Neural Nets use for satellite telemetry analysis in application for KazSTSAT mission

Paper number

IAC-19,B4,6A,10,x54983

Author

Mr. Arman Bekembayev, Kazakhstan, Ghalam LLP

Coauthor

Dr. Vladimir Ten, Kazakhstan, Ghalam LLP

Coauthor

Prof. Rustem Takhanov, Kazakhstan

Coauthor

Mr. Manap Shymyr, Kazakhstan, Nazarbayev University

Year

2019

Abstract

\begin{document}
KazSTSAT mission was launched on the 3rd December 2018 and so far looking good with some minor anomalies encountered during commissioning phase. But there is a need in a tool analyzing vast scope of information obtaned by KazSTSAT spacecraft operation center. 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.\newline
The expected output is the deep learning software application that can be widely used for:
\begin{itemize}\item Failure Detection Isolation and Recovery (FDIR) analysis as the real-word modelling environment;\end{itemize}
\begin{itemize}\item System functional tests as the additional verification method of the Concept of Operations; \end{itemize}
\begin{itemize}\item Spacecraft operators training to predict final spacecraft subsystems states in case of the intentionally induced anomalies; \end{itemize}
\begin{itemize}\item On-orbit commissioning and operations to reduce the risks of fatal mission anomalies. \end{itemize} \newline
The paper provides an overview of the application development steps, the difficulties encountered during the design and implementation on real world telemetry data.
\end{document}

Abstract document

IAC-19,B4,6A,10,x54983.brief.pdf

Manuscript document

IAC-19,B4,6A,10,x54983.pdf (🔒 authorized access only).

To get the manuscript, please contact IAF Secretariat.