《机电工程》杂志社科技期刊核心期刊论文投稿机电一体化机械、仪表电工自动化、计算机浙江大学主办

Introduction

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

Fault diagnosis of rolling bearings experiencing variable loads based on InMPE and MFO-SVM

Published:2023-10-19 author:YUAN Jian-ming，LIU Yu，HU Zhi-hui，et al. Browse: 377 Check PDF documents

Fault diagnosis of rolling bearings experiencing variable loads based on

InMPE and MFO-SVM

YUAN Jian-ming1, LIU Yu1,2, HU Zhi-hui1, WANG Lei1

(1.School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan 430063,

China; 2.Hainan Institute, Wuhan University of Technology, Sanya 572024, China)

Abstract: Aiming at the problems of difficult extraction of fault features and low accuracy of fault identification for rolling bearing under variable loads, a fault diagnosis method was proposed based on interpolation multiscale permutation entropy (InMPE) and moth-flame optimized support vector machine (MFOSVM). Firstly, the cubic spline interpolation was used to replace the linear interpolation in the traditional multiscale permutation entropy (MPE), and the InMPE algorithm was designed. The effects of different sequence length, embedding dimension and load on InMPE were studied by using the bearing data set of Case Western Reserve University (CWRU). Then, the moth-flame optimization (MFO) was used to optimize the SVM, and the fault diagnosis model based on InMPE and MFO-SVM was constructed. Finally, a bearing fault diagnosis test-bed was built, the fault feature sample set of rolling bearing under variable load condition was made, and the effectiveness and advancement of the proposed fault diagnosis method were verified. The research results show that under variable load conditions, the fault identification accuracy based on InMPE and MFO-SVM is 98.5%, while that based on the traditional MPE method is 95.9%. Under the background of noise, the fault identification accuracy of the proposed method is 92.4%, which is better than the latter's 80.0% accuracy. The results show that the proposed method can effectively identify the fault information of rolling bearings and is robust to noise.

Key words: rolling bearing; fault diagnosis; variable loads condition; multiscale permutation entropy (MPE); interpolation multiscale permutation entropy (InMPE); moth-flame optimization (MFO); support vector machine (SVM)

Advanced Search

Online Office System

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