Abstract:
Today’s aircraft are very complex in design and need constant monitoring of the
systems to establish the overall health status. Integrated Vehicle Health
Management (IVHM) is a major component in a new future asset management
paradigm where a conscious effort is made to shift asset maintenance from a
scheduled based approach to a more proactive and predictive approach. Its goal is
to maximize asset operational availability while minimising downtime and the
logistics footprint through monitoring deterioration of component conditions.
IVHM involves data processing which comprehensively consists of capturing data
related to assets, monitoring parameters, assessing current or future health
conditions through prognostics and diagnostics engine and providing
recommended maintenance actions.
The data driven prognostics methods usually use a large amount of data to learn
the degradation pattern (nominal model) and predict the future health. Usually
the data which is run-to-failure used are accelerated data produced in lab
environments, which is hardly the case in real life. Therefore, the nominal model
is far from the present condition of the vehicle, hence the predictions will not be
very accurate. The prediction model will try to follow the nominal models which
mean more errors in the prediction, this is a major drawback of the data driven
techniques.
This research primarily presents the two novel techniques of adaptive data driven
prognostics to capture the vehicle operational scalability degradation. Secondary
the degradation information has been used as a Health index and in the Vehicle
Level Reasoning System (VLRS). Novel VLRS are also presented in this research
study. The research described here proposes a condition adaptive prognostics
reasoning along with VLRS.
