MD-Transformer: a noise-oriented lightweight bearing fault diagnosis model
Bibliographic record
Abstract
Abstract In complex industrial environments, rolling bearing vibration signals are often contaminated by noise, making it difficult to extract key fault features and reducing diagnostic accuracy. To address this issue, a lightweight and noise-resilient Transformer-based model, termed MD-Transformer, is designed. First, a novel multi-scale excitation convolution module is designed to extract local features across multiple receptive fields using four parallel depthwise separable convolutions and average pooling layers. A squeeze-and-excitation module is incorporated to further enhance the representation of noise-sensitive fault features. Additionally, a dynamic depthwise separable attention (DDSA) mechanism is developed to improve global feature modelling and noise robustness. Unlike conventional attention, DDSA dynamically adjusts attention weights via learnable depthwise convolutions, enabling adaptive noise suppression and better focus on fault-related features. Experiments conducted on the Ottawa bearing dataset demonstrate that MD-Transformer achieves an average diagnostic accuracy of 96.63% across a signal-to-noise ratio range of –2 dB to 8 dB, outperforming existing lightweight and Transformer-based models by 1.55%–4.33% while maintaining low computational cost. These results highlight the model’s effectiveness in robust feature extraction and its potential for real-time edge-level industrial 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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".