Hierarchical fault diagnosis and health monitoring in multi-platform space systems

Current spacecraft health monitoring and fault diagnosis practices that involve around-the-clock limit-checking and trend analysis on large amount of telemetry data, do not scale well for future multi-platform space missions due to the presence of larger amount of telemetry data and an increasing need to make the long-duration missions cost-effective by limiting the size of the operations team. The need for efficient utilization of telemetry data by employing machine learning and rule-based reasoning has been pointed out in the literature in order to enhance diagnostic performance and assist the less-experienced personnel in performing monitoring and diagnosis tasks. In this research we develop a systematic and transparent fault diagnosis methodology within a hierarchical fault diagnosis framework for multiplatform space systems. Our proposed Bayesian network-based hierarchical fault diagnosis methodology allows fuzzy rule-based reasoning at different components in the hierarchy. Due to the unavailability of real formation flight data, we demonstrate the effectiveness of our proposed methodology by using synthetic data of a leader-follower formation flight. Our proposed methodology is likely to enhance the level of autonomy in ground support based spacecraft health monitoring and fault diagnosis.