Intelligent Integrated System Health Management
- Sunday, 01 November 2009
Stennis Space Center is NASA’s primary center for rocket engine testing. The facilities include large test stands built for the Apollo Program that are being used to test Space Shuttle Main Engines, smaller test stands for smaller rockets and components, and a new test stand, the A3 Test Stand with capability to simulate high-altitude conditions. All test stands are complex systems that provide oxidizer, fuel, and purge fluids, often at extreme pressures and high velocities. The test stand systems must also manage cryogenic temperatures from liquid oxygen, liquid hydrogen, and liquid nitrogen, as well as high temperatures from rocket plumes. Further more, test stands include hundreds of sensors, and accurate and reliable measurement systems to obtain data that can be used in the design, validation, and certification of engines and components.
Rocket engine testing is a complex and potentially hazardous operation, not unlike a spacecraft launch. Protocols and processes are followed in order to ensure readiness to test. In order to improve efficiencies and safety in test stand operations, it is crucial to develop systems that can help provide comprehensive and continuous vigilance of each element on the test stand. An ISHM system will provide this capability.
Integrated System Health Management (ISHM) capability is fundamentally linked to the management of data, information, and knowledge (DIaK) to determine the health of a system. It is similar to having a team of experts who are all individually and collectively observing and analyzing a complex system, and communicating effectively with each other in order to arrive to an accurate and reliable assessment of its health. ISHM is a capability that is achieved by integrating DIaK that might be distributed throughout the system elements. DIaK must be available to any element of a system at the right time and in accordance with a meaningful context. ISHM Functional Capability Level (FCL) is measured by how well a system performs the following functions: (1) detect anomalies, (2) diagnose causes, (3) predict future anomalies/ failures, and (4) provide users with an integrated awareness about the condition of every element in the system and guide user decisions.
The primary technologies that enable achievement of ISHM capability include:
- Algorithms/approaches/methodologies for anomaly detection.
- Approaches and methodologies for root-cause analysis to diagnose causes of anomalies.
- Approaches and methodologies for prediction of future anomalies.
- Architectures/taxonomies/ontologies that enable management of DIaK – where management implies distributed storage, sharing, processing, maintenance, configuration, and evolution.
- Software environments that integrate contributing technologies in a modular plug-and-play fashion, adhering to a defined architecture/ taxonomy/ontology.
- Standards that allow plug and play and interoperability among elements of an ISHM system.
- User interfaces to provide the user with integrated system awareness.
Developing solutions to the primary technologies must also consider intelligence and integration. In telligence implies that a credible ISHM capability that allows systematic augmentation of that capability must be a knowledgebased system. implies that inferences and decisions about the health of any element must incorporate and reason using other elements and physical phenomena through out the system.