Abstract: This invention relates to a method for monitoring a rotary machine (MAC) based on a vibration signal (SIG), the rotary machine (MAC) comprising a plurality of subsystems (SA-SB) of mechanical parts in rotation (LA1-LA2, LB1-LB2) and the vibration signal (SIG) comprising vibrational contributions of the subsystems (SA-SB), the method comprising, for at least one said subsystem (SA), steps consisting in: estimating (S210) the vibrational contribution of said subsystem (SA) from a set of synchronous averages of the vibration signal (SIG) associated with rotation frequencies (FA1-FA2) of the parts of said subsystem (SA) and with multiples of these rotation frequencies (FA1-FA2); determining (S310) whether or not said subsystem (SA) is faulty by comparative analysis of a so-called health indicator corresponding to the estimated vibrational contribution (SIGA) of said subsystem (SA).

Abstract: A method for automatically monitoring a plurality of rotating parts of rotating machines on the basis of a target database including a plurality of time signals from a distribution generated from each rotating part and on the basis of a source database including a plurality of time signals from a distribution S different from the distribution T generated from a source rotating part of a source rotating machine and being associated with an operating class, the monitoring being carried out by an adaptive deep learning model making it possible to adapt the source distribution to the target distribution, the deep learning module being trained by minimization of a cost function relating to Gaussian kernel functions having a parameter ?; ? being calculated in each period on the basis of the difference in distributions weighted by a constant static value estimated on the basis of a Pascal's triangle.