Machine Learning Methods for Spacecraft Telemetry Mining

Abstract

Spacecrafts are critical systems that have to survive space environment effects. Due to its complexity, these types of systems are designed in a way to mitigate errors and maneuver the critical situations. Spacecraft delivers to the ground operator an abundance data related to system status telemetry; the telemetry parameters are monitored to indicate spacecraft performance. Recently, researchers proposed using Machine Learning (ML)/Telemetry Mining (TM) techniques for telemetry parameters forecasting. Telemetry processing facilitates the data visualization to enable operators understanding the behavior of the satellite in order to reduce failure risks. In this paper, we introduce a comparison between the different machine learning techniques that can be applied for low earth orbit satellite telemetry mining. The techniques are evaluated on the bases of calculating the prediction accuracy using mean error and correlation estimation. We used telemetry data received from Egyptsat-1 satellite including parameters such as battery temperature, power bus voltage and load current. The research summarizes the performance of processing telemetry data using autoregressive integrated moving average (ARIMA), Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), Long Short-Term Memory Recurrent Neural Network (LSTM RNN), Deep Long Short-Term Memory Recurrent Neural Networks (DLSTM RNNs), Gated Recurrent Unit Recurrent Neural Network (GRU RNN), and Deep Gated Recurrent Unit Recurrent Neural Networks (DGRU RNNs).