To address the challenge of limited labeled data and complex fault characteristics in small-sample rolling bearing diagnosis, an intelligent diagnosis method of rolling bearing based on single working condition data expansion and transfer under small samples is proposed. Eighteen state simulation schemes of rolling bearing including loose sensor connection under six working conditions were designed, and the variational mode decomposition-gray texture image (VMD-GTI) samples were obtained by using the vibration signal conversion method. To enhance diagnostic reliability under small-sample conditions, an improved deep convolutional generative adversarial network (DCGAN) is employed for small-sample image expansion, thereby enriching data diversity. To enhance feature representation and improve fault diagnosis accuracy, an enhanced ResNet-18-EMA-Conv is developed by incorporating exponential moving average (EMA) convolution into residual neural network (ResNet). To enable knowledge transfer under limited data, the improved DCGAN is adopted to augment single-condition samples, and the pretrained ResNet-18-EMA-Conv model is validated through both self-transfer and cross-condition transfer. The results show that when the number of original samples is 100, the optimal expansion ratio is 1:1. After expansion, the accuracy of fault diagnosis using ResNet is improved from 0.8968 to 0.9467, which is increased by 0.0499, and the accuracy of fault diagnosis model improved by EMA convolution is further improved from 0.9467 to 0.9732, which is increased by 0.0265. Using the self-transfer of single-working condition data, the accuracy of fault diagnosis is improved from 0.9732 to 0.9810 again, which is improved by 0.0078. The average testing accuracy increased from 0.8523 to 0.9378 and increased by 0.0855 under six working conditions. These results confirm that the proposed framework effectively enhances diagnostic accuracy and generalization for complex bearing fault modes under small samples and multi-condition scenarios.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap. Mech Syst Signal Process2020; 138: 106587.
2.
LiJLuoWBaiM.Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signal. Meas Sci Technol2024; 35: 092001.
3.
AbboudDAntoniJSieg-ZiebaS, et al. Envelope analysis of rotating machine vibrations in variable speed conditions: a comprehensive treatment. Mech Syst Signal Process2017; 84: 200–226.
4.
AltmannJMathewJ.Multiple band-pass autoregressive demodulation for rolling-element bearing fault diagnosis. Mech Syst Signal Process2001; 15: 963–977.
5.
ZhengJPanHChengJ.Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines. Mech Syst Signal Process2017; 85: 746–759.
6.
VanMHoangDTKangHJ.Bearing fault diagnosis using a particle swarm optimization-least squares wavelet support vector machine classifier. Sensors2020; 20: 3422.
7.
Gilbert ChandraDSrinivasulu ReddyUUmaG, et al. Group normalization-based 2D-convolutional neural network for intelligent bearing fault diagnosis. J Braz Soc Mech Sci Eng2023; 45: 585.
8.
ShaoHJiangHLinY, et al. A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders. Mech Syst Signal Process2018; 102: 278–297.
9.
XuYYanXSunB, et al. Dually attentive multiscale networks for health state recognition of rotating machinery. Reliab Eng Syst Safety2022; 225: 108626.
10.
GammaitoniLHänggiPJungP, et al. Stochastic resonance. Rev Mod Phys1998, 70(1): 223.
11.
QiaoZZhangCZhangC, et al. Stochastic resonance array for designing noise-boosted filter banks to enhance weak multi-harmonic fault characteristics of machinery. Appl Acoust2025; 236: 110710.
12.
SongDXuFHuJ, et al. Fault feature recognition of centrifugal compressor with cracked blade based on SNR estimation and adaptive stochastic resonance. Struct Health Monit. 2022; 22(1): 131–150.
13.
San MartinGLópez DroguettEMeruaneV, et al. Deep variational auto-encoders: a promising tool for dimensionality reduction and ball bearing elements fault diagnosis. Struct Health Monit2018; 18: 1092–1128.
14.
XinLHaidongSHongkaiJ, et al. Modified Gaussian convolutional deep belief network and infrared thermal imaging for intelligent fault diagnosis of rotor-bearing system under time-varying speeds. Struct Health Monit2021; 21: 339–353.
15.
ZhangJZhangQQinX, et al. Robust fault diagnosis of quayside container crane gearbox based on 2D image representation in frequency domain and CNN. Struct Health Monit2023; 23: 324–342.
16.
ShiJPengDPengZ, et al. Planetary gearbox fault diagnosis using bidirectional-convolutional LSTM networks. Mech Syst Signal Process2022; 162: 107996.
17.
LuoWLiJSongM, et al. Fault diagnosis of high-speed rolling bearings based on multi-feature fusion fuzzy c-means. Digit Signal Process2025; 159: 105011.
18.
MengHZhangJZhaoJ, et al. A multi-scale feature extraction and fusion method for bearing fault diagnosis based on hybrid attention mechanism. Signal Image Video Process2024; 18: 31–41.
19.
LiDLiMYangL, et al. Rolling bearing fault diagnosis in strong noise background based on vibration signals. Signal Image Video Process2023; 18: 1295–1303.
20.
