Intelligent fault diagnosis of mechanical equipment is crucial to ensure safe industrial operation, but the high cost of manual labeling and the scarcity of fault data seriously restrict the performance of traditional methods. In order to identify faults under the condition of few samples and improve the performance of cross-domain classification performance in semi-supervised learning, this paper proposes a meta-learning method based on multi-label cosine similarity (MCML). This method dynamically assigns multiple high-probability pseudolabels to unlabeled data through a multi-label classifier to retain the potential similarity between categories, introduces cosine similarity as a meta-learning metric to effectively alleviate the sensitivity of Euclidean distance in high-dimensional feature space, and designs a dynamic two-stage Adam optimizer to adaptively adjust the learning rate to accelerate convergence. Experiments show that on the rotor rolling bearing, Case Western Reserve University bearing and Southeast University gearbox datasets, MCML has the highest accuracy of 100% in the 10-way-5-shots sample task, and the cross-equipment and cross-fault domain diagnosis accuracy are 100 and 92.38% respectively, which is significantly better than convolutional neural network, Prototype Networks, and other comparison models. This study provides an efficient solution for small-sample fault diagnosis in industrial scenarios.
FengKXiaoHZhangJ, et al. A digital twin methodology for vibration-based monitoring and prediction of gear wear. Wear2025; 571: 205806.
2.
FengKJiJCLiY, et al. A novel cyclic-correntropy based indicator for gear wear monitoring. Tribol Int2022; 171: 107528.
3.
ZhaoHLiuMSunY, et al. Automated design of fault diagnosis CNN network for satellite attitude control systems. IEEE Trans Cybern2024; 54: 4028–4038.
4.
RuanDWangJYanJ, et al. CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis. Adv Eng Inform2023; 55: 101877.
5.
ChoudharyAMishraR KFatimaS, et al. Multi-input CNN based vibro-acoustic fusion for accurate fault diagnosis of induction motor. Eng Appl Artif Intell2023; 120: 105872.
6.
ChenXZhangBGaoD. Bearing fault diagnosis base on multi-scale CNN and LSTM model. J Intell Manuf2021; 32(4): 971–987.
7.
ZhuJJiangQShenY, et al. Application of recurrent neural network to mechanical fault diagnosis: a review. J Mech Sci Technol2022; 36(2): 527–542.
8.
ZhouQCShenHHZhaoJ, et al. Bearing fault diagnosis based on improved stacked recurrent neural network. J Tongji Univ2019; 47(10): 1500–1507.
9.
ChadhaGSPanambillyASchwungA, et al. Bidirectional deep recurrent neural networks for process fault classification. ISA Trans2020; 106: 330–342.
10.
PangS. Stacked maximum independence autoencoders: a domain generalization approach for fault diagnosis under various working conditions. Mech Syst Signal Process2024; 208: 111035.
11.
WangHWangJZhaoY, et al. Few-shot learning for fault diagnosis with a dual graph neural network. IEEE Trans Industr Inform2022; 19(2): 1559–1568.
12.
DengCDengZMiaoJ. Semi-supervised ensemble fault diagnosis method based on adversarial decoupled auto-encoder with extremely limited labels. Reliab Eng Syst Saf2024; 242: 109740.
13.
RuanDChenXGühmannC, et al. Improvement of generative adversarial network and its application in bearing fault diagnosis: a review. Lubricants2023; 11(2): 74.
14.
ZhongHYuSTrinhH, et al. Fine-tuning transfer learning based on DCGAN integrated with self-attention and spectral normalization for bearing fault diagnosis. Measurement2023; 210: 112421.
15.
HeJOuyangMChenZ, et al. A deep transfer learning fault diagnosis method based on WGAN and minimum singular value for non-homologous bearing. IEEE Trans Instrum Meas2022; 71: 1–9.
16.
AhangMJalayerMShojaeinasabA, et al. Synthesizing rolling bearing fault samples in new conditions: a framework based on a modified CGAN. Sensors2022; 22(14): 5413.
17.
GuoQLiYLiuY, et al. Data augmentation for intelligent mechanical fault diagnosis based on local shared multiple-generator GAN. IEEE Sens J2022; 22(10): 9598–9609.
18.
LuoWYangWHeJ, et al. Fault diagnosis method based on two-stage GAN for data imbalance. IEEE Sens J2022; 22(22): 21961–21973.
19.
