The diagnosis of compound faults in bearings is a challenging issue in real industrial scenarios, as these faults have a significant impact on production and safety. Moreover, the data related to these compound faults are difficult to collect and label, making data-driven fault diagnosis methods inapplicable. To address the scarcity of compound-fault data and the absence of labeled samples in bearing systems, this article proposes a zero-shot diagnosis method based on semantic embedding. By training solely on single-fault data, this approach effectively overcomes the shortage of compound fault samples. First, a binary semantic representation is constructed for each single fault using Top-
k
masking, and a neural semantic composer (NSC) is pretrained to generate realistic compound-fault prototypes. Second, a multisensor robust convolutional neural network is designed for feature extraction. Finally, a synthetic compound-fault training strategy is introduced to enhance model generalization. By aligning the compound semantic targets generated from feature mixing and NSC, this strategy enables the model to learn the patterns in unseen compound samples. The necessity of each module is demonstrated through ablation experiments. The effectiveness and generalization ability of the method are verified using the HDU and HUST datasets. Under various operating conditions, the proposed method demonstrates optimal or nearly optimal accuracy. The code will be made publicly available on
https://github.com/su-yibei/zero-shot-fault-diagnosis
.
Sitong Jiao, Shijie Ning, Xiaomin Zhu et al.· Structural Health Monitoring· 0 citations
Field vibration monitoring of EMU traction motor bearings is commonly constrained by weak or relative labels, fluctuations in operating conditions, and limited abnormal samples. Under these conditions, learning a normal boundary from a single bearing position may be unstable, and isolated score spikes may lead to unreliable alarms. To address these issues, this study proposes a multi-axle reference and temporal-consistency-enhanced Deep SVDD framework, termed MA-TC-Deep SVDD, for field anomaly detection of EMU traction motor bearings. Unlike closed-set fault diagnosis that requires known fault labels, the proposed framework focuses on identifying deviations from the stable operating regime. First, a compact 10-dimensional time-frequency representation is constructed from valid vibration segments. Second, stable samples from the target bearing position and screened stable samples from other monitored positions on the same EMU are organized as a multi-axle reference set for one-class normal-boundary learning. Third, feature recalibration, temporal-consistency regularization, reference-score standardization, causal smoothing, and consecutive-alarm judgment are incorporated to improve robustness against field disturbances. The anomaly-prior-guided health-state interpretation module is retained only as post hoc evidence for describing severity evolution and does not feed back into the anomaly detection threshold. Field data collected from an in-service EMU over D1–D5 are used for validation. The results show that bearing position 1 has low anomaly scores on D1–D2, exhibits transitional deviation on D3, and shows persistent state deviation on D4–D5, while the other monitored positions remain comparatively stable. Under the current weak-label evaluation protocol, MA-TC-Deep SVDD achieves higher average anomaly detection performance than the compared baseline methods, with AUC = 0.909, AP = 0.872, Precision = 0.887, Recall = 0.802, F1 = 0.843, and FAR = 0.047. These results indicate that the proposed framework can provide field anomaly-warning and severity-oriented interpretation under weak-label monitoring conditions. However, it should not be interpreted as a replacement for disassembly-confirmed fault-type diagnosis or remaining useful life prediction.
Qi Wu, Xiaomin Zhu, Zhikai Jia et al.· Italian National Conference...· 0 citations
Switch machines are critical components in rail transit signal systems, ensuring the safe, efficient, and smooth operation of trains. However, due to the harsh working conditions, they are the most failure-prone among all ground signal devices. Existing studies mainly pursue higher diagnostic accuracy via specialized models, often at the expense of interpretability, diagnostic transparency, and adaptability to different signal representations. In this article, a visual interpretation-based intelligent fault diagnosis framework is developed for switch-machine fault diagnosis using acoustic signals. A flexible time-frequency transformation module is used to convert signals into time-frequency representations, which are then input into a convolutional neural network for fault classification. Heatmaps obtained by the gradient-weighted class activation mapping (Grad-CAM) method are employed to visually explain the fault diagnosis results. To enhance both accuracy and interpretability, an entropy-regularized composite loss function is introduced by combining cross-entropy loss with a Grad-CAM-derived two-dimensional local information entropy term. This design encourages the model to form more compact fault-related saliency distributions while maintaining classification accuracy. Experimental results on the constructed laboratory dataset show that the framework achieves high diagnostic accuracy under different time–frequency representations, with several configurations reaching 100% accuracy under the current evaluation protocol. These results demonstrate the feasibility of visual interpretation for acoustic-based switch-machine fault diagnosis.
Wei Cai, Xiaomin Zhu, Qianxia Ma et al.· Structural Health Monitoring· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