HongweiFCeyiXJiatengM, et al. A novel intelligent diagnosis method of rolling bearing and rotor composite faults based on vibration signal-to-image mapping and CNN-SVM. Meas Sci Technol2023; 34: 044008.
21.
DjaballahSMeftahKKhelilK, et al. Deep transfer learning for bearing fault diagnosis using CWT Time–Frequency images and convolutional neural networks. J Fail Anal Prev2023; 23: 1046–1058.
22.
NacerSMNadiaBAbdelghaniR, et al. A novel method for bearing fault diagnosis based on BiLSTM neural networks. Int J Adv Manuf Technol2023; 125: 1477–1492.
23.
GroverCTurkN.A novel fault diagnostic system for rolling element bearings using deep transfer learning on bispectrum contour maps. Eng Sci Technol2022; 31: 101049.
24.
TomaRNPiltanFKimJ-M.A deep autoencoder-based convolution neural network framework for bearing fault classification in induction motors. Sensors2021; 21: 8453.
25.
Nishat TomaRKimC-HKimJ-M. Bearing fault classification using ensemble empirical mode decomposition and convolutional neural network. Electronics2021; 10: 1248.
26.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial networks. Commun ACM2020; 63: 139–144.
27.
QianQQinYLuoJ, et al. Deep discriminative transfer learning network for cross-machine fault diagnosis. Mech Syst Signal Process2023; 186: 109884.
RadfordAMetzLChintalaS.Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint2015, http://arxiv.org/abs/1511.06434
30.
ArjovskyMChintalaSBottouL.Wasserstein GAN. In: Proceedings of the 34th International Conference on Machine Learning (ICML), 2017, pp.214–223. Sydney, Australia: ACM.
31.
GulrajaniIAhmedFArjovskyM, et al. Improved training of Wasserstein GANs. Adv Neural Inf Process Syst2017; 30: 5767–5777.
32.
WuJHuangZThomaJ, et al. Wasserstein divergence for gans. In: Proceedings of the European conference on computer vision (ECCV), 2018, pp.653–668. Munich, Germany: Springer.
33.
LiuSJiangHWuZ, et al. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis. Measurement2021; 168: 108371.
34.
QinRQinMBaoH, et al. A novel GAN-based signal resolution enhancement method for mechanical fault diagnosis under sample insufficiency. IEEE Trans Instrum Meas2025; 74: 1–11.
35.
WuJZhaoZSunC, et al. Ss-InfoGAN for class-imbalance classification of bearing faults. Procedia Manuf2020; 49: 99–104.
36.
SunLWuJLiG, et al. A data enhanced algorithm for fault diagnosis of slewing bearings based on times-series generative adversarial networks. Signal Image Video Process2025; 19, 329.
37.
FanHMaJZhangX, et al. Intelligent data expansion approach of vibration gray texture images of rolling bearing based on improved WGAN-GP. Adv Mech Eng2022; 14: 168781322210861.
38.
ChenXYangRXueY, et al. Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Meas2023; 72: 1–21.
39.
VashishthaGChauhanSSehriM, et al. Advancing machine fault diagnosis: a detailed examination of convolutional neural networks. Meas Sci Technol2024; 36: 022001.
40.
XuGGuoRYinZ, et al. MCRCNet: a bearing fault diagnosis method for unknown faults based on transfer learning. Appl Sci2025; 15: 921.
41.
ShaoHXiaMHanG, et al. Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images. IEEE Trans Indus Inform2021; 17: 3488–3496.
42.
YangSZhengX.A novel bearing fault diagnosis method with feature selection and manifold embedded domain adaptation. Proc Inst Mech Eng C: J Mech Eng Sci2022; 236: 8185–8197.
43.
KimTChaiJ.Pre-processing method to improve cross-domain fault diagnosis for bearing. Sensors2021; 21: 4970.
44.
FanHChenBCaoX, et al. An intelligent multi-element fault diagnosis method of rolling bearings considering damage degrees and sensor abnormity under small samples. Proc Inst Mech Eng C J Mech Eng Sci2024; 239: 2334–2356.
45.
HaynesDCornsSVenayagamoorthyGK.An exponential moving average algorithm. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC), 2012, pp.1–8. Brisbane, Australia: IEEE.
46.
FanHRenZZhangX, et al. A gray texture image data-driven intelligent fault diagnosis method of induction motor rotor-bearing system under variable load conditions. Measurement2024; 233: 114742.
47.
FanHRenZCaoX, et al. A GTI&Ada-Act LMCNN method for intelligent fault diagnosis of motor rotor-bearing unit under variable conditions. IEEE Trans Instrum Meas2024; 73: 1–14.
48.
LecunYBottouL.Gradient-based learning applied to document recognition. Proc IEEE1998; 86: 2278–2324.
49.
KrizhevskyASutskeverIHintonG.ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst2012; 2: 1097–1105.
50.
SzegedyCLiuWJiaY, et al. Going deeper with convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp.1–9. Boston, MA: IEEE.
51.
HuangGLiuZVan Der MaatenL, et al. Densely connected convolutional networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp.2261–2269. Honolulu, HI: IEEE.
