Intelligent bearing fault diagnosis methods based on deep learning have achieved massive results. However, acquiring sufficient labeled samples in engineering is a time-consuming and laborious task, and the signals are often contaminated by strong noise. Therefore, two main strategies are integrated to address these challenges. First, to address insufficient labeled samples, an improved dynamic pseudo-label learning strategy is developed, improving model generalization by involving more unlabeled data in training. Then, to solve the problem of strong noise faced in engineering, a noise reduction learning strategy based on self-supervised learning is proposed, extracting invariant features under noise conditions by a new optimization objective. In addition, a novel dynamic channel pruning strategy is proposed, which prunes channels that play a smaller role in the model, reducing the size of the model and decreasing the model hardware requirements for engineering applications. Finally, the effectiveness and robustness of the proposed strategies are verified on the two high-speed train wheelset-bearing datasets.
ChenBSongDZhangW, et al. A novel spectral coherence-based envelope spectrum for railway axle-box bearing damage identification. Struct Health Monit2023; 22(2): 879–896.
2.
DingPXuYSunX-M.Multi-task learning for aero-engine bearing fault diagnosis with limited data. IEEE Trans Instrum Meas2024; 73: 1–11.
3.
YanSShaoHWangX, et al. Few-shot class-incremental learning for system-level fault diagnosis of wind turbine. IEEE/ASME Trans Mechatr2024; 99: 1–10.
4.
LiXYuTZhangF, et al. Mixed style network based: a novel rotating machinery fault diagnosis method through batch spectral penalization. Reliab Eng Syst Saf2025; 255: 110667.
5.
ChengYZhouNWangZ, et al. CFFsBD: a candidate fault frequencies-based blind deconvolution for rolling element bearings fault feature enhancement. IEEE Trans Instrum Meas2023; 72: 1–12.
6.
ZhaoZLiTWuJ, et al. Deep learning algorithms for rotating machinery intelligent diagnosis: an open source benchmark study. ISA Trans2020; 107: 224–255.
7.
LiYMenZBaiX, et al. A bearing fault diagnosis method based on M-SSCNN and M-LR attention mechanism. Struct Health Monit2024; 24(2): 830–852.
8.
YanJChengYWangQ, et al. Transformer and graph convolution-based unsupervised detection of machine anomalous sound under domain shifts. IEEE Trans Emerg Top Comput Intell2024; 8(4): 2827–2842.
9.
ZhouHLiuRLiY, et al. A rolling bearing fault diagnosis method based on a convolutional neural network with frequency attention mechanism. Struct Health Monit2023; 23(4): 2475–2495.
10.
YanSZhongXShaoH, et al. Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization. Reliab Eng Syst Saf2023; 239: 109522.
11.
ChengYYanJZhangF, et al. Surrogate modeling of pantograph-catenary system interactions. Mech Syst Signal Proc2025; 224: 112134.
12.
LiXLiJZhaoC, et al. Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1d separable convolution with residual connection. Mech Syst Signal Proc2020; 142: 106740.
13.
YanJChengYZhangF, et al. Multi-modal imitation learning for arc detection in complex railway environments. IEEE Trans Instrum Meas2025; 74: 1–13.
14.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Proc2020; 138: 106587.
15.
YuTRenZZhangY, et al. LAFICNN: a novel convolutional adaptive fusion framework for fault diagnosis of rotating machinery. IEEE Trans Instrum Meas2024; 73: 1–9.
16.
TomásMJalaliSTabathaK.A deep neural network for electrical resistance calibration of self-sensing carbon fiber polymer composites compatible with edge computing structural monitoring hardware electronics. Struct Health Monit2024; 23(2): 750–775.
17.
CuiMWangYLinX, et al. Fault diagnosis of rolling bearings based on an improved stack autoencoder and support vector machine. IEEE Sensors J2020; 21(4): 4927–4937.
18.
GunerkarRSJalanAKBelgamwarSU.Fault diagnosis of rolling element bearing based on artificial neural network. J Mech Sci Technol2019; 33: 505–511.
19.
QinYWangLQianQ, et al. Zero-shot attribute consistent model for bearing fault diagnosis under unknown domain. IEEE Trans Instrum Meas2024; 73: 1–11.
20.
DingYJiaMMiaoQ, et al. A novel time–frequency transformer based on self–attention mechanism and its application in fault diagnosis of rolling bearings. Mech Syst Signal Proc2022; 168: 108616.
21.
KimTLeeS.Deep learning integrated Bayesian health indicator for cross-machine health monitoring. Struct Health Monit2024; 23(6): 3416–3429.
22.
TangYZhangCWuJ, et al. Deep learning-based bearing fault diagnosis using a trusted multi-scale quadratic attention-embedded convolutional neural network. IEEE Trans Instrum Meas2024; 73: 1–15.
23.
HouYWangJChenZ, et al. Diagnosisformer: an efficient rolling bearing fault diagnosis method based on improved transformer. Eng Appl Artif Intell2023; 124: 106507.
24.
ChenRZhuJHuX, et al. Fault diagnosis method of rolling bearing based on multiple classifier ensemble of the weighted and balanced distribution adaptation under limited sample imbalance. ISA Trans2021; 114: 434–443.
25.
YuXDongFXiaB, et al. An intelligent fault diagnosis scheme for rotating machinery based on supervised domain adaptation with manifold embedding. IEEE Internet Things J2022; 10(1): 953–972.
26.
DengSZhaoHFangW, et al. Edge intelligence: the confluence of edge computing and artificial intelligence. IEEE Internet Things J2020; 7(8): 7457–7469.
27.
