Application of blind source separation in rotating machine diagnosis
Mingfu Liao · Machinery Design and Manufacture · 2006
In implementing the fault diagnosing of rotating machine, the measured vibration signals, include both noise and the signals from other machines. Therefore it is an essential step to separate the individual signals of each machine and reduce noise from the signal mixture . In this paper, the source separati on is performed by means of fourth order cumulants methods, with which the vibra tion signals will be separated. The computer simulation and experimental verific ation show that the algorithm can well restore source signals from their mixture ..This method can be seen as a pre-processing step that improves the diagnosis.