Pneuma releases aircraft time-series data for predictive maintenance
Original title: Pneuma: A Large-Scale Real-World Time Series Benchmark for Commercial Aircraft Predictive Maintenance
The public set has over 920 million steps, four aircraft types, and nine verified fault scenarios.
Pneuma is a public benchmark of onboard time series from in-service commercial aircraft, centered on bleed air systems and aligned with maintenance logs. It covers multivariate forecasting, supervised fault classification, and unsupervised anomaly detection. The authors evaluate more than 25 models from four families on nine subsets and report that strong models still miss subtle fault signatures.
- Labels come from actual maintenance records.
- Challenges include class imbalance, subtle faults, and configuration variance.
- Forecasting quality was strongly associated with anomaly detection.
- More in-context examples and multivariate inference improved results.
From the original article
1 min read at arxiv.orgPredictive maintenance is vital for commercial aviation, yet progress remains hindered by the lack of public, large-scale real-world datasets. As a result, most methods are developed and evaluated on proprietary data, limiting reproducibility. We introduce Pneuma, the first publicly available large-scale benchmark for predictive maintenance using onboard time series from in-service commercial aircraft.
By Jiafeng Lin · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.