A Reliable Deep Learning Approach for Time-Varying Faults Identification: Spacecraft Reaction Wheel Case Study

Abstract

Reaction wheels are key components for the spacecraft attitude control subsystems. Faults in reaction wheels may lead to high energy consumption, lack of spacecraft attitude control, and in case of failure, loss of the spacecraft. The accurate identification of reaction wheels anomalies is a challenging task due to the internal nonlinearities of the reaction wheels. This study proposes a fast and accurate end-to-end architecture for detecting and identifying the anomalies occurring in spacecraft reaction wheels using One-Dimensional Convolutional Neural Network (1D-CNN) with Long Short-Term Memory (LSTM) network architecture. 1D-CNN is used to capture the useful features from the raw residual signals. The Long Short-Term Memory layer is used due to its effectiveness in handling the time series data and its capabilities for learning long-term dependencies. The proposed architecture is directly trained using the raw torque residual signals captured from a 3-axis attitude control subsystem simulation model. In this way, this scheme eliminates the need for a specific feature extraction method. Results showed that the proposed algorithm represents a reliable and robust anomaly detection and identification mechanism with compact system architecture. Furthermore, the obtained results revealed the superiority and generalizability of the proposed model in diagnosing time-varying reaction wheel faults over other recent approaches. Ultimately, the proposed approach is considered to be a generic fault diagnosis architecture for safety-critical systems. The dataset is available for download at: https://dx.doi.org/10.21227/jr1c-bm66.