基于非线性关联挖掘的航空发动机气路故障诊断方法

doi:10.7527/S1000-6893.2026.33321

Abstract

Abstract:

Gas path fault diagnosis is an essential component of aero-engine health management systems， with fault feature extraction being its key aspect. In recent years， with the advancement of deep learning techniques， gas path fault feature extraction methods based on graph neural networks have attracted considerable attention. However， conventional graph neural networks can only capture linear weighted aggregation relationships among nodes while neglecting the nonlinear coupling relationships prevalent in engine gas path systems， resulting in insufficient cross-condition diagnostic accuracy and interpretability. To address this issue， a gas path fault diagnosis method based on nonlinear correlation mining is proposed. This method achieves interpretable extraction of gas path fault features through an original nonlinear correlation mining layer and an improved graph convolutional layer. The performance of the proposed method was validated using full-lifecycle simulation data encompassing 500 flight sorties. The proposed method achieved zero false alarms throughout the entire operational period， with a detection rate of 88.99% and an isolation rate of 98.61%， significantly outperforming comparative methods based on convolutional， graph convolutional， and graph attention networks in terms of convergence and diagnostic accuracy.

Key words: aero-engine, gas path diagnosis, feature extraction, graph neural network, interpretability

CLC Number:

V263

Keyi ZHAN, Zengbu LIAO, Wenlong LENG, Yi PAN, Zhiping SONG, Weina HUANG. Aero-engine gas path fault diagnosis method based on nonlinear correlation mining[J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(15): 633321.

