《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

Rolling bearing fault diaqnosis method based on MGWO-SCN

Published:2022-12-20 author:FENG Ling, ZHANG Chu, LIU Wei-wei. Browse: 1121 Check PDF documents

Rolling bearing fault diaqnosis method based on MGWO-SCN

FENG Ling1, ZHANG Chu2, LIU Wei-wei3

(1.Intelligent Manufacturing College, Sichuan Chemical Industry Polytechnic, Luzhou 646000, China;

2.School of Artificial Intelligence, Southwest University, Chongqing 400715, China;

3.School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China)

Abstract: In order to improve the robustness and generalization ability of the fault diagnosis model of rolling bearing, a rolling bearing fault diagnosis model based on the modified gray wolf algorithm to optimize stochastic configuration networks(MGWOSCN)was proposed. Firstly, in order to improve the generalization ability of SCN in practical applications, the L2 norm penalty term in the SCN was introduced.Then, the differential evolution mechanism was integrated into the gray wolf algorithm(GWO), and the modified gray wolf algorithm (MGWO) was constructed, which was used to optimize the penalty coefficient C of SCN.Finally, by analyzing the frequency domain characteristic information of the bearing vibration signal data set of Case Western Reserve University(CWRU), a vibration data set based on the frequency domain characteristic parameters was constructed, and BP neural network (BPNN), extreme learning machine (ELM) and support vector machine (SVM) diagnostic model, as well as MGWO and particle swarm optimization algorithm (PSO) were used to compare and simulate the model.The experimental results show that the method can accurately identify 12 kinds of bearing operating states in 30 repeated experiments. Comparing with the BPNN, ELM and SVM bearing diagnosis methods, the average accuracy is respectively increased by 7.27%, 6.47% and 8.67%. In addition, MGWO has stronger global search ability in optimizing the proposed model,comparing with GWOSCN and PSOSCN, the deviation value of the prediction results of the proposed model is smaller, and the accuracy of the test set is higher.

Key words: rotating machinery; rolling bearing fault diagnosis model; modified gray wolf algorithmstochastic configuration networks(MGWOSCN); robustness; generalization ability

Advanced Search

Online Office System

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