Embedded and Distributed Machine Learning for Prognostics Monitoring

Scheduled maintenance is inefficient and costly with no ability to take into account actual hardware degradation. The goal of this project is to develop a generic cost-effective embodiment that is relatively independent of the type of physical equipment being monitored by employing machine learning for prognostics monitoring. Prototype units will be developed with embedded novel machine learning algorithms for cryogenic equipment in the engine test complex as pilot demonstration systems. Energy harvesting technologies will also be integrated to further demonstrate low powered energy harvesting health monitoring capabilities.

Beyond the initially intended use in propulsion test facilities, the machine learning for diagnostics and prognostics has real applicability to support autonomy throughout NASA facilities and for missions employing autonomy in flight computing and robotic and system autonomy to handle failures and readapting when independent from Earth. This capability additionally has potential for missions that need to reduce the necessity for human intervention in maintaining equipment such as with Deep Space Missions.

This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.