Fault Diagnosis of Rolling Bearing Based on Improved VMD and KNN

Variational modal decomposition (VMD) has the end effect, which makes it difficult to efficiently obtain fault eigenvalues from rolling bearing fault signals. Inspired by the mirror extension, an improved VMD is proposed. This method combines VMD and mirror extension. The mirror extension is a basic algorithm to inhibit the end effect. A comparison is made with empirical mode decomposition (EMD) for fault diagnosis. Experiments show that the improved VMD outperforms EMD in extracting the fault eigenvalues. The performance of the new algorithm is proven to be effective in real-life mechanical fault diagnosis. Furthermore, in this article, combining with singular value decomposition (SVD), fault eigenvalues are extracted. In this way, fault classification is realized by K-nearest neighbor (KNN). Compared with EMD, the proposed approach has advantages in the recognition rate, which can accurately identify fault types.

END EFFECTS MITIGATION FOR EMPIRICAL MODE DECOMPOSITION WITH NONLINEAR GRAY MODEL

To mitigate end effects of empirical mode decomposition (EMD), a novel approach inspired by the nonlinear gray model (GM) termed as GM(1,1,α) is presented. Other than traditional linear or mirror extension on the boundary, the GM(1,1,α) model is applied to predict two extrema at both ends of the data. It is worth noting that our GM(1,1,α) model is particularly useful for predicting uncertainty data. According to numerical experiments on synthetic signal as well as real data series, the proposed method gives very comparable results with other three generally acknowledged methods, including the linear extension (LE), window function (WF), and mirror symmetry (MS) based methods. That is, the proposed method can reduce end effects and improve decomposition results of EMD significantly.

BOUNDARY EXTENSION AND STOP CRITERIA FOR EMPIRICAL MODE DECOMPOSITION

In this paper, a new idea about the boundary extension has been introduced and applied to the Empirical Mode Decomposition (EMD) algorithm. Instead of the traditional mirror extension on the boundary, we propose a ratio extension on the boundary. We also adopt the stop criteria by Rilling et al. for B-Spline based EMD algorithm. Numerical experiments are used for empirically assessing performance of the modified EMD algorithm. The examples indicate that the ratio boundary extension indeed improves the result of the original EMD.