Abstract

A novel method of fault diagnosis for rolling bearing, which combines the dual tree complex wavelet packet transform (DTCWPT), the improved multiscale permutation entropy (IMPE), and the linear local tangent space alignment (LLTSA) with the extreme learning machine (ELM), is put forward in this paper. In this method, in order to effectively discover the underlying feature information, DTCWPT, which has the attractive properties as nearly shift invariance and reduced aliasing, is firstly utilized to decompose the original signal into a set of subband signals. Then, IMPE, which is designed to reduce the variability of entropy measures, is applied to characterize the properties of each obtained subband signal at different scales. Furthermore, the feature vectors are constructed by combining IMPE of each subband signal. After the feature vectors construction, LLTSA is employed to compress the high dimensional vectors of the training and the testing samples into the low dimensional vectors with better distinguishability. Finally, the ELM classifier is used to automatically accomplish the condition identification with the low dimensional feature vectors. The experimental data analysis results validate the effectiveness of the presented diagnosis method and demonstrate that this method can be applied to distinguish the different fault types and fault degrees of rolling bearings.

Highlights

  • Rolling bearings are one of the most widely used parts in rotating machineries because they affect the operation reliability, the performance precision, and the service life of the entire equipment

  • Considering the disadvantage of the single scale analysis, the multiscale entropy (MSE) was developed by Costa et al [8] to estimate the complexity of time series over a range of scales, and this technology was used by Zhang et al [9] to extract the features of bearing signal

  • In order to reduce the interference among the components in the original sample and discover the hidden feature information more effectively, each sample is decomposed to 2 levels using dual tree complex wavelet packet transform (DTCWPT)

Read more

Summary

Introduction

Rolling bearings are one of the most widely used parts in rotating machineries because they affect the operation reliability, the performance precision, and the service life of the entire equipment. The multiscale permutation entropy (MPE) method based on PE was further proposed by Aziz and Arif [11] to depict the multiple temporal scale structures of the signal This method was, respectively, applied by Li and Zheng to bearing fault diagnosis [12, 13]. In view of the advantage of IMPE in digging the inherent features of signal, this method is introduced to the field of fault diagnosis and utilized to identify the condition of rolling bearing in this paper. The collected bearing signals are more or less contaminated by external environmental noises, and the interference between the components in the complicated signal is inevitable These factors lead to the difficulty of feature information extraction using IMPE method directly.

Feature Extraction Based on DTCWPT and IMPE
LLTSA for Dimension Reduction
ELM Classifier
The Proposed Fault Diagnosis Method
Analysis on Experimental Data
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call