Aug 2026· PeerJ Computer Science· Vol 12, pp. e4075· 0 citations· 29 references
TL;DR
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.
Abstract
High-Speed Railway (HSR) bearing health monitoring is essential for ensuring operational safety, reducing unexpected service interruptions, and supporting condition-based maintenance in practical railway systems. In real engineering environments, however, bearing fault diagnosis remains challenging because field vibration signals are usually unlabeled, affected by changing operating conditions, and may contain superimposed fault components rather than isolated single fault patterns. To address these challenges, this study proposes a lightweight and interpretable transfer learning framework for HSR bearing fault diagnosis under limited labeled data and compound fault conditions. The proposed framework integrates data cleaning, resampling to 24 kHz according to the Nyquist sampling theorem, wavelet threshold denoising, and multi-domain feature extraction from time, frequency, and time-frequency domains. The discriminative capability of the extracted 25-dimensional feature representation was verified using Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Random Forest, and Light Gradient Boosting Machine (LightGBM) models, all of which achieved source domain classification accuracies above 99%. To reduce the gap between laboratory single fault data and unlabeled field compound fault data, a feature-level Dirichlet-weighted nonlinear synthesis strategy was developed to generate synthetic composite fault feature vectors from source domain samples. A lightweight fully connected regressor was then trained to estimate proportional fault contributions for target domain samples, enabling probabilistic diagnosis without target domain labels. The effectiveness of domain adaptation was confirmed by t-distributed Stochastic Neighbor Embedding (t-SNE) visualization, which showed clear alignment between source and target feature distributions. External validation on a public multi-domain compound fault dataset achieved 80.99% accuracy, with a Mean Squared Error (MSE) of 0.0799 and a Mean Absolute Error (MAE) of 0.1452. These 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.
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.
Zhihao Zhao, Li Xu, Jingjing Cai et al.· Measurement and control (Lon...· 1 citation
To overcome the difficulties faced by current bearing fault diagnosis methods in industrial applications, such as the difficulty in obtaining sufficient labeled real fault training samples and the subpar performance of cross-domain fault diagnosis due to data distribution deviation, a new bearing cross-domain fault diagnosis method based on wavelet time-frequency maps and Resnet transfer learning (CDF-WTI-RTL) is proposed.In the context of the Industrial Internet of Things (IIoT) and Industry 5.0, real-time condition monitoring and intelligent predictive maintenance have become critical for ensuring manufacturing system resilience and sustainability. First, raw vibration signals are processed using continuous wavelet transform to obtain two-dimensional time-frequency maps. Second, a Resnet network adapted for bearing fault diagnosis is constructed to autonomously mine deep features from source and target domains. A random forest classifier is then employed to build a cross-domain fault pattern recognition classifier. Experimental analysis of training samples using two different bearing fault datasets shows that the accuracy of the CDF-WTI-RTL model reaches 98.38% and 91.5% with unbalanced training samples respectively, notably surpassing the other 5 comparative models. The results demonstrate that the proposed method can be effectively deployed in IIoT architectures for reliable, cross-condition bearing fault diagnosis.
Wanchuan Wang· ICST Transactions on Scalabl...· 0 citations
Reliable state assessment of railway traction power transformers is challenged by heterogeneous operating environments, measurement disturbances, coupled gas-generation mechanisms, and uneven fault-sample distributions. Conventional dissolved gas analysis (DGA) ratio rules and single-model classifiers often show insufficient generalization when rare faults and boundary-ambiguous operating states are encountered. To address this issue, this paper proposes a feature-guided stacking framework for state assessment of oil-immersed railway power transformers. First, a DGA-oriented fusion-feature representation is established by combining raw gas concentrations, gas-ratio descriptors, and an aggregated dissolved-gas analysis factor. Second, DBSCAN-assisted sample structuring is introduced to identify density patterns, sparse rare fault regions, and boundary samples, thereby improving the organization of imbalanced monitoring records. Third, a monitoring-feature-embedded stacking model is developed in which heterogeneous base learners are adaptively weighted according to feature-reliability information and integrated through a cross-validated meta-learner. This synthetic-data-based validation provides a controlled and reproducible proof-of-concept. Therefore, the reported results should be interpreted as evidence of methodological feasibility. Under the default synthetic setting, the proposed feature-guided stacking (FE-stacking) method achieves an accuracy of 99.70% and a macro-F1 of 99.55%. Under the severe minority-retention setting in which only 25% of low-energy discharge (LD) and low-temperature overheating (LT) training samples are preserved, it obtains an accuracy of 99.62%, a macro-F1 of 99.40%, and an LT recall of 96.61%, slightly surpassing random forest (RF) and outperforming Original Stacking in rare fault robustness. These results indicate that feature-guided ensemble learning can improve the generalization stability of DGA-based transformer state assessment under imbalanced and boundary-ambiguous conditions. From a practical perspective, the proposed framework can serve as a decision-support module for transformer condition screening, maintenance prioritization, and alarm verification in railway traction power-supply systems.
Results show that using statistical vibration features with ensemble classifiers is a good way to diagnose multi-class bearing faults and establishes a comprehensive benchmark for ML- and DL-based rolling bearing FDD.
M. I. Quamar, Abdulrazaq Nafiu Abubakar, Ali Nasir· Journal of Vibration Enginee...· 0 citations
The increasing demand for reliability in wind turbine systems makes early bearing fault detection under variable-speed conditions a persistent challenge. This paper proposes a hybrid methodology for classifying degradation stages and estimating a relative RUL-related degradation indicator for bearings by integrating synthetic data modeling, feature selection, and a combined unsupervised–supervised learning approach. Synthetic vibration signals are generated through logistic-curve interpolation with pink noise, enabling controlled degradation simulation. Features from time, frequency, and time–frequency domains were ranked using Mutual Information, and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) was employed to identify progressive wear stages. Cluster centers serve as anchors for mapping degradation into RUL percentages, while classification ensures stage consistency. Experimental results demonstrate six well-defined clusters for inner-race faults (Silhouette 0.5190), three moderate clusters for outer-race faults (0.2339), and overlapping patterns for rolling element faults (–0.1527), with zero RUL deviation in the best case. The proposed framework combines real and synthetic data to enhance generalization while reducing computational cost, offering a reliable and scalable solution for predictive maintenance and assessment of degradation progression in wind turbine bearings.
Gustavo Gomes Do Valle, Benjamin Soudhan, Meisam Mahdavi et al.· IEEE Access· 0 citations
This smart fault diagnosis method based on the Time Convolution Network - Bidirectional Gated Recurrent Unit - Attention Model (TCN-BiGRU-Attention) can achieve high-precision and stable fault diagnosis for rolling bearings, providing an effective intelligent diagnosis solution for engineering applications.
Ming-Li Li, Zhu Yuan· Frontiers of Mechanical Engi...· 0 citations
