Machine Learning Approaches for Data-Driven Self-Diagnosis and Fault Detection in Spacecraft Systems

Abstract

Ensuring the reliability and robustness of spacecraft systems remains a key challenge, particularly given the limited feasibility of continuous real-time monitoring during on-orbit operations. In the domain of Fault Detection, Isolation, and Recovery (FDIR), no universal strategy has yet emerged. Traditional approaches often rely on precise, model-based methods executed onboard. This study explores data-driven alternatives for self-diagnosis and fault detection using Machine Learning techniques, focusing on spacecraft Guidance, Navigation, and Control (GNC) subsystems. A high-fidelity functional engineering simulator is employed to generate realistic datasets from typical onboard signals, including sensor and actuator outputs. Fault scenarios are defined based on potential failures in these elements, guiding the data-driven feature extraction and labeling process. Supervised learning algorithms, including Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs), are implemented and benchmarked against a simple threshold-based detection method. Comparative analysis across multiple failure conditions highlights the strengths and limitations of the proposed strategies. Results indicate that Machine Learning techniques are best applied not as replacements for classical methods, but as complementary tools that enhance robustness through higher-level self-diagnostic capabilities. This synergy enables more autonomous and reliable fault management in spacecraft systems.