Classification and Severity Estimation of Eccentricity Faults in Salient Pole Synchronous Machine Using Deep Learning
Bibliographic record
Abstract
The presented research work is focused on the classification and severity estimation of eccentricity faults in Salient Pole Synchronous Machines. Building on our comparative study of Artificial Neural Network and Convolutional Neural Network for eccentricity fault classification, we propose an end-to-end deep learning model, namely Hierarchical Convolutional Neural Network, for eccentricity classification and severity estimation. The deep learning model inherently consists of an eccentricity detection component for fault classification and a severity estimation component for fault quantification. The deep learning model is built using the experimental data of a 3-phase, 2-kW, salient pole synchronous machine. The machine is subjected to 20%, 40%, and 60% severities of static and dynamic eccentricity faults under different loading conditions. Stator line currents and line-to-line voltages obtained from different operating conditions are used to train, validate and test the proposed model. To enhance the model's performance, time delay construction was incorporated to augment the datasets and carefully evaluate the impact of selected raw input features, specifically stator currents and voltages, as well as the load. Among the evaluated scenarios, the use of voltage with time delay (V, TD) as input features produced the best results, achieving 100% classification accuracy and a root mean square error of 0.0046 for static eccentricity and 0.0188 for dynamic eccentricity estimation. Results indicate that the model performs excellently in fault classification and severity estimation. Compared to traditional machine learning models, the presented model is an end-to-end deep learning architecture devoid of manual feature extraction and is robust to load variations.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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".