Distributed Diagnostics and Prognostics

NASA has developed a method that prevents total system failure during emergencies, allowing parts of the system to continue to function, and making overall system recovery faster. A heterogeneous set of system components monitored by a varied suite of sensors and a health monitoring framework has been developed with the power and flexibility to adapt to different diagnostic and prognostic needs. Current state-of-the-art monitoring and health management systems are mostly centralized in nature, where all the processing is reliant on a single processor. This requires information to be sent and processed in one location. With increases in the volume of sensor data as well as the need for associated processing, traditional centralized systems tend to be somewhat ungainly; in particular, when faced with multi-tasking of computationally heavy algorithms. The distributed architecture is more efficient, allows for considerable flexibility in number and location of sensors placed, scales up well, and is more robust to sensor or processor failure.