Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis
The accuracy of a support vector machine (SVM) classifier is decided by the selection of optimal parameters for the SVM. The Backtracking Search Optimization Algorithm (BSA) is often applied to resolve the global optimization problem and adapted to optimize SVM parameters. In this research, a SVM pa...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
JVE International
2019-02-01
|
Series: | Journal of Vibroengineering |
Subjects: | |
Online Access: | https://www.jvejournals.com/article/19859 |
id |
doaj-517c87a427214e6a9f61ce4e09c66c9a |
---|---|
record_format |
Article |
spelling |
doaj-517c87a427214e6a9f61ce4e09c66c9a2020-11-24T20:40:19ZengJVE InternationalJournal of Vibroengineering1392-87162538-84602019-02-01211668110.21595/jve.2018.1985919859Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosisVantrong Thai0Junsheng Cheng1Viethung Nguyen2Phuonganh Daothi3State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, ChinaState Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, ChinaState Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha, ChinaFaculty of Information Technology, University Economic and Technical Industries, Hanoi, VietnamThe accuracy of a support vector machine (SVM) classifier is decided by the selection of optimal parameters for the SVM. The Backtracking Search Optimization Algorithm (BSA) is often applied to resolve the global optimization problem and adapted to optimize SVM parameters. In this research, a SVM parameter optimization method based on BSA (BSA-SVM) is proposed, and the BSA-SVM is applied to diagnose gear faults. Firstly, a gear vibration signal can be decomposed into several intrinsic scale components (ISCs) by means of the Local Characteristics-Scale Decomposition (LCD). Secondly, the MPE can extract the fault feature vectors from the first few ISCs. Thirdly, the fault feature vectors are taken as the input vectors of the BSA-SVM classifier. The analysis results of BSA-SVM classifier show that this method has higher accuracy than GA (Genetic Algorithm) or PSO (Particles Swarm Algorithm) algorithms combined with SVM. In short, the BSA-SVM based on the MPE-LCD is suitable to diagnose the state of health gear.https://www.jvejournals.com/article/19859signal processingfault detectiongearsartificial neural networksbacktracking search optimization algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Vantrong Thai Junsheng Cheng Viethung Nguyen Phuonganh Daothi |
spellingShingle |
Vantrong Thai Junsheng Cheng Viethung Nguyen Phuonganh Daothi Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis Journal of Vibroengineering signal processing fault detection gears artificial neural networks backtracking search optimization algorithm |
author_facet |
Vantrong Thai Junsheng Cheng Viethung Nguyen Phuonganh Daothi |
author_sort |
Vantrong Thai |
title |
Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis |
title_short |
Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis |
title_full |
Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis |
title_fullStr |
Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis |
title_full_unstemmed |
Optimizing SVM’s parameters based on backtracking search optimization algorithm for gear fault diagnosis |
title_sort |
optimizing svm’s parameters based on backtracking search optimization algorithm for gear fault diagnosis |
publisher |
JVE International |
series |
Journal of Vibroengineering |
issn |
1392-8716 2538-8460 |
publishDate |
2019-02-01 |
description |
The accuracy of a support vector machine (SVM) classifier is decided by the selection of optimal parameters for the SVM. The Backtracking Search Optimization Algorithm (BSA) is often applied to resolve the global optimization problem and adapted to optimize SVM parameters. In this research, a SVM parameter optimization method based on BSA (BSA-SVM) is proposed, and the BSA-SVM is applied to diagnose gear faults. Firstly, a gear vibration signal can be decomposed into several intrinsic scale components (ISCs) by means of the Local Characteristics-Scale Decomposition (LCD). Secondly, the MPE can extract the fault feature vectors from the first few ISCs. Thirdly, the fault feature vectors are taken as the input vectors of the BSA-SVM classifier. The analysis results of BSA-SVM classifier show that this method has higher accuracy than GA (Genetic Algorithm) or PSO (Particles Swarm Algorithm) algorithms combined with SVM. In short, the BSA-SVM based on the MPE-LCD is suitable to diagnose the state of health gear. |
topic |
signal processing fault detection gears artificial neural networks backtracking search optimization algorithm |
url |
https://www.jvejournals.com/article/19859 |
work_keys_str_mv |
AT vantrongthai optimizingsvmsparametersbasedonbacktrackingsearchoptimizationalgorithmforgearfaultdiagnosis AT junshengcheng optimizingsvmsparametersbasedonbacktrackingsearchoptimizationalgorithmforgearfaultdiagnosis AT viethungnguyen optimizingsvmsparametersbasedonbacktrackingsearchoptimizationalgorithmforgearfaultdiagnosis AT phuonganhdaothi optimizingsvmsparametersbasedonbacktrackingsearchoptimizationalgorithmforgearfaultdiagnosis |
_version_ |
1716827432579760128 |