Fault diagnosis approaches leveraging deep transfer learning typically assume that the fault classes in the source and target domains are identical. However, this assumption is often unrealistic in engineering practice due to operational complexity and uncertainty that result in unknown fault classes. In this paper, a dual-path adversarial and progressive self-training network (DAPSN) is proposed for cross-condition open-set domain adaptation (OSDA) fault diagnosis. A three-stage dual-path adversarial progressive self-training strategy is designed to mitigate negative transfer. Through the integration of a gradient reversal layer and a dual-path adversarial discriminator, DAPSN concurrently filters novel target samples and aligns representations of known classes, thereby enhancing inter-class separability and intra-class cohesion. Its effectiveness is verified under two OSDA scenarios. Comparative experiments demonstrate that the proposed DAPSN sustains high classification accuracy and reliable unknown-class detection across varying domain shifts and different proportions of open-set samples, outperforming existing baselines. The DAPSN method combines dual-path adversarial and progressive self-training mechanisms to achieve precise classification of known faults and effective identification of unknown faults.
YangFNHuaCRMuJY, et al. Fault diagnosis of high-speed train suspension systems under variable speeds based on dynamic transfer loss weight-deep subdomain adaptation network. Adv Eng Inform2025; 64: 103091.
2.
HeJLHuangWTLiuY, et al. Data imbalance fault diagnosis method based on an ensemble multi-scale convolutional attention network. Mech Syst Signal Process2025; 236: 112934.
3.
DengCYDengZHMiaoJG.Semi-supervised ensemble fault diagnosis method based on adversarial decoupled auto-encoder with extremely limited labels. Reliab Eng Syst Saf2024; 242: 109740.
4.
ZhaoBYZhangQXHeW, et al. A deep belief rule base-based fault diagnosis method for complex systems. ISA Trans2024; 150: 77–91.
5.
NieGCZhangZWJiaoZH, et al. A novel intelligent bearing fault diagnosis method based on image enhancement and improved convolutional neural network. Measurement2025; 242: 116148.
6.
GhazimoghadamSYHosseinzadehS.A novel unsupervised deep learning approach for vibration-based damage diagnosis using a multi-head self-attention LSTM autoencoder. Measurement2024; 229: 114410.
7.
LiHSpencerBFMaoJ, et al. Toward data anomaly detection for automated structural health monitoring: exploiting generative adversarial nets and autoencoders. Struct Health Monit2021; 20: 1609–1626.
8.
HuangKRenZJZhuLB, et al. Intra-domain self generalization network for intelligent fault diagnosis of bearings under unseen working conditions. Adv Eng Inform2025; 64: 102997.
9.
HuangRYLiJPLiaoYX, et al. Deep adversarial capsule network for compound fault diagnosis of machinery toward multidomain generalization task. IEEE Trans Instrum Meas2020; 70: 1–11.
10.
LiDPChenJXHuangRY, et al. Sensor-aware CapsNet: towards trustworthy multisensory fusion for remaining useful life prediction. J Manuf Syst2024; 72: 26–37.
11.
LiWHLanHChenJB, et al. WavCapsNet: an interpretable intelligent compound fault diagnosis method by backward tracking. IEEE Trans Instrum Meas2023; 72: 1–11.
12.
HuangRYChenYLiuC.Revealing state-feature dependencies in dynamic degradation: an exofeature-aware transformer for battery state-of-health prediction. IEEE Trans Consum Electron2025: 3631954.
13.
ZhangXWangJRHanBK, et al. Feature distance-based deep prototype network for few-shot fault diagnosis under open-set domain adaptation scenario. Measurement2022; 201: 111522.
14.
HeiZDSunWFYangHY, et al. Novel domain-adaptive Wasserstein generative adversarial networks for early bearing fault diagnosis under various conditions. Reliab Eng Syst Saf2025; 257: 110847.
15.
WengCYLuBCGuQ, et al. A novel hierarchical transferable network for rolling bearing fault diagnosis under variable working conditions. Nonlinear Dyn2023; 111: 11315–11334.
16.
LeiYGYangBJiangXW, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
17.
QianQWangYZhangTS, et al. Maximum mean square discrepancy: a new discrepancy representation metric for mechanical fault transfer diagnosis. Knowl Based Syst2023; 276: 110748.
18.
KuangJCXuGHTaoTF, et al. Domain conditioned joint adaptation network for intelligent bearing fault diagnosis across different positions and machines. IEEE Sens J2023; 23: 4000–4010.
