Condition-Based Maintenance Scheduling Using Probability Distribution Function and Agglomerative Hierarchical Clustering Approaches: AI-Driven Predictive Maintenance Mapping
Bibliographic record
Abstract
Advanced industries such as wind turbines aim for condition-based maintenance (CBM) to enhance system availability and reach higher revenue. Hence, decision making plays an essential role in optimizing the maintenance planning process and achieving a more reliable system. In this work, a hierarchical decision process using remaining useful life (RUL) information is introduced for the maintenance scheduling of wind farms. Real-time condition monitoring and failure prognosis are conducted through a Bayesian approach to obtain probability distribution functions (PDFs) for the faulty turbines/components and predict their associated RUL. Following that, an augmented probability model is built by adding the RULs to create a feature map for maintenance. Finally, hierarchical clustering is applied to schedule maintenance times by setting certain planning policy rules using a dendrogram chart along with the wind farm information. This work’s main contribution is that the proposed decision process includes PDFs of faulty turbines used to deliver an optimized maintenance schedule based on the suggested probability feature map. In addition, the hierarchical clustering using wind farm information enhances wind turbine availability and reduces maintenance costs. Field data from wind turbines located in Chile confirm the superior performance of the proposed hierarchical decision policy in comparison with the conventional corrective maintenance strategy.
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".