Advanced framework for intelligent fault diagnosis in rotary machinery with out-of-distribution recognition
Bibliographic record
Abstract
Abstract Fault diagnosis plays a crucial role in maintaining mechanical equipment reliability. Deep neural networks have exhibited superior performance in fault diagnosis under closed sample space assumptions. However, the deployment of neural network models in practical industrial environments faces significant challenges due to the emergence of out-of-distribution (OOD) data, particularly novel fault categories that deviate substantially from the initial training assumptions. To address these limitations, we propose a robust fault diagnosis framework incorporating OOD sample detection and adaptive learning capabilities. The framework utilizes a novel Mixture of Experts model (MoEFormer) as the feature extraction mechanism, which enables fine-grained feature representation while enhancing computational efficiency. Furthermore, we introduce a Gaussian density peak clustering algorithm for OOD data identification and autonomous model retraining. This integrated framework enables real-time adaptation and online diagnosis in industrial scenarios where novel fault categories may emerge. Experimental validation was conducted using the bearing fault dataset from the University of Ottawa and the gear fault dataset from Xi’an Jiaotong University. The results demonstrate that our proposed method outperforms existing state-of-the-art approaches in identifying unknown OOD faults and achieves superior diagnostic performance. The adaptively updated model attained a diagnostic accuracy of 96.0%, representing a significant improvement of approximately 30 percentage points compared to non-adaptive methods.
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 | 0.001 | 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 | 0.001 | 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".