A bearing fault diagnosis method based on the fusion of dynamic separable CNN and LSTM
Bibliographic record
Abstract
As a core component of rotating machinery, the operational status of bearings directly affects the safety and reliability of equipment. Timely and accurate fault diagnosis is of great significance for preventing malignant accidents and reducing maintenance costs. To address the above issues, this paper proposes a bearing fault diagnosis method based on the fusion model of Relative Angle Matrix, Dynamic Separable Multi-scale Convolutional Neural Network, and Long Short-Term Memory network. This method first converts one-dimensional vibration signals into two-dimensional images through RAM, retaining the temporal correlation and amplitude information of the signals. Then, building on the Convolutional Neural Network architecture, a Dynamic Separable Convolution Module is constructed. By optimizing convolutional operations, this module significantly reduces the number of learnable parameters and computational overhead. Specifically, it leverages dynamic separable convolution to extract spatial features from image-derived signals; meanwhile, it is integrated with a Long Short-Term Memory network to capture temporal dependencies in feature sequences. Finally, the proposed method was tested on the public bearing dataset of Case Western Reserve University, and its diagnostic precision reached 95.4%, which is higher than that of current mainstream methods. The experimental results indicate that the algorithm exhibits high accuracy and efficiency in fault diagnosis tasks.
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 | 0.001 | 0.001 |
| 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) | 0.001 | 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".