Query based learning via conformal uncertainty for RUL prediction
Bibliographic record
Abstract
The rapid advancement of sensor technologies in industrial systems has led to the continuous accumulation of high-dimensional, time-series data, presenting significant challenges for Prognostics and Health Management (PHM). These challenges include increasing computational burdens, the need for scalable model training, and the difficulty of labeling large datasets in dynamic environments. To address these issues, this research proposes a systematic methodology for Remaining Useful Life (RUL) prediction that integrates conformal prediction with an active learning framework. A novel sample selection strategy is introduced, combining RUL-guided and uncertainty-driven acquisition based on the distribution-free uncertainty estimates provided by conformal prediction. This approach adaptively identifies informative and representative samples from the data stream to incrementally build and refine the RUL prediction model using a limited amount of labeled data, thereby reducing training costs while maintaining high prognostic accuracy. The proposed method is validated using the real-world C-MAPSS dataset and demonstrates superior performance over other baselines, such as random sampling and uncertainty sampling, in terms of prediction accuracy, label efficiency, and adaptability to evolving system conditions.
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 | 0.007 |
| 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 | 0.002 |
| Open science | 0.002 | 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".