Fault diagnosis based on optimized node entropy using lifting wavelet packet transform and genetic algorithms

Abstract

The current paper presents a novel scheme for bearing fault diagnosis based on lifting wavelet packet transform (LWPT), sample entropy (SampEn), support vector machines (SVMs), and genetic algorithms (GAs). In the proposed scheme, bearing vibration signals were first decomposed into different frequency sub-bands through a four-level LWPT, resulting in a total of 31 node signal components throughout all layers of the LWPT decomposition tree. The SampEns of all 31 components were then calculated as an original feature pool to characterize the complexity of the bearing vibration signals within the corresponding frequency bands. For selecting the most informative features thus reducing the number of features, a GA was applied to simultaneously pick out the salient features and optimize the parameters of SVMs so as to avoid the curse of dimensionality, alleviate computational burden, and improve the subsequent classification. Experiments were conducted on an induction motor with respect to various bearing faults and a range of fault severities. As an example here, three salient features were selected from the original 31 features, with the dimension of features reduced dramatically. The selected three features were then presented into the optimized SVM to identify various bearing conditions. The scheme was compared with the widely used WPT-Energy method and with a neural network classifier with respect to feature extractions and fault classifications, respectively. The results are in favour of the proposed scheme in terms of the feature dimension, number of support vectors, robustness to the data partition, and classification rate.

Remaining Useful Life Model and Assessment of Mechanical Products: A Brief Review and a Note on the State Space Model Method

“…In early 1990s, Vapnik [47] put forward Support vector machines (SVM) and the concept of VC (Vapnik-Chervonenkis) dimension. These can deal with small sample prediction effectively and are widely adopted in life prediction research [48][49][50]. But the application of SVM is basically aimed at univariate time series.…”

Related Entropy Theories Application in Condition Monitoring of Rotating Machineries

“…Singular value decomposition and sample entropy can be used to extract fault characteristics due to their sensitivity to irregular and periodic fault signal [93]. Zhang et al [94] propose a novel scheme for bearing fault diagnosis based on lifting wavelet packet transform and sample entropy. Bearing vibration signals are decomposed into different frequency sub-bands through lifting wavelet packet transform.…”

“…In addition, the sample entropy is proved to have powerful effects on condition monitoring of bear by studying the field data of the wind turbine transmission system, as given in [98]. Zhang et al [94] lifting wavelet package transform + sample entropy 3 Seera et al [95] power spectrum + sample entropy 4 Han et al [96] local mean decomposition + sample entropy +energy ratio 5 Yang et al [97] mutual information + sample entropy 6 Ni et al [98] sample entropy…”

Elucidation of ball bearing performance utilizing product functions of vibration signals and locality sensitive discriminant analysis

“…In some recent similar works, energy and entropy value-based features have built up exceptional suitability in condition monitoring of bearings. 40,41 The feature space utilized in this work is an extracted sub-set using LSDA from original features space of energy and entropy. To the best of authors' knowledge, LSDA has been implemented first time in bearing PDA.…”