Identification of abnormal event by usage and flight data monitoring

International audienceMany maintenance actions, related to as mechanical, electrical, hydraulic systems, are mandatory to maintain a helicopter in operational conditions. A lot of researches have been performed in order to optimize maintenance actions. Each field of expertise assesses the good health of a part of helicopter by using its own experts, its own methods, and sometimes its own data. Nevertheless, all these domains composed the same machine and no interaction between systems is considered. Our study is not based on physical approaches but it uses operational data and mathematical tools to assess, on ground, the current state of the system. The proposed paper concerns a new concept which consists in characterizing the normal usage of the helicopter by using flight data in order to detect any abnormal event. This abnormal event could be assimilated as a global behavioural drift of the aircraft, a behaviour which is different than usual