Yan Su 1, Xuerui Liang 1, Chenxuan Gu 1, Varun Khemani 2, and Michael Pecht 2
1 Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
2 CALCE, Center for Advanced Life Cycle Engineering, Department of Mechanical Engineering, University of Maryland, College Park, Maryland 20740, USA
Abstract:
Diagnostic strategy optimization is a critical part of
testability design. The complex functional structure of aircraft
systems leads to a large number of failure modes and
corresponding tests. Many tests of aircraft systems have
multivalued attributes that correspond to different states of the
system. These attributes lead to the computational complexity of
existing test and diagnostic methods. Considering the multivalued
test diagnosis problems of aircraft systems, this paper develops a
multivalued test and diagnostic strategy optimization generation
method based on rollout and information entropy. A rollout
algorithm was combined with an information entropy algorithm
to iteratively update information entropy and achieve balance
between computational complexity and accuracy. The method is
applied to the diagnostic strategy optimization generation of an
engine air-bleed system for a certain type of aircraft.