIANG Y Z， ZHANG S Y， et al. Physics-informed springback prediction of 3D aircraft tubes with six-axis free-bending manufacturing［J］. Aerospace Science and Technology， 2024， 147： 109022.
[21]	YANG F， YANG L P， ZHU Y W. A physics-informed deep learning framework for spacecraft pursuit-evasion task assessment［J］. Chinese Journal of Aeronautics， 2024， 37（5）： 363-376.
[22]	LI J W， LONG X Y， DENG X Y， et al. A principled distance-aware uncertainty quantification approach for enhancing the reliability of physics-informed neural network［J］. Reliability Engineering & System Safety， 2024， 245： 109963.
[23]	TOGNI S， NIKOLAIDIS T， SAMPATH S. A combined technique of Kalman filter， artificial neural network and fuzzy logic for gas turbines and signal fault isolation［J］. Chinese Journal of Aeronautics， 2021， 34（2）： 124-135.
[24]	FEI C W， HAN Y J， WEN J R， et al. Deep learning-based modeling method for probabilistic LCF life prediction of turbine blisk［J］. Propulsion and Power Research， 2024， 13（1）： 12-25.
[25]	TENG D， FENG Y W， CHEN J Y， et al. Intelligent vectorial surrogate modeling framework for multi-objective reliability estimation of aerospace engineering structural systems［J］. Chinese Journal of Aeronautics， 2024， 37（12）： 156-173.
[26]	LIAO D， ZHU S P， GAO J W， et al. Energy field intensity approach for probabilistic Notch fatigue assessment under size effect［J］. Chinese Journal of Aeronautics， 2025， 38（2）： 103304.
[27]	GUI J， SUN Z N， WEN Y G， et al. A review on generative adversarial networks： algorithms， theory， and applications［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（4）： 3313-3332.
[28]	于文家，丁世飞. 基于自注意力机制的条件生成对抗网络［J］. 计算机科学， 2021， 48（1）： 241-246.
	YU W J， DING S F. Conditional generative adversarial network based on self-attention mechanism［J］. Computer Science， 2021， 48（1）： 241-246 （in Chinese）.
[29]	ZAREI M， HELLINGA B， IZADPANAH P. Application of Conditional Deep Generative Networks （CGAN） in empirical Bayes estimation of road crash risk and identifying crash hotspots［J］. International Journal of Transportation Science and Technology， 2024， 13： 258-269.

序号	参数名称	参数描述	单位
1	LG Lever Up	起落架手柄收起
2	LG Up	起落架收起
3	LG Lever Dn	起落架手柄放下
4	LG Dn	起落架放下
5	HYD 2 Oil Quantity	2号液压系统油量	%
6	L In Wheel Brake Pressure	左内刹车压力	Pa
7	PACU Retraction Commanded	PACU起落架放下指令
8	Selector Valve Location	选择阀位置
9	Actuating Cylinder Pressure	收放作动筒压力	Pa
10	Scavenge Pressure	回油路压力	Pa
11	Retaining Valve On	单向阀打开
12	LG Uplock Unlocked	起落架上位锁未锁定
13	LG Downlock not Locked	起落架下位锁未解锁
14	T1、T2 Stage	T1、T2阶段
15	L Stage	L阶段
16	Retain Pressure	供油路压力	Pa

模型编号	准确率	精确率	召回率	F₁
1	0.907	0.933	0.965	0.949
2	0.915	0.946	0.967	0.956
3	0.909	0.930	0.952	0.941
4	0.913	0.941	0.952	0.947

生成对抗模型	GAN	CGAN	SA-CGAN	CGAN-EB
生成器结构	MLP-2（240-120-60-16）
判别器结构	MLP-2（160-80-30-2）
其他结构	无	无	自注意力	贝叶斯网络
训练停止轮数	117	97	104	73

抽样规模/10⁴次	平均可靠度	标准差	误差边界
2	0.996 3	0.009 2	±0.007 51
4	0.996 9	0.004 9	±0.004 00
6	0.997 6	0.002 1	±0.001 72
8	0.998 5	0.001 3	±0.001 06
10	0.999 1	0.000 7	±0.005 72

序号	参数名称	参数描述	单位
1	ACMP 1B Commanded	1号系统电动泵工作指令
2	ACMP 1B Cockpit Sw	1号系统电动泵驾驶舱开关
3	ACMP 1B Press Low	1号系统电动泵压力低
4	Airspeed	空速	kt
5	Engine Shutdown 1	1号发动机关闭
6	Landing Gear Status	起落架轮载状态
7	ACMP 1B Contactor	1号系统电动泵通电状态
8	EDP 1A Prs Low	1号系统发动机驱动泵压力低
9	HYD System Pressure 1	1号液压系统压力	psi

Operational reliability evaluation method for civil aircraft based on mechanism-enhanced conditional generative adversarial

