IEEE International Conference on Prognostics and Health Management (ICPHM), June 17-19, 2019, Burlingame, CA

A Multivalued Test and Diagnostic Strategy Optimization Method for Aircraft System Fault Diagnosis

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


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.

This article is available online here and to CALCE Consortium Members for personal review.

[Home Page] [Articles Page]
Copyright © 2019 by CALCE and the University of Maryland, All Rights Reserved