融合物理信息与参数动量的民机液压系统油液渗漏预测

冯蕴雯; 潘维煌; 贺延琛; 陈东; 路成

doi:10.13700/j.bh.1001-5965.2025.0537

融合物理信息与参数动量的民机液压系统油液渗漏预测

doi: 10.13700/j.bh.1001-5965.2025.0537

冯蕴雯^{1, 2, ,},
潘维煌^{1, 2},
贺延琛³,
陈东³,
路成^{1, 2}

1.
西北工业大学航空学院，西安 710072
2.
飞行器基础布局全国重点实验室，西安 710072
3.
陆军装备部航空军事代表局驻成都地区航空军事代表室，成都 610036

详细信息

通讯作者:
E-mail：fengyunwen@nwpu.edu.cn

中图分类号: V267
计量
- 文章访问数: 298
- HTML全文浏览量: 207
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2025-08-01
- 录用日期: 2025-09-12
- 网络出版日期: 2025-09-28
- 整期出版日期: 2026-08-31

Fluid leakage prediction for civil aircraft hydraulic systems by fusing physics-informed and parameter momentum

FENG Yunwen^{1, 2
, ,},
PAN Weihuang^{1, 2},
HE Yanchen³,
CHEN Dong³,
LU Cheng^{1, 2}

1.
School of Aeronautics，Northwestern Polytechnical University，Xi’an 710072，China
2.
National Key Laboratory of Aircraft Configuration Design，Xi’an 710072，China
3.
Chengdu Military Representative Office of the Army Aeronautical Department，Chengdu 610036，China

More Information

Corresponding author: E-mail：fengyunwen@nwpu.edu.cn

摘要

摘要:
民机液压系统油液渗漏存在高发性、隐蔽性及潜在的安全风险，需要通过故障预测技术实现视情维修，以达到早期识别和预防的目的。然而，油液渗漏故障预测面临监测参数有限、机载告警粒度粗、航前勤务工作导致油量数据不连续等难题。为此，提出一种融合物理信息与油量参数动量的时序模型，量化油液渗漏发生概率。该模型引入油液热膨胀系数与手册渗漏率作为物理信息约束；通过区分航班内与跨航班模式，构建油量参数动量指标以捕捉因勤务加油而中断的累积趋势；利用时序模型映射油量变化规律，实现对早期微小油液渗漏的预测。以国产民机运行数据开展油液渗漏预测分析，案例表明：所提方法能有效利用机载数据量化油液渗漏在未来一段时间内发生的概率，为液压系统的视情维修与健康管理提供决策支持。
- 液压油液渗漏 /
- 物理信息 /
- 参数动量变化 /
- 时序预测模型 /
- 故障预测
Abstract:
Due to its high frequency, sneaky nature, and possible safety hazards, hydraulic fluid leakage in civil aircraft systems necessitates fault prognostics technology to enable condition-based maintenance for early identification and avoidance. However, leakage fault prognostics faces challenges such as limited monitoring parameters, coarse granularity of onboard alerts, and discontinuity in fluid quantity data caused by pre-flight servicing. In order to estimate the likelihood of leakage occurring, this research suggests a time-series model that combines physics data with fluid amount momentum. The model first introduces physical constraints such as the fluid’s coefficient of thermal expansion and the manual-specified allowable leakage rate. Furthermore, by distinguishing between intra-flight and inter-flight modes, a parameter momentum indicator for fluid quantity is constructed to capture the cumulative trend interrupted by servicing and refueling. Finally, a time-series model is utilized to map the dynamics of the fluid quantity, enabling accurate prediction of early and minor leakages. Leveraging real-world operational data from a domestically produced commercial aircraft, this case study validates the proposed method’s capability to effectively predict the probability of incipient leakage. The approach offers valuable decision support for implementing condition-based maintenance and advancing the health management of the hydraulic system.
- hydraulic fluid leakage /
- physics-informed /
- parameter momentum change /
- time-series prediction model /
- fault prognostics

HTML全文

图 1 2号液压系统示意图

Figure 1. Schematic of hydraulic system 2

下载: 全尺寸图片幻灯片

图 2 油量在飞行中的变化

Figure 2. Fuel quantity changes during flight

下载: 全尺寸图片幻灯片

图 3 基于物理信息约束的时序注意力油液渗漏分析架构

Figure 3. Temporal attention fluid leakage analysis architecture based on physics-informed constrained

