Bearing fault diagnosis based on intrinsic time-scale decomposition and improved Support vector machine model

In order to achieve the bearing fault diagnosis so as to ensure the steadiness of rotating machinery. This article proposed a model based on intrinsic time-scale decomposition (ITD) and improved support vector machine method (ISVM), so as to deal with the non-stationary and nonlinear characteristics of bearing vibration signals. Firstly, the feature extraction method intrinsic time-scale decomposition (ITD) is used and the energy entropy are extracted so as to process the vibration signal in this paper. Then, the local tangent space alignment (LTSA) method is introduced to extract the characteristic features and reduce the dimension of the selected entropy features. Finally, the features are used to train the ISVM model as to classify bearings defects. Cases of actual were analyzed. The results validate the effectiveness of the proposed algorithm.