Quantifying the Relative Change in Maintenance Costs due to Delayed Maintenance Actions in Transportation Infrastructure
Bibliographic record
Abstract
Identifying optimal maintenance policies for transportation infrastructure such as bridges, is a challenging task that requires taking into account many aspects relating to budget availability, resource allocation and traffic rerouting. In practice, it is difficult to accurately quantify all of the aforementioned factors; accordingly, it is equally difficult to obtain network-scale optimal maintenance policies. This paper presents an approach to evaluate the costs associated with deviations from optimal bridge-level maintenance policies, specifically focusing on delays in maintenance actions. Evaluating the cost of maintenance delays is performed using a reinforcement learning (RL) approach that relies on a probabilistic deterioration model to describe the deterioration in the structural components. The RL framework provides estimates for the total expected discounted maintenance costs associated with each maintenance policy over time, allowing comparison of maintenance policies where maintenance actions are delayed against an optimal maintenance policy. The comparisons are performed by probabilistically quantifying the ratio of expected costs associated with each maintenance policy. This ratio represents the trade-offs between performing or delaying maintenance actions over time. Moreover, the proposed approach is scalable, making it applicable to bridges with numerous structural elements. Example of application using the proposed framework is demonstrated using inspection data from bridges in the Quebec province of Canada.
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 | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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) | 0.001 | 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".