Fault diagnosis method for lightweight gearboxes based on depth-separable cascaded residual block and feature-weighted module
Bibliographic record
Abstract
Aiming at the problem of insufficient feature extraction in some deep learning-based gearbox fault diagnosis models under small sample conditions leading to lower fault diagnosis accuracy and larger number of parameters, in this paper, a lightweight gearbox fault diagnosis method based on depth-separable cascade residual block and feature weighting module is proposed. Firstly, the one-dimensional original signal of the gearbox is used as the input of this model, which reduces the loss of information in data processing. Then the depth-separable cascade residual block is constructed, which utilizes the depth-separable convolution with a cascade residual structure to maximize the extraction of fault information while reducing the amount of feature parameters. Finally, the feature weighting module strengthened the model's identification and exploitation of key features by calculating the contribution of each channel and giving them weighting. The experimental validation is given by the gearbox dataset of Southeast University, and the experimental results show that the proposed method achieves 99.99% fault diagnosis accuracy under the original signal, and 99.60% under the SNR=6dB noise environment, which shows that the proposed method has high fault diagnosis accuracy and low complexity under the small sample condition.
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 | 0.000 |
| 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".