19.
BustoPPGallJ.Open set domain adaptation. Proc IEEE Int Conf Comput Vis2017; 88: 754–763.
20.
SaitoKYamamotoSUshikuY, et al. Open set domain adaptation by backpropagation. Proc Eur Conf Comp Vis (ECCV), 2018, pp. 153–168. Cham: Springer International Publishing.
21.
GaoFLPengXYangD, et al. A novel distributed fault diagnosis scheme toward open-set scenarios based on extreme value theory. IEEE Trans Ind Inform2023; 19: 10454–10466.
22.
ZhangWLiXMaH, et al. Open-set domain adaptation in machinery fault diagnostics using instance-level weighted adversarial learning. IEEE Trans Ind Inform2021; 17: 7445–7455.
23.
ZhaoCShenWM.Dual adversarial network for cross-domain open set fault diagnosis. Reliab Eng Syst Saf2022; 221: 108358.
24.
FangZLuJLiuF, et al. Open set domain adaptation: theoretical bound and algorithm. IEEE Trans Neural Netw Learn Syst2022; 32: 4309–4322.
25.
DengYFLvJHuangDL, et al. Combining the theoretical bound and deep adversarial network for machinery open-set diagnosis transfer. Neurocomputing2023; 548: 126391.
26.
TianJHHanDYKarimiHR, et al. Deep learning-based open set multi-source domain adaptation with complementary transferability metric for mechanical fault diagnosis. Neural Netw2023; 162: 69–82.
27.
LiuHCaoZJLongMS, et al. Separate to adapt: open set domain adaptation via progressive separation. Proc IEEE/CVF Conf Comput Vis Patt Recognit2019, pp. 2917–2926. Los Alamitos: IEEE Computer Society.
28.
FuBCaoZJLongMS, et al.Learning to detect open classes for universal domain adaptation. In: European conference on computer vision (ECCV), 2020, pp. 567–583. Cham: Springer International Publishing.
29.
LiJPHuangRYHeGL, et al. A deep adversarial transfer learning network for machinery emerging fault detection. IEEE Sens J2020; 20: 8413–8422.
30.
YuXLZhaoZBZhangXW, et al. A universal transfer network for machinery fault diagnosis. Comput Ind2023; 151: 103976.
31.
HuangNQSongMMTangYH, et al. Research on fault diagnosis method for variable condition planetary gearbox based on SKN attention mechanism and deep transfer learning. Sci Rep2025; 15: 22921.
32.
LinFWGuoCZhaoZB, et al. A universal domain adaptation method with cluster matching for machinery fault diagnosis. IEEE Internet Things J2024; 12: 7487–7502.
33.
ZhangYCLiuTLLongMS, et al. Bridging theory and algorithm for domain adaptation. Int Conf Mach Learn2019; 97: 7404–7413.
34.
ZhongLFangZLiuF, et al. Bridging the theoretical bound and deep algorithms for open set domain adaptation. IEEE Trans Neural Netw Learn Syst2021; 34: 3859–3873.
35.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial nets. Adv Neural Inform Process Syst2014; 27: 2672–2680.
36.
LiYFXuXHHuL, et al. Double-level discriminative domain adaptation network for cross-domain fault diagnosis. Appl Intell2025; 55: 333.
37.
KongLTWangJRWangDW, et al. A new adaptive multi-scale attention adversarial network for cross-domain fault diagnosis. Knowl Based Syst2025; 311: 113066.
38.
MaatenLHintonG.Visualizing data using t-SNE. J Mach Learn Res2008; 9: 2579–2605.
39.
XuZBDingGGNieYX, et al. A weighted DJP-MMD based deep transfer metric learning for the fault diagnosis of bearing under variable working conditions. Front Mech Eng2025; 20: 16.
40.
LeiTFPanFHuJB, et al. A fault diagnosis method for rolling bearings in open-set domain adaptation with adversarial learning. Sci Rep2025; 15: 10793.
41.
ParameswaranSFangYGautamC, et al. Learning to identify seen, unseen and unknown in the open world: a practical setting for zero-shot learning. In: IEEE/CVF winter conference on applications of computer vision (WACV), Tucson, AZ, USA, 2025, pp. 6868–6878. Los Alamitos: IEEE Computer Society.
42.
PanCLShangZWTangLT, et al. Open-set domain adaptive fault diagnosis based on supervised contrastive learning and a complementary weighted dual adversarial network. Mech Syst Signal Process2025; 222: 111780.
