A Novel Mechanical Fault Diagnosis Based on Transfer Learning with Probability Confidence Convolutional Neural Network Model
Bibliographic record
Abstract
For fault diagnosis, convolutional neural networks (CNN) have been performing as a data-driven method to identify mechanical fault features in forms of vibration signals. However, because of CNN’s ineffective and inaccurate identification of unknown fault categories, we propose a model based on transfer learning with probability confidence CNN (TPCCNN) to model the fault features of rotating machinery for fault diagnosis. TPCCNN includes three major modules: (1) feature engineering to perform a series of data pre-processing and feature extraction; (2) transferring learning features of heterogeneous datasets for different datasets to have better generality in model training and reduce the time for modeling and parameter tuning; and (3) building a PCCNN model to classify known and unknown fault categories. In addition to solving the problem of an imbalanced sample size, TPCCNN self-learns and retrains by iterating with unknown classes to the original model. This model is verified with the use of the open-source datasets CWRU and Ottawa. The experimental results showing the feature transfer of heterogeneous datasets are of average accuracy rates of 99.2% and 93.8% respectively for known and unknown categories, and TPCCNN is then proven effectively in training heterogeneous datasets. Likewise, similar feature sets can also be applied to reduce the training of predicting models by 34% and 68% of the time.
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 | 0.002 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 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".