To address inter-class confusion and ambiguous decision boundaries in traditional rolling-bearing fault diagnosis under varying operating conditions, we propose a reliable domain adversarial network (RDAN) that enables more discriminative and robust cross-condition fault identification. Specifically, the RDAN is designed with a multi-modal and multi-channel feature extractor, which sufficiently captures domain-invariant features from both the frequency and time–frequency domains. In addition, a novel Dirichlet-evidence-based classification loss is introduced to jointly model classification accuracy and predictive uncertainty, by integrating evidential learning with a Kullback–Leibler divergence term. Furthermore, a new distribution alignment regularization method is proposed to minimize inter-class correlations and reinforce prediction consistency under various input perturbations, thereby effectively mitigating class confusion and enhancing the model’s robustness to signal variations. Finally, comparative experiments conducted on the Case Western Reserve University and drivetrain dynamics simulator (DDS) bearing fault datasets demonstrate the effectiveness and superiority of RDAN over other unsupervised domain adaptation methods in cross-domain bearing fault diagnosis.
GawdeSPatilSKumarS, et al. An explainable predictive maintenance strategy for multi-fault diagnosis of rotating machines using multi-sensor data fusion. Decis Anal J2024; 10: 100425.
2.
JiangYShiZTangC, et al. Cross-conditions fault diagnosis of rolling bearings based on dual domain adversarial network. IEEE Trans Instrum Meas2023; 72: 1–15.
3.
BashirAMohsinMAJazibM, et al. Mindtwin AI: multiphysics informed digital-twin for fault localization in induction motor using AI. In: 2023 International conference on big data, knowledge and control systems engineering (BdKCSE), Sofia, New York, 2023, pp. 1–8. IEEE.
4.
RenHWangJZhuZ, et al. Domain fuzzy generalization networks for semi-supervised intelligent fault diagnosis under unseen working conditions. Mech Syst Signal Process2023; 200: 110579.
5.
ZhangXZhaoBLinY.Machine learning based bearing fault diagnosis using the case western reserve university data: a review. IEEE Access2021; 9: 155598–155608.
6.
ChenXYangRXueY, et al. Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Meas2023; 72: 1–21.
7.
WangJRenHShenC, et al. Multi-scale style generative and adversarial contrastive networks for single domain generalization fault diagnosis. Reliab Eng Syst Saf2024; 243: 109879.
8.
YuJJiangYWangW, et al. A discriminator-free adversarial network for bearing fault diagnosis under unseen operating conditions. Appl Acoust2025; 240: 110877.
9.
SingletonRC.On computing the fast Fourier transform. Commun ACM1967; 10(10): 647–654.
10.
ZhangD. Wavelet transform. In: Fundamentals of image data mining: analysis, features, classification and retrieval. Springer, 2019, pp. 35–44.
11.
RillingGFlandrinPGoncalvesP. On empirical mode decomposition and its algorithms. In: IEEE-EURASIP workshop on nonlinear signal and image processing NSIP-03, Grado, Italy, 2003. New York: IEEE.
12.
DragomiretskiyKZossoD.Variational mode decomposition. IEEE Trans Signal Process2013; 62(3): 531–544.
13.
BonizziPKarelJMMesteO, et al. Singular spectrum decomposition: a new method for time series decomposition. Adv Adapt Data Anal2014; 6(04): 1450011.
ZhaoKLiuZZhaoB, et al. Class-aware adversarial multiwavelet convolutional neural network for cross-domain fault diagnosis. IEEE Trans Ind Inform2023; 20(3): 4492–4503.
16.
XueLLeiCJiaoM, et al. Rolling bearing fault diagnosis method based on self-calibrated coordinate attention mechanism and multi-scale convolutional neural network under small samples. IEEE Sens J2023; 23(9): 10206–10214.
17.
LiuBYanCHeC, et al. An interpretable physics-informed subdomain moment-enhanced adaptation network for unsupervised transfer fault diagnosis of rolling bearing. Adv Eng Inform2025; 67: 103491.
18.
HeDZhaoJJinZ, et al. DCAGGCN: a novel method for remaining useful life prediction of bearings. Reliab Eng Syst Saf2025; 260: 110978.
19.
JiangYZhengLTangC, et al. LSTM-based node-gated graph neural network for cross-condition few-shot bearing fault diagnosis. IEEE Sens J2024; 24(3): 3445–3456.
20.
LiuBYanCLiuY, et al. ISEANet: an interpretable subdomain enhanced adaptive network for unsupervised cross-domain fault diagnosis of rolling bearing. Adv Eng Inform2024; 62: 102610.
21.
