基于故障逻辑的民机液压状态监控与故障诊断

doi:10.12305/j.issn.1001-506X.2025.03.16

摘要/Abstract

摘要：

当前民用飞机的监测数据难以有效应用于状态监测与故障诊断，限制了其安全性和可靠性的提升。为此，本文提出一种基于液压系统部件设计与监测数据的决策树模型，用于实现液压系统运行状态的监控；同时提出一种基于故障逻辑与运行数据的迁移学习模型，用于故障诊断与定位，以提升状态监控能力与故障诊断效率。首先，分析液压系统原理，依据机组操作手册(flight crew operating manual, FCOM)额定参数与监测数据建立运行监控指标，采用决策树模型监控液压系统的运行状态；随后通过故障形成条件梳理成逻辑图，结合逻辑图的输入信号参数采集快速存取记录器(quick access recorder, QAR)数据，开发迁移学习模型实现故障诊断与定位。最后以某型国产民机液压低压故障为例，验证了所提方法的应用效果。结果表明，该运行状态监控方法能有效量化液压系统状态，故障诊断方法则能高效识别故障原因。

关键词: 状态监控, 故障诊断与定位, 逻辑图, 监测参数, 迁移学习

Abstract:

Current monitoring data from civil aircraft are difficult to effectively apply to condition monitoring and fault diagnosis, which limits improvements in safety and reliability. To address this, this paper proposes a decision tree model based on hydraulic system component design and monitoring data to achieve operational condition monitoring of the hydraulic system. Additionally, a transfer learning model based on fault logic and operational data is proposed for fault diagnosis and localization, aiming to enhance condition monitoring capabilities and fault diagnosis efficiency. First, the principles of the hydraulic system are analyzed, and operational monitoring indicators are established based on rated parameters from the Flight Crew Operating Manual (FCOM) and monitoring data, with a decision tree model employed to monitor the hydraulic system's operational condition. Subsequently, fault formation conditions are organized into a logic diagram, and data from the Quick Access Recorder (QAR) are collected in conjunction with the input signal parameters of the logic diagram to develop a transfer learning model for fault diagnosis and localization. Finally, the proposed methods are validated using a case study of a hydraulic low-pressure fault in a specific type of domestically produced civil aircraft. The results demonstrate that the condition monitoring method effectively quantifies the hydraulic system's operational state, while the fault diagnosis method efficiently identifies the causes of faults.

Key words: state monitoring, fault diagnosis and localization, logic diagram, monitoring parameters, transfer learning

中图分类号:

V267

冯蕴雯, 潘维煌, 路成, 刘佳奇. 基于故障逻辑的民机液压状态监控与故障诊断[J]. 系统工程与电子技术, 2025, 47(3): 842-854.

Yunwen FENG, Weihuang PAN, Cheng LU, Jiaqi LIU. Civil aircraft hydraulic state monitoring and fault diagnosis based on fault logic[J]. Systems Engineering and Electronics, 2025, 47(3): 842-854.