HeJZhuZFanX, et al. Few-shot learning for fault diagnosis: semi-supervised prototypical network with pseudo-labels. Symmetry2022; 14(7): 1489.
28.
TaoXRenCLiQ, et al. Bearing defect diagnosis based on semi-supervised kernel local fisher discriminant analysis using pseudo labels. ISA Trans2021; 110: 394–412.
29.
GaoD-WZhuY-SYanK, et al. Joint learning system based on semi–pseudo–label reliability assessment for weak–fault diagnosis with few labels. Mech Syst Signal Proc2023; 189: 110089.
30.
SohnKBerthelotDCarliniN, et al. Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv Neural Inform Proc Syst2020; 33: 596–608.
31.
GuoL-ZLiY-F.Class-imbalanced semi-supervised learning with adaptive thresholding. In: International conference on machine learning. Cambridge, MA: PMLR, 2022, pp. 8082–8094.
32.
WangYChenHHengQ, et al. Freematch: self-adaptive thresholding for semi-supervised learning. arXiv preprint arXiv:2205.07246, 2022.
33.
ChenHTaoRFanY, et al. Softmatch: addressing the quantity-quality trade-off in semi-supervised learning. arXiv preprint arXiv:2301.10921, 2023.
34.
ChengYWangSChenB, et al. An improved envelope spectrum via candidate fault frequency optimization-gram for bearing fault diagnosis. J Sound Vibr2022; 523: 116746.
35.
ChenJLiZPanJ, et al. Wavelet transform based on inner product in fault diagnosis of rotating machinery: a review. Mech Syst Signal Proc2016; 70: 1–35.
36.
HaoHWangHRehmanN.A joint framework for multivariate signal denoising using multivariate empirical mode decomposition. Signal Proc2017; 135: 263–273.
37.
ChenBZhangWGuJX, et al. Product envelope spectrum optimization-gram: an enhanced envelope analysis for rolling bearing fault diagnosis. Mech Syst Signal Proc2023; 193: 110270.
38.
JiaoZPanLFanW, et al. Partly interpretable transformer through binary arborescent filter for intelligent bearing fault diagnosis. Measurement2022; 203: 111950.
39.
ChaoZHanT.A novel convolutional neural network with multiscale cascade midpoint residual for fault diagnosis of rolling bearings. Neurocomputing2022; 506: 213–227.
40.
WuKLiZChenC, et al. Multi-branch convolutional attention network for multi-sensor feature fusion in intelligent fault diagnosis of rotating machinery. Qual Eng2023; 36(3): 609–623.
41.
HanSMaoHDallyWJ.Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149, 2015.
42.
MolchanovPMallyaATyreeS, et al. Importance estimation for neural network pruning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA, 15–20 June 2019, pp. 11264–11272.
43.
ChenTZhangHZhangZ, et al. Linearity grafting: relaxed neuron pruning helps certifiable robustness. In: International conference on machine learning. Cambridge, MA: PMLR, 2022, pp. 3760–3772.
44.
LuoJ-HWuJLinW. ThiNet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22–29 October 2017, pp. 5058–5066.
45.
HeYZhangXSunJ. Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22–29 October 2017, pp. 1389–1397.
46.
FengK-YFeiXGongM, et al. An automatically layer-wise searching strategy for channel pruning based on task-driven sparsity optimization. IEEE Trans Circuits Syst Video Technol2022; 32(9): 5790–5802.
47.
HuangZWangN. Data-driven sparse structure selection for deep neural networks. In: Proceedings of the European conference on computer vision (ECCV), Munich, Germany, 8–14 September 2018, pp. 304–320.
48.
LiYLiuZWuW, et al. Weight-dependent gates for network pruning. IEEE Trans Circuits Syst Video Technol2022; 32(10): 6941–6954.
49.
WuHPrasadS.Semi-supervised deep learning using pseudo labels for hyperspectral image classification. IEEE Trans Image Proc2017; 27(3): 1259–1270.
50.
Van EngelenJEHoosHH. A survey on semi-supervised learning. Mach Learn2020; 109(2): 373–440.
51.
ZhangBWangYHouW, et al. FlexMatch: boosting semi-supervised learning with curriculum pseudo labeling. Adv Neural Inform Proc Syst2021; 34: 18408–18419.
52.
HeKFanHWuY, et al. Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, 14–19 June 2020, pp. 9729–9738.
53.
JingLTianY.Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans Pattern Anal Mach Intell2020; 43(11): 4037–4058.
54.
BachmanPAlsharifOPrecupD.Learning with pseudo-ensembles. Adv Neural Inform Proc Syst2014; 27: 3365–3373.
55.
YeJLuXLinZ, et al. Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers. arXiv preprint arXiv:1802.00124, 2018.
56.
PengHWuJChenS, et al. Collaborative channel pruning for deep networks. In: International conference on machine learning. Cambridge, MA: PMLR, 2019, pp. 5113–5122.
57.
MessaoudiABenchabaneFSrairiK.DCT-based color image compression algorithm using adaptive block scanning. Signal Image Video Proc2019; 13(7): 1441–1449.
58.
GuoLLeiYXingS, et al. Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Indus Elect2018; 66(9): 7316–7325.
59.
PengDWangHLiuZ, et al. Multibranch and multiscale CNN for fault diagnosis of wheelset bearings under strong noise and variable load condition. IEEE Trans Indus Inform2020; 16(7): 4949–4960.
60.
WangHLiuZPengD, et al. Attention-guided joint learning CNN with noise robustness for bearing fault diagnosis and vibration signal denoising. ISA Trans2022; 128: 470–484.
