The field of bearing fault diagnosis has witnessed remarkable advancements with cross-domain fault diagnosis techniques. Nonetheless, these existing methods suffer from two main drawbacks. First, the input length of these methods is fixed, such as 2048 sample points, irrespective of the diverse sampling frequencies, bearing structure parameters, and rotational speeds observed among transfer objects. Additionally, the transfer learning methods currently employed are not robust to noise, rendering them incapable of functioning optimally in contaminated target domains. To address the aforementioned challenges, this study presents an unsupervised transfer network for train axle bearing fault diagnosis. First, an adaptive input module is proposed, which enables the input length of the proposed network to be adaptively selected based on parameters such as sampling frequency and bearing structure. Then, an enhanced feature learning block with sharing parameters is designed to enhance the transfer learning feature extraction capability under noise condition. Next, a dynamic channel pruning module is proposed to optimize of the proposed network. Finally, the transferability of the proposed network is demonstrated through experiments involving two types of transfer learning tasks. The proposed network exhibits robustness to noise and outperforms existing methods by achieving higher diagnostic accuracy and stability.
LiWHuangRLiJ, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mech Syst Signal Process2022; 167: 108487.
2.
ChenBZhangWSongD, et al. Squared envelope sparsification via blind deconvolution and its application to railway axle bearing diagnostics. Struct Health Monit2023; 22: 3637–3658.
3.
ChenBSongDZhangW, et al. A novel spectral coherence-based envelope spectrum for railway axle-box bearing damage identification. Struct Health Monit2023; 22(2): 879–896.
4.
San MartinGLopez DroguettEMeruaneV, et al. Deep variational auto-encoders: a promising tool for dimensionality reduction and ball bearing elements fault diagnosis. Struct Health Monit2019; 18(4): 1092–1128.
5.
ZhaoZZhangQYuX, et al. Applications of unsupervised deep transfer learning to intelligent fault diagnosis: a survey and comparative study. IEEE Trans Instrum Meas2021; 70: 1–28.
6.
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: 818–835.
7.
WuXZhangYChengC, et al. A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery. Mech Syst Signal Process2021; 149: 107327.
8.
LiangPDengCWuJ, et al. Single and simultaneous fault diagnosis of gearbox via a semi-supervised and high-accuracy adversarial learning framework. Knowledge-Based Syst2020; 198: 105895.
9.
YuKLinTRTanJ.A bearing fault and severity diagnostic technique using adaptive deep belief networks and dempster–shafer theory. Struct Health Monit2020; 19(1): 240–261.
10.
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.
11.
WangCZhuGLiuT, et al. A sub-domain adaptive transfer learning base on residual network for bearing fault diagnosis. J Vibr Control2023; 29(1–2): 105–117.
12.
DengYHuangDDuS, et al. A double-layer attention based adversarial network for partial transfer learning in machinery fault diagnosis. Comput Ind2021; 127: 103399.
13.
WangZHeXYangB, et al. Subdomain adaptation transfer learning network for fault diagnosis of roller bearings. IEEE Trans Ind Electron2021; 69(8): 8430–8439.
14.
QianQQinYLuoJ, et al. Deep discriminative transfer learning network for cross-machine fault diagnosis. Mech Syst Signal Process2023; 186; 109884.
15.
WangMDengW.Deep visual domain adaptation: a survey. Neurocomputing2018; 312: 135–153.
16.
TzengEHoffmanJZhangN, et al. Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
17.
LongMCaoYWangJ, et al. Learning transferable features with deep adaptation networks. In: International conference on machine learning, Lille, France, 2015, pp. 97–105. PMLR.
18.
SunBSaenkoK. Deep coral: correlation alignment for deep domain adaptation. In: Computer vision–ECCV 2016 workshops. Amsterdam, The Netherlands, 8–10 and 15–16 October 2016, Proceedings, Part III 14, 2016, pp. 443–450. Springer.
19.
GaninYUstinovaEAjakanH, et al. Domainadversarial training of neural networks. J Mach Learn Res2016; 17(1): 2096–2030.
20.
YuCWangJChenY, et al. Transfer learning with dynamic adversarial adaptation network. In: 2019 IEEE international conference on data mining (ICDM), Beijing, China, 2019, pp. 778–786. IEEE.
21.
BousmalisKTrigeorgisGSilbermanN, et al. Domain separation networks. Adv Neural Inform Process Syst2016; arXiv preprint arXiv:1608.06019. DOI: 10.48550/arXiv.1608.06019.
22.
GhifaryMKleijnWBZhangM, et al. Deep reconstruction-classification networks for unsupervised domain adaptation. In: Computer Vision– ECCV 2016: 14th European conference, Amsterdam, The Netherlands, 11–14 October 2016, Proceedings, Part IV 14, 2016, pp. 597–613. Springer.
23.
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.
24.
