Research on axle bearing fault detection method based on multilayer feature fusion under sparse training samples
Bibliographic record
Abstract
Train axle bearing faults pose safety risks if unaddressed, but acquiring sufficient labeled fault samples for training models is challenging due to high data collection costs and risks. This work proposes a multi-scale fusion feature extraction strategy and domain knowledge embedding bearing fault diagnosis method. Complementary ensemble empirical mode decomposition (CEEMD) extracts intrinsic mode functions (IMFs) carrying the highest correlation from vibration signals at different frequency scales. Our multi-scale multilayer perceptron (MSMLP) model obtains general features by learning the two-dimensional matrix obtained by the short-time Fourier transform (STFT) of IMF at different scales. The denoised signal decomposed and reconstructed by CEEMD uses the wavelet packet-energy entropy (WPT-EE) algorithm to obtain physical characteristics. Then, physical features and general features are fused by improving the attention mechanism. Finally, fault classification is achieved through the MLP network. Our framework has been shown to be effective in classifying different fault states and health states of bearings in sparse sample train axle box failure experiments. Compared with several advanced methods, the advantages of this method in terms of accuracy and stability of bearing fault diagnosis are also confirmed. Therefore, this technique shows promise for practical train axle bearing condition monitoring applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".