ZhaoJHeDJinZ, et al. A new method for bearing remaining useful life prediction based on dynamic wavelet and physical information constraints. Expert Syst Appl2025; 296: 129023.
22.
ZhangALiSCuiY, et al. Limited data rolling bearing fault diagnosis with few-shot learning. IEEE Access2019; 7: 110895–110904.
23.
GaninYLempitskyV.Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, 2015, pp. 1180–1189. PMLR.
https://doi.org/10.48550/arXiv.1409.7495.
24.
WangMDengW.Deep visual domain adaptation: a survey. Neurocomputing2018; 312: 135–153.
25.
LongMCaoYWangJ, et al. Learning transferable features with deep adaptation networks. In: International conference on machine learning, 2015, pp. 97–105. PMLR. https://doi.org/10.48550/arXiv.1409.7495.
26.
ZhuYZhuangFWangJ, et al. Deep subdomain adaptation network for image classification. IEEE Trans Neural Netw Learn Syst2020; 32(4): 1713–1722.
27.
SunBSaenkoK.Deep coral: correlation alignment for deep domain adaptation. In European conference on computer vision, 2016, pp. 443–450. Springer. https://doi.org/10.48550/arXiv.2106.09388.
28.
JiangYHeYShiZ, et al. Cross-conditions fault diagnosis of rolling bearing based on transitional domain adversarial network. IEEE Sens J2024; 25(1): 1978–1993.
29.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial nets. Adv Neural Inform Process Syst2014; 27: 139–144.
ChenLChenHWeiZ, et al. Reusing the task-specific classifier as a discriminator: discriminator-free adversarial domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 7181–7190.
32.
ZhuZChenGTangG.Domain adaptation with multi-adversarial learning for open-set cross-domain intelligent bearing fault diagnosis. IEEE Trans Instrum Meas2023; 72: 1–11.
33.
SunKHuangZMaoH, et al. Multiscale margin disparity adversarial network transfer learning for fault diagnosis. IEEE Trans Instrum Meas2023; 72: 1–12.
34.
AnYZhangKChaiY, et al. Bearing fault diagnosis under variable working conditions base on contrastive domain adaptation method. IEEE Trans Instrum Meas2022; 71: 1–11.
35.
SaitoKWatanabeKUshikuY, et al. Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3723–3732. https://doi.org/10.48550/arXiv.1712.02560.
36.
LiuWWangXOwensJ, et al. Energy-based out-of-distribution detection. Adv Neural Inform Process Syst2020; 33: 21464–21475.
37.
WangXLiuF.Triplet loss guided adversarial domain adaptation for bearing fault diagnosis. Sensors2020; 20(1): 320.
38.
WangQMichauGFinkO.Missing-class-robust domain adaptation by unilateral alignment. IEEE Trans Ind Electron2020; 68(1): 663–671.
39.
JalayerRJalayerMMorA, et al. Evaluating deep learning models for fault diagnosis of a rotating machinery with epistemic and aleatoric uncertainty. arXiv:2412.18980, 2024. https://doi.org/10.48550/arXiv.2412.18980.
40.
RenJWenJZhaoZ, et al. Uncertainty-aware deeplearning: a promising tool for trustworthy fault diagnosis. IEEE/CAA J Automatic Sin2024; 11(6): 1317–1330.
41.
GaoTYangJTangQ.A multi-source domain information fusion network for rotating machinery fault diagnosis under variable operating conditions. Inform Fusion2024; 106: 102278.
42.
SensoyMKaplanLKandemirM.Evidential deep learning to quantify classification uncertainty. Adv Neural Inform Process Syst2018; 31:3183–3193.
GougamFRahmouneCBenazzouzD, et al. Bearing faults classification under various operation modes using time domain features, singular value decomposition, and fuzzy logic system. Adv Mech Eng2020; 12(10): 1687814020967874.
45.
JohnsonDHSinanovicS.Symmetrizing the Kullback-Leibler distance. IEEE Trans Inform Theory2001; 1(1): 1–10.
46.
KingmaDPBaJ.ADAM: a method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
JinYWangXLongM, et al. Minimum class confusion for versatile domain adaptation. In: European conference on computer vision, 2020, pp. 464–480. Springer. https://doi.org/10.48550/arXiv.2106.09388.
49.
DeVriesTTaylorGW. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017. https://doi.org/10.48550/arXiv.1708.04552.
50.
SmithWARandallRB.Rolling element bearing diagnostics using the case western reserve university data: a benchmark study. Mech Syst Signal Process2015; 64: 100–131.
51.
LessmeierCKimothoJKZimmerD, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification. In: PHM society European conference, 2016, vol. 3. https://doi.org/10.48550/arXiv.1712.02560.
