Aug 2026· Measurement and control (London. 1968)· Vol 59, pp. 1436 - 1458· 1 citation· 46 references
TL;DR
A four-branch multi-modal unsupervised domain-adaptive fault diagnosis framework, termed CRG-DA Net, based on ConvNeXt and ResNet1D, aimed at enabling cross-condition fault diagnosis under unlabeled target data is proposed.
Abstract
The non-stationarity of high-speed train axle-box bearing vibration signals, combined with distribution discrepancies between laboratory and field data, makes it challenging to directly apply fault diagnosis methods trained on experimental data to actual operating conditions. This paper proposes a four-branch multi-modal unsupervised domain-adaptive fault diagnosis framework, termed CRG-DA Net, based on ConvNeXt and ResNet1D, aimed at enabling cross-condition fault diagnosis under unlabeled target data. Multi-scale and multi-domain fault features are extracted from raw vibration signals using envelope spectrum analysis, short-time Fourier transform, and wavelet transform. A four-branch parallel network is then constructed, employing ConvNeXt-Tiny for modeling the time-frequency representations and ResNet1D for learning the time-domain characteristics of raw signals, with each branch generating high-dimensional feature representations and corresponding fault prediction logits. To account for the varying discriminative contributions of different modalities, a gated dynamic fusion mechanism is introduced, which computes sample-specific fusion weights from the concatenated branch features and integrates the individual branch predictions into a final fused output. In addition, adversarial domain adaptation combined with pseudo-label self-training is employed to align the source and target domain feature distributions, while target samples are classified following the same gated fusion and prediction procedure. Extensive experiments on multi-condition laboratory datasets and real-world operating data demonstrate that the proposed CRG-DA Net achieves outstanding fault diagnosis performance, meeting the expected experimental performance and exhibiting strong generalization across different operating conditions.
Experiments demonstrate that this method can diagnose bearing failures under cross-conditions—even when trained solely on source-domain data and without exposure to target-domain data during training—and that its DG accuracy outperforms that of existing mainstream advanced methods.
Yu-Han Liu, Yong-Fang Yao, Juan Ren et al.· Engineering Research Express· 0 citations
Cross-machine bearing fault diagnosis is strongly affected by inconsistencies in vibration measurement conditions, including rotational speed, sampling frequency, and structural transmission paths. These factors cause speed-induced fault-frequency drift and cross-domain distribution discrepancies, making features learned from source-domain measurements unreliable in target-domain scenarios. Existing transfer learning (TL) methods are predominantly data-driven and insufficiently exploit mechanism-related prior information, which limits their interpretability and cross-machine generalization. To address these challenges, this paper proposes a prior-augmented dual-branch cross-attention network, termed PA-DCA Net, for cross-domain adaptive bearing fault diagnosis. First, a multi-scale S-transform with channel-weighted fusion is used to construct informative time-frequency representations from vibration signals. Meanwhile, a speed-normalized prior feature is introduced at the input-feature level to encode the relative rotational-speed discrepancy between the current operating condition and the source-domain reference condition. This prior feature is combined with eight conventional time-domain statistical features to form a statistical-prior feature vector. Second, an image-statistical dual-branch network is constructed, in which the image branch extracts deep time-frequency features and the statistical branch maps the statistical-prior vector into a high-dimensional representation. Multi-head cross-attention is then employed to achieve directed feature interaction between the two modalities. Third, a progressive TL framework integrating source-domain supervised pretraining, few-shot target-domain fine-tuning, CORAL, multi-kernel maximum mean discrepancy, and FixMatch-based consistency regularization is adopted. The proposed method is validated on five cross-domain tasks constructed from three public bearing datasets. PA-DCA Net achieves average accuracies of 97.10% and 96.92% on the Case Western Reserve University (CWRU)-to-Jiangnan University and CWRU-to-Huazhong University of Science and Technology cross-machine tasks, respectively, outperforming several representative transfer-learning baselines.
Xinyu Zhu, Hua Huang, Xilong Zhang et al.· Engineering Research Express· 0 citations
The results show that SAMACNN outperforms both classical and advanced methods on the two datasets, demonstrating strong robustness and generalization capability in complex variable-condition measurement environments.
DaXin Li, Hong Wang, Hai Xue et al.· Engineering Research Express· 0 citations
A hybrid deep learning architecture is proposed for robust vibration-based fault diagnosis in industrial machinery by jointly modeling time-domain, frequency-domain, and temporal dynamics, enabling coherent cross-domain interaction and robust fault characterization.
Canan Taştimur· Information Technology and C...· 0 citations
Vibration signals of planetary gearboxes under variable-speed conditions exhibit strong non-stationarity and modulation, so a single feature representation cannot comprehensively describe intricate fault patterns, and distribution discrepancies across rotating speeds degrade the cross-condition generalization of diagnostic models. To address these limitations, this paper proposes an adaptive domain-aligned multi-modal feature fusion network (ADAMFFN). Three parallel branches extract complementary features from dual-channel vibration signals: spatial coupling features from orbit images, time–frequency energy features from continuous wavelet transform (CWT) representations, and frequency-domain statistical (FreqStat) features from power and envelope spectra. Heterogeneous features are mapped into a shared latent subspace through a unified projection layer, deep cross-modal interaction is realized by a progressive fusion network, and a domain alignment mechanism based on a domain-adversarial neural network (DANN) is introduced to eliminate source–target distribution gaps via adversarial training. On eight leave-one-speed-out (LOSO) cross-speed tasks constructed on the public WT-Planetary Gearbox dataset, ADAMFFN achieves an average accuracy of 99.25%, outperforming the best single-branch and dual-branch schemes by 2.63 and 0.40 percentage points, respectively; ablation experiments verify the complementarity of the three modalities and the effectiveness of domain alignment. Cross-condition external validation on the Southeast University (SEU) gearbox dataset further demonstrates its generalization capability under a different test rig and acquisition conditions.
Results indicate that the proposed framework can identify bearing fault components under real compound machine fault interference and provide a practical solution for HSR bearing health monitoring, early fault warning, and maintenance decision support when labeled field data are limited.
Hanwei Zheng, Hong-Yi Zhang, Ming Yang et al.· PeerJ Computer Science· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
