Bearing fault diagnosis is an important research field for rotating machinery health monitoring. Recently, many intelligent fault diagnosis methods driven by big data, such as transfer learning, have been studied. However, there are two shortcomings for the prior transfer learning method in industry application. First, it is necessary to design a complex loss function to enhance the similarity between the two domains further. Second, previous studies required big data both in source and target task, without considering the lack of sufficient training samples. Inspired by relevant research work, this article proposes a local joint distribution discrepancy to increase similar features. A sub-domain adaptive transfer learning is designed to detect bearing faults based on the residual network. Two kinds of transfer experiments are designed to verify the method effectiveness. After that, the impact of small training samples and noise on the results is explored. The proposed method reaches high accuracy.
Ben-DavidSBlitzerJCrammerK, et al. (2010) A theory of learning from different domains. Mach. Learn79(1–2): 151–175.
2.
CerradaMSánchezR-VLiC, et al. (2018) A review on data-driven fault severity assessment in rolling bearings. Mechanical Systems and Signal Processing99: 169–196.
3.
ChengCZhouBMaG, et al. (2020) Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis with unlabeled or insufficient labeled data. Neurocomputing409: 35–45.
4.
GaninYUstinovaEAjakanH, et al. (2015) Domain-adversarial training of neural networks. Computer Science17: 1–35.
5.
GuoLLeiYXingS, et al. (2019) Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Transactions on Industrial Electronics66(9): 7316–7325.
6.
HofferEHubaraISoudryD (2017) Train longer, generalize better: closing the generalization gap in large batch training of neural networks. Advances in Neural Information Processing Systems30: 1731–1741.
7.
InceTKiranyazSErenL, et al. (2016) Real-time motor fault detection by 1-D convolutional neural networks. IEEE Transactions on Industrial Electronics63(11): 7067–7075.
8.
JiangG.HeH.YanJ., et al. (2019) Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox. IEEE Transactions on Industrial Electronics66(4): 3196–3207.
9.
JiaoJZhaoMLinJ, et al. (2020) Residual joint adaptation adversarial network for intelligent transfer fault diagnosis. Mechanical Systems and Signal Processing145: 106962.
10.
KaimingHXiangyuZShaoqingR, et al. (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 27-30 June. DOI: 10.1109/CVPR.2016.90.770-778
11.
KingmaDBaJ (2014) Adam: a method for stochastic optimization. Computer Science.
12.
LeiYYangBJiangX, et al. (2020) Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing138: 106587.
13.
LiCZhangSQinY, et al. (2020a) A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing407: 121–135.
14.
LiXZhangWMaH, et al. (2020b) Partial transfer learning in machinery cross-domain fault diagnostics using class-weighted adversarial networks. Neural Networks129: 313–322.
15.
MaSChuFHanQ (2019) Deep residual learning with demodulated time-frequency features for fault diagnosis of planetary gearbox under nonstationary running conditions. Mechanical Systems and Signal Processing127: 190–201.
16.
MingshengLJianminWJordanMI (2016) Deep Transfer Learning with Joint Adaptation Networks[arXiv]. arXiv. 10 pp.
17.
PanS. J.YangQ. (2010) A survey on transfer learning. Ieee Transactions on Knowledge and Data Engineering22(10): 1345–1359.
18.
QiuHLeeJLinJ, et al. (2006) Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics. Journal of Sound and Vibration289(4–5): 1066–1090.
19.
SmithWARandallRB (2015) Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mechanical Systems and Signal Processing64-65: 100–131.
20.
TongHZhiZHangZ, et al. (2019) Bag of tricks for image classification with convolutional neural networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, pp. 558–567.
21.
van der MaatenLHintonG (2008) Visualizing data using t-SNE. Journal of Machine Learning Research9: 2579–2605.
22.
WangCXieYZhangD (2021) Deep learning for bearing fault diagnosis under different working loads and non-fault location point. Journal of Low Frequency Noise, Vibration and Active Control40(1): 588–600.
23.
WenLGaoLLiX (2019) A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE Transactions on Systems, Man, and Cybernetics: Systems49(1): 136–144.
24.
WuZJiangHLuT, et al. (2020) A deep transfer maximum classifier discrepancy method for rolling bearing fault diagnosis under few labeled data. Knowledge-Based Systems196: 105814.
25.
YangBLeiYJiaF, et al. (2019) An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mechanical Systems and Signal Processing122: 692–706.
26.
ZhangWLiCPengG, et al. (2018) A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical Systems and Signal Processing100: 439–453.
27.
ZhangWLiXDingQ (2019) Deep residual learning-based fault diagnosis method for rotating machinery. Isa Transactions95: 295–305.
28.
ZhaoRYanRChenZ, et al. (2019) Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing115: 213–237.
29.
ZhuXHouDZhouP, et al. (2019) Rotor fault diagnosis using a convolutional neural network with symmetrized dot pattern images. Measurement138: 526–535.
30.
ZhuYZhuangFWangJ, et al. (2021) Deep subdomain adaptation network for image classification. IEEE Transactions on Neural Networks and Learning Systems32(4): 1713–1722.
