Autonomous Spacecraft Subsystem Fault Detection, Isolation, Diagnosis, and Recovery
Stottler Henke has developed a sophisticated spacecraft subsystem Fault Detection, Isolation, and Diagnosis capability that, when combined with our Aurora Space Application Planning and Scheduling framework, provides high-level, closed loop capability for fully automatically detecting faults and anomalies; diagnosing the underlying causes; and planning, scheduling, and executing recovery and reconfiguration activities to maximally recoup system capabilities and optimally fulfill mission objectives to the degree possible with the possibly degraded system. Our MAESTRO (Management through intelligent, AdaptivE, autonomouS, faulT identification and diagnosis, Reconfiguration/replanning/rescheduling Optimization) architecture is designed for straight-forward reapplication to different spacecraft subsystem management problems. It has been applied to the xEMU Portable Life Support System (PLSS), Gateway PPE Electrical Power System (EPS), MSU Cubesat EPSs, Mars Transit Vehicle, and International Space Station (ISS) experiment.
During normal operations, MAESTRO monitors onboard sensor values in order to: automatically characterize subsystem components and to be prepared to detect failures; based on that characterization, automatically predicts resource availability over time; and automatically schedules the actions (i.e., determine what activities will occur and when (along with the modes of the associated equipment)). During a failure scenario, MAESTRO first detects the problem; immediately safes the spacecraft to minimize damage; diagnoses the problem and determines the root cause; determines potential feasible courses of action (COAs) given the failed components or set of possible failed components; determines the impact and ramifications of each COA; selects the most appropriate COA; generates the detailed schedule/sequence of actions to implement the COA; and finally adaptively executes the required actions.
Select components of MAESTRO have been ported to Radiation-Tolerant, FPGA-based processors and adapted to managing the EPS and redundant radiation tolerant processors on an ISS experiment to be launched later this month (February, 2022)
MAESTRO has already diagnosed real known and novel faults in various subsystem hardware and been integrated with NASA’s core Flight System (cFS) and NASA JSC’s IRIS architecture. MAESTRO’s symbolic Model-Based Reasoning (MBR) techniques are being combined with our ADTM SOM ML technology to create a hybrid system that combines the advantages of each approach while mitigating each’s weaknesses.