As a core component of the aeroengine, the main shaft bearing faces significant challenges in practical fault diagnosis, including the difficulty of simultaneously capturing both local and global features during feature extraction, and the scarcity of high-quality labeled data under varying operating conditions, which limit the generalization ability of diagnostic models. To address these issues, this article proposes a lightweight transfer learning-based fault diagnosis method built upon a Bi-Sandwich architecture and maximum mean square difference (MMSD). A novel Bi-Sandwich model is designed by integrating multiscale separable convolutions and a broadcast attention mechanism, enabling effective extraction of both local and global features while reducing computational complexity. To mitigate domain discrepancies under different working conditions, an MMSD-based domain adaptation metric using second-order statistics is introduced to align feature distributions between the source and target domains. Experimental results on two aero-engine main shaft bearing datasets demonstrate that the proposed method achieves excellent fault identification accuracy and cross-domain generalization across different loads and rotational speeds.
LiBZhaoY-P.Group reduced kernel extreme learning machine for fault diagnosis of aircraft engine. Eng Appl Artif Intell2020; 96: 103968.
2.
YangZHongJWangD, et al. Failure analysis of an aero-engine inter-shaft bearing due to clearance between the outer ring and its housing. Eng Fail Anal2023; 150: 107298.
3.
LiXWuXWangT, et al. Fault diagnosis method for imbalanced data based on adaptive diffusion models and generative adversarial networks. Eng Appl Artif Intell2025; 147: 110410.
4.
LiYLiMYanZ, et al. Application of life cycle of aeroengine mainshaft bearing based on digital twin. Processes2023; 11(6): 1768.
5.
RejithRKesavanDChakravarthyP, et al. Bearings for aerospace applications. Tribol Int2023; 181: 108312.
6.
WuHZhongSZhaoM, et al. Continual contrastive reinforcement learning: towards stronger agent for environment-aware fault diagnosis of aero-engines through long-term optimization under highly imbalance scenarios. Adv Eng Inform2025; 65: 103297.
7.
LiMWangZXuR, et al. Advances in plasma-assisted ignition and combustion for combustors of aerospace engines. Aerosp Sci Technol2021; 117: 106952.
8.
GaoTYuanS-MLiuY-Q, et al. Paroxysmal impulse vibration analysis of an aero-engine dual-rotor system with a defective inner ring for the inter-shaft bearing. Commun Nonlinear Sci Numer Simul2024; 131: 107864.
9.
ZaidanMAMillsARHarrisonRF, et al. Gas turbine engine prognostics using Bayesian hierarchical models: a variational approach. Mech Syst Signal Process2016; 70: 120–140.
10.
FangMYuMGuoG, et al. Research on compound faults identification of aeroengine inter-shaft bearing based on CCF–Complexity–VMD–SVD. Struct Health Monit2023; 22(4): 2688–2707.
11.
Jia-QiLYun-WenFDaT, et al. Operational reliability evaluation and analysis framework of civil aircraft complex system based on intelligent extremum machine learning model. Reliab Eng Syst Saf2023; 235: 109218.
12.
LiXXiaoSLiQ, et al. The bearing multi-sensor fault diagnosis method based on a multi-branch parallel perception network and feature fusion strategy. Reliab Eng Syst Saf2025; 261: 111122.
13.
QiJChenZKongY, et al. Attention-guided graph isomorphism learning: a multi-task framework for fault diagnosis and remaining useful life prediction. Reliab Eng Syst Saf2025; 263: 111209.
14.
KumarNSatapathyR.Bearings in aerospace, application, distress, and life: a review. J Fail Anal Prev2023; 23(3): 915–947.
15.
RathNMishraRKushariA.Aero engine health monitoring, diagnostics and prognostics for condition-based maintenance: an overview. Int J Turbo Jet Engines2024; 40(s1): s279–s292.
16.