Figures/Tables 22

Table 1

Fig.1

Fig.2

Fig.3

Table 2

Table 3

Table 4

Table 5

Table 6

Fig.4

Table 7

Table 8

Table 9

Fig.5

Fig.6

Fig.7

Table 10

Fig.8

Table 11

Table 12

Table 13

Fig.9

References 34

[1]	黄维娜，黎方娟，祁宏斌. 航空发动机数字工程初步研究与发展思考［J］. 航空学报， 2024， 45（5）： 529693.
	HUANG W N， LI F J， QI H B. Preliminary investigation and thoughts on aero-engine digital engineering development［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（5）： 529693 （in Chinese）.
[2]	MEHER-HOMJI C B， CHAKER M， BROMLEY A F. The fouling of axial flow compressors： Causes， effects， susceptibility， and sensitivity［C］∥ASME Turbo Expo 2009： Power for Land， Sea， and Air. New York： ASME， 2009： 571-590.
[3]	GANNAN A. Cascade testing and CFD applied to gas turbine performance improvement with compressor cleaning［D］. Bedford： Cranfield University， 2010： 57.
[4]	METWALLY M， TABAKOFF W， HAMED A. Blade erosion in automotive gas turbine engine［J］. Journal of Engineering for Gas Turbines and Power， 1995， 117（1）： 213-219.
[5]	EJAZ N， QURESHI IN， RIZVI SA. Creep failure of low pressure turbine blade of an aircraft engine［J］. Engineering Failure Analysis， 2011，18（6）：1407-1414.
[6]	IATA. Maintenance costs for aging aircraft［M］. Montreal： International Air Transport Association， 2018.
[7]	LAPESA BARRERA D. AMP content and maintenance planning document （MPD）［M］∥Aircraft Maintenance Programs. Cham： Springer International Publishing， 2022：33-46.
[8]	廖增步，张瑞，耿佳，等. 小涵道比涡扇发动机机载气路故障诊断研究综述：边界条件与研究难点［J］. 推进技术， 2024， 45（12）： 24-40.
	LIAO Z B， ZHANG R， GENG J， et al. A review on onboard gas-path fault diagnosis for low bypass ratio turbofan engines： Boundaries and challenges［J］. Journal of Propulsion Technology， 2024， 45（12）： 24-40 （in Chinese）.
[9]	URBAN L A. Gas path analysis applied to turbine engine condition monitoring［J］. Journal of Aircraft， 1973， 10（7）： 400-406.
[10]	LUPPOLD R， ROMAN J， GALLOPS G， et al. Estimating in-flight engine performance variations using Kalman filter concepts［C］∥ 25th Joint Propulsion Conference. Reston： AIAA， 1989.
[11]	李国庆. 人工智能方法在航空发动机故障诊断中的应用研究［D］. 沈阳：沈阳航空航天大学， 2019： 2.
	LI G Q. Application research of artificial intelligence methods in aero-engine fault diagnosis［D］. Shenyang： Shenyang Aerospace University， 2019： 2 （in Chinese）.
[12]	吴超，陈磊，刘渊，等. 基于特征优化和支持向量机的航空发动机气路故障诊断［J］. 航空发动机， 2024， 50（4）： 30-37.
	WU C， CHEN L， LIU Y， et al. Aeroengine gas-path fault diagnosis based on feature optimization and support vector machine［J］. Aeroengine， 2024， 50（4）： 30-37 （in Chinese）.
[13]	ZHONG S S， FU S， LIN L. A novel gas turbine fault diagnosis method based on transfer learning with CNN［J］. Measurement， 2019， 137： 435-453.
[14]	XU C Y， GUI X C， ZHAO Y. Digital twin-assisted multiview reconstruction enhanced domain adaptation graph networks for aero-engine gas path fault diagnosis. IEEE Sensors Journal， 2024， 24（13）：21694-21705.
[15]	曹力昂，于博升，张会生. 基于层次自适应特征提取的航空发动机气路故障诊断［J/OL］. 上海交通大学学报，（2025-04-29）［2025-12-20］. .
	CAO L A， YU B S， ZHANG H S. Hierarchical adaptive feature extraction-based gas path fault diagnosis for aero-engine［J/OL］. Journal of Shanghai Jiao Tong University，（2025-04-29）［2025-12-20］. （in Chinese）.
[16]	张世杰，胡家文，苗国磊. 基于工况识别与自训练时空图卷积的航空发动机气路故障诊断［J］. 推进技术， 2024， 45（11）： 251-260.
	ZHANG S J， HU J W， MIAO G L. Fault diagnosis of aero-engine gas path based on condition recognition and self-training ST-GCN model［J］. Journal of Propulsion Technology， 2024， 45（11）： 251-260 （in Chinese）.
[17]	BAO P， YI W， ZHU Y， et al. STHFD： Spatial-temporal hypergraph-based model for aero-engine bearing fault diagnosis［J］. Aerospace， 2025， 12（7）： 612.
[18]	SHAH B， SARVAJITH M， SANKAR B， et al. Multi-auto associative neural network based sensor validation and estimation for aero-engine［C］∥2013 IEEE AUTOTESTCON. Piscataway： IEEE， 2013： 1-7.
[19]	LI T， ZHAO Z， SUN C， et al. Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction［J］. Reliability Engineering & System Safety， 2021， 215： 107878.
[20]	XU C Y， GUI X C， HUO M X. Domain adversarial enhanced multi-channel graph networks for aeroengine gas path fault diagnosis［C］∥IECON 2023-49th Annual Conference of the IEEE Industrial Electronics Society. Piscataway： IEEE， 2023： 1-6.
[21]	GOYAL V. Anomaly detection and failure prediction in gas turbines［D］. Orlando： University of Central Florida， 2021： 14.
[22]	HUANG Y F， TAO J， ZHAO J Y， et al. Graph structure embedded with physical constraints-based information fusion network for interpretable fault diagnosis of aero-engine［J］. Energy， 2023， 283：129120.
[23]	ZHANG S M， SONG P Y， ZHAO C H. Multi-conditional adjacency learning and grouping method for monitoring gas turbine generation process with nonstationarity［C］∥2023 China Automation Congress （CAC）. Piscataway： IEEE， 2024.
[24]	CHENG K R， ZHANG K Y， WANG Y Z， et al. Research on gas turbine health assessment method based on physical prior knowledge and spatial-temporal graph neural network［J］. Applied Energy， 2024， 367： 123419.
[25]	CHEN Y， LIANG C， LIU D， et al. Embedding-graph neural-network for transient NO _x emissions prediction［J］. Energies， 2023， 16（1）： 3.
[26]	WANG Z， FU X， ZHANG R， et al. Knowledge and data jointly driven aeroengine gas path performance assessment method［J］. Chinese Journal of Aeronautics， 2024， 37（5）： 533-557.
[27]	LU F， LI Z， HUANG J， et al. Hybrid state estimation for aircraft engine anomaly detection and fault accommodation［J］. AIAA Journal， 2020， 58 （4）： 1748-1762.
[28]	YANG K， TU Q， ZENG Y， et al. Parameter selection for aeroengine transient state gas path analysis［J］. Journal of the Global Power and Propulsion Society， 2022， 6： 61-73.
[29]	VELIČKOVIĆ P， CUCURULL G， CASANOVA A， et al. Graph attention networks［C］∥6th International Conference on Learning Representations. 2018.
[30]	匡育衡，王正宁，王正，等. 基于双注意力时空图卷积神经网络的4D轨迹预测方法［J］. 电子科技大学学报， 2025， 54（5）： 641-651.
	KUANG Y H， WANG Z N， WANG Z， et al. 4D trajectory prediction based on dual-attention spatiotemporal graph convolutional neural network［J］. Journal of University of Electronic Science and Technology of China， 2025， 54（5）： 641-651 （in Chinese）.
[31]	JIANG K， ZENG H， WU Z， et al. Study on the effect of parameter sensitivity on engine optimization results［J］. Energies， 2023， 16（23）： 7899.
[32]	LIAO Z B， WANG J， LIU J X， et al. Uncertainties in gas path diagnosis of gas turbines： Representation and impact analysis［J］. Aerospace Science and Technology， 2021， 113： 106724.
[33]	SALLEE G P. Performance deterioration based on existing （historical） data； JT9D jet engine diagnostics program： NASA-CR-135448［R］. Washington， D.C.： NASA， 1978.
[34]	LIAO Z B， ZHAN K Y， ZHAO H， et al. Addressing class imbalanced learning in real-time aero-engine gas-path fault diagnosis via feature filtering and mapping［J］.Reliability Engineering & System Safety， 2024， 249： 110189.

