Although the Space Shuttle is a high reliability system, the health of the Space Shuttle must be accurately diagnosed in real-time. Two problems current plague the system, false alarms that may be costly, and missed alarms which may be not only expensive, but also dangerous to the crew. This paper describes the results of a feasibility study where a multivariate state estimation technique is coupled with a Bayesian Belief Network to provide both fault detection and fault diagnostic capabilities for the Space Shuttle Main Engines (SSME). Five component failure modes and several single sensor failures are simulated in our study and correctly diagnosed. The results indicate that this is a feasible fault detection and diagnosis technique and fault detection and diagnosis can be made earlier than standard redline methods allow.
Overview on hybrid approaches to fault detection and diagnosis: Combining data-driven, physics-based and knowledge-based models