To address the issues of generalization and robustness in bearing fault diagnosis models under unknown working conditions, this article proposes a dual-stage adaptive mixed domain generalization network as a novel domain generalization approach. This method employs a dual-stage domain mixed enhancement strategy at both the primary-level and feature-level to generate diverse intermediate domain, aiming to efficiently minimize the distributional differences between the source domain and the target domain. At the primary-level, a convex combination of multisource domain raw vibration signals is employed to construct virtual domain samples with smooth transition features. At the feature-level, a more discriminative feature representation space is constructed by performing linear interpolation on the extracted domain-invariant features. Meanwhile, an adaptive triplet loss function is designed to optimize the relative distance relationships between sample pairs, thereby guiding the feature space to automatically form a discriminative geometric structure. Experiments on two bearing datasets show that the proposed method achieves diagnostic accuracies of 92.80 and 94.39%, respectively, demonstrating its cross domain generalization performance and robustness.
ZhangLQiuJLiuJ, et al. CTNet: an interpretable convolutional neural network for bearing fault diagnosis. Struct Health Monit2025.
2.
ZhangLWangJXiaoQ, et al. A bearing fault diagnosis method with implementation of multiscale time-frequency feature fusion and bidirectional information interaction. IEEE Sens J2025; 25: 23740–23756.
3.
ZhangYHuaJFangX, et al. Trackside acoustic fault diagnosis of bearing based on doppler knowledge embedded in domain adaptation network. IEEE Trans Instrum Meas2024; 73: 1–13.
4.
FanZLiuXCaoZ, et al. Digital twin-driven feature enhancement generative adversarial network for rolling bearings fault diagnosis. Struct Health Monit2025.
5.
LiuJWangCWangR, et al. A novel multiscale adaptive graph adversarial network for mechanical fault diagnosis. Knowl Based Syst2025; 309: 112787.
6.
QiuBLiuSLiW, et al. Dynamic adaptive fault diagnosis using multi-channel image fusion and deep learning in channel failure occasions on rolling bearings. Adv Eng Inform2025; 68: 103631.
7.
XuZLeeCKMWongC-N.A novel fault diagnosis method based on deep stable learning for bearings with imbalanced data samples. Expert Syst Appl2025; 281: 127634.
8.
DuanYYangTWangC, et al. LSBT-Net: a lightweight framework for fault diagnosis of bearings based on an interpretable spatial-temporal model. Expert Syst Appl2025; 281: 127718.
9.
TangTLiuZQiuC, et al. Transfer learning for bearing fault diagnosis based on graph neural network with dilated KNN and adversarial discriminative domain adaptation. Meas Sci Technol2024; 35: 065106.
10.
MengLXieJChengL, et al. Multi-condition bearing fault diagnosis method based on RP–MBRN. Struct Health Monit2024; 25(1): 456–467.
11.
LiuJWanLXieF, et al. Cross-machine deep subdomain adaptation network for wind turbines fault diagnosis. Mech Syst Signal Process2024; 210: 111151.
12.
BaiGXingTSunW, et al. Unsupervised multiple-target domain adaptation for bearing fault diagnosis. Eng Appl Artif Intell2025; 154: 111063.
13.
MaWZhangYMaL, et al. An unsupervised domain adaptation approach with enhanced transferability and discriminability for bearing fault diagnosis under few-shot samples. Expert Syst Appl2023; 225: 120084.
14.
ZhongJLinCGaoY, et al. Fault diagnosis of rolling bearings under variable conditions based on unsupervised domain adaptation method. Mech Syst Signal Process2014; 215: 111430.
15.
GhorveiMKavianpourMBeheshtiMTH, et al. Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosis. Neurocomputing2023; 517: 44–61.
16.
KongLWangJWangD, et al. A new adaptive multi-scale attention adversarial network for cross-domain fault diagnosis. Knowl Based Syst2025; 311: 113066.
17.
