Enhanced approach for gears-bearings defect diagnosis based on optimized artificial neural network model and features selection graphical technique
Bibliographic record
Abstract
This study presents a high-performance artificial neural network system, optimized using the Grey–Taguchi multi-objectif optimization technique, for accurate diagnosis of single and compound gear–bearing faults in rotating machinery. The proposed approach integrates automated feature extraction with a robust feature selection framework combining class-wise discriminative analysis based on global one-way ANOVA, effect size estimation, Fisher scores, and a One-vs-Rest strategy. Graphical validation of the selected features is further conducted using box-and-whisker plots to enhance interpretability and ensure measurement stability. To address non-stationary industrial noise, a Least Mean Squares (LMS) adaptive filter is employed to suppress irrelevant components while preserving impulsive and modulation-related fault vibration signatures. Experimental validation is carried out using three-axis vibration measurements acquired from a Machine Fault Simulator operating under magnetic brake conditions, effectively emulating a realistic noisy environment. The optimized model achieved a global correlation coefficient (RG) of 98.593 %, a mean squared error (MSE) of 0.019799, and an overall macro-averaged F1-score of 98.40 % within 39 training epochs. Incorporating the most discriminative features further enhanced the diagnostic performance, achieving an overall macro-averaged F1-score of 99.64 % (RG=99.955 %). These results demonstrate the robustness, reliability, and practical suitability of the proposed methodology for advanced condition monitoring under noisy and compound fault scenarios.
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 | 0.000 | 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 | 0.001 |
| 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".