下载: 全尺寸图片幻灯片

图 4 提前30 min渗漏预测的模型训练损失

Figure 4. Training loss of model for 30-minute early leakage prediction

下载: 全尺寸图片幻灯片

图 5 提前80 min渗漏预测的模型训练损失

Figure 5. Training loss of model for 80-minute early leakage prediction

下载: 全尺寸图片幻灯片

图 6 提前30 min油液渗漏预测分析结果

Figure 6. Analysis results of 30-minute early fluid leakage prediction

下载: 全尺寸图片幻灯片

图 7 提前80 min油液渗漏预测分析结果

Figure 7. Analysis results of 80-minute early fluid leakage prediction

下载: 全尺寸图片幻灯片

表 1 液压系统油液渗漏案例

Table 1. Hydraulic system fluid leakage cases

序号	飞机注册号	日期	事件简述
1	B-3XX7	2021-07-13	12日温州落地检查发现2号液压系统液压油漏光
2	B-3XX8	2020-07-17	空中出现EICAS告警信息“HYD 2 PRESS LO”“HYD 2 QTY LO”
3	B-6XXA	2022-04-06	航后检查右发下部排气格栅有大量疑似液压油
4	B-6XXE	2022-08-01	航前发现右发EDP漏油
5	B-6XXN	2022-08-01	机务检查发现右发EDP漏油
6	B-6XXT	2023-01-04	机务检查发现右发EDP漏油
7	B-6XXD	2023-03-10	机务报告左发EDP漏油
8	B-3XX6	2023-05-30	机务检查发现右发EDP漏油

下载: 导出CSV

表 2 ARJ21液压系统油液渗漏数据概况

Table 2. Overview of ARJ21 hydraulic system fluid leakage data

序号	飞机注册号	航班架次	是否渗漏
1	B-6XXN	256	是
2	B-6XXM	270	否
3	B-3XX6	57	是
4	B-3XX1	30	否
5	B-3XX7	32	是
6	B-6XXA	10	否

下载: 导出CSV

表 3 各模型评价指标

Table 3. Evaluation metrics of each model

模型		AUC	F₁分数	精确率	召回率	训练时间/s
提前30 min预测	TA-PINN	0.9973	0.8	0.625	0.8333	44.53
	LSTM	0.9907	0.625	0.4444	0.6667	19.66
	TCN	0.9953	0.8	0.625	0.8333	55.95
提前80 min预测	TA-PINN	0.9637	0.3704	0.1905	0.8	36.07
	LSTM	0.9288	0.2326	0.1081	0.8	17.5
	TCN	0.9656	0.3125	0.1538	0.8	63.49

下载: 导出CSV

参考文献(26)

