Gearbox Fault Diagnosis Based on Hierarchical Instantaneous Energy Density Dispersion Entropy and Dynamic Time Warping

Abstract

The accurate fault diagnosis of gearboxes is of great significance for ensuring safe and efficient operation of rotating machinery. This paper develops a novel fault diagnosis method based on hierarchical instantaneous energy density dispersion entropy (HIEDDE) and dynamic time warping (DTW). Specifically, the instantaneous energy density (IED) analysis based on singular spectrum decomposition (SSD) and Hilbert transform (HT) is first applied to the vibration signal of gearbox to acquire the IED signal, which is designed to reinforce the fault feature of the signal. Then, the hierarchical dispersion entropy (HDE) algorithm developed in this paper is used to quantify the complexity of the IED signal to obtain the HIEDDE as fault features. Finally, the DTW algorithm is employed to recognize the fault types automatically. The validity of the two parts that make up the HIEDDE algorithm, i.e., the IED analysis for fault features enhancement and the HDE algorithm for quantifying the information of signals, is numerically verified. The proposed method recognizes the fault patterns of the experimental data of gearbox accurately and exhibits advantages over the existing methods such as multi-scale dispersion entropy (MDE) and refined composite MDE (RCMDE).

A new approach to health condition identification of rolling bearing using hierarchical dispersion entropy and improved Laplacian score

“…Thus, to solve this issue, HDE is formulated by the integration of hierarchical analysis and DE. 32 Schematic diagram of hierarchical analysis is shown in Figure 3. Detailed calculation process of HDE is described as follows:…”

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

“…It extracts the outer ring fault at a frequency of 160 Hz, the gearbox fault with a characteristic frequency of 360 Hz and its double frequency of 720 Hz. Cheng et al [135] ensemble empirical mode decomposition + sample entropy 5 Chen et al [136] fuzzy entropy 6 Zhang et al [137] continuous vibration separation + minimum entropy deconvolution 7 Tang et al [138] hierarchical Instantaneous energy density dispersion entropy + dynamic time warping 8 Cai et al [139] combining product function + multipoint optimal minimum entropy deconvolution adjusted…”

“…MED is applied to enhancing fault induced impulses. Tang et al [138] propose a method based on hierarchical instantaneous energy density dispersion entropy (HIEDDE) and dynamic time warping (DTW). HIEDDE is defined as the fault feature, which is calculated by the hierarchical dispersion entropy (HDE) algorithm.…”

“…Authors Methodologies 1 Bokoski and Jurii [132] wavelet packet transform + Rényi entropy 2 Chen et al [133] entropy feature fusion of dual-tree complex wavelet transform + optimized kernel Fisher discriminant analysis 3 Zhang et al [134] minimum entropy deconvolution + improved dual-tree complex wavelet transform 4 Cheng et al [135] ensemble empirical mode decomposition + sample entropy 5 Chen et al [136] fuzzy entropy 6 Zhang et al [137] continuous vibration separation + minimum entropy deconvolution 7 Tang et al [138] hierarchical Instantaneous energy density dispersion entropy + dynamic time warping 8 Cai et al [139] combining product function + multipoint optimal minimum entropy deconvolution adjusted…”

A Comprehensive Fault Diagnosis Method for Rolling Bearings Based on Refined Composite Multiscale Dispersion Entropy and Fast Ensemble Empirical Mode Decomposition

“…The diagnosis results may be not ideal when the bearing fault is of different type and severity. Considering the nonlinear and non-stationary characteristics of vibration signals, entropy-based methods are often combined with the time–frequency analysis technique to extract the fault information from bearings [ 24 ]. The typical time–frequency analysis technique, such as wavelet transform (WT) [ 25 ], variational mode decomposition (VMD) [ 26 ], empirical mode decomposition (EMD) [ 27 ] and local mean decomposition (LMD) [ 28 , 29 ], is firstly to decompose complicated signals into a set of components which represent its intrinsic characteristic.…”