WangXShenCXiaM, et al. Multi-scale deep intra-class transfer learning for bearing fault diagnosis. Reliab Eng Syst Safety2020; 202: 107050.
25.
ZhangWLiXMaH, et al. Open-set domain adaptation in machinery fault diagnostics using instance-level weighted adversarial learning. IEEE Trans Ind Inform2021; 17(11): 7445–7455.
26.
ZhuJChenNShenC.A new deep transfer learning method for bearing fault diagnosis under different working conditions. IEEE Sens J2019; 20(15): 8394–8402.
27.
LiXZhangWDingQ.Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks. IEEE Trans Ind Electron2018; 66(7): 5525–5534.
28.
LiuYWangYChowTW, et al. Deep adversarial subdomain adaptation network for intelligent fault diagnosis. IEEE Trans Ind Inform2022; 18(9): 6038–6046.
29.
ZhuJChenNShenC.A new multiple source domain adaptation fault diagnosis method between different rotating machines. IEEE Trans Ind Inform2020; 17(7): 4788–4797.
30.
YuYGuoLTanY, et al. Multisource partial transfer network for machinery fault diagnostics. IEEE Trans Ind Electron2021; 69(10): 10585–10594.
31.
ChenBZhangWGuJX, et al. Product envelope spectrum optimization-gram: an enhanced envelope analysis for rolling bearing fault diagnosis. Mech Syst Signal Process2023; 193: 110270.
32.
LiuZWangHLiuJ, et al. Multitask learning based on lightweight 1DCNN for fault diagnosis of wheelset bearings. IEEE Trans Instrum Meas2020; 70: 1–11.
33.
DengMDengAShiY, et al. Correlation regularized conditional adversarial adaptation for multi-target-domain fault diagnosis. IEEE Trans Ind Inform2022; 18(12): 8692–8702.
34.
JiangYXiaTWangD, et al. Adversarial regressive domain adaptation approach for infrared thermography-based unsupervised remaining useful life prediction. IEEE Trans Ind Inform2022; 18(10): 7219–7229.
35.
QinYQianQWangY, et al. Intermediate distribution alignment and its application into mechanical fault transfer diagnosis. IEEE Trans Ind Inform2022; 18(10): 7305–7315.
36.
GaninYLempitskyV. Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, Lille, France, 2015, pp. 1180–1189. PMLR.
37.
LiXZhangW.Deep learning-based partial domain adaptation method on intelligent machinery fault diagnostics. IEEE Trans Ind Electron2020; 68(5): 4351–4361.
38.
QinNWuBHuangD, et al. Stepwise adaptive convolutional network for fault diagnosis of high-speed train bogie under variant running speeds. IEEE Trans Ind Inform2022; 18(12): 8389–8398.
39.
YangBXuSLeiY, et al. Multi-source transfer learning network to complement knowledge for intelligent diagnosis of machines with unseen faults. Mech Syst Signal Process2022; 162: 108095.
40.
YangBLeeCGLeiY, et al. Deep partial transfer learning network: a method to selectively transfer diagnostic knowledge across related machines. Mech Syst Signal Process2021; 156: 107618.
41.
GuoLYuYDuanA, et al. An unsupervised feature learning based health indicator construction method for performance assessment of machines. Mech Syst Signal Process2022; 167: 108573.
42.
PeiXDongSTangB, et al. Bearing running state recognition method based on feature-to-noise energy ratio and improved deep residual shrinkage network. IEEE/ASME Trans Mechatron2021; 27(5): 3660–3671.
43.
HuHPengRTaiYW, et al. Network trimming: a data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250, 2016.
44.
PrecheltL.Early stopping-but when?MontavonG (ed.) In: Neural networks: tricks of the trade, 2002, pp. 55–69. London: Springer.
45.
CuiSWangSZhuoJ, et al. Towards discriminability | diversity: Batch nuclear-norm maximization under label insufficient situations. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, 2020, pp. 3941–3950.
46.
SunBSaenkoK. Deep coral: correlation alignment for deep domain adaptation. In: Computer vision–ECCV 2016 workshops, Amsterdam, The Netherlands, 8–10 and 15–16 October 2016, Proceedings, Part III 14, 2016, pp. 443–450. Springer.
47.
ZhuYZhuangFWangJ, et al. Deep subdomain adaptation network for image classification. IEEE Trans Neural Netw Learn Syst2020; 99: 1–10.
48.
YuCWangJChenY, et al. Transfer learning with dynamic adversarial adaptation network. In: 2019 IEEE international conference on data mining (ICDM), 2019, pp. 778–786. IEEE. Beijing, China.
49.
GuoLLeiYXingS, et al. Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans Ind Electron2018; 66(9): 7316–7325.
50.
XiaPHuangYLiP, et al. Fault knowledge transfer assisted ensemble method for remaining useful life prediction. IEEE Trans Ind Inform2021; 18(3): 1758–1769.