[1]	Ranasinghe K, Sabatini R, Gardi A, et al. Advances in integrated system health management for mission-essential and safety-critical aerospace applications[J]. Progress in Aerospace Sciences, 2022, 128: 100758.
[2]	王少萍. 液压系统故障诊断与健康管理技术[M]. 北京: 机械工业出版社, 2014. Wang S P. Fault diagnosis and health management technology of hydraulic system[M]. Beijing: China Machine Press, 2014(in Chinese).
[3]	王少萍, MILETA TOMOVIC, 刘红. 民机液压系统: 英文版[M]. 上海: 上海交通大学出版社, 2015. Wang S P, Tomovic M, Liu H. Commercial aircraft hydraulic system[M]. Shanghai: Shanghai Jiao Tong University Press, 2015(in Chinese).
[4]	孙见忠, 王卓健, 闫洪胜, 等. 航空预测性维修研究进展[J]. 航空学报, 2025, 46(7): 6-29. Sun J Z, Wang Z J, Yan H S, et al. Research advances in aircraft predictive maintenance[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(7): 6-29(in Chinese).
[5]	孙明敏, 胡汉纯, 朱昕昀, 等. 基于健康监测的民机系统预测维修任务分析方法[J/OL]. 北京航空航天大学学报, 2024(2024-10-14)[2025-07-01]. https://doi.org/10.13700/j.bh.1001-5965.2024.0528. Sun M M, Hu H C, Zhu X Y, et al. A health monitoring-based approach to predictive maintenance task analysis for civil aircraft systems[J/OL]. Journal of Beijing University of Aeronautics and Astronautics, 2024(2024-10-14)[2025-07-01]. https://doi.org/10.13700/j.bh.1001-5965.2024.0528(in Chinese).
[6]	Qiu Z W, Min R, Wang D Z, et al. Energy features fusion based hydraulic cylinder seal wear and internal leakage fault diagnosis method[J]. Measurement, 2022, 195: 111042.
[7]	Wang S, Zheng D X, Wu S W, et al. Hydraulic excavator track supporting wheel oil leakage fault analysis[J]. Engineering Failure Analysis, 2024, 164: 108680.
[8]	Ma R Q, Zhao H Y, Wang K, et al. Leakage fault diagnosis of lifting and lowering hydraulic system of wing-assisted ships based on WPT-SVM[J]. Journal of Marine Science and Engineering, 2023, 11(1): 27.
[9]	Ma R Q, Zhao H Y, Wang K, et al. A novel wavelet packet transform-fuzzy pattern recognition-based method for leakage fault diagnosis of sail slewing hydraulic system[J]. Machines, 2023, 11(2): 286.
[10]	Dziubak T, Szczepaniak P. Modelling internal leakage in the automatic transmission electro-hydraulic controller, taking into account operating conditions[J]. Energies, 2023, 16(22): 7667.
[11]	Li W J, Qian X B, Chen X Y, et al. Validation research of pressure decay test method for internal leakage detection of hydraulic cylinder[J]. Eksploatacja i Niezawodnosc-Maintenance and Reliability, 2024, 26(2): 184039.
[12]	Tao W F, Ren Y, Tang H S, et al. Lifetime analysis of hydraulic directional valves in a contaminated fluid condition based on internal leakage due to wear[J]. Measurement Science and Technology, 2025, 36(3): 035006.
[13]	Kumar P, Park S, Zhang Y L, et al. A review of hydraulic cylinder faults, diagnostics, and prognostics[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2024, 11(5): 1637-1661.
[14]	Yao H Q, Wu X. Feature analysis and fault diagnosis of internal leakage in dual-cylinder parallel balance oil circuit[J]. Applied Sciences, 2025, 15(2): 972.
[15]	Cai B P, Yang C, Liu Y H, et al. A data-driven early micro-leakage detection and localization approach of hydraulic systems[J]. Journal of Central South University, 2021, 28(5): 1390-1401.
[16]	张轩, 张旭, 黄亦翔, 等. 基于时间特征分割和降维谱聚类的液压系统内泄漏故障诊断[J]. 液压与气动, 2021, 45(6): 14-19. Zhang X, Zhang X, Huang Y X, et al. Fault diagnosis of internal leakage in hydraulic system based on time feature segmentation and dimensionality reduction spectrum clustering[J]. Chinese Hydraulics & Pneumatics, 2021, 45(6): 14-19(in Chinese).
[17]	AIRBUS. A320 ECAM system logic data[Z]. Toulouse: AIRBUS, 2016.
[18]	BOEING. 737 flight crew operations manual[Z]. Washington, D. C. : BOEING, 2014.
[19]	彭朝琴, 李奇聪, 陈娟, 等. 基于GRU和改进注意力机制的多信息融合的EMA故障诊断方法[J]. 北京航空航天大学学报, 2025, 51(11): 3734-3744. Peng Z Q, Li Q C, Chen J, et al. Fault diagnosis method for EMA based on multi-source signal fusion with GRU and improved attention mechanism[J]. Journal of Beijing University of Aeronautics And Astronautics, 2025, 51(11): 3734-3744(in Chinese).
[20]	张海燕, 吴红兰, 刘豪, 等. 基于改进线性注意力Transformer轻量化滚动轴承故障诊断[J/OL]. 北京航空航天大学学报, 2024(2024-09-10)[ 2025-07-01]. https://doi.org/10.13700/j.bh.1001-5965.2024.0366. Zhang H Y, Wu H L, Liu H, et al. Lightweight fault diagnosis of rolling bearings based on improved linear attention transformer[J/OL]. Journal of Beijing University of Aeronautics and Astronautics, 2024(2024-09-10)[2025-07-01]. https://doi.org/10.13700/j.bh.1001-5965.2024.0366(in Chinese).
[21]	He Z Z, Wang S P, Shi J, et al. Physics-informed neural network supported Wiener process for degradation modeling and reliability prediction[J]. Reliability Engineering & System Safety, 2025, 258: 110906.
[22]	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 6000-6010.
[23]	Cho K, Van Merriënboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Kerrville: Association for Computational Linguistics, 2014: 1724-1734.
[24]	李航. 机器学习方法[M]. 北京: 清华大学出版社, 2022: 17-27. LI H. Machine learning method[M]. Beijing: Tsinghua University Press, 2022: 17-27(in Chinese).
[25]	Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[26]	Bai S J, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. (2018-04-19)[2025-07-01]. https://arxiv.org/abs/1803.01271.