International Standard Serial Number:

ISSN 1001-4551

Sponsor:

Zhejiang University;

Zhejiang Machinery and Electrical Group

Edited by:

Editorial of Journal of Mechanical & Electrical Engineering

Chief Editor:

ZHAO Qun

Vice Chief Editor:

TANG ren-zhong,

LUO Xiang-yang

Tel:

86-571-87041360,87239525

Fax:

86-571-87239571

Add:

No.9 Gaoguannong,Daxue Road,Hangzhou,China

P.C:

310009

E-mail:

meem_contribute@163.com

Rolling bearing fault identification based on improved hierarchical range entropy and WOA-ELM
Published:2023-11-27 author:LI Nana, WAN Zhong. Browse: 214 Check PDF documents
Rolling bearing fault identification based on improved hierarchical 
range entropy and WOA-ELM


LI Nana1, WAN Zhong2

(1.Department of Mechanical Engineering, Xi'an Jiaotong University City College, Xi'an 710018, China; 

2.Xi'an Kunlun Industrial Group Corporation, Xi'an 710043, China)


Abstract: The traditional multi-scale entropy feature extraction method cannot extract the high-frequency fault features of the signal, hence the feature extraction is not complete enough,and the accuracy of fault identification is also low. Therefore, a fault diagnosis strategy of rolling bearing based on improved hierarchical extreme range entropy (IHRE) and whale algorithm (WOA) and optimized extreme learning machine (ELM) was proposed. Firstly, based on the improved hierarchical analysis and range entropy, a time series complexity measurement method called IHRE was proposed, which could simultaneously analyze the low frequency and high frequency components of the rolling bearing vibration signals, and was used to extract the deep fault characteristics of the rolling bearing vibration signals. Then, the WOA was used to optimize the key parameters of the ELM, and the whale algorithm-extreme learning machine (WOA-ELM) classifier with the best network structure was built. Finally, the constructed IHRE fault features were input to WOA-ELM classifier for classification, and fault identification of rolling bearings was completed. Based on rolling bearing experiment data, the effectiveness of the algorithm was analyzed and compared from multiple dimensions,and the superiority of the algorithm was analyzed. The results show that the IHRE method has the highest accuracy of fault identification, reaching 100%, and the average recognition accuracy of multiple experiments has also reached 99.82%, which is superior to the improved hierarchical sample entropy, hierarchical range entropy and multi-scale range entropy methods. WOA-ELM classification model outperforms PSO-ELM and GA-ELM classifiers in terms of classification time and accuracy, proving that the fault diagnosis strategy based on IHRE and WOA-ELM can quickly and effectively identify the fault types of rolling bearings, and has application potential.

Key words: improved hierarchical range entropy(IHRE); whale optimization algorithm optimized extreme learning machine(WOA-ELM); rolling bearing; fault diagnosis

  • Chinese Core Periodicals
  • Chinese Sci-tech Core Periodicals
  • SA, INSPEC Indexed
  • CSA: T Indexed
  • UPD:Indexed

Copyright 2010 Zhejiang Information Institute of Mechinery Industry All Rights Reserved

Technical Support:Hangzhou Bory science and technology

You are 1895221 visit this site