An Information Fusion Based Incipient Fault Diagnosis Method for Railway Vehicle Door System
Bibliographic record
Abstract
The safety and reliability of the railway vehicle door system are critical to ensure passengers’ safety and transportation efficiency. Fault diagnosis is essential for such a purpose. However, due to various uncertainties in the models and measurements, as well as the existence of incipient faults, traditional fault diagnosis methods often suffer from high false alarms. In this study, an incipient fault diagnosis method is developed using an information fusion strategy, which can greatly reduce false alarms and hence improve the reliability and accuracy of fault diagnosis results. The proposed fault diagnosis method is a data-driven approach, where current, rotational speed, rotational angle/distance signals collected from the driven motor and vibration signals collected from the supporting elements and door leaves are used for fault diagnosis. Initially, features are extracted from the signals to train two classifiers. Subsequently, these classifiers generate probabilities for different fault types. Then fault diagnosis model is developed using an information fusion strategy where evidence belief divergence and fuzzy preference relationship are employed to handle conflicts between different evidence. The principal contributions center on the elimination of information uncertainties within the railway door system, enabling precise diagnosis of incipient faults. To validate the methodology, verifications are conducted on a vehicle door test bench. Comparative experiments are also conducted to demonstrate the superiorities of the proposed method in comparison to approaches that do not incorporate information fusion or address information conflicts. The experimental results show that the proposed method significantly enhances diagnosis accuracy by at least 10%.
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".