《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 bearing by fusing IHBSE with SMA-SVM model

Published:2023-09-20 author:ZHANG Jie, WANG Hua, SUN Shun-hong. Browse: 423 Check PDF documents

Fault diagnosis of bearing by fusing IHBSE with SMA-SVM model

ZHANG Jie1, WANG Hua2, SUN Shun-hong3

(1.College of Intelligent Technology, Chongqing Three Gorges University, Chongqing 404000, China;

2.College of Artificial

Intelligence, Chongqing Creation Vocational College, Chongqing 402160, China;

3.Department of Electronic Information

Engineering, Zhangzhou City University, Zhangzhou 363000, China)

Abstract: Aiming at the problem of feature extraction and fault state recognition of coal mine machinery bearings, a fault diagnosis model by fusing the improved hierarchical base scale entropy (IHBSE) for feature extraction with the slime mold algorithm (SMA)-support vector machine (SVM) classification model was proposed. Firstly, the IHBSE method, which could simultaneously analyze the low frequency and high frequency information of the signals, was introduced to capture the multi-dimensional fault features in the coal mine machinery bearing vibration signals under different states to build feature vectors. Then, the slime mold algorithm with excellent global optimization performance was used to search the optimal value of the penalty coefficient and kernel function of the support vector machine, and the slime mold algorithm-support vector machine (SMA-SVM) model was proposed. Finally, the diagnosis model was trained with some feature samples, and the bearing fault type and fault severity were judged by the trained SMA-SVM classifier with the best parameters. The research results show that the proposed scheme can effectively identify the running state of coal mine machinery bearings, and the classification accuracy rate reaches 1, while the average accuracy rate under multiple experiments is also higher than 0.98, which has certain reference value for practical engineering applications.

Key words: coal mine machinery bearing; fault diagnosis; improved hierarchical base scale entropy(IHBSE); slime mold algorithm(SMA); support vector machine(SVM); fault state recognition

Advanced Search

Online Office System

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