Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings

Overstudy or understudy phenomena can sometimes occur due to the strong dependence of support vector machine (SVM) algorithms on particular parameters and the lack of systems theory relating to parameter selection. In this paper, a parameter optimization algorithm for the SVM is proposed based on mu...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianbin Xiong, Qinghua Zhang, Qiong Liang, Hongbin Zhu, Haiying Li
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2018/3091618
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850159442657542144
author Jianbin Xiong
Qinghua Zhang
Qiong Liang
Hongbin Zhu
Haiying Li
author_facet Jianbin Xiong
Qinghua Zhang
Qiong Liang
Hongbin Zhu
Haiying Li
author_sort Jianbin Xiong
collection DOAJ
description Overstudy or understudy phenomena can sometimes occur due to the strong dependence of support vector machine (SVM) algorithms on particular parameters and the lack of systems theory relating to parameter selection. In this paper, a parameter optimization algorithm for the SVM is proposed based on multi-genetic algorithm. The algorithm optimizes the correlation kernel parameters of the SVM using evolutionary search principles of multiple swarm genetic algorithms to obtain a superior SVM prediction model. The experimental results demonstrate that by combining the genetic algorithm and SVM algorithm, fault diagnosis can be effectively realized for bearings of rotating machinery.
format Article
id doaj-art-b93293df2f044a2b9632a376d4c0a94f
institution OA Journals
issn 1070-9622
1875-9203
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-b93293df2f044a2b9632a376d4c0a94f2025-08-20T02:23:32ZengWileyShock and Vibration1070-96221875-92032018-01-01201810.1155/2018/30916183091618Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of BearingsJianbin Xiong0Qinghua Zhang1Qiong Liang2Hongbin Zhu3Haiying Li4School of Automation, Guangdong Polytechnic Normal University, Guangzhou 510665, ChinaGuangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis, Maoming 525000, ChinaSchool of Computer, Guangdong Polytechnic Normal University, Guangzhou 510665, ChinaGuangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis, Maoming 525000, ChinaSchool of Computer, Jiaying University, Meizhou 514015, ChinaOverstudy or understudy phenomena can sometimes occur due to the strong dependence of support vector machine (SVM) algorithms on particular parameters and the lack of systems theory relating to parameter selection. In this paper, a parameter optimization algorithm for the SVM is proposed based on multi-genetic algorithm. The algorithm optimizes the correlation kernel parameters of the SVM using evolutionary search principles of multiple swarm genetic algorithms to obtain a superior SVM prediction model. The experimental results demonstrate that by combining the genetic algorithm and SVM algorithm, fault diagnosis can be effectively realized for bearings of rotating machinery.http://dx.doi.org/10.1155/2018/3091618
spellingShingle Jianbin Xiong
Qinghua Zhang
Qiong Liang
Hongbin Zhu
Haiying Li
Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings
Shock and Vibration
title Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings
title_full Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings
title_fullStr Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings
title_full_unstemmed Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings
title_short Combining the Multi-Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings
title_sort combining the multi genetic algorithm and support vector machine for fault diagnosis of bearings
url http://dx.doi.org/10.1155/2018/3091618
work_keys_str_mv AT jianbinxiong combiningthemultigeneticalgorithmandsupportvectormachineforfaultdiagnosisofbearings
AT qinghuazhang combiningthemultigeneticalgorithmandsupportvectormachineforfaultdiagnosisofbearings
AT qiongliang combiningthemultigeneticalgorithmandsupportvectormachineforfaultdiagnosisofbearings
AT hongbinzhu combiningthemultigeneticalgorithmandsupportvectormachineforfaultdiagnosisofbearings
AT haiyingli combiningthemultigeneticalgorithmandsupportvectormachineforfaultdiagnosisofbearings