Multiscale morphological manifold for rolling bearing fault diagnosis

Abstract

The vibration signals of fault rolling bearing are high-dimensional information with complex components. In order to identify different classes of bearing fault, a new multiscale morphological manifold method based on multiscale morphology and manifold learning is proposed. The multiscale morphological manifold method consists of three main steps. Firstly, multiscale difference filter based on multiscale morphological transformation is applied to obtain multiscale observation results of each signal sample. Secondly, the nonlinear feature vectors of each signal sample are constructed according to the observation approach. Finally, manifold learning is introduced to extract the low-dimensional multiscale morphological manifold features through reducing the dimension of nonlinear features. The low-dimensional multiscale morphological manifold features can reveal the differences of signal classes, which are applicable for fault diagnosis. The performance of proposed method is tested by experimental data from bearings with different types of defects. Experimental verifications confirm that the proposed method is applicable and effective for rolling bearing fault diagnosis.