Feature Extraction and Fault Detection Based on Telemetry Data for Satellite TX-I

In this paper the telemetry data of Satellite TX-I are analyzed in order to have a better understanding of the satellite operating status, and to lay the foundation for fault detection task. Given the high dimensional data, the locally linear embedding (LIE), a kind of manifold learning schemes, is applied to perform dimensionality reduction and feature extraction. Furthermore the data-driven fault detection can be effectively implemented by means of the statistic indexes T2 and SPE. Simulation results presented in the paper demonstrate that not only the data processing, like feature extraction, hut the fault detection scheme is effective.