In this paper, the issue of cross-condition fault diagnosis of bearing is studied. During actual operation, the conditions of bearing vary due to changes in factors such as rotation speed and load, and the data distribution between different working conditions varies. Deep learning models that perform well in one condition are not ideal when applied to another condition directly. To address this problem, a novel unsupervised domain adaptation fault diagnosis method based on joint feature alignment is proposed in this paper. 1D-CNN is used as a weight-shared feature extractor to extract the features from both the source and target domains. The discrepancies in marginal and conditional distributions between the source and target domains are comprehensively considered by multi-layer multi-bandwidth Cauchy kernel maximum mean discrepancy (MB-CMMD) and mutual information (MI). The domain drift is reduced by aligning the feature representations of source and target domains. The network after feature alignment demonstrates a notable enhancement in the diagnostic accuracy of unlabeled samples within the target domain. The experimental results demonstrate that, in comparison to other domain adaptation approaches, The proposed approach can significantly enhance the accuracy of fault diagnosis while realizing feature alignment.
ChenXYangRXueY, et al. Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Meas2023; 72: 1–21.
2.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587–106587. DOI: 10.1016/j.ymssp.2019.106587
3.
XiaoDHuangYQinC, et al. Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis. Proc IMechE, Part C: J Mechanical Engineering Science2019; 233(14): 5131–5143.
4.
ZhangWPengGLiC, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors (Basel)2017; 17(2): 425. DOI: doi: 10.3390/s17020425
5.
HoangD-TKangH-J.Rolling element bearing fault diagnosis using convolutional neural network and vibration image. Cogn Syst Res2019; 53: 42–50.
6.
HouJLuXZhongY, et al. Rolling bearing fault diagnosis method by using feature extraction of convolutional time-frequency image. Proc IMechE, Part C: J Mech Eng Sci2024; 238(9): 4212–4228.
7.
MaoWTianSLiangX, et al. Online bearing fault diagnosis using support vector machine and stacked auto-encoder. In: IEEE International conference on prognostics and health management (ICPHM), Seattle, WA, 11–13 June 2018.
8.
NiQJiJCFengK, et al. Data-driven bearing health management using a novel multi-scale fused feature and gated recurrent unit. Reliab Eng Syst Saf2024; 242: 253–246.
9.
ChenZDengSChenX, et al. Deep neural networks-based rolling bearing fault diagnosis. Microelectron Reliab2017; 75: 327–333.
10.
CenJChenZWuY, et al. Intelligent machine fault diagnosis based on deep transfer convolutional neural network and extreme learning machine. Proc IMechE, Part C: J Mech Eng Sci2023; 237(9): 2201–2212.
11.
KouwWvan der MaatenLKrijtheJ, et al. Feature-level domain adaptation. J Mach Learn Res2016; 17: 1–32.
12.
LuWLiangBChengY, et al. Deep model based domain adaptation for fault diagnosis. IEEE Trans Ind Electron2017; 64(3): 2296–2305.
13.
FengKJiJCZhangY, et al. Digital twin-driven intelligent assessment of gear surface degradation. Mech Syst Signal Process2023; 186: 167–178.
14.
GaninYUstinovaEAjakanH.Domain-adversarial training of neural networks. J Mach Learn Res2016; 17: 1–35. 2016.
15.
JiamengLFanfanZLibingL, et al. Fault diagnosis method for bearings based on domain adversarial neural networks. J Mech Electr Eng2020; 37: 227–233.
16.
RuohuiHMinZWenxinX.Cross-domain fault diagnosis of rolling element bearings using DCGAN and DANN. J Vib Shock2022; 41(21-22): 21–29.
17.
ZhangYJiJCRenZ, et al. Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing. Reliab Eng Syst Saf2023; 234: 1067–1083. DOI: 10.1016/j.ress.2023.109186
18.
LiRLiSXuK, et al. A novel symmetric stacked autoencoder for adversarial domain adaptation under variable speed. IEEE Access2022; 10: 24678–24689.