AnYZhangKChaiY, et al. Bearing fault diagnosis under variable working conditions base on contrastive domain adaptation method. IEEE Trans Instrum Meas2022; 71: 1–11.
18.
ZhaoCZioEShenW.Domain generalization for cross-domain fault diagnosis: an application-oriented perspective and a benchmark study. Reliab Eng Syst Saf2024; 245: 109964.
19.
PangBLiuQXuZ, et al. Fault vibration model driven fault-aware domain generalization framework for bearing fault diagnosis. Adv Eng Inform2024; 62: 102620.
20.
LiCZhangSQinY, et al. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing2020; 407: 121–135.
21.
ZhaoZZhangQYuX, et al. Applications of unsupervised deep transfer learning to intelligent fault diagnosis: a survey and comparative study. IEEE Trans Instrum Meas2021; 70: 1–28.
22.
ShiHCaoSZuoH, et al. Deep subdomain adversarial network with self-supervised learning for aero-engine high speed bearing fault diagnosis with unknown working conditions. Measurement2025; 241: 115668.
23.
ZhangQZhaoZZhangX, et al. Conditional adversarial domain generalization with a single discriminator for bearing fault diagnosis. IEEE Trans Instrum Meas2021; 70: 1–15.
24.
ChenGYeJLiD, et al. Domain generalization for bearing fault diagnosis via meta-learning with gradient alignment and data augmentation. Machines2025; 13: 960.
25.
GuoZXuLZhengY, et al. Bearing fault diagnostic framework under unknown working conditions based on condition-guided diffusion model. Measurement2025; 242: 115951.
26.
SunKYinAHuY, et al. Partial domain generalization via variable data augmentation for machine fault diagnosis. Measurement2026; 257: 118690.
27.
LiQChenLKongL, et al. Cross-domain augmentation diagnosis: an adversarial domain-augmented generalization method for fault diagnosis under unseen working conditions. Reliab Eng Syst Saf2023; 234: 109171.
28.
HanTLiY-FQianM.A hybrid generalization network for intelligent fault diagnosis of rotating machinery under unseen working conditions. IEEE Trans Instrum Meas2021; 70: 1–11.
29.
JiangJTaoGLiangH, et al. A structure information-assisted generalization network for fault diagnosis of out-of-round wheels of metro trains. Measurement2025; 244: 116519.
30.
YuanJMaXChenD, et al. Label-efficient domain generalization via collaborative exploration and generalization. In: Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022, pp. 2361–2370.
31.
LiuJXieFZhangQ, et al. A multisensory time-frequency features fusion method for rotating machinery fault diagnosis under nonstationary case. J Intell Manuf2023; 35: 3197–3217.
YuKLinTRMaH, et al. A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning. Mech Syst Signal Process2021; 146: 107043.
34.
ZhaoCShenW.Adaptive open set domain generalization network: learning to diagnose unknown faults under unknown working conditions. Reliab Eng Syst Saf2022; 226: 108672.
35.
YangYYinJZhengH, et al. Learn generalization feature via convolutional neural network: a fault diagnosis scheme toward unseen operating conditions. IEEE Access2020; 8: 91103–91115.
36.
RagabMChenZZhangW, et al. Conditional contrastive domain generalization for fault diagnosis. IEEE Trans Instrum Meas2022; 71: 1–12.
37.
CaoWMengZLiJ, et al. A bearing fault diagnosis method for unknown operating conditions based on differentiated feature extraction. ISA Trans2025; 156: 468–478.
38.
SunBSaenkoK. Deep CORAL: correlation alignment for deep domain adaptation. In: Computer Vision – ECCV 2016 Workshops, 2016, pp. 443–450.
39.
WangBWenLLiX, et al. Adaptive class center generalization network: a sparse domain-regressive framework for bearing fault diagnosis under unknown working conditions. IEEE Trans Instrum Meas2023; 72: 1–11.
