Jul 2026· Engineering Research Express· Vol 8, pp. 155208· 0 citations· 24 references
Physics
TL;DR
A contrastive error-perception-based partial adversarial domain adaptation method, named CEPADA, which introduces an error-perception mechanism to jointly evaluate class-level transfer reliability and sample-level uncertainty in cross-condition bearing fault diagnosis.
Abstract
In cross-condition bearing fault diagnosis, the target domain often contains only a subset of the fault classes available in the source domain. This asymmetric label-space setting makes conventional domain alignment prone to negative transfer, because source-private and unreliable samples may still participate in adaptation. To address this problem, this paper proposes a contrastive error-perception-based partial adversarial domain adaptation method, named CEPADA. Instead of relying only on class-level target predictions, CEPADA introduces an error-perception mechanism to jointly evaluate class-level transfer reliability and sample-level uncertainty. Samples with high error risk are assigned lower influence during adversarial alignment, while more reliable shared-class samples are emphasized. Meanwhile, contrastive learning is embedded into the adaptation process to make features of the same fault class more compact and features of different classes more separable. A pseudo-label refinement strategy is also used to provide additional target-domain guidance under the unlabeled setting. Experiments on the case western reserve university and JNU bearing datasets show that CEPADA achieves average accuracies of 93.17% and 86.02%, respectively, with improvements of 1.47 and 1.52 percentage points over the best-performing compared unsupervised baseline in our experiments.
Fault diagnosis of train bearings is crucial for railway safety, yet models trained on a single operating condition often experience significant performance degradation when subjected to variations in speed or load. This paper proposes a new single-source domain generalization (SDG) model named adaptive mask flow adversarial network (AMFAN), aiming to enhance generalization capability by effective cross-domain simulation based on learnable perturbations in feature space. An adaptive mask mechanism is designed to determine domain-sensitive feature elements. And a feature perturbation strategy is conducted to the determined feature elements via a pre-trained flow model. Experiments on two train bearing datasets verify the superior performance over state-of-the-art methods. The results prove that the controlled feature expansion provides a viable and robust pathway for SDG, showing strong potential for real-world train bearing fault diagnosis when confronting unknown operating conditions.
Jun Wang, Bo Yu, He Ren et al.· ISA transactions· 0 citations
To address the issue that intelligent fault diagnosis models for rolling bearings are susceptible to the effects of load and speed variations, as well as shifts in data distribution, when applied across different operating conditions, this paper proposes a fault diagnosis domain generalization method that combines mean difference constraints with domain adversarial learning. Taking raw one-dimensional vibration signals as input, this method first employs a multiscale one-dimensional convolutional network to extract fault impact features and periodic features across different time scales; Subsequently, mean difference constraints between source domains are introduced in the feature space to reduce the offset in the centers of feature distributions across different source operating conditions; simultaneously, a domain-adversarial discriminator based on gradient inversion layers is constructed to weaken the operating condition discriminative information in the feature representations, thereby prompting the model to learn domain-invariant features that possess both fault class discriminability and operating condition insensitivity. Experiments were conducted using two rolling bearing datasets from Case Western Reserve University (CWRU) and Paderborn University (PU) to establish a leave-one-out cross-condition diagnosis task. The results show that the proposed method achieves an average accuracy of 99.08% ± 0.19% on the CWRU dataset, and an average accuracy of 91.86% ± 0.34% on the PU dataset, both outperforming comparison methods such as SVM, 1D-CNN, ResNet1D, TCN, CORAL, MMD, and DANN. Furthermore, a Welch’s t-test based on summary statistics indicates that the improvement over the best baseline method is statistically significant. Ablation experiments and parameter sensitivity analysis further validate the effectiveness of multiscale feature extraction, mean difference constraints, and domain adversarial learning in enhancing the model’s generalization capability across different operating conditions.
