Open AccessAnomaly Detection Method for Spacecraft System Based on High Dimensional Space Mapping
Author(s) -
Xiangyan Zhang,
Zhiqiang Li
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2006/1/012069
Subject(s) - anomaly detection , spacecraft , telemetry , computer science , anomaly (physics) , preprocessor , orbit (dynamics) , process (computing) , real time computing , orbit determination , data mining , remote sensing , satellite , aerospace engineering , engineering , physics , artificial intelligence , geology , telecommunications , condensed matter physics , operating system
Spacecraft system, as a typical complex system, is also a high-risk field. Even small faults in local links may bring huge losses or disasters. Analyzing the system level associated anomaly detection method caused by the interaction of multiple telemetry parameters can provide technical means for the rapid and accurate detection of system level in orbit associated faults. In this paper, firstly, a system anomaly detection method based on high-dimensional space mapping is proposed. Secondly, based on the preprocessing of telemetry data, the division of telemetry subsystem is realized. Thirdly, Based on the dimension reduction of subsystem space, the system anomaly detection method is given, and the technical process of the method is given. Finally, through the verification of on orbit actual data, it shows that the system anomaly detection result is accurate.