The possibility of using machine learning for network-wide predictive maintenance on urban railway tracks – URITMIS project case study
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Manual measurements with hand-held measuring equipment have become ineffective due to their time consumption and disruption of the regular operation schedule. In recent years, new measuring methods have been established, using specialized or in-service vehicles to collect significant amounts of data on condition of railway or tramway track infrastructure. However, accessing large datasets requires an extensive amount of time to process and evaluate the data before providing valuable information on track infrastructure condition to the operator. Effective large dataset analysis method could simplify the maintenance and intervention plan for the tramway infrastructure and improve the quality of track monitoring system. Several researchers and authors have investigated the possibility of implementing various machine learning approaches to speed up and automate the evaluation of track condition data. Based on historic and real-time data from in-service vehicles, using machine learning it is possible to detect irregularities and update digital twin model of the track for predictive maintenance. As part of the project URITMIS - Urban Railway Infrastructure Maintenance System, machine learning techniques and digital twin models of the tramway track will be investigated to improve maintenance efficiency and track reliability and resilience of Zagreb's tramway network. This paper presents current state of art as well as case-study of weld detection and evaluation from in-service vehicle bogie acceleration signals using machine learning techniques.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it