A machine learning approach for the operational situational awareness (OSA) in flight operations is presented. The spacecraft health and safety telemetry are generally time dependent and periodical. The machine learning algorithms, such as neural networks, are used to capture the time dependent trend of the telemetry datasets characterized by their data patterns and noise level, which provides a direct insights into the health and safety status of telemetry datasets. As the time dependent trends are highly sensitive to changes above the noise level, the potential anomalies can be detected at much early stage, which leads to a more proactive flight operations and a more resilient system. The challenges for the machine-learning approach in the spacecraft ground system are to develop a systematic, accurate, adaptive and efficient data training strategy, and a representation to meet persistent requirement. The focus of this paper is to present a machine-learning approach for the time dependent trending of spacecraft datasets with arbitrary scales. The data training algorithms have been developed and implemented in neural networks, which are shown to generate highly accurate time dependent trend. The OSA tool, ASRC Intelligent Monitoring System (AIMS), is presented, which implements the machine-learning algorithm. The extensions of machine-learning algorithms in developing capabilities to improve the mission efficiency and enable more autonomous operations are discussed.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Machine Learning in Spacecraft Ground Systems


    Contributors:


    Publication date :

    2017-09-01


    Size :

    535616 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Autonomic Computing for Spacecraft Ground Systems

    Li, Zhenping / Savkli, Cetin / Jones, Lori | NTRS | 2007


    Autonomic computing for spacecraft ground systems

    Zhenping Li, / Savkli, C. | IEEE | 2006