Degradation feature extraction of rolling bearing based on equalization symbol sequence entropy

Abstract

Aiming at the problem of degradation feature extraction of rolling bearings, a degradation feature extraction technique based on the equalization symbol sequence entropy is proposed. Considering the uniformity of the symbolization standard, the technique takes the root mean square of the normal condition signal as the basis to establish a unified basic scale, and combines the information entropy theory to quantitatively measure the complexity of the signal symbol sequence. Instance analysis is carried out with the lifetime data of intelligent maintenance systems bearing. The results show that the proposed feature is able to characterize the complexity of the nonlinear time series, and sensitively describe the whole process of rolling bearing performance degradation. The calculation speed is fast, and it is resistant to noise; thus, this technique is suitable for application to online condition monitoring and degradation feature extraction.

An identification method of compound faults of rolling bearings blending variational mode decomposition and vector bispectrum

“…1 The vibration signal during a bearing fault usually contains considerable noise and numerous frequency components, showcasing characteristics such as non-linearity, non-stationarity, weak periodicity, and a low signal-to-noise ratio. [2][3][4] Signals decompose algorithms, addressing non-linearity and nonstationarity, are a typical class of methods for fault feature extraction including local feature scale decomposition, 5,6 intrinsic time scale decomposition, 7 and local mean decomposition. Huang et al proposed the empirical mode decomposition (EMD) method, which offers stabilization of complex signals and decomposes vibration signals into multiple intrinsic mode functions (IMF).…”