Diagnostic and decision support systems by identification of abnormal events: Application to helicopters

Today, aircraft manufacturers are trying to improve costs benefits by the implementation of technical solutions like health monitoring, efficient diagnosis or condition based maintenance. These improvements need to develop robust approaches. However the growing complexity of system made maintenance difficult. It is more complex to identify and localize failures and degradation. In consequence, trying to work on causes of failure and degradation should be interesting. This paper focuses on the reason of failures and degradations which lead to maintenance operations. Most of researches proposed are based on physics: physical model of a specific failure, law of ageing, etc. In spite of their performances, these approaches are quite difficult to implement on a complex integrated system. Each field of expertise assesses the good health of a helicopter part by using its own experts, its own methods, and, in some cases, its own data. Nevertheless, these fields all make up the same machine, and no interaction between systems is considered. Our study is not based on physical approaches but uses operational data and mathematical tools to diagnose, off-line, the current state of the system. The proposed paper concerns a new concept consisting in characterizing normal helicopter utilization by used flight data. The life profile of the helicopter is described by employing all the flight data available to determine, on the one hand, all normal events and, on the other, to identify abnormal events according to their position compared to the normal envelope. Flight data are then specifically analyzed to characterize the level of criticism of an event considered to be abnormal. This abnormal event could be assimilated to a global behavioral drift of the aircraft, a behavior which is different than usual.