19.
LiuZ-HLuBLWeiH-L, et al. Deep adversarial domain adaptation model for bearing fault diagnosis. IEEE Trans Syst Man Cybern Syst2021; 51(7): 4217–4226.
20.
SaitoKWatanabeKUshikuY, et al. Maximum classifier discrepancy for unsupervised domain adaptation. In: 31st IEEE/CVF conference on computer vision and pattern recognition (CVPR), Salt Lake City, UT, 18-23 June 2018, pp. 3723-3732.
21.
WenLGaoLLiX.A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE Trans Syst Man Cybern Syst2019; 49(1): 136–144.
22.
YuhanYXiaoxiaZJingW, et al. Fault Diagnosis of Bearing Based on Improved Particle Filter and Domain Adaptative CNN. Modul Machine Tool Automat Manuf Techn2023: 100-104. DOI: 10.13462/j.cnki.mmtamt.2023.02.023
23.
CheCWangHNiX, et al. Domain adaptive deep belief network for rolling bearing fault diagnosis. Comput Ind Eng2020; 143: 106427–106427. DOI: 10.1016/j.cie.2020.106427
24.
XiaYXuW.A deep adaptive network for cross-domain bearing fault diagnosis. J Vib Shock2022; 41: 45–53.
25.
NiQJiJCHalkonB, et al. Physics-informed residual network (PIResNet) for rolling element bearing fault diagnostics. Mech Syst Signal Process2023; 200: 236–254.
26.
JiaSDengYLvJ, et al. Joint distribution adaptation with diverse feature aggregation: a new transfer learning framework for bearing diagnosis across different machines. Measurement2022; 187: 332–357.
27.
LongMWangJDingG, et al. Transfer feature learning with joint distribution adaptation. In: 2013 IEEE international conference on computer vision, 2013, pp. 2200–2207.
28.
WangJChenYHaoS, et al. Balanced distribution adaptation for transfer learning. In: 2017 IEEE international conference on data mining (ICDM), 2017, pp. 1129–1134.
29.
BorgwardtKMGrettonARaschMJ, et al. Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics2006; 22(14): e49–e57.
30.
WangJJYWangYZhaoS, et al. Maximum mutual information regularized classification. Eng Appl Artif Intell2015; 37: 1–8.
31.
ChenJWangJZhuJ, et al. Unsupervised cross-domain fault diagnosis using feature representation alignment networks for rotating mMachinery. IEEE/ASME Trans Mechatron2021; 26(5): 2770–2781.
32.
WangYFengLZhangZ, et al. An unsupervised domain adaptation deep learning method for spatial and temporal transferable crop type mapping using Sentinel-2 imagery. ISPRS J Photogramm Remote Sens2023; 199: 102–117.
33.
XiangGChenWPengY, et al. Deep transfer learning based on convolutional neural networks for intelligent fault diagnosis of spacecraft. In: Chinese Automation Congress (CAC), Shanghai, Peoples R China, 6-8 November 2020, 2020Chinese Automation Congress (CAC 2020), pp. 5522–5526.
34.
XiangLZhangXZhangY, et al. A novel method for rotor fault diagnosis based on deep transfer learning with simulated samples. Measurement2023; 207: 109–121. DOI: 10.1016/j.measurement.2022.112350
35.
ShaoJHuangZZhuJ.Transfer learning method based on adversarial domain adaption for bearing fault diagnosis. IEEE Access2020; 8: 119421–119430.
36.
SmithWARandallRB.Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study. Mech Syst Signal Process2015; 64-65: 100–131.
37.
LongMCaoYWangJ, et al. Learning transferable features with deep adaptation networks. In: 32nd International conference on machine learning, Lille, France, 7-9 July 2015, vol. 37, pp. 97–105.
38.
ZhuJChenNShenC.A new deep transfer learning method for bearing fault diagnosis under different working conditions. IEEE Sens J2020; 20(15): 8394–8402.
