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 3axis 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.

Reaction wheels are crucial actuators in spacecraft attitude control subsystem (ACS). The precise modeling of reaction wheels is of fundamental need in spacecraft ACS for design, analysis, simulation, and fault diagnosis applications. The complex nature of the reaction wheel leads to modeling difficulties utilizing the conventional modeling schemes. Additionally, the absence of reaction wheel providers’ parameters is crucial for triggering a new modeling scheme. The Radial Basis Function Neural Network (RBFNN) has an efficient architecture, alluring generalization properties, invulnerability against noise, and amazing training capabilities. This research proposes a promising modeling scheme for the spacecraft reaction wheel utilizing RBFNN and an improved variant of the Quantum Behaved Particle Swarm Optimization (QPSO). The problem of enhancing the network parameters of the RBFNN at the training phase is formed as a nonlinear constrained optimization problem. Thus, it is proposed to efficiently resolve utilizing an enhanced version of QPSO with mutation strategy (EQPSO-2M). The proposed technique is compared with the conventional QPSO algorithm and different variants of PSO algorithms. Evaluation criteria rely upon convergence speed, mean best fitness value, stability, and the number of successful runs that has been utilized to assess the proposed approach. A non-parametric test is utilized to decide the critical contrast between the results of the proposed algorithm compared with different algorithms. The simulation results demonstrated that the training of the proposed RBFNN-based reaction wheel model with enhanced parameters by EQPSO-2M algorithm furnishes a superior prediction accuracy went with effective network architecture.