Bearing multi-faults diagnosis based on stator current bi-spectrum features and support vector machines

Abstract

Condition monitoring and fault diagnosis of rolling element bearings timely and accurately are very important to ensure the reliability of rotating machinery. This paper presents a novel pattern classification approach for bearings diagnostics, which combine the higher order spectra analysis features and support vector machine classifier. The use of non-linear features motivated by the higher order spectra has been reported to be a promising approach to analyze the non-linear and non-Gaussian characteristics of the stator current signals. To deal with the frequency analysis, a mathematical model of the stator current has been derived and used into the bi-spectrum formulas. The stator current bi-spectrum patterns are extracted as the feature vectors presenting different faults of the bearings. The extracted bi-spectrum features are subjected to principal component analysis for dimensionality reduction. These principal components were fed to support vector machine to distinguish six kinds of fault bearing signals which were measured in the experimental test bench running under different working conditions. In order to find the optimal parameters for the multi-class Support vector machine model, a grid-search method in combination with 10-fold cross-validation has been used. The results indicated that the proposed method can reliably identify different fault patterns of rolling element bearings based on the stator current signals.