Bearing health assessment based on Hilbert transform envelope analysis and cluster analysis

The rolling bearings are one of the most critical and prevalent elements in rotating machinery. It is necessary to develop a suitable health assessment method to prevent malfunctions and breakages during operation. In this paper, a novel health assessment method for bearings based on Hilbert transform envelope analysis and cluster analysis is proposed. The high-pass filter and Hilbert transform envelope analysis are used to enable the original signal to become smooth and gentle, so as to reduce the influence of noise. And the combination of time domain features parameters is chosen to evaluate the bearing health state. Then extracted feature parameters are clustered by using improved K-means algorithm. In this paper, bearing degradation data and fault data are used to prove the effectiveness of the method.