Defects diagnosis and classification for rolling bearing based on mathematical morphology

The defects diagnosis and pattern classification are presented in this paper. Morphological pattern spectrum describes the shape characteristics of the inspected signal based on the morphological opening operation with multi-scale structuring elements. The pattern spectrum entropy and the barycenter scale location of the spectrum curve are extracted as the feature vector presenting different defects of the rolling bearings. The support vector machinery (SVM) algorithm is adopted to distinguish different kinds of defective bearing signals. The recognition results of the SVM are ideal and more precise than that of the artificial neural network. The combination of the morphological pattern spectrum parameter analysis and the SVM algorithm is suitable for the on-line automated defect diagnosis of the rolling bearing.