序号	参数名称	变量符号
1	风扇转速	N₁
2	压气机转速	N₂
3	环境静压	P₀
4	风扇进口总温	T_t2
5	风扇进口总压	P_t2
6	压气机进口总温	T_t25
7	压气机进口总压	P_t25
8	压气机出口静压	P_s31
9	低压涡轮出口总温	T_t6
10	低压涡轮出口总压	P_t6
11	风扇导叶角度	α₁
12	压气机导叶角度	α₂
13	主燃油流量	W_f
14	加力燃油流量	W_fa
15	喷口面积	A₈

仿真条件	训练集	测试集1	测试集2
故障注入	起动时注入，固定		动态注入
架次数	170	50	500
载荷谱	1~10	1~10	11~20
个体差异	无	无	表3
性能衰退	无	无	图4
传感器噪声	3项	3项	4项
故障模式	表4	表5	表4+表5

序号	表征参数	数值/‰
1	风扇效率特性差异系数	-0.007
2	风扇流量特性差异系数	1.840
3	压气机效率特性差异系数	-1.349
4	压气机流量特性差异系数	-1.524
5	燃烧室总压损失差异系数	-1.105
6	高压涡轮效率特性差异系数	-0.638
7	高压涡轮临界面积差异系数	0.845
8	低压涡轮效率特性差异系数	0.034
9	低压涡轮临界面积差异系数	1.022
10	涡轮出口面积差异系数	-0.896
11	外涵道出口面积差异系数	0.723
12	尾喷管临界面积差异系数	0.623

序号	故障部件	效率拉偏/%	流量拉偏/%	拉偏比值
1	风扇	-3.31	-6.62	0.5
2		-4.04	-5.05	0.8
3		-3.93	-3.14	1.25
4		-4.09	-2.04	2.0
5	压气机	-2.23	-4.45	0.5
6		-3.45	-4.32	0.8
7		-3.61	-2.89	1.25
8		-3.55	-1.77	2.0
9	高压涡轮	-1.40	2.80	0.5
10		-1.70	2.12	0.8
11		1.94	-1.55	1.25
12		-2.13	1.06	2.0
13	低压涡轮	-0.77	1.53	0.5
14		-1.17	1.46	0.8
15		-1.71	1.37	1.25
16		-2.49	1.24	2.0

序号	故障部件	效率拉偏/%	流量拉偏/%	拉偏比值
1	风扇	-3.97	-3.97	1.0
2	压气机	-3.57	-3.57	1.0
3	高压涡轮	-1.82	1.82	1.0
4	低压涡轮	-1.42	1.42	1.0

Aero-engine gas path fault diagnosis method based on nonlinear correlation mining

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 22

References 34

Related Articles 15

Recommended Articles

Metrics

Comments

故障轮次	故障部件	拉偏比值	起止架次
1	风扇	0.5	61~65
2	压气机	0.5	71~75
3	高压涡轮	0.5	81~85
4	低压涡轮	0.5	91~95
5	风扇	0.8	121~125
6	压气机	0.8	146~150
7	高压涡轮	0.8	166~170
8	低压涡轮	0.8	186~190
9	风扇	1.0	221~225
10	压气机	1.0	241~245
11	高压涡轮	1.0	261~265
12	低压涡轮	1.0	281~285
13	风扇	1.25	326~330
14	压气机	1.25	346~350
15	高压涡轮	1.25	366~370
16	低压涡轮	1.25	386~390
17	风扇	2.0	421~425
18	压气机	2.0	441~445
19	高压涡轮	2.0	461~465
20	低压涡轮	2.0	481~485

气路部件	衰退量/%
气路部件	效率特性	流量特性
风扇	-0.852	-1.159
压气机	-0.829	-1.181
高压涡轮	-1.494	+1.000
低压涡轮	-0.307	+0.148

