An integrated condition monitoring method for rolling element bearings based on perceptual vibration hashing and SOM

Rolling element bearings are widely used in rotating machinery. Bearing faults will result in damage to property. So, the condition monitoring of bearings is of great significance, but few methods can achieve both degradation assessment and fault diagnosis. In this paper, an integrated condition monitoring method for rolling element bearings based on perceptual vibration hashing (PVH) and self-organizing maps (SOM) is proposed. Distance matric based on PVH is used as a health indicator for degradation assessment, in which the baseline of healthy state is selected based on the clustering centre of SOM instead of experience. When the value of health indicator exceeds the pre-set threshold, visualized fault diagnosis can also be achieved by training the SOM network. The effectiveness of the developed method is verified with the vibration data from accelerated degradation tests of rolling element bearings.