Spacecraft Anomaly Analysis and Prediction System – SAAPS
Peter Wintoft1), Henrik Lundstedt1), Lars Eliasson2), Leif Kalla2), and Alain Hilgers3)
1)Swedish Institute of Space Physics – Lund 2)Swedish Institute of Space Physics – Kiruna 3)ESA/ESTEC
Spacecraft Anomaly Analysis and Prediction System SAAPS Peter - - PowerPoint PPT Presentation
Spacecraft Anomaly Analysis and Prediction System SAAPS Peter Wintoft 1) , Henrik Lundstedt 1) , Lars Eliasson 2) , Leif Kalla 2) , and Alain Hilgers 3) 1) Swedish Institute of Space Physics Lund 2) Swedish Institute of Space Physics
Peter Wintoft1), Henrik Lundstedt1), Lars Eliasson2), Leif Kalla2), and Alain Hilgers3)
1)Swedish Institute of Space Physics – Lund 2)Swedish Institute of Space Physics – Kiruna 3)ESA/ESTEC
Spacecraft Anomaly Analysis and Prediction System
– Development of AI Methods in Spacecraft Anomaly Predictions
Develop tools for the analysis and prediction of spacecraft anomalies.
as neural networks, for predictions.
spacecraft anomalies.
Database SAPM SAAM DBT
SAAPS
User User User External databas e
HTTP / Ja va FTP / J ava
IRF-Lun
ACE GOES
SEC
Kp
SAAPS
Dst, pred Kp, pred AE, pred
NSSD C
OMNI
S/C op.
keV el.
LANL
Anomaly
ESA
Anomaly
– Superposed epoch analysis – Correlations (linear and entropy based) – Cluster analysis – Pattern definition and search
A(t+1d) Kp(t-8*24h) Kp(t) ΣKp(t-8d) ΣKp(t)
Mutual information between average ΣKp and ESD anomaly data
Mutual information between ΣKp and ESD anomaly data
– communicate over port 2001 => Firewall problems. – use of RMI for data access => RMI might be a problem on specific OS.
– Merged MAG and SWEPAM data – 64 second resolution