FlexDx: A Reconfigurable Diagnosis Framework
Detecting and isolating multiple faults is a computationally expensive
task. It typically consists of computing a set of tests
and then computing the diagnoses based on the test results. This paper
describes FlexDx, a reconfigurable diagnosis framework which reduces
the computational burden while retaining the isolation performance by
only running a subset of all tests that is sufficient to find new
conflicts. Tests in FlexDx are thresholded residuals used to indicate
conflicts in the monitored system. Special attention is given to the
issues introduced by a reconfigurable diagnosis framework. For
example, tests are added and removed dynamically, tests are partially
performed on historic data, and synchronous and asynchronous
processing are combined. To handle these issues FlexDx has been
implemented using DyKnow, a stream-based knowledge processing
middleware framework. Concrete methods for each component in the
FlexDx framework are presented. The complete approach is exemplified
on a dynamic system which clearly illustrates the complexity of the
problem and the computational gain of the proposed
approach.
Mattias Krysander, Fredrik Heintz, Jacob Roll and Erik Frisk
Engineering Applications of Artificial Intelligence,
2010
Informationsansvarig: webmaster
Senast uppdaterad: 2021-11-10
LiU Homepage
