Physics Informed Machine Learning for Space Power System Diagnostics and Control

This NASA Postdoctoral Program fellowship offers a unique research opportunity to engage in ongoing NASA research at a NASA Center. The research focuses on deriving physics informed machine learning techniques to support fault diagnostics and control of space based power systems. Exploration to deep space will require unprecedented levels of reliability and resilience to ensure mission success. Studies have shown that a high percentage of faults that occur onboard spacecraft were not accounted for in the original fault management design. These unanticipated faults and disturbances present great challenges in the detection, isolation, and control of dynamic systems such as electrical power. Recent advances in machine learning present new opportunities to enhance the level of fault management and control in NASA's future power system applications. This one- to three-year fellowship is designed to advance NASA's missions in space science, Earth science, aeronautics, space operations, exploration systems, and astrobiology.