《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 diagnosis method based on two-stage fuzzy cognitive map

Published:2023-07-18 author:ZENG Xiang-zu, GAN Qun-feng, GAN Jun-tong. Browse: 1173 Check PDF documents

Rolling bearing fault diagnosis method based on two-stage

fuzzy cognitive map

ZENG Xiang-zu1, GAN Qun-feng2, GAN Jun-tong1

(1.National Zeng Xiangzu Skills Master Studio, Heyuan Technician Institute, Heyuan 517000, China;

2.College of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin 132000, China)

Abstract: Aiming at the problems of traditional fuzzy cognitive maps (FCMs) time series classification algorithm, such as insufficient sensitivity to noise and opaque decision-making process, a two-stage fuzzy cognitive maps (TFCMs) method was proposed to diagnose rolling bearing faults. Firstly, the fuzzy C-mean algorithm was used to convert the time series existing in two-dimensional space into C-dimensional space. Then, the convex optimization algorithm (CVX) was used to quickly and effectively learn the FCMs model from the noise data. Finally, particle swarm optimization (PSO) was used to construct a FCMs classifier to effectively classify the weight matrix, and the proposed method was verified by using western reserve university bearing data set (CWRU) and time series classification reference data. The results indicate that the convex optimization algorithm is superior to the particle swarm optimization algorithm in the ability of extracting features of noise data, and the accuracy of the two public classification reference data is increased by 4%. In the two bearing fault data sets, the average accuracy reaches more than 99.5%. In the comparison experiment, the accuracy of the TFCMs method in dataset A and dataset B is respectively improved by 3.67% and 2.36%. The TFCMs method is superior to the existing methods. More importantly, the modeling process of the TFCMS method is transparent and interpretable.

Key words: bearing fault diagnosis; twostage fuzzy cognitive maps (TFCMs); time series classification; two-stage model; particle swarm optimization (PSO); convex optimization algorithm (CVX)

Advanced Search

Online Office System

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