Currently, fault diagnosis based on domain generalization (DG) for unseen target domains has become a prominent research topic. Despite significant progress, several challenges remain, including domain-dependent features in the extracted features and the overlap of feature clusters across different classes. To address these challenges, we propose a novel DG network that integrates invariance and cohesiveness. First, based on the information bottleneck, we present a domain-invariant feature loss that compresses redundant features and eliminates domain-dependent ones. Second, by employing feature segmentation and maximum mean discrepancy, we propose a new feature cohesion regularization method that enhances the model’s clustering performance. Finally, the feature invariance and cohesion losses are integrated into a unified framework. Experiments conducted on two fault datasets demonstrate that the method exhibits strong generalization diagnostic capability and high diagnostic accuracy, and can be applied to fault diagnosis of rolling bearings under unseen operating conditions.
WangRYanFYuL, et al. Joint Wasserstein distance matching under conditional probability distribution for cross-domain fault diagnosis of rotating machinery. Mech Syst Signal Process2024; 210: 111121.
2.
LiaoWFuWYangK, et al. Multi-scale residual neural network with enhanced gated recurrent unit for fault diagnosis of rolling bearing. Meas Sci Technol2024; 35(5): 056114.
3.
ZhaoCShenW.A domain generalization network combing invariance and specificity towards real-time intelligent fault diagnosis. Mech Syst Signal Process2022; 173: 108990.
4.
SunSPengTZhouY, et al. Contrastive learning and dynamics embedding neural network for label-free interpretable machine fault diagnosis. ISA Trans2024; 144: 436–451.
5.
SheDZhangHWangH, et al. Intelligent fault diagnosis method of rolling bearing based on multi-source domain fast adversarial network. Meas Sci Technol2024; 35(5): 056119.
6.
YanSZhongXShaoH, et al. Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization. Reliab Eng Syst Safety2023; 239: 109522.
7.
ZhaoMZhongSFuX, et al. Deep residual shrinkage networks for fault diagnosis. IEEE Trans Ind Inf2020; 16(7): 4681–4690.
8.
ChenZMauricioALiW, et al. A deep learning method for bearing fault diagnosis based on Cyclic Spectral Coherence and Convolutional Neural Networks. Mech Syst Signal Process2020; 140: 106683.
9.
ShaoHLaiYLiuH, et al. LSFConvformer: a lightweight method for mechanical fault diagnosis under small samples and variable speeds with time-frequency fusion. Mech Syst Signal Process2025; 236: 113016.
10.
ShaoHJiangHZhangH, et al. Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing. Mech Syst Signal Process2018; 100: 743–765.
11.
ChenXZhangBGaoD.Bearing fault diagnosis base on multi-scale CNN and LSTM model. J Intell Manuf2021; 32(4): 971–987.
12.
MaoWFengWLiuY, et al. A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mech Syst Signal Process2021; 150: 107233.
13.
PangS.Stacked maximum independence autoencoders: a domain generalization approach for fault diagnosis under various working conditions. Mech Syst Signal Process2024; 208: 111035.
14.
QinYWangZQianQ, et al. Discriminative manifold domain adaptation for cross-domain fault diagnosis of rotating machineries. Knowledge-Based Syst2024; 285: 111332.
15.
WangZHuangWChenY, et al. Multisource cross-domain fault diagnosis of rolling bearing based on subdomain adaptation network. Meas Sci Technol2022; 33(10): 105109.
16.
SheDZhangHWangH, et al. Intelligent fault diagnosis method of rolling bearing based on multi-source domain fast adversarial network. Meas Sci Technol2024; 35(5): 056119.
17.
ZhangBHuoTZhengL, et al. Novel adversarial unsupervised subdomain adaption multi-channel deep convolutional network for cross-operating fault diagnosis of rolling bearings. IEEE Access2024; 12: 42068–42082.
18.
HuoTDengLZhangB, et al. Novel imbalanced subdomain adaption multiscale convolutional network for cross-domain unsupervised fault diagnosis of rolling bearings. Meas Sci Technol2024; 35(1): 015905.
19.
WangRYanFYuL, et al. Joint Wasserstein distance matching under conditional probability distribution for cross-domain fault diagnosis of rotating machinery. Mech Syst Signal Process2024; 210: 111121.
20.
ChenPZhaoRHeT, et al. A novel bearing fault diagnosis method based joint attention adversarial domain adaptation. Reliab Eng Syst Safety2023; 237: 109345.
21.
KuangJXuGTaoT, et al. Domain conditioned joint adaptation network for intelligent bearing fault diagnosis across different positions and machines. IEEE Sens J2023; 23(4): 4000–4010.