序号	网络层	激活值尺寸
1	输入	10×10
2	卷积层+线性整流	10×10×10
3	卷积层+线性整流	10×10×10
4	滤波器响应归一化层	10×10×10
5	池化层	10×5×5
6	全连接层	50×1
7	随机失活层	50×1
8	全连接层	5×1

序号	参数名称	变量符号
1	换算主燃油流量	W_fcor
2	加力燃油流量	W_fa
3	喷口面积	A₈
4	风扇换算转速	N_1cor
5	压气机换算转速	N_2cor
6	压气机进口换算总温	T_t25cor
7	压气机进口换算总压	P_t25cor
8	压气机出口换算静压	P_s31cor
9	低压涡轮出口换算总温	T_t6cor
10	低压涡轮出口换算总压	P_t6cor

算法	CNN	GAT	GCN	本文方法
检测率/%	99.43	98.86	99.37	99.62
隔离率/%	99.49	99.28	99.45	99.81
虚警率/%	0.19	0.23	0.10	0.06

序号	网络层	激活尺寸
1	输入	1×8×10
2	卷积层+线性整流	10×8×10
3	卷积层+线性整流	10×8×10
4	池化层	10×4×5
5	全连接层+线性整流	200×1
6	全连接层+维度重构	2×10×5×5

算法	CNN	GCNA	GAT	本文方法
检测率/%	84.71	77.87	86.06	88.99
隔离率/%	98.75	92.82	96.89	98.61
虚警次数	1	0	0	0

[1]	Hang GENG, Yixuan WU, Xuan GOU, Xinjian LI, Kai CHEN. Intelligent camouflaged target detection based on information of aerospace unmanned platforms [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(S1): 732819-732819.
[2]	Wei XIONG, Dong ZHANG, Shuheng YANG, Zhi REN, Wenyi LIU. Manned/unmanned aerial vehicle collaborative interpretable method for intelligent air combat [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(7): 332547-332547.
[3]	Donghuan WANG, Hai JIN, Dongkai WAN, Jun WANG, Hong XIAO. Real-time monitoring and evaluation method for aero-engine performance degradation based on performance digital twin [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(5): 132459-132459.
[4]	Rongling LANG, Cailun WEI, Ya FAN, Fei GAO. Sparse point matching-based collaborative category-agnostic object tracking method [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(3): 632425-632425.
[5]	Xiangxin ZHANG, Fuhui LYU, Yi ZOU, Xianghua HUANG. Aero-engine component degradation assessment based on engine physics-guided optimization algorithm [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(15): 633304-633304.
[6]	Geng ZHANG, Lijun XIAO, Ming ZHONG, Piqiang SU, Xiaohuang LAI. Rotating stall identification algorithm based on power spectrum cross-correlation [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(15): 633320-633320.
[7]	Wei TIAN, Yanfei LIU, Shaoping ZHANG, Wangyang ZHANG, Dongzhe ZHANG, Huiming GUO, Zuojun LI. Research progress and application of lattice materials in aero-engines [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(11): 432073-432073.
[8]	Lifen ZHANG, Qixi CHEN, Kai WANG, Yaguo LYU, Zhenxia LIU. Influence of directed flow nozzle swirl enhancer on heat transfer at engine lip [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(11): 633024-633024.
[9]	Xueqi CHEN, Zuoxiang ZHANG, Dong WANG, Yanhong MA, Jie HONG. Loading of intermediate bearing-support structure and its impact on structural integrity [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(1): 232061-232061.
[10]	Guanwei YAO, Gaowen LIU, Yan CHEN, Xiaozhi KONG, Aqiang LIN. Forward design of high-performance turbine low-radius pre-swirl system [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(7): 130832-130832.
[11]	Yaling HE, Tao JIANG, Shen DU, Guoqiang XU. Research progress on performance boundary of air heat exchanger within flight envelope [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(5): 531745-531745.
[12]	Xuanjun TAO, Pingchao YU, Yize JIN, Zhenyang XIANG, Dayi ZHANG. Simulation method and dynamic characteristics analysis of complex blade rubbing in aero-engines [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(24): 232058-232058.
[13]	Bin TANG, Xiaogang YANG, Ruitao LU, Zhenyu ZHANG, Shuang SU. Aircraft infrared/satellite heterogenous fast matching localization method based on image translation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(23): 631961-631961.
[14]	Qi LIU, Zhixiang PEI, Le HUI, Mingyi HE, Yuchao DAI. Dual-branch feature aggregation for UAV visual place recognition [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(23): 632457-632457.
[15]	Chenhao ZHAO, Dewei WU, Jing HE, Qian WU. A semantic feature matching algorithm for UAV visual pose estimation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(2): 330406-330406.