A Novel Predictive Selective Maintenance Strategy Using Deep Learning and Mathematical Programming
Bibliographic record
Abstract
Many systems are required to perform a series of missions with finite breaks between successive missions. For such systems, one of the most widely used maintenance strategies is selective maintenance (SM). Under certain maintenance constraints, the SM problem (SMP) consist in selecting an optimal subset of feasible maintenance actions to maximize the system reliability for the upcoming mission. Almost all SMP models proposed in the literature are focused on traditional physics-based reliability models, where component lifetimes can be modeled using a stochastic process. With the application of new technologies such as wireless sensors and Industrial Internet of Things (IIoT), and the recent advancements in Deep Learning (DL) algorithms for prognostics, predictive maintenance based on data-driven methods has become a very popular maintenance strategy. These data driven methods have shown extreme accuracy in predicting remaining useful life (RUL) of components and systems. The goal of this paper is to introduce a predictive selective maintenance strategy that can be used to solve complex and relatively large multi-component systems. A DL algorithm will be used to estimate the probability that each component will successfully complete the upcoming mission, a selective maintenance optimization model will then be used to identify the maintenance actions that will maximize the system reliability. An efficient solution method is devised to solve the resulting complex optimization problem. The NASA C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) dataset is used to train and evaluate the DL algorithm. The numerical experiments carried out show that the proposed novel predictive maintenance strategy is accurate and yields valid decisions.
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 | 0.002 | 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".