图/表 15

图1

表1

图2

图3

图4

图5

图6

表2

表3

图7

表4

图8

表5

图9

图10

参考文献 31

1	冯蕴雯, 刘佳奇, 潘维煌, 等. 民用飞机运行可靠性研究进展[J]. 国防科技大学学报, 2023, 45 (4): 66- 93.
	FENG Y W , LIU J Q , PAN W H , et al. Research progress of operational reliability of civil aircraft[J]. Journal of National University of Defense Technology, 2023, 45 (4): 66- 93.
2	PAN W H , FENG Y W , LIU J Q , et al. Operation reliability monitoring towards fault diagnosis of airplane hydraulic system using quick access recorder flight data[J]. Measurement Science and Technology, 2023, 34, 055111. doi: 10.1088/1361-6501/acb83c
3	PAN W H , FENG Y W , LIU J Q , et al. Analyzing the operation reliability of aeroengine using quick access recorder flight data[J]. Reliability Engineering & System Safety, 2023, 235, 109193.
4	LEE H , LIM H J , CHATTOPADHYAY A . Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft[J]. Neural Computing and Applications, 2021, 33, 3235- 3250. doi: 10.1007/s00521-020-05186-x
5	BALAKRISHNAN N , DEVASIGAMANI A I , ANUPAMA K R , et al. Aero-engine health monitoring with real flight data using whale optimization algorithm based artificial neural network technique[J]. Optical Memory and Neural Networks, 2021, 30, 80- 96. doi: 10.3103/S1060992X21010094
6	LIU Z C , SHAO T P , YIN L X , et al. Local structural health monitoring system in aircraft based on fiber Bragg grating array[J]. Results in Optics, 2023, 11, 100393. doi: 10.1016/j.rio.2023.100393
7	WANG Y , QIU L , LUO Y J , et al. A piezoelectric sensor network with shared signal transmission wires for structural health monitoring of aircraft smart skin[J]. Mechanical Systems and Signal Processing, 2020, 141, 106730. doi: 10.1016/j.ymssp.2020.106730
8	曹明, 黄金泉, 周健, 等. 民用航空发动机故障诊断与健康管理现状、挑战与机遇Ⅰ: 气路、机械和FADEC系统故障诊断与预测[J]. 航空学报, 2022, 43 (9): 625573.
	CAO M , HUANG J Q , ZHOU J , et al. 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.
9	林京, 张博瑶, 张大义, 等. 航空燃气涡轮发动机故障诊断研究现状与展望[J]. 航空学报, 2022, 43 (8): 626565.
	LIN J , ZHANG B Y , ZHANG D Y , et al. Research status and prospect of fault diagnosis for gas turbine aeroengine[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43 (8): 626565.
10	AHMED U , ALI F , JENNIONS I . Acoustic monitoring of an aircraft auxiliary power unit[J]. ISA Transactions, 2023, 137, 670- 691. doi: 10.1016/j.isatra.2023.01.014
11	贾宝惠, 姜番, 王玉鑫, 等. 基于民机维修文本数据的故障诊断方法[J]. 航空学报, 2023, 44 (5): 326598.
	JIA B H , JIANG F , WANG Y X , et al. Fault diagnosis method based on civil aircraft maintenance text data[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44 (5): 326598.
12	聂同攀, 曾继炎, 程玉杰, 等. 面向飞机电源系统故障诊断的知识图谱构建技术及应用[J]. 航空学报, 2022, 43 (8): 625499.
	NIE T P , ZENG J Y , CHENG Y J , et al. Knowledge graph construction technology and its application in aircraft power system fault diagnosis[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43 (8): 625499.
13	DONG Y T , JIANG H K , MU M Z , et al. Multi-sensor data fusion-enabled lightweight convolutional double regularization contrast transformer for aerospace bearing small samples fault diagnosis[J]. Advanced Engineering Informatics, 2024, 62, 102573. doi: 10.1016/j.aei.2024.102573
14	DONG Y T , JIANG H K , JIANG W X , et al. Dynamic normalization supervised contrastive network with multiscale compound attention mechanism for gearbox imbalanced fault diagnosis[J]. Advanced Engineering Informatics, 2024, 133, 108098.
15	WANG S Q , LIAN G G , CHENG C , et al. A novel method of rolling bearings fault diagnosis based on singular spectrum decomposition and optimized stochastic configuration network[J]. Neurocomputing, 2024, 574, 127278. doi: 10.1016/j.neucom.2024.127278
16	KOSOVA F , UNVER H O . A digital twin framework for aircraft hydraulic systems failure detection using machine learning techniques[J]. Proc.of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2023, 237 (7): 1563- 1580. doi: 10.1177/09544062221132697
17	YAN H S , SUN J Z , ZUO H F . Anomaly detection based on multivariate data for the aircraft hydraulic system[J]. Proceedings of the Institution of Mechanical Engineers Part Ⅰ-Journal of Systems and Control Engineering, 2020, 235 (5): 593- 605.
18	YU Y , HAMID R K , SHI P M , et al. A new multi-source information domain adaption network based on domain attributes and features transfer for cross-domain fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 211, 111194. doi: 10.1016/j.ymssp.2024.111194
19	ARATHI A. Remaining useful life prediction of aircraft engines based on transfer learning[D]. Gainesville: Virginia State University, 2022.
20	HUO C R , JIANG Q S , SHEN Y H , et al. Enhanced transfer learning method for rolling bearing fault diagnosis based on linear superposition network[J]. Engineering Applications of Artificial Intelligence, 2023, 121, 105970. doi: 10.1016/j.engappai.2023.105970
21	HUO C R , JIANG Q S , SHEN Y H , et al. A class-level matching unsupervised transfer learning network for rolling bearing fault diagnosis under various working conditions[J]. Applied Soft Computing, 2023, 146, 110739. doi: 10.1016/j.asoc.2023.110739
22	AIRIN D. Data-driven methods for probabilistic fault diagnosis in multirotor aircraft[D]. New York: Rensselaer Polytechnic Institute, 2022.
23	SAKIB A Z. Pushing the boundaries of sparse sensor array based structural health monitoring via physics-informed deep learning[D]. Raleigh: North Carolina State University, 2022.
24	LIU D , ZHONG S S , LIN L , et al. Feature-level SMOTE: augmenting fault samples in learnable feature space for imbalanced fault diagnosis of gas turbines[J]. Expert Systems with Applications, 2024, 238, 122023. doi: 10.1016/j.eswa.2023.122023
25	FREEMAN B. A framework for non-intrusive ocean current turbine rotor blade imbalance fault detection[D]. Florida: Florida Atlantic University, 2022.
26	AMRUTHNATH N. Embedded fault class detection methodology for condition-based machine monitoring and predictive maintenance[D]. Kalamazoo: Western Michigan University, 2019.
27	CHEN T, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proc. of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785-794.
28	MA L M , JIANG B , XIAO L F , et al. Digital twin-assisted enhanced meta-transfer learning for rolling bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 200, 110490. doi: 10.1016/j.ymssp.2023.110490
29	WU Z H , JIANG H K , LIU S W , et al. Conditional distribution-guided adversarial transfer learning network with multi-source domains for rolling bearing fault diagnosis[J]. Advanced Engineering Informatics, 2023, 56, 101993. doi: 10.1016/j.aei.2023.101993
30	PAN S J , YANG Q . A survey on transfer learning[J]. IEEE Trans.on Knowledge and Data Engineering, 2009, 22 (10): 1345- 1359.
31	李航. 机器学习方法[M]. 北京: 清华大学出版社, 2024.
	LI H . Machine learning: the art of scientific computing[M]. Beijing: Tsinghua University Press, 2024.

