Improvement of railroad maintenance program: predicting the degradation level of railroad timber ties through the application of the random forest model
Bibliographic record
Abstract
Railway infrastructure is one of the most significant pieces of the contemporary transportation sector, with railway ties being central components of railway tracks, whose deterioration poses substantial safety concerns. The main objective of this study is to find practical and optimal solutions to address the tie maintenance and replacement program by accurately estimating the proportions of defective and marginal ties that exceed or fall below certain thresholds for different classes of rail. As a result, machine learning (ML) methodologies are employed and applied to the most recent tie replacement data, alongside other influential input parameters. The random forest (RF) model demonstrated the highest accuracy in estimating the proportions of marginal and poor ties that either exceed or fall below predetermined thresholds over a defined timeframe following the last tie replacement. Although the results of two other models; decision tree (DT) and long-short term memory (LSTM), were also incorporated and displayed, the RF model consistently exhibited superior precision. When these thresholds are surpassed, it signifies the need to include the corresponding mileposts into the tie replacement program to ensure the safety and reliability of the operations within the railroad system. The data used in this study were obtained from the Canadian National (CN) Railway Company, spanning their entire rail network, integrating the data from inspection cars with some additional pertinent variables, totaling 45 parameters. The proposed approach has the potential to reshape the established practices and deliver a valuable improvement to current rail maintenance program.
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 | 0.002 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".