In this paper an automatic method for condition monitoring of rolling element bearings, based on classification techniques, is proposed. The method, applied to the vibration signals of bearings monitored on two experimental test rigs, seems to overcome the limits of the traditional methods of vibration analysis. In particular, it can automatically diagnose various types of defects, which may occur, one at a time or simultaneously, on one or more bearings. Actually, the guidelines of the proposed method establish a standard methodology for automatic diagnosis that can be applied to all cases in which one can collect an appropriate number of signals related to the basic types of defects to be monitored. Finally, the robustness of the method to noise was also studied by analysing the trend of correct classification of the signals as function of the signal-to-noise ratio.
Rolling Bearing Monitoring Using Classification Techniques
COCOCCIONI, MARCO;FORTE, PAOLA;
2009-01-01
Abstract
In this paper an automatic method for condition monitoring of rolling element bearings, based on classification techniques, is proposed. The method, applied to the vibration signals of bearings monitored on two experimental test rigs, seems to overcome the limits of the traditional methods of vibration analysis. In particular, it can automatically diagnose various types of defects, which may occur, one at a time or simultaneously, on one or more bearings. Actually, the guidelines of the proposed method establish a standard methodology for automatic diagnosis that can be applied to all cases in which one can collect an appropriate number of signals related to the basic types of defects to be monitored. Finally, the robustness of the method to noise was also studied by analysing the trend of correct classification of the signals as function of the signal-to-noise ratio.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.