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 27

References 29

Related Articles 15

Recommended Articles

Metrics

Comments

网络名称	网络层	神经元数量	激活函数
生成器	隐藏层1	160	ReLU
	隐藏层2	80	ReLU
	隐藏层3	30	ReLU
	输出层	9	Sigmoid
判别器	隐藏层1	200	LeakyReLU
	隐藏层2	100	LeakyReLU
	隐藏层3	40	LeakyReLU
	输出层	2	Sigmoid
逻辑检验器	隐藏层1	24	ReLU
	隐藏层2	12	ReLU
	输出层	2	Sigmoid

生成对抗模型	GAN	CGAN	SA-CGAN	CGAN-EB
生成器结构	MLP-2（160-80-30-9）
判别器结构	MLP-2（200-100-40-2）
其他结构	无	无	自注意力	贝叶斯网络
训练停止轮数	92	67	43	59

抽样规模/（10⁴次）	平均可靠度	标准差	误差边界
1	0.986 3	0.012 9	±0.010 53
2	0.982 6	0.007 1	±0.005 79
3	0.990 2	0.003 3	±0.002 69
4	0.991 5	0.000 9	±0.000 74
5	0.991 7	0.000 6	±0.000 49

[1]	Qulong WEI, Lihong JIANG, Zheng LIU, Lin ZHU, Lianhai FAN, Guangang WANG, Mingjie ZHAO, Zhenghua GUO. Lattice structure and mechanical properties of TPMS prepared by selective laser melting [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 430593-430593.
[2]	Junqiang WU, Zhi WEI, Yang LIU, Min ZHONG, Fujun YANG, Yonggang YU. Civil aircraft standard model system and construction of aerodynamic subject database [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(24): 132030-132030.
[3]	Kefeng ZHENG, Wenping SONG, Han NIE, Yulin DING, Jianling QIAO, Qing CHEN, Yiheng WANG, Ke SONG, Keshi ZHANG. Natural laminar flow wing design method for supersonic civil aircraft considering full-aircraft sonic-boom characteristics [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531214-531214.
[4]	Chao YANG, Yuting TAN, Wei WANG, Yan ZHAO, Xiongqing YU. Multidisciplinary optimization with low-boom design for supersonic civil aircraft conceptual design [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531457-531457.
[5]	Linxuan YANG, Huicai MA, Liping PANG. Design and performance simulation of environmental control system for supersonic civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531585-531585.
[6]	Tianyu GONG, Chengjun SHAN, Lizhe YI, Yaosong LONG, Zhongtao CHENG. Impact of engine geometric parameters on sonic boom characteristics of supersonic civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531592-531592.
[7]	Liwen ZHANG, Zhonghua HAN, Keshi ZHANG, Ke SONG, Wenping SONG. High-fidelity numerical simulation of near-/mid-field sonic boom propagation using a space-marching method for supersonic civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531935-531935.
[8]	Wei WANG, Junfu LI, Fengxue QIAN, Yuting TAN, Yan ZHAO, Bowen ZHAO, Qing CHEN, Ke SONG. Wind tunnel test of low sonic boom high efficiency layout for supersonic civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531941-531941.
[9]	Zuotai LI, Shusheng CHEN, Shiyi JIN, Zhenghong GAO, Weiguo ZHOU. Optimization design and data mining for supersonic civil aircraft based on sonic boom efficient prediction [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531920-531920.
[10]	Qing CHEN, Zhonghua HAN, Keshi ZHANG, Jianling QIAO, Yulin DING, Wenping SONG. A full-carpet design optimization method for low-boom supersonic civil aircraft configuration [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531909-531909.
[11]	Hui ZHANG, Junqiang AI, Kun QIN, Xiangxi TANG, Jun JI. Wind tunnel test for thrust characteristics of supersonic ejector exhaust system [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531934-531934.
[12]	Zhenrong LIAO, Junfu LI, Bowen ZHAO, Ming ZHANG, Lu XIE, Zhonghua HAN, Mengqi AI. Broad-speed-range wing design of supersonic civil aircraft based on engineering [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(20): 531915-531915.
[13]	Xulong XI, Xiaochuan LIU, Chunyu BAI, Hezhao HAN, Xinyue ZHANG, Xiaocheng LI, Pu XUE, Rangke MU, Xianfeng YANG. Comparison of crash response between fuselage section and full-scale civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(15): 231597-231597.
[14]	Xianchao MENG, Jun TAO. An airfoil inverse design method based on target testing conditional generative adversarial network [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631182-631182.
[15]	Junfu LI, Qing CHEN, Wei WANG, Zhonghua HAN, Yuting TAN, Yulin DING, Lu XIE, Jianling QIAO, Ke SONG, Junqiang AI. Design of low sonic boom high efficiency layout for advanced supersonic civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(6): 629613-629613.