Distributed data and information fusion for nuclear reactor condition monitoring

An increasing number of civil nuclear reactors world
wide are approaching, and have in many cases exceeded, their
original design lives. In order to satisfy regulatory requirements
and ensure that the reactors are safe to operate, whilst maximising
availability and ensuring economic viability, the volume
of installed condition monitoring has increased significantly in
recent years. Due to the age of many stations however, there is
often the lack of a modern, integrated IT infrastructure with
many, often overlapping, data sources of varying measurement
types and sample rates. This paper describes a method for the
distributed condition monitoring of nuclear reactors using intelligent
software agents, which by means of a common ontology can
autonomously collect and analyse data from multiple locations.
The use of data and information fusion to derive more detailed
condition monitoring results is shown to be a task well suited
to agent based condition monitoring and a prototype system
designed along these principles is described. Case studies are
presented of the application of the prototype system to condition
monitoring analysis of real data sets from nuclear reactors in the
UK.