Research on information fusion for engineering system integrated health management

摘要

Integrated Health Management technology is the emerging paradigm in system supervision and maintenance area, and it is the key to achieving true condition-based maintenance. But this task is complicated by the extremely large amount of the data available, the existence of uncertainties, and interactive engineering system operational conditions. Therefore, it is reasonable to research the health information fusion technology to achieve better performance and a higher level of autonomy for IHM system. This paper analyses the requirements of the information fusion in an IHM system, describes the fusion application areas, proposes the Health Sensing Unit (HSU) concept, and designs the distributed hierarchical fusion architecture. Using the confidence distance matrix as the measure of HSU's performance, this paper proposes a fusion algorithm to fuse multiple HSUs' output, and figure out the system health index according to the maximum likelihood principle. The simulation result yields conclusive evidence that fusion can be very valuable in the IHM technology for the system supervision and maintenance.