Abstract
This paper presents the development of an integrated set of methodologies for the
detection, identification, and evaluation of a wide variety of failures of aircraft sub-systems.
The detection feature represents the capability to declare that a failure within any of the
aircraft sub-systems has occurred. The identification process has two phases. The first
phase consists of determining which of the large categories of sub-systems is affected
(actuators, sensors, engines, structure, etc.). The outcome of the second phase specifies the
failed element. The evaluation of the failure addresses three aspects. The qualitative
evaluation attempts to specify the type of the failure. The quantitative evaluation has two
components. The direct failure evaluation consists of estimating the magnitude of the failure
while the indirect failure evaluation includes the re-assessment of the flight envelope and
prediction of the limitations and constraints on the performance and handling qualities
inflicted by the presence of the failure. Failure detection, identification, and evaluation
schemes are included using the bio-immune system metaphor combined with other artificial
intelligence techniques such as genetic algorithms, artificial neural networks, and fuzzy logic
based adaptive thresholds. The immunity-based fault detection operates in a similar manner
as does the immune system - according to the principle of self-non-self discrimination - when
it distinguishes between entities that belong to the organism and entities that do not. This
approach addresses directly the complexity and multi-dimensionality of aircraft dynamic
response in the context of abnormal conditions and provides the adequate tools to solve the
failure detection problem in an integrated and comprehensive manner.
Original language | American English |
---|---|
DOIs | |
State | Published - Aug 10 2009 |
Event | AIAA Guidance, Navigation, and Control Conference 2009 - Chicago, IL Duration: Aug 1 2009 → … |
Conference
Conference | AIAA Guidance, Navigation, and Control Conference 2009 |
---|---|
Period | 8/1/09 → … |
Keywords
- Fault diagnosis
- Aerodynamics
- Aircraft
- Failure analysis
Disciplines
- Aeronautical Vehicles
- Systems Engineering and Multidisciplinary Design Optimization
- Computer Sciences
- Artificial Intelligence and Robotics