A comparative study of adaptive filters in detecting a naturally degraded bearing within a gearbox

(in lingua inglese)

The techniques used in this paper are typically used for applications where strong background noise masks the defect signature of interest within the measured vibration signature. Of all the techniques presented, the LMS algorithm succeeded
in detecting the bearing outer race fault earliest at 24% of bearing life. FBLMS technique detected the bearing outer race fault
at 27% of bearing life. In addition, the LMS algorithm was the only technique that successfully identified both the outer race
and ball spin faults. The SANC algorithm detected the fault at 30% of bearing life, though SANC showed its capability in
reducing the background noise and facilitating the identification of the different components in the signal spectrum.