《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 identification of rolling bearing based on EVMD & SODN

Published:2021-12-22 author:YANG Run-xian, GUO Lin-yang, ZHOU Zheng-ping，et al. Browse: 893 Check PDF documents

YANG Run-xian1,2, GUO Lin-yang1,3, ZHOU Zheng-ping4,

CHANG Zhao-qing4, LI Guo-wei5,XU Qing-le6

(1.Smart Manufacturing Institute, Yangzhou Polytechnic Institute, Yangzhou 225000, China;2.College of Automation

Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;3.State Key Laboratory on

High Power Semiconductor Laser, Changchun University of Science and Technology, Changchun 130000, China;

4.Jiangsu Shuguang Electro-Optics Co., Ltd., Yangzhou 225000, China;5.School of Mechanical and Electrical

Engineering, Henan University of Science and Technology, Luoyang 471003, China;6.Zhengzhou Machinery

Research Institute Co. Ltd., Zhengzhou 450001, China)

Abstract: The traditional methods for rolling bearing fault identification were difficulty in manual feature extraction, manual feature selection and fault identification of rolling bearing vibration signals. Aiming at the problems, a method based on enhanced variational mode decomposition (EVMD) and self-organizing deep network (SODN) was proposed. Firstly, a new power spectrum segmentation method was proposed to determine the number of decomposed modes of VMD automatically and improve the signal-to-noise ratio (SNR) of bearing vibration signals. Then, the vibration signals of rolling bearings were adaptively decomposed into several intrinsic modal functions (IMFs), and the IMFs components which can reflect the fault characteristics of rolling bearing were selected and then be reconstructed by comprehensive index to reach the purpose of signals noise reduction. Finally, the self-organizing strategy was introduced into deep auto-encoder (DAE), then SODN was constructed. And a comparative experiment of automatic feature learning and fault recognition was carried out to verify the feasibility and effectiveness of the method. The results show that the fault identification rate of the proposed EVMD-SODN method reaches 99.15% and the standard deviation is only 0.10. Comparing with other traditional methods and deep learning methods, the EVMD-SODN has great advantages in fault identification accuracy and can alleviate the dependence on artificial feature extraction and tedious feature selection to a certain extent.

Key words: rolling bearing; fault identification; variational mode decomposition(VMD); self-organizing deep network (SODN); deep autoencoder(DAE); intrinsic modal functions (IMFs)

YANG Run-xian, GUO Lin-yang, ZHOU Zheng-ping，et al.Fault identification of rolling bearing based on EVMD & SODN[J].Journal of Mechanical & Electrical Engineering,2021,38(10):1221-1229.

Advanced Search

Online Office System

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