WangQMichauGFinkO. Domain adaptive transfer learning for fault diagnosis. In: 2019 Prognostics and system health management conference (PHM-Paris), Paris, France, 2–5 May 2019, pp. 279–285. IEEE Computer Society.
20.
MaoWLiuYDingL, et al. A new structured domain adversarial neural network for transfer fault diagnosis of rolling bearings under different working conditions. IEEE Trans Instrum Meas2020; 70: 1–3.
21.
LiuKLiY. Remaining useful life prediction across machines using multi-source adversarial online knowledge distillation. Eng Appl Artif Intell2024; 130: 107726.
22.
XieYJTangH. Low-supervised domain-adversarial neural network for cross-domain mooring line failure detection. Appl Ocean Res2024; 149: 104066.
23.
ZhangZShaoMMaC, et al. An enhanced domain-adversarial neural networks for intelligent cross-domain fault diagnosis of rotating machinery. Nonlinear Dyn2022; 108(3): 2385–2404.
24.
XuYLiuJWanZ, et al. Rotor fault diagnosis using domain-adversarial neural network with time-frequency analysis. Machines2022; 10(8): 610.
25.
SuHXiangLHuA, et al. A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions. Mech Syst Signal Process2022; 169: 108765.
26.
ChenJHuWCaoD, et al. A meta-learning method for electric machine bearing fault diagnosis under varying working conditions with limited data. IEEE Trans Industr Inform2022; 19(3): 2552–2564.
27.
YangTTangTWangJ, et al. A novel cross-domain fault diagnosis method based on model agnostic meta-learning. Measurement2022; 199: 111564.
28.
LiuXShaDZhangQ, et al. A novel multi-task transfer model to realize unsupervised fault diagnosis of newly constructed wind turbines under variable conditions. In: 2023 4th international conference on mechanical engineering, intelligent manufacturing and automation technology (MEMAT 2023), Guilin, China, vol. 13082, April 2024, pp. 258–268. SPIE, Bellingham, WA, USA.
29.
LinJShaoHZhouX, et al. Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals. Expert Syst Appl2023; 230: 120696.
30.
WangYLiuS. A multi scale meta-learning network for cross domain fault diagnosis with limited samples. J Intell Manuf2024; 36: 1–21.
31.
LuoJShaoHLinJ, et al. Meta-learning with elastic prototypical network for fault transfer diagnosis of bearings under unstable speeds. Reliab Eng Syst Saf2024; 245: 110001.
32.
SongSZhangSDongW, et al. Multi-source information fusion meta-learning network with convolutional block attention module for bearing fault diagnosis under limited dataset. Struct Health Monit2024; 23(2): 818–835.
33.
GaoYQiJSunY, et al. Industrial process fault diagnosis based on feature enhanced meta-learning toward domain generalization scenarios. Knowl Based Syst2024; 289: 111506.
34.
LiYGengCYangY, et al. Extraction of instantaneous frequencies for signals with intersecting and intermittent trajectories. Mech Syst Signal Process2025; 223: 111835.
35.
Ramírez-SanzJMMaestro-PrietoJAArnaiz-GonzálezÁ, et al. Semi-supervised learning for industrial fault detection and diagnosis: a systemic review. ISA Trans2023; 143: 255–270.
36.
LiSJiJFengK, et al. Composite neuro-fuzzy system-guided cross-modal zero-sample diagnostic framework using multi-source heterogeneous non-contact sensing data. IEEE Trans on Fuzzy Syst2024; 33: 302–313.
37.
ZhangWChenDXiaoY, et al. Semi-supervised contrast learning based on multi-scale attention and multi-target contrast learning for bearing fault diagnosis. IEEE Trans Industr Inform2023; 19: 10056–10068.
38.
ChengCLiuXZhouBYuanY. Intelligent fault diagnosis with noisy labels via semi-supervised learning on industrial time series. IEEE Trans Industr Inform2023; 19(6): 7724–7732.
39.
SuHYaoQXiangL, et al. Semi-supervised temporal meta learning framework for wind turbine bearing fault diagnosis under limited annotation data. IEEE Trans Instrum Meas2024; 73: 1–9.
40.
FengYChenJZhangT, et al. Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis. ISA Trans2022; 120: 383–401.
41.
MaRHanTLeiW. Cross-domain meta learning fault diagnosis based on multi-scale dilated convolution and adaptive relation module. Knowl Based Syst2023; 261: 110175.
42.
WangLYoonKJ. Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans Pattern Anal Mach Intell2021; 44(6): 3048–3068.
