Importance

Loading Importance Indicators...

Abstract

The invention relates to a method of analyzing flight data recorded during N flights of at least one aircraft, by means of a flight data recorder of an aircraft, the data being grouped together by flight i in a signature vector of the flight X_i of size d, the components of which correspond to data recorded during said flight i of the aircraft, a flight i being thus defined by the signature vector X_i, the method comprising the following steps: Gaussian kernel entropy component analysis of the flight signatures X_i to obtain a zone of normal flights and classifying the flight signatures X_i with respect to their distance to said zone; determining, for each flight i, an abnormality score z_i defined by the distance of a flight signature X_i with respect to the zone of normal flights; detecting, as a function of the abnormality score z_i, at least one abnormal flight.

Loading the Abstract Image...

First Claim