SBIR/STTR Award attributes
sci_Zone and John Hopkins University are proposing QuickSAT/SHERLOCK-MD, a system for Vehicle Health Management and Fault Detection with Fault Classification Functions. QuickSAT, a flight proven environment, is the framework containing the SHERLOCK-MD architecture providing edge-capable AI, sensing suite integration and vehicle tracking functions that are tied with the vehicle fault management system perceiving rapidly potential faults that might occur. SHERLOCK-MD ties into on-edge sensing suites plus on-board fault monitoring systems and vehicle health data building an internal knowledge base for event/fault classification. This data is fed into a preliminary analysis system designed to extract key features. This takes the form of anomaly detection or binary/multi-class status checks. SHERLOCK-MD relies on a system built on the Security Risk Taxonomy for Commercial Space Missions. By comparing symptoms evident in the data analysis with a historical database of faults and events, the diagnostic produces a set of likely candidates for mission and/or experimentnbsp;failure and propose appropriate action. SHERLOCK-MD has the ability to feed directly into the decision support module of the incident-response architecture.nbsp; Phase I shall focus on development of algorithms/code classifying detected faults using different satellite datasets, nbsp;conduct a comprehensive comparative assessment, provide anbsp;detailed concept for autonomy technology to support Gateway operations including visiting vehicles and experiments, trade study of recommended supporting hardware, and a baseline demonstration of QuickSAT/SHERLOCK-MD.
