ADAPTIVE LIMIT-CHECKING FOR SPACECRAFT USING RELEVANCE VECTOR AUTOREGRESSIVE MODEL

Development of advanced anomaly detection and failure diagnosis technologies for spacecraft is a quite significant issue in the space industry, because the space environment is harsh, distant and uncertain. While several modern approaches based on qualitative reasoning, expert systems, and probabilistic reasoning have been developed recently for this purpose, any of them has a common difficulty in obtaining accurate and complete a priori knowledge on the space systems from human experts. A reasonable alternative to this conventional anomaly detection method is to reuse a vast amount of telemetry data which is multi-dimensional time-series continuously produced from a number of system components in the spacecraft. This paper proposes a novel ”knowledge-free” anomaly detection method for spacecraft based on data-mining techniques. This method constructs a non-linear probabilistic model regarding the behavior of a spacecraft in the learning phase by applying the relevance vector regression and autoregressive model to a massive telemetry data of a spacecraft, and then monitors the on-line telemetry data using the constructed model and detects anomalies. We have confirmed the effectiveness of the proposed anomaly detection method by applying it to the telemetry data obtained from a simulator of an orbital transfer vehicle designed to make a rendezvous maneuver with the International Space Station and the real-telemetry data of Engineering Test Satellite VII(ETS-VII).

[1]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[2]  Yoshikiyo Kato,et al.  Fault Detection by Mining Association Rules from House-keeping Data , 2001 .

[3]  Christopher M. Bishop,et al.  Variational Relevance Vector Machines , 2000, UAI.

[4]  Eric Horvitz,et al.  Display of Information for Time-Critical Decision Making , 1995, UAI.

[5]  Marie B. Levine,et al.  Automated Event Detection in Space Instruments: A Case Study Using IPEX-2 Data and Support Vector Ma , 2000 .

[6]  Michael E. Tipping,et al.  Fast Marginal Likelihood Maximisation for Sparse Bayesian Models , 2003 .

[7]  Michael E. Tipping The Relevance Vector Machine , 1999, NIPS.

[8]  Michael E. Tipping,et al.  Analysis of Sparse Bayesian Learning , 2001, NIPS.

[9]  John Durkin,et al.  FIDEX: An expert system for satellite diagnostics , 1991 .

[10]  FunctionsDennis DeCosteMonitoring Automated Learning and Monitoring of Limit , 1997 .

[11]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[12]  Michael E. Tipping Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[13]  Frank Hutter,et al.  The Gaussian Particle Filter for Diagnosis of Non-Linear Systems , 2003 .

[14]  S. Roberts,et al.  Bayesian methods for autoregressive models , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[15]  Shinichi Nakasuka,et al.  Summarization of Spacecraft Telemetry Data by Extracting Significant Temporal Patterns , 2004, PAKDD.

[16]  Brian C. Williams,et al.  Diagnosis with Behavioral Modes , 1989, IJCAI.

[17]  Brian C. Williams,et al.  Improving Model-based Mode Estimation through Offline Compilation , 2001 .

[18]  Anton Schick,et al.  Efficient prediction for linear and nonlinear autoregressive models , 2006 .

[19]  Richard J. Doyle,et al.  Focused Real-time Systems Monitoring Based on Multiple Anomaly Models , 2003 .