Rolling bearings are fundamental components in machinery, and precise fault diagnosis is critical for assessing the overall reliability of mechanical systems. In cross-domain fault diagnosis, domain drift presents a primary challenge, often leading to performance degradation or model failure, particularly under cross-machine conditions characterized by pronounced distributional discrepancies. This study introduces an innovative framework for cross-machine fault diagnosis, termed the dynamical joint distribution domain adaptation (DJDA) network. In the DJDA framework, a dynamic weighting mechanism is employed to adaptively and quantitatively adjust both overall alignment and individual class discrimination between domains, while simultaneously learning marginal and conditional feature distributions. The multilayer-multiple universal-order moment matching technique is utilized to enhance global distribution alignment between domains, while multiclassifier-assisted adversarial domain adaptation (multiclassifier-GADA) automatically mitigates class discrepancies. Extensive experiments reveal that the proposed framework significantly outperforms state-of-the-art methods and demonstrates promising potential for application in industrial contexts.
JiangXWangJShenC, et al. An adaptive and efficient variational mode decomposition and its application for bearing fault diagnosis. Struct Health Monit2021; 20(5): 2708–2725.
2.
ZhangCZhangL.Wind turbine pitch bearing fault detection with Bayesian augmented temporal convolutional networks. Struct Health Monit2024; 23(2): 1089–1106.
3.
ZhangHWangWZhangS, et al. A novel method for intersecting machining feature segmentation via deep reinforcement learning. Adv Eng Inform2024; 59: 102256.
4.
ZhaoXJiaM.A novel unsupervised deep learning network for intelligent fault diagnosis of rotating machinery. Struct Health Monit2020;19(6): 1745–1763.
5.
LiYBaoTGaoZ, et al. A new dam structural response estimation paradigm powered by deep learning and transfer learning techniques. Struct Health Monit2022;21(3): 770–787.
6.
WuZZhangHGuoJ, et al. Imbalanced bearing fault diagnosis under variant working conditions using cost-sensitive deep domain adaptation network. Expert Syst Appl2022; 193: 116459.
7.
AsutkarSChalkeCShivganK, et al. TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis. Expert Syst Appl2023; 213: 119016.
8.
WeiXWenBYangF, et al. Task-oriented contrastive learning for unsupervised domain adaptation. Expert Syst Appl2023; 229: 120471.
9.
YuXWangYLiangZ, et al. An adaptive domain adaptation method for rolling bearings’ fault diagnosis fusing deep convolution and self-attention networks. IEEE Trans Instrum Meas2023; 72: 1–14.
10.
GhorveiMKavianpourMBeheshtiMT, et al. Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosis. arXiv Preprint 2021; 2021: 2112.06033.
11.
ChenXYangRWenH, et al. Transfer learning with unsupervised domain adaptation method for bearing fault diagnosis. In: 2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes (SAFEPROCESS), December 2021, Chengdu, China: IEEE, pp.1–6.
12.
ZhaoHJinX. Deep joint discriminative feature learning and class-aware domain alignment for unsupervised domain adaptation. In: 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN), February 2020, Noida, India: IEEE, pp.761–766.
13.
CaoHShaoHLiuB, et al. Clustering-guided novel unsupervised domain adversarial network for partial transfer fault diagnosis of rotating machinery. IEEE Sensors J. 2022; 22(14): 14387–14396.
14.
LiangPWangBJiangG, et al. Unsupervised fault diagnosis of wind turbine bearing via a deep residual deformable convolution network based on subdomain adaptation under time-varying speeds. Eng Appl Artif Intell2023; 118: 105656.
15.
HeJSuNXuC, et al. A cross-modality feature transfer method for target detection in SAR images. IEEE Trans Geosci Remote Sens2023; 233: 9003.
16.
LiuYHuangX.Efficient cross-modality insulator augmentation for multi-domain insulator defect detection in UAV images. Sensors2023; 293: 121003.
17.
DingYDingPZhaoX, et al. Transfer learning for remaining useful life prediction across operating conditions based on multisource domain adaptation. IEEE/ASME Trans Mech2022; 4143: 4152.
18.
LiXZhangWLiX, et al. Partial domain adaptation in remaining useful life prediction with incomplete target data. IEEE/ASME Trans Mech2023; 203: 117297.
19.
LeeJKoJUKimT, et al. Domain adaptation with label-aligned sampling (DALAS) for cross-domain fault diagnosis of rotating machinery under class imbalance. Expert Syst Appl2024; 243: 122910.
20.
ZhaoKJiaFShaoH.A novel conditional weighting transfer Wasserstein auto-encoder for rolling bearing fault diagnosis with multi-source domains. Knowl Based Syst2023; 262: 110203.
21.
XiaYShenCWangD, et al. Moment matching-based intraclass multisource domain adaptation network for bearing fault diagnosis. Mech Syst Signal Process2022; 168: 108697.
