We are developing methods that can detect and predict failures in liquid-fueled rocket engines, in particular, the Space Shuttle Main Engine (SSME).
Data mining researchers at NASA Ames Research Center's IDU Group are working with rocket propulsion experts at other NASA centers and at Pratt & Whitney Rocketdyne to apply data mining algorithms to historical data from the Space Shuttle Main Engine (SSME) for real time prognostics and diagnostics.
The IDU Group is working to develop algorithms to detect and predict significant unknown anomalies. Existing and novel algorithms that can be applied to historical data will be adapted into real-time algorithms for on-board flight use.
( Fort details, see our Publications Page )
Data Mining for Liquid Propulsion is widely applicable:
Better methods for detecting anomalies in SSME data may benefit the Space Shuttle Program by providing engineers with better tools for analyzing data after a test or flight.
Our long-term goal is to provide algorithms that can be used on board the Crew Launch Vehicle, which is expected to use several different liquid-fuelled rocket engines.