Abstract: A method for automatic fault detection with data representing a fault in an on-board system, the method including: determining, with a processor, at least two physical variables represented by said data, said at least two physical variables including at least one time-dependent variable representative of a persistence of an event in time, and at least one instantaneous variable; representing, with the processor, said data by points of a space whose coordinates are values of said at least two physical variables; an detecting, with the processor, a fault by employing a frontier defining a subspace of said space in which representation of a datum is associated with the detection of a fault.

Abstract: The method includes: a step (505) of determining at least two physical variables represented by the said data, the said physical variables including at least: one time-dependent variable representative of the persistence of an event in time and at least one instantaneous variable; a step (530) of representing the said data by points of a space whose coordinates are the values of the said physical variables and a step (535) of employing a frontier defining a subspace of the said space in which the representation of a datum is associated with the detection of a fault. In some embodiments, there is performed a step (540) of estimating the reactivity of detection of the said fault as a function of the said frontier and of the position of the representation of the first datum associated with a fault in the said subspace.