Abstract
The satellite power subsystem is responsible for all power supply in a satellite, and is an important component of it. The system’s performance has a direct impact on the operations of other systems as well as the satellite’s lifespan. Sequence to sequence (seq2seq) learning has recently advanced, gaining even more power in evaluating complicated and large-scale data. The potential of the seq2seq model in detecting anomalies in the satellite power subsystem is investigated in this work. A seq2seq-based scheme is given, with a thorough comparison of different neural-network cell types and levels of data smoothness. Three specific approaches were created to evaluate the seq2seq model performance, taking into account the unsupervised learning mechanism. The findings reveal that a CNN-based seq2seq with attention model under suitable data-smoothing conditions has a better ability to detect anomalies in the satellite power subsystem.
Highlights
The satellite power subsystem converts solar energy into electrical energy to provide power for the satellite’s routine operation
When an anomaly arises in the satellite power subsystem, it may take longer to reach full power charging, and this anomaly is a time-dependent anomaly according to Section 3.4
The seq2seq model is more promising for practical applications, because the telemetry data of satellite power subsystem health monitoring are time series data with few abnormal samples
Summary
The satellite power subsystem converts solar energy into electrical energy to provide power for the satellite’s routine operation. The normal operation of the power subsystem is very important to the satellite [1]. Due to the special working environment, the proportion of satellite power subsystem failures has reached 30%, according to statistics of 300 cases of on-orbit spacecraft failures from 1993 to 2012 [2]. There are many sensors in the power subsystem to monitor its working status. These sensors generate a vast quantity of timeseries data, known as the telemetry data, which are relayed back to the ground, where experts may evaluate it to see if the power subsystem is malfunctioning [3]. Anomaly detection in the power subsystem has become a problem of how to find anomalies from multivariate time series without supervision [4,5]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
