arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.17841cs.LGcs.AI

面向航天器姿态传感器的多变量时间序列中基于机器学习与基于深度学习的异常检测对比

Machine Learning-based vs Deep Learning-based Anomaly Detection in Multivariate Time Series for Spacecraft Attitude Sensors

Airbus Defence and Space GmbH(空中客车防务与航天有限公司);Delft University of Technology(代尔夫特理工大学)

R. Gallon, F. Schiemenz, A. Krstova, A. Menicucci, E. Gill

AI总结:

本文比较了机器学习与深度学习方法在航天器姿态传感器多变量时间序列卡滞值检测中的性能、可解释性与泛化能力,为航天器FDIR提供AI新方案。

摘要:

在航天器故障检测、隔离与恢复(FDIR)框架下,最新的研究中正在涌现基于人工智能的新方法,以克服传统阈值检查通常带来的局限性。本研究旨在刻画两种不同方法在航天器姿态传感器多变量时间序列中卡滞值检测问题上的表现。分析揭示了两种方法在性能上的差异,同时对其可解释性和在不同场景下的泛化能力进行了评述。

英文摘要:

In the framework of Failure Detection, Isolation and Recovery (FDIR) on spacecraft, new AI-based approaches are emerging in the state of the art to overcome the limitations commonly imposed by traditional threshold checking. The present research aims at characterizing two different approaches to the problem of stuck values detection in multivariate time series coming from spacecraft attitude sensors. The analysis reveals the performance differences in the two approaches, while commenting on their interpretability and generalization to different scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