Bearing fault identification using watershed-based thresholding method

Abstract

In this work, a novel thresholding method is proposed to improve the accuracy in segmentation process on thermal images. Characteristics of the thermal distribution around convex Regions of Interest (ROI) are the core of this method, used as input markers for a segmentation process based on watershed transform. This method based on data variability reduces the classification error by about 10% and reduces the number of features by about 80% from the set of 360 elements. Moreover, the proposed method provides some tracks for fault localization, demonstrated for a bearing unbalance test rig.