Adaptive local binarization feature mode decomposition and its application in combined failure identification of rolling bearings

Abstract

The combined failure from rolling bearings is featured by weakness and complexity and hard to be recognized precisely. One-dimensional local binary pattern (1D-LBP) manifests failure information of rolling bearings from textural analysis. However, when signals are quantized with 1D-LBP, the periodic impact feature of fault signal itself will be excluded from consideration and consequently, the fault features will be hard to be dug sufficiently. Feature mode decomposition (FMD) is sensitive to impulse and periodicity of fault signals, but the number of decomposition modes and the length of filter determines accuracy of signal decomposition. To solve these problems, an adaptive local binarization feature mode decomposition (ALBFMD) method was proposed. ALBFMD method represents compound failure information of rolling bearings from textural feature extraction and inherent features of fault signal. Furthermore, with minimum permutation entropy as criterion, the number of decomposition modes and the length of filter of ALBFMD was adaptively determined. According to power spectrums of reconstructed signals, the type of combined faults could be precisely identified. The proposed method was compared with FMD and VMD method and analyzed in different situations. Its superiority in terms of feature extraction and combined failure identification of bearings has been verified.