Numerous research has confirmed the efficacy of utilizing deep learning for diagnosing faults in rotating machinery. However, this approach often overlooks the practical constraints in industrial scenarios, such as the variable operating environments characteristic of mechanical systems, and the limited availability of fault data. In this article, we propose an improved model-agnostic meta-learning method for few-shot cross-domain fault diagnosis based on parallel synergistic network (IMAML-PSN). This method first utilizes fourier transform-gramian angular summation field (FT-GASF) for data preprocessing to emphasize fault features and ensure that they are not affected by cross-domains. Then, the training moderator variable optimizes the meta-learning training process and improves diagnostic performance according to different meta-tasks. A feature encoder based on parallel synergistic attention mechanism captures the interaction relationships between multidimensional features and learns shared diagnostic knowledge. Comparative cross-domain experiments on bearing fault datasets confirm the method’s diagnostic efficacy and robustness, under the complex operating environments constrained by sample scarcity.
LiXYuTWangX, et al. Multi-scale ECA attention network: a rotation mechanical domain adaptation method with minimal class confusion. Struct Health Monit2024; 24(4): 2504–2520.
2.
FengYChenJXieJ, et al. Meta-learning as a promising approach for few-shot cross-domain fault diagnosis: algorithms, applications, and prospects. Knowl Based Syst2022; 235: 107646.
3.
LiuYJiangHYaoR, et al. Counterfactual-augmented few-shot contrastive learning for machinery intelligent fault diagnosis with limited samples. Mech Syst Signal Process2024; 216: 111507.
4.
SongBLiuYFangJ, et al. An optimized CNN-BiLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples. Neurocomputing2024; 574: 127284.
5.
LiXYuTWangX, et al. Fusing joint distribution and adversarial networks: a new transfer learning method for intelligent fault diagnosis. Appl Acoust2024; 216: 109767.
6.
ZhaoSDuanYRoyN, et al. A deep learning methodology based on adaptive multiscale CNN and enhanced highway LSTM for industrial process fault diagnosis. Reliab Eng Syst Safe2024; 249: 110208.
7.
LiQChenLKongL, et al. Cross-domain augmentation diagnosis: an adversarial domain-augmented generalization method for fault diagnosis under unseen working conditions. Reliab Eng Syst Safe2023; 234: 109171.
8.
LiXWuXWangT, et al. Fault diagnosis method for imbalanced data based on adaptive diffusion models and generative adversarial networks. Eng Appl Artif Intell2025; 147: 110410.
9.
HeDZhaoJJinZ, et al. DCAGGCN: a novel method for remaining useful life prediction of bearings. Reliab Eng Syst Safe2025; 260: 110978.
10.
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 Safe2025; 261: 111122.
11.
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 Reliab2026; 28(1): 205977.
12.
LiQLiHHuW, et al. Transparent operator network: a fully interpretable network incorporating learnable wavelet operator for intelligent fault diagnosis. IEEE Trans Industr Inform2024; 20(6): 8628–8638.
13.
QinZQinLZhuQ, et al. An ultrasensitive self-powered smart bearing pedestal with fault locating capability. Mech Syst Signal Process2025; 235: 112924.
14.
JinZXuQJiangC, et al. Ordinal few-shot learning with applications to fault diagnosis of offshore wind turbines. Renew Energy2023; 206: 1158–1169.
15.
JiangLWangSZhangT, et al. Semi-supervised few-shot fault diagnosis driven by multi-head dynamic graph attention network under speed fluctuations. Digit Signal Process2024; 151: 104528.
16.
FanCZhangYMaH, et al. A novel metric-based model with the ability of zero-shot learning for intelligent fault diagnosis. Eng Appl Artif Intell2024; 129: 107605.
17.
LiXLiJQuY, et al. Semi-supervised gear fault diagnosis using raw vibration signal based on deep learning. Chin J Aeronaut2020; 33(2): 418–426.
18.
ZhiSSuKYuJ, et al. An unsupervised transfer learning bearing fault diagnosis method based on multi-channel calibrated Transformer with shiftable window. Struct Health Monit2025; 34: 14759217251324671.
19.
CuiZLuYYanX, et al. Compound fault diagnosis of diesel engines by combining generative adversarial networks and transfer learning. Expert Syst Appl2024; 251: 123969.
20.
ZhengBHuangJMaX, et al. An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis. Mech Syst Signal Process2024; 208: 111047.
21.
TangSMaJYanZ, et al. Deep transfer learning strategy in intelligent fault diagnosis of rotating machinery. Eng Appl Artif Intell2024; 134: 108678.
22.
LinJShaoHZhouX, et al. Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals. Expert Syst Appl2023; 230: 120696.
23.
LiXSuHXiangL, et al. Transformer-based meta learning method for bearing fault identification under multiple small sample conditions. Mech Syst Signal Process2024; 208: 110967.
24.
LuoJShaoHLinJ, et al. Meta-learning with elastic prototypical network for fault transfer diagnosis of bearings under unstable speeds. Reliab Eng Syst Safe2024; 245: 110001.
25.
YangTTangTWangJ, et al. A novel cross-domain fault diagnosis method based on model agnostic meta-learning. Measurement2022; 199: 111564.
26.
HospedalesTAntoniouAMicaelliP, et al. Meta-learning in neural networks: a survey. IEEE Trans Pattern Anal Mach Intell2022; 44(9): 5149–5169.
27.
SuHHuJYuS, et al. Successive model-agnostic meta-learning for few-shot fault time series prognosis. Neurocomputing2024; 595: 127879.
28.
LeeSKKimHChaeM, et al. Self-supervised feature learning for motor fault diagnosis under various torque conditions. Knowl Based Syst2024; 288: 111465.
29.
HendriksJDumondPKnoxDA.Towards better benchmarking using the CWRU bearing fault dataset. Mech Syst Signal Process2022; 169: 108732.
30.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
31.
LiXYuTZhangF, et al. Mixed style network based: a novel rotating machinery fault diagnosis method through batch spectral penalization. Reliab Eng Syst Safe2025; 255: 110667.
32.
ZhangSYeFWangB, et al. Few-shot bearing fault diagnosis based on model-agnostic meta-learning. IEEE Trans Ind Appl2021; 57(5): 4754–4764.
33.
LiXZhengYZhuR, et al. ReNAP: relation network with adaptive prototypical learning for few-shot classification. Neurocomputing2023; 520: 356–364.
34.
SnellJSwerskyKZemelR.Prototypical networks for few-shot learning. Adv Neural Inf Process Syst2017; 30: 4077–4087.
35.
AntoniouAEdwardsHStorkeyA.How to train your MAML. Proc Int Conf Mach Learn2020; 119: 187–198.
36.
JalayerMOrsenigoCVercellisC.Fault detection and diagnosis for rotating machinery: a model based on convolutional LSTM, fast Fourier and continuous wavelet transforms. Comput Ind2021; 125: 103378.
37.
ParkJKimYNaK, et al. An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery. Mech Syst Signal Process2022; 167: 108524.
38.
BaiRMengZXuQ, et al. Fractional Fourier and time domain recurrence plot fusion combining convolutional neural network for bearing fault diagnosis under variable working conditions. Reliab Eng Syst Safe2023; 232: 109076.
