Fault diagnosis of rolling bearing with variable working conditions in noisy environment based on dynamic soft threshold and attention mechanism
Bibliographic record
Abstract
Abstract In response to the complex and variable working conditions faced by rolling bearings during actual operation, as well as the issue of vibration signal acquisition being easily disrupted by noise interference, the study describes the multi-source domain anti-noise rolling bearing failure detection approach (MEDThresNet). The purpose of this model’s design is to solve the challenges of a lack of corresponding sample data and noisy signals in bearing fault classification. Using multi-condition source domains, as opposed to a single working condition source domain data, might help gain information from diverse domains and minimize overreliance on data from a specific working condition source domain. This can significantly increase the model’s generalization and robustness, and fault identification accuracy. Convolutional modules with soft thresholding and attention mechanisms are applied in this network structure. Soft thresholding helps to suppress noise in the data during the training phase while keeping critical characteristics. The attention mechanism, on the other hand, allows the model to automatically focus on the critical areas of the defect information in the bearing vibration signals throughout the training phase, hence improving the network’s performance and generalization ability. Furthermore, the network aligns the joint distribution of source and target domain data across many particular levels using the joint maximum mean discrepancy approach to accomplish unsupervised domain adaptation. This allows the network to successfully transfer information learnt from the source domain data of the faulty bearing to the target domain of the faulty bearing, improving the model’s generalizability on the target domain. This research tests the network on two datasets with varied working conditions, CWRU and Ottawa, and the findings demonstrate that the network is high robustness and accurate for multi-source domain transfer diagnosis in noisy environments.
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 | 0.001 | 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 | 0.000 |
| 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".