参数	额定运行值	运行范围
P1/psi	3 000	[1 800, 3 300]
T1/℃	30	[-40, 135]
Q1/%	60	[6, 100]

序号	P1/psi	Q1/%	T1/℃
1	3 057	50.9	16.3
2	3 057	50.9	16.3
3	3 058	50.9	16
4	3 058	50.9	16
5	3 061	50.9	16

序号	P1/psi	Q1/%	T1/℃	Cos	OR
1	0.262 5	0.504 2	0.181 5	0.895 6	1
2	0.236 2	0.504 2	0.181 5	0.876 9	1
3	0.210 0	0.504 2	0.181 5	0.856 1	1
4	0.183 7	0.504 2	0.181 5	0.833 0	0
5	0.157 5	0.504 2	0.181 5	0.807 6	0

序号	P1/psi	Q1/%	T1/℃
131	1 908	53.4	28.5
132	1 868	53.4	28.5
133	1 828	53.4	28.5
134	1 788	53.4	28.5
135	1 748	53.4	28.5
136	1 708	53.4	28.5
137	1 668	53.4	28.5
138	1 628	53.4	28.5
139	1 588	53.4	28.5
140	1 548	53.4	28.5

序号	EDP_low	ACMP_low	HYD_P_1	Eng	ACMP_E	ACMP_ON	COUNT_ACMP_ON	Plane_stats	Plane_V	COUNT_Fault_time	classification
1	NOT-LOW	LOW	3 036	57.9	OFF	OFF	0	GND	0	0	NO
2	NOT-LOW	LOW	3 027	52.9	OFF	OFF	0	GND	0	0	NO
3	NOT-LOW	LOW	3 032	48.7	OFF	OFF	0	GND	0	0	NO
4	LOW	LOW	3 061	95.8	OFF	OFF	0	GND	0	0	NO
5	LOW	LOW	3 061	95.9	OFF	OFF	0	GND	0	0	NO
6	LOW	LOW	3 061	95.9	OFF	OFF	0	GND	0	1	Fault1
7	LOW	LOW	3 061	95.9	OFF	OFF	0	GND	0	1	Fault1
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
38 682	LOW	LOW	1 750	0	ON	ON	1	AIR	268.5	1	Fault92
38 725	LOW	LOW	1 750	96	ON	ON	1	AIR	268.5	1	Fault93