Vehicle Event Condition Monitoring Reliability in Mass Transit Fleets Using A Simplified Covariate Non-Honogeneous Poisson Proces Model
Bibliographic record
Abstract
Summary & Conclusions This paper describes how the rolling stock real-time vehicle events are processed and diagnosed; how its reliabilities are modeled and trends predicted by an unprecedented use of a Covariate Non-Homogeneous Poisson Process (NHPP). The strategy proved vital to anticipate, prevent and correct for future incidents such as component or system failures causing or not service disruptions in the form of train delays or suspensions. Vehicle real-time events have been continuously produced over a period of 20 years, from critical systems in the revenue subway fleets, such as Brakes, Propulsion, Doors and Air, Air Conditioning, Automatic Train Operation ATO … etc. Events are produced and transmitted from the vehicle by radio and collected in the Subway Maintenance System (SMS) Event Module when trains pass through the yards' portals. The information captured in the Toronto Transit Commission (TTC) Computerized Maintenance Management System (CMMS), Subway Maintenance System (SMS) is used by front line maintainers to correct faults and failures. Subsequently, modelled by reliability engineering to determine the impacts of configuration modifications and maintenance programs over the asset life and to recommend optimization, in the form of additional improvements in asset repair programs and design to enhance serviceability performance. Modern prescriptive vehicle “health” analytics uses events produced by the train, which are an essential information to assist with the Enterprise Asset Management EAM at a tactical level, an initiative applicable to the Vehicle Condition Monitoring at the EAM Strategic level. If an asset repair is not properly described, diagnosed, prescribed and executed, it could cause more negative impact in customer service, frustrating the expectation of a reliable performance. If an asset that doesn't expose typical age-related wear out failure distribution pattern is placed under a scheduled time-based maintenance repair or overhauls, it will not or marginally benefit from the program work; inevitably can re- introduce “infant-mortality” or premature failures. Results suggest that maintenance does not improve asset reliability, it is meant to restore an item functions as close as new possible, however it is observed that there is always decay and problems of obsolescence. We argue that the results presented in this paper are a novel practical application of the Non-Homogeneous Poisson Process NHPP, quantitatively confirmed, driven by the use of evidence based information from the TTC CMMS SMS.
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 | 0.003 |
| 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 | 0.001 | 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".