RESEARCH BY INDUSTRY
Find published research and synthetic demonstrations, with planned and developing topics clearly separated.
9 published public-data studies4 synthetic demonstrations51 planned or developing topics
1 published study · 2 planned or developing topics
S13 / Manufacturing
A manufacturing quality leader must identify high-risk units without flooding inspection capacity. Test whether a stable, compact sensor model can match a more complex classifier while controlling missed failures.
Evaluated public-data study
Read the finding and evidence ↗These topics are separate from completed findings. Each status reflects the work actually performed.
S14 / Manufacturing
A maintenance team needs warnings early enough to schedule work, with few false alarms. Compare interpretable vibration change detection against an unsupervised anomaly model across independent bearing experiments.
Planned topic
Spectral features; control charts; change-point detection
Extract spectral-band energy, envelope features and robust distribution summaries from vibration windows. Define an early-run reference period explicitly rather than assuming verified healthy labels. Compare robust control charts/change-point methods with a compact anomaly detector and enforce an alarm-persistence rule.
Evaluation: Keep complete experiments or bearings together and show leave-run-out results wherever the small number of runs allows. Report time before documented failure, false alarms per operating hour and sensitivity to window length. Bootstrap by run only when meaningful; emphasize per-run results over spurious narrow intervals.
Boundary: A few laboratory failures cannot establish fleet-wide reliability. The onset of degradation is not fully labeled; maintenance savings and the effect of a repair policy require explicit simulation or prospective data.
S15 / Manufacturing
A fleet planner must choose when to replace an asset when failure timing is uncertain. Test whether calibrated remaining-life distributions improve a simulated replacement policy relative to point estimates.
Planned topic
Degradation modeling; quantile sequences; asymmetric decision loss
Use engine-level C-MAPSS train/test partitions and preserve operating-condition subsets. Compare an engineered degradation-index baseline, boosted quantile regression and one sequence model. Make remaining-life label capping and sensor normalization explicit, including ablations.
Evaluation: Report engine-level RUL error, the benchmark's asymmetric score and interval coverage by operating condition and life stage. Test an unseen-condition subset. Simulate replacement using only sequentially available measurements and compare fixed-age, point-estimate and uncertainty-aware rules.
Boundary: C-MAPSS is simulator-generated. Both asset behavior and the policy economics must be labeled as simulation; no real fleet savings or safety validation are established.
The 60-topic program spans 20 industries, with 9 studies published. Synthetic demonstrations are counted separately. Unpublished topics have no public case-study route.
