Data-based anomaly detection model for solar array power of in-orbit satellites

Abstract

For unpredictable failures of in-orbit satellites, a data-based anomaly detection method, which is based on normal historical telemetry data, is proposed to detect in-orbit anomaly with the real-time telemetry data. Firstly, a solar array current prediction model is constructed based on the relationship between the satellite solar array and the sun angle meter. Moreover, a false alarm filtering strategy is applied to reduce the false alarm rate. Finally, the model is used in an in-orbit satellite failure case, and the experimental results indicate that the proposed method can timely and accurately identify the solar array output failure with little time delay.