22.
ZhaoCZioEShenW. Domain generalization for cross-domain fault diagnosis: an application-oriented perspective and a benchmark study. Reliab Eng Syst Safety2024; 245: 109964.
23.
GaoTYangJWangW, et al. A domain feature decoupling network for rotating machinery fault diagnosis under unseen operating conditions, Reliab Eng System Safety2024; 252: 110449.
24.
ZhangXWangJJiangX, et al. Working condition decoupling adversarial network: a novel method for multi-target domain fault diagnosis. Neurocomputing2025; 616: 128953.
25.
WangJLanCLiuC, et al. Generalizing to unseen domains: a survey on domain generalization. IEEE Trans Knowl Data Eng2022; 14(8): 1–20.
26.
QinXWangJChenY, et al. Domain generalization for activity recognition via adaptive feature fusion. ACM Trans Intell Syst Technol2023; 14(1): 1–21.
27.
GuoCZhaoZRenJ, et al. Causal explaining guided domain generalization for rotating machinery intelligent fault diagnosis. Expert Syst Appl2024; 243: 122806.
28.
HuangZWangHXingEP, et al. Self-challenging improves cross-domain generalization. arXiv: arXiv:2007.02454, 2020.
29.
PezeshkiMKabaS-OBengioY, et al. Gradient starvation: a learning proclivity in neural networks. arXiv: arXiv:2011.09468, 2021.
30.
ZhouKLiuZQiaoY, et al. Domain generalization: a survey. IEEE Trans Pattern Anal Mach Intell2023; 45(4): 4396–4415.
31.
ArjovskyMBottouLGulrajaniI, et al. Invariant risk minimization. arXiv: arXiv:1907.02893, 2020.
32.
KruegerD, et al. Out-of-distribution generalization via risk extrapolation (REx). arXiv: arXiv:2003.00688, 2021.
33.
XiaoYShaoHYanS, et al. Domain generalization for rotating machinery fault diagnosis: a survey. Adv Eng Inform2025; 64: 103063.
34.
YangYYinJZhengH, et al. Learn generalization feature via convolutional neural network: a fault diagnosis scheme toward unseen operating conditions. IEEE Access2020; 8: 91103–91115.
35.
AhujaKCaballeroZhangD, et al. Invariance principle meets information bottleneck for out-of-distribution generalization. arXiv: arXiv:2106.06607, 2022.
36.
RenLMoTChengX.Meta-learning based domain generalization framework for fault diagnosis with gradient aligning and semantic matching. IEEE Trans Ind Inf2024; 20(1): 754–764.
37.
WangHBaiXWangS, et al. Generalization on unseen domains via model-agnostic learning for intelligent fault diagnosis. IEEE Trans Instrum Meas2022; 71: 1–11.
38.
ZhaoCShenW.Adversarial mutual information-guided single domain generalization network for intelligent fault diagnosis. IEEE Trans Ind Inf2023; 19(3): 2909–2918.
39.
ShiYDengADengM, et al. Domain augmentation generalization network for real-time fault diagnosis under unseen working conditions. Reliab Eng Syst Safety2023; 235: 109188.
40.
RagabMChenZZhangW, et al. Conditional contrastive domain generalization for fault diagnosis. IEEE Trans Instrum Meas2022; 71: 1–12.
41.
ZhaoCShenW. A domain generalization network combing invariance and specificity towards real-time intelligent fault diagnosis. Mech Syst Signal Process2022; 173: 108990.
42.
ShiZChenJZhangX, et al. A reliable feature-assisted contrastive generalization net for intelligent fault diagnosis under unseen machines and working conditions. Mech Syst Signal Process2023; 188: 110011.
43.
RenHWangJHuangW, et al. Domain-invariant feature fusion networks for semi-supervised generalization fault diagnosis. Eng Appl Artificial Intell2023; 126: 107117.
44.
ZhaiPZhangS.Adversarial information bottleneck. IEEE Trans Neural Netw Learning Syst2024; 35(1): 221–230.
45.
AlemiAAFischerIDillonJV, et al. Deep variational information bottleneck. arXiv: arXiv:1612.00410, 2018.
46.
FarniaFTseD.A minimax approach to supervised learning. arXiv: arXiv:1606.02206, 2017.
47.
XiaoYShaoHMinZ, et al. Multiscale dilated convolutional subdomain adaptation network with attention for unsupervised fault diagnosis of rotating machinery cross operating conditions. Measurement2022; 204: 112146.
