A Prediction Method of Spacecraft Telemetry Parameter Based on Chaos Theory

Spacecraft state prediction is an important method to solve the related problems of spacecraft health management, fault diagnosis and so on. Chaos theory is widely used in electric power and machinery industries. It can describe the whole system with some parameters. It is proved that spacecraft telemetry parameters are chaotic by calculating the chaotic characteristics. Aiming at the problems of complicated spacecraft system, complicated parameters and difficult to establish accurate mathematical model, a prediction method based on phase space reconstruction is proposed. The adaptive feature extraction of spacecraft telemetry data is realized by phase space reconstruction, and the prediction of telemetry data is realized by RBF neural network and Volterra filter. The experimental results show that the proposed method has better prediction performance.