Remaining Useful Life Prediction of Control Moment Gyro in Orbiting Spacecraft Based on Variational Autoencoder

For the telemetry data generated by the key components of spacecraft during the orbital operation contain a lot of degradation information, and these telemetry data have the characteristics of large data volume and high dimensionality which are difficult to process. In this paper, we present CMG-VAE, a variational autoencoder-based method for predicting the remaining useful life of control moment gyro in orbiting spacecraft. The method improves the structure of the variational autoencoder. In the encoding phase, the temporal convolutional network is used to extract time-dependent information from the telemetry data, while a graph representation learning approach is used to obtain structural information about the data. The final output of the encoding part is obtained by weighted fusion using a feature fusion approach. One part of the newly fused features is fed into the decoder for data reconstruction and the other part is fed into the remaining useful life prediction module for prediction. To evaluate the effectiveness of the proposed method, this paper uses a set of control moment gyro data obtained from a space station and NASA’s C-MAPSS simulation dataset for validation. The experimental results show that our proposed method achieves the best results compared to other state-of-the-art benchmarks. In particular, on the control moment gyro dataset, the root mean square error (RMSE) obtained by the method proposed in this paper is reduced by 24% compared to the obtained by the best-performing baseline method.