Abstract
KazSTSAT mission was launched on the 3rd December 2018 and so far the results are exceeding the pre-launch expectations. As with any serious mission there is a need for short and long term analysis of the telemetry, which is traditionally achieved by qualified operators looking at the data. A ML tool analyzing vast scope of information obtained from a spacecraft would be very useful for KazSTSAT and other missions. The research has the aim to make use of automatic self-learning machines that can predict future states of the space system based on the archived and real-time telemetry and telecommand data. The expected output is the deep learning software application that can be widely used for: • Failure Detection Isolation and Recovery (FDIR) analysis as the real-word modelling environment; • System functional tests as the additional verification method of the Concept of Operations; • Spacecraft operators training to predict final spacecraft subsystems states in case of the intentionally induced anomalies; • On-orbit commissioning and operations to reduce the risks of mission critical anomalies. The paper provides an overview of the application development steps, the difficulties encountered during the design and implementation on real world telemetry data.
Original language | English |
---|---|
Article number | IAC-19_B4_6A_10_x54983 |
Journal | Proceedings of the International Astronautical Congress, IAC |
Volume | 2019-October |
Publication status | Published - Jan 1 2019 |
Event | 70th International Astronautical Congress, IAC 2019 - Washington, United States Duration: Oct 21 2019 → Oct 25 2019 |
Keywords
- Machine Learning
- Neural Nets
- Telemetry processing
ASJC Scopus subject areas
- Aerospace Engineering
- Astronomy and Astrophysics
- Space and Planetary Science