Bearing remain life prediction based on weighted complex SVM models
Aiming to achieve the bearing remaining life prediction, this research proposed a method based on the weighted complex support vector machine (SVM) model. Firstly, the features are extracted by time domain, time-frequency domain method, so as the extract the original features. However, the extracted...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
JVE International
2016-09-01
|
Series: | Journal of Vibroengineering |
Subjects: | |
Online Access: | https://www.jvejournals.com/article/16910 |
id |
doaj-17d70b845fae48fe893a15a8cf78c4f4 |
---|---|
record_format |
Article |
spelling |
doaj-17d70b845fae48fe893a15a8cf78c4f42020-11-24T21:12:55ZengJVE InternationalJournal of Vibroengineering1392-87162538-84602016-09-011863636365310.21595/jve.2016.1691016910Bearing remain life prediction based on weighted complex SVM modelsShaojiang Dong0Jinlu Sheng1Zhu Liu2Li Zhong3Hanbing Wei4School of Mechatronics and Automotive Engineering, Chongqing Jiaotong University, Chongqing 400074, People’s Republic of ChinaCollege of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, People’s Republic of ChinaQingdao Ocean Shipping Mariners College, Qingdao, 266071, People’s Republic of ChinaSchool of Mechatronics and Automotive Engineering, Chongqing Jiaotong University, Chongqing 400074, People’s Republic of ChinaSchool of Mechatronics and Automotive Engineering, Chongqing Jiaotong University, Chongqing 400074, People’s Republic of ChinaAiming to achieve the bearing remaining life prediction, this research proposed a method based on the weighted complex support vector machine (SVM) model. Firstly, the features are extracted by time domain, time-frequency domain method, so as the extract the original features. However, the extracted original features still with high dimensional and include superfluous information, the multi-features fusion technique principal component analysis (PCA) is used to merge the features and reduce the dimension. And the bearing degradation indicator is constructed based on the first principal component, which can indicate the bearing early failure state precisely. Then, based on the life condition indicator, the weighted complex SVM model is used to achieve the bearing remain life prediction, in this model, the particle swarm algorithm (PSO) method is used to select the SVM internal parameters, the phase space reconstruction algorithm is used to determine the structure of the SVM. Cases of actual were analyzed, the results proved the effectiveness of the methodology.https://www.jvejournals.com/article/16910principal component analysissupport vector machinedegradation indicatorremaining life predictionbearing |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shaojiang Dong Jinlu Sheng Zhu Liu Li Zhong Hanbing Wei |
spellingShingle |
Shaojiang Dong Jinlu Sheng Zhu Liu Li Zhong Hanbing Wei Bearing remain life prediction based on weighted complex SVM models Journal of Vibroengineering principal component analysis support vector machine degradation indicator remaining life prediction bearing |
author_facet |
Shaojiang Dong Jinlu Sheng Zhu Liu Li Zhong Hanbing Wei |
author_sort |
Shaojiang Dong |
title |
Bearing remain life prediction based on weighted complex SVM models |
title_short |
Bearing remain life prediction based on weighted complex SVM models |
title_full |
Bearing remain life prediction based on weighted complex SVM models |
title_fullStr |
Bearing remain life prediction based on weighted complex SVM models |
title_full_unstemmed |
Bearing remain life prediction based on weighted complex SVM models |
title_sort |
bearing remain life prediction based on weighted complex svm models |
publisher |
JVE International |
series |
Journal of Vibroengineering |
issn |
1392-8716 2538-8460 |
publishDate |
2016-09-01 |
description |
Aiming to achieve the bearing remaining life prediction, this research proposed a method based on the weighted complex support vector machine (SVM) model. Firstly, the features are extracted by time domain, time-frequency domain method, so as the extract the original features. However, the extracted original features still with high dimensional and include superfluous information, the multi-features fusion technique principal component analysis (PCA) is used to merge the features and reduce the dimension. And the bearing degradation indicator is constructed based on the first principal component, which can indicate the bearing early failure state precisely. Then, based on the life condition indicator, the weighted complex SVM model is used to achieve the bearing remain life prediction, in this model, the particle swarm algorithm (PSO) method is used to select the SVM internal parameters, the phase space reconstruction algorithm is used to determine the structure of the SVM. Cases of actual were analyzed, the results proved the effectiveness of the methodology. |
topic |
principal component analysis support vector machine degradation indicator remaining life prediction bearing |
url |
https://www.jvejournals.com/article/16910 |
work_keys_str_mv |
AT shaojiangdong bearingremainlifepredictionbasedonweightedcomplexsvmmodels AT jinlusheng bearingremainlifepredictionbasedonweightedcomplexsvmmodels AT zhuliu bearingremainlifepredictionbasedonweightedcomplexsvmmodels AT lizhong bearingremainlifepredictionbasedonweightedcomplexsvmmodels AT hanbingwei bearingremainlifepredictionbasedonweightedcomplexsvmmodels |
_version_ |
1716749513153052672 |