Hierarchical Intelligent Data Fusion Architecture for System Health Management

The complexity of modern systems and the stringent performance requirements for operation and uptime suggest that optimum and robust means must be deployed to make effective use of multiple sensor suites for assessing risk, identifying system degradation, understanding how system degradation progresses to failure, etc. Global Technology Connection and Georgia Tech proposes the development of data fusion architecture based on a hybrid analytical / intelligent methodology that exploits the concept of "focus of attention" via active perception in order to optimize degradation/fault classification accuracy while reducing substantially the computational burden. The fusion scheme incorporates several levels of abstraction: fusion at the data level, the feature level and the sensor level. The overall architecture employs technologies from soft computing, Dempster-Shafer theory and game theory to provide a robust and reliable platform for critical aerospace systems. Phase I effort will develop a data fusion algorithms for system degradation/fault identification.

Phase II will address design and construction of prototype field hardware for implementing the data fusion concept for components.

Several aerospace end users like Lockheed Martin and Boeing have already expressed interest in the commercial applications (Phase III) of this approach for health monitoring and life determination of Aerospace vehicles/systems.