Jiabing Zhou, Xiang Gu, Bo Zhang et al.· Advanced Engineering&Pre...· 0 citations
In practical industrial scenarios, high-quality bearing fault samples are often difficult to obtain. Although simulation methods can generate a certain amount of data, obvious distribution shifts still exist between simulated and measured signals due to model simplification, parameter uncertainty, and differences in noise structures, which limit their direct application in measured scenarios. To address this issue, this article proposes a cross-domain bearing fault diagnosis method based on dynamic simulation and a multiscale beta-distribution-guided domain-adversarial neural network (MBDANN), denoted as Sim2Real-MBDANN. First, a rolling bearing dynamic model is established based on actual operating parameters, and simulation is used to generate data samples covering different operating states, thereby alleviating the shortage of real fault data and the difficulty of annotation. Second, the MBDANN model is constructed using simulated data to achieve feature transfer and knowledge alignment from the simulation domain to the measured domain. The network adopts a feature extractor that integrates multiscale convolution kernels and a temporal attention mechanism to enhance the representation capability of multilevel fault features; meanwhile, a Beta-distribution-based feature alignment mechanism is introduced to improve the stability of adversarial alignment for marginal distributions, and a dynamically threshold-driven local maximum mean discrepancy (LMMD) loss is designed to improve the reliability of class-conditional distribution alignment. Finally, experimental results on the CWRU public dataset and a self-built experimental dataset show that, using only simulated signals as the source domain, the proposed method achieves average diagnostic accuracies of 94.71 % and 87.37 %, respectively, demonstrating its good generalization performance and cross-domain diagnosis capability.
Jian Yang, Faguo Huang, Tianping Huang et al.· IEEE Transactions on Instrum...· 0 citations
Open-set fault diagnosis of planetary gearboxes under varying operating conditions remains a challenging issue in health monitoring because the target domain may contain fault categories which are unavailable in the labelled source domain. Most existing domain adaptation methods assume that the source and target domains share an identical label space. Under open-set conditions, this assumption may force unknown target samples to be aligned with known source classes, resulting in negative transfer and unreliable diagnostic results. To address this issue, a multi-adversarial open-set domain adaptation network, termed MA-OSDAN, is proposed for planetary gearbox fault diagnosis. The proposed framework jointly addresses transferable feature learning for shared known classes and decision boundary construction for unknown target samples. A global-local distribution alignment strategy is introduced to reduce both global distribution discrepancy and class-level local mismatch between domains. Conditional adversarial adaptation is further incorporated to exploit classifier prediction information during domain alignment, thereby enhancing the discriminability of transferable features. To suppress the interference of potential unknown target samples, an entropy-guided instance weighting mechanism is designed to reduce the contribution of highly uncertain samples during adversarial adaptation. Moreover, an extended classifier with an additional unknown-class output is constructed to strengthen the separation between known and unknown fault categories. Experiments are conducted on the public Case Western Reserve University bearing dataset, the Shandong University of Science and Technology planetary gearbox dataset, and a self-built planetary gearbox dataset. The results demonstrate that MA-OSDAN achieves better performance than representative open-set domain adaptation methods in both known-class recognition and unknown-fault recognition.
Zongyao Liu, Jiang Huang, Jun-Wen Chen et al.· Measurement science and tech...· 0 citations
A novel and robust Source-Free Domain Adaptation (SFDA) framework equipped with post-hoc explainability for bearing fault diagnosis is proposed, and a post-hoc visualization mechanism is incorporated to explain the model's decision-making process, enhancing the transparency and credibility of the diagnosis for practical industrial deployment.
Cheng-Hao Yan, Dong-Sheng Liu, Tong Wu et al.· Measurement science and tech...· 0 citations
Extensive experiments on multiple bearing fault datasets demonstrate that CSR-DGAN outperforms existing generative augmentation methods in terms of distribution similarity, cross-domain consistency, and downstream diagnostic performance, highlighting the effectiveness of the proposed problem-driven dual-domain generative framework for robust fault diagnosis under imbalanced conditions.
Lifang Chen, Zihan Ren, Lingjing Kong et al.· International Journal of Dat...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
