Summary
Predictive maintenance helps keep airplanes safe by spotting problems before they cause failures, but the lack of large public data has made progress hard. The authors created Pneuma, a huge public dataset with real sensor data from commercial planes and actual maintenance records. It includes many types of subtle faults and covers different airplane models, reflecting real challenges seen in practice. They tested many existing models and found that even strong methods have trouble detecting these hidden problems, offering insights to improve future approaches. This dataset aims to make developing and comparing predictive maintenance techniques easier and more reliable.
What this means in practice
- •For aviation maintenance teams: Accurately evaluate and improve fault detection models using real-world aircraft sensor data aligned with maintenance logs.
- •For industrial iot engineers: Use a large real-world time series dataset with subtle fault patterns to develop anomaly detection methods beyond aviation.
Authors
Jiafeng Lin, Yutian Zhang, Huan Zhang, Yuxuan Wang, Jinyan Feng, Yuhui Liu, Zhongyi Pei, Jianmin Wang
Abstract
Predictive 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. Built around bleed air systems, Pneuma contains over 920 million multivariate time steps across four aircraft types and 9 verified fault scenarios, directly aligned with real maintenance logs. The dataset exhibits key real-world challenges, including substantial class imbalance, subtle fault evolution patterns, and significant variance across aircraft configurations. We structure the benchmark around three tasks: multivariate forecasting, supervised fault classification, and unsupervised anomaly detection, with labels derived from actual maintenance records. Under unified settings, we evaluate over 25 models from four methodological families on 9 carefully curated subsets. The results reveal that even strong contemporary models struggle with subtle fault signatures. Further analyses show consistent gains from additional in-context examples and multivariate inference, while forecasting quality is strongly associated with anomaly detection performance. Together, these findings provide practical insights into effectively modeling complex real-world aviation time series. We hope Pneuma will serve as a rigorous and reproducible foundation for advancing data-driven predictive maintenance toward real-world deployment in commercial aviation.