ZhangJYiSLiangG, et al. A new bearing fault diagnosis method based on modified convolutional neural networks. Chin J Aeronaut2020; 33(2): 439–447.
17.
GeYZhangFRenY.Adaptive fault diagnosis method for rotating machinery with unknown faults under multiple working conditions. J Manuf Syst2022; 63: 177–184.
18.
XuZSalehJH.Machine learning for reliability engineering and safety applications: review of current status and future opportunities. Reliab Eng Syst Saf2021; 211: 107530.
19.
ZhouLZhangDHeT, et al. Unbalance identification for a practical turbofan engine using augmented Kalman filter improved with the convergence criterion. J Vib Control2024; 30(7–8): 1566–1579.
20.
ChengLMaWGaoZ.Rolling bearing degradation trend prediction based on composite multiscale grey entropy and dynamic particle filter. Meas Sci Technol2024; 35(6): 066119.
21.
MinghuiHYaHXinzhiL, et al. Digital twin model of gas turbine and its application in warning of performance fault. Chin J Aeronaut2023; 36(3): 449–470.
22.
ShiMDingCWangR, et al. Deep hypergraph autoencoder embedding: an efficient intelligent approach for rotating machinery fault diagnosis. Knowl Based Syst2023; 260: 110172.
23.
LiXRanGXiaoS, et al. A fault diagnosis method for bearings based on multiscale graph convolutional network under non-stationary speed conditions. Mech Mach Theory2025; 217: 106267.
24.
LiXLiGWangT, et al. Knowledge extraction and retrieval-augmented generation for intelligent maintenance of wind power equipment based on graph attention networks. Chin J Mech Eng2025: 100141.
25.
LiQLiHHuW, et al. Transparent operator network: a fully interpretable network incorporating learnable wavelet operator for intelligent fault diagnosis. IEEE Trans Ind Inform2024; 20(6): 8628–8638.
26.
HouYWangJChenZ, et al. Diagnosisformer: an efficient rolling bearing fault diagnosis method based on improved Transformer. Eng Appl Artif Intell2023; 124: 106507.
27.
HuangDSuXYangJ, et al. An improved dual-channel CNN-BILSTM fusion attention model for fault diagnosis of aero-engine bearings. Measurement2025, 253: 117761.
28.
LiXWuXYuJ, et al. A fault diagnosis data augmentation method integrating multimodal non-Gaussian denoising diffusion generative adversarial network. Adv Eng Inform2025; 68: 103776.
29.
LinHHuangXChenZ, et al. Matching pursuit network: an interpretable sparse time–frequency representation method toward mechanical fault diagnosis. IEEE Trans Neural Netw Learn Syst2024; 36: 12377–12388.
30.
ZhiSNiuYMaL, et al. Local entropy selection scaling-extracting Chirplet transform for enhanced time-frequency analysis and precise state estimation in reliability-focused fault diagnosis of non-stationary signals. Maint Reliab2025; 28(1): 205977.
31.
LiBZhaoY-PChenY-B.Unilateral alignment transfer neural network for fault diagnosis of aircraft engine. Aerosp Sci Technol2021; 118: 107031.
32.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
33.
YanRLiWLuS, et al. Transfer learning for prognostics and health management: advances, challenges, and opportunities. J Dyn Monit Diagn2024; 3: 60–82.
34.
ZhuYGuoTLiX, et al. Domain generalization prognosis method for lithium-ion battery state of health with transformer and multikernel MMD. J Dyn Monit Diagn2024; 3(4): 311–323.
35.
ShiMDingCChangS, et al. Cross-domain class incremental broad network for continuous diagnosis of rotating machinery faults under variable operating conditions. IEEE Trans Ind Inform2024; 20(4): 6356–6368.
36.
LiXYuTWangX, et al. Fusing joint distribution and adversarial networks: A new transfer learning method for intelligent fault diagnosis. Appl Acoust2024; 216: 109767.
37.