22.
WanLLiYChenK, et al. A novel deep convolution multi-adversarial domain adaptation model for rolling bearing fault diagnosis. Measurement2022; 191: 110752.
23.
LuFTongQFengZ, et al. Unbalanced bearing fault diagnosis under various speeds based on spectrum alignment and deep transfer convolution neural network. IEEE Trans Ind Inform. 2023; 19(7): 8295–8306.
24.
TanHXieSMaW, et al. Correlation feature distribution matching for fault diagnosis of machines. Reliab Eng Syst Saf2023; 231: 108981.
25.
WangZHeXYangB, et al. Subdomain adaptation transfer learning network for fault diagnosis of roller bearings. IEEE Trans Ind Electron2022; 69(8): 8430–8439.
26.
SuZZhangJTangJ, et al. A novel deep transfer learning method with inter-domain decision discrepancy minimization for intelligent fault diagnosis. Knowl Based Syst2023; 259: 110065.
27.
JiaSDengYLvJ, et al. Joint distribution adaptation with diverse feature aggregation: a new transfer learning framework for bearing diagnosis across different machines. Measurement2022; 187: 110332.
28.
RenHLiuWShanM, et al. A novel wind turbine health condition monitoring method based on composite variational mode entropy and weighted distribution adaptation. Renew Energy2021; 168: 972–980.
QianWLiSWangJ.A new transfer learning method and its application on rotating machine fault diagnosis under variant working conditions. IEEE Access2017; 6: 11.
31.
ZouQLuLYangZ, et al. Multi-source cross project defect prediction with joint wasserstein distance and ensemble learning. In: 2021 IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE), October 2021, Wuhan, China: IEEE, pp. 57–68.
32.
LuoSHuangXWangY, et al. Transfer learning based on improved stacked autoencoder for bearing fault diagnosis. Knowl Based Syst2022; 256: 109846.
33.
ChenZXiaJLiJ, et al. Generalized open-set domain adaptation in mechanical fault diagnosis using multiple metric weighting learning network. Adv Eng Inform2023; 57: 102033.
34.
ChenCFuZChenZ, et al. HoMM: higher-order moment matching for unsupervised domain adaptation. Proc AAAI Conf Artif Intell2020; 34(4): 3422–3429.
35.
GaoYLiuXHuangH, et al. A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems. ISA Trans2021; 108: 356–366.
36.
WangRHuangWShiJ, et al. A higher-order moment matching based fine-grained adversarial domain adaptation method for intelligent bearing fault diagnosis. Meas Sci Technol2022; 33(5): ac471d.
37.
ZhaoWPangGKHWongN. Automatic adaptive multi-point moment matching for descriptor system model order reduction. In: 2013 International Symposium onVLSI Design, Automation, and Test (VLSI-DAT), April 2013, Hsinchu: IEEE, pp.1–4.
38.
ZellingerWGrubingerTLughoferE, et al. Central moment discrepancy (CMD) for domain-invariant representation learning. arXiv Preprint2019; 2019: 1702.08811.
39.
WeiRZhangFDongB, et al. DWMD: dimensional weighted orderwise moment discrepancy for domain-specific hidden representation matching. arXiv Preprint2020; 2020: 2007.09312.
40.
DanJJinTChiH, et al. HOMDA: high-order moment-based domain alignment for unsupervised domain adaptation. Knowl Based Syst2023; 261: 110205.
41.
ChangQFangCZhouW, et al. A multi-order moment matching-based unsupervised domain adaptation with application to cross-working condition fault diagnosis of rolling bearings. Structural Health Monitoring2024; 14759217241262386.
42.
ZhangYFanJMengZ, et al. Multi-source domain adaptive network based on local kernelized higher-order moment matching for rotating machinery fault diagnosis. ISA Transactions2024; 150: 311–321.
43.
HanMLiuCYangW, et al. Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application. ISA Transactions2020; 97: 269–281.
44.
JiaSDengYLvJ, et al. Joint distribution adaptation with diverse feature aggregation: a new transfer learning framework for bearing diagnosis across different machines. Measurement2022; 187: 110332.
45.
ZhuQLiuHLiuH-Q, et al. Decoupled interpretable robust domain generalization networks: a fault diagnosis approach across bearings, working conditions, and artificial-to-real scenarios. Adv Eng Inform2024; 61: 102445.
46.
YanZXuZZhangY, et al. FTSDC: a novel federated transfer learning strategy for bearing cross-machine fault diagnosis based on dual-correction training. Adv Eng Inform2024; 61: 102499.
47.
LiXZhangWDingQ.Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks. IEEE Trans Ind Electron2019; 66(7): 5525–5534.
48.
LinJShaoHMinZ, et al. Cross-domain fault diagnosis of bearing using improved semi-supervised meta-learning towards interference of out-of-distribution samples. Knowl Based Syst2022; 252: 109493.
