Japan Aerospace Exploration Agency (JAXA)
Japan Aerospace Exploration Agency (JAXA)
Japan Aerospace Exploration Agency (JAXA)
The University of Tokyo
The University of Tokyo
The University of Tokyo
出版者
日本航空宇宙学会(JSASS)
出版者（英）
The Japan Society for Aeronautical and Space Sciences (JSASS)
雑誌名
第59回宇宙科学技術連合講演会講演集
雑誌名(英)
Proceedings of 59th Space Sciences and Technology Conference
We have studied learning-based telemetry monitoring system using machine learning, for the acquisition of high-performance fault diagnosis technology that leads to the stable operation of the satellite. In consideration of the past, we confirmed the effectiveness of the anomaly detection. Currently, in order to improve the detection rate of satellite state change that is difficult to be detected like precursory phenomenon of abnormality, we are considering the improvement of the analytical method. This paper describes the performance evaluation of telemetry monitoring and anomaly detection system based on data mining and machine learning which was carried out using the operating system of small satellite SDS-4.
内容記述
形態: カラー図版あり
内容記述（英）
Physical characteristics: Original contains color illustrations
SDS-4運用における学習型テレメトリ監視システムの性能向上検討(2): 検証と評価