HeZShaoHZhangX, et al. Improved deep transfer auto-encoder for fault diagnosis of gearbox under variable working conditions with small training samples. IEEE Access2019; 7: 115368–115377.
38.
YueKLiJChenJ, et al. Intelligent cross-domain fault diagnosis for rotating machinery using multiscale adversarial convolutional neural network. In: Proceedings of the 2022 IEEE international instrumentation and measurement technology conference (I2MTC), Ottawa, ON, Canada, 2022. New York, NY, USA: IEEE, 2022.
39.
YangBLeiYJiaF, et al. A transfer learning method for intelligent fault diagnosis from laboratory machines to real-case machines. In: Proceedings of the 2018 international conference on sensing, diagnostics, prognostics, and control (SDPC), Xi’an, China, 2018. New York, NY: IEEE.
40.
ZhiSSuKYuJ, et al. An unsupervised transfer learning bearing fault diagnosis method based on multi-channel calibrated Transformer with shiftable window. Struct Health Monit2025: 2014759217251324671.
41.
ZhaoY-PChenY-B.Extreme learning machine based transfer learning for aero engine fault diagnosis. Aerosp Sci Technol2022; 121: 107311.
42.
BerghoutTBenbouzidM.Diagnosis and prognosis of faults in high-speed aeronautical bearings with a collaborative selection incremental deep transfer learning approach. Appl Sci2023; 13(19): 10916.
43.
SmolaAJGrettonABorgwardtK.Maximum mean discrepancy. In: Proceedings of the 13th international conference, ICONIP, Hong Kong, China, 2006. Berlin, Heidelberg: Springer.
44.
KennedyRASadeghiP.Hilbert space methods in signal processing. Cambridge University Press, Cambridge, UK, 2013.
45.
LucasCMioM.Proof theory of Riesz spaces and modal Riesz spaces. Log Methods Comput Sci2022; 18: 1–64.
46.
GhojoghBGhodsiAKarrayF, et al. Reproducing kernel Hilbert space, Mercer’s theorem, Eigenfunctions, Nystrom method, and use of kernels in machine learning: tutorial and survey. arXiv:210608 443, 2021.
47.
LiuXPengHZhengN, et al. Efficientvit: memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver, Canada, 2023. New York, NY: IEEE.
48.
DagaAPFasanaAMarchesielloS, et al. The Politecnico di Torino rolling bearing test rig: description and analysis of open access data. Mech Syst Signal Process2019; 120: 252–273.
49.
YangBLeiYJiaF, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech Syst Signal Process2019; 122: 692–706.
50.
CaoHShaoHZhongX, et al. Unsupervised domain-share CNN for machine fault transfer diagnosis from steady speeds to time-varying speeds. J Manuf Syst2022; 62: 186–198.
51.
LiXYuanPSuK, et al. Innovative integration of multi-scale residual networks and MK-MMD for enhanced feature representation in fault diagnosis. Meas Sci Technol2024; 35(8): 086108.
52.
LiXSuKLiD, et al. Transfer learning for bearing fault diagnosis: adaptive batch normalization and combined optimization method. Meas Sci Technol2024; 35(4): 046106.
53.
QianQLuoJQinY.Adaptive intermediate class-wise distribution alignment: a universal domain adaptation and generalization method for machine fault diagnosis. IEEE Trans Neural Netw Learn Syst2024; 36: 4296–4310.
54.
YangYJingJZhangJ, et al. Discriminative fault diagnosis transfer learning network under joint mechanism. Sci Rep2025; 15(1): 8888.
55.
GaoYLiX.Fault diagnosis of centrifugal fan bearings based on I-CNN and JMMD in the context of sample imbalance. Maint Reliab2024; 26(4): 191459.
56.
HouLYiHJinY, et al. Inter-shaft bearing fault diagnosis based on aero-engine system: a benchmarking dataset study. J Dyn Monit Diagn2023; 2: 228–242.
