RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION
In order to solve interference of the neighborhood size of the linear local tangent space alignment（ LLTSA） when used in fault feature reduction,in this paper,a fault diagnosis method based on linear local tangent space alignment（ NALLTSA） for dimension reduction is proposed. Firstly,the high-dimens...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Strength
2018-01-01
|
| Series: | Jixie qiangdu |
| Subjects: | |
| Online Access: | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2018.01.005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841535471010709504 |
|---|---|
| author | XU QiongYan WU YinHua |
| author_facet | XU QiongYan WU YinHua |
| author_sort | XU QiongYan |
| collection | DOAJ |
| description | In order to solve interference of the neighborhood size of the linear local tangent space alignment（ LLTSA） when used in fault feature reduction,in this paper,a fault diagnosis method based on linear local tangent space alignment（ NALLTSA） for dimension reduction is proposed. Firstly,the high-dimensional fault feature of mechanical vibration signal are extracted. And then,the neighborhood adaptive linear local tangent space alignment with Parzen window density estimation is used to reduce the high-dimensional set to the low-dimensional compressed sensitive feature subset. Finally,the corresponding relationship between low-dimensional feature and fault classes are established by using support vector machine（ SVM）.Dimension reduction with NA-LLTSA can effectively increase the discrimination of fault feature,and furthermore,SVM can further improve fault diagnosis accuracy with its excellent pattern recognition capacity. Finally,the effectiveness of the proposed method was verified through the fault diagnosis experiment of rolling bearing. |
| format | Article |
| id | doaj-art-a723d6425f2a493aabe6f3a6bacaace4 |
| institution | Kabale University |
| issn | 1001-9669 |
| language | zho |
| publishDate | 2018-01-01 |
| publisher | Editorial Office of Journal of Mechanical Strength |
| record_format | Article |
| series | Jixie qiangdu |
| spelling | doaj-art-a723d6425f2a493aabe6f3a6bacaace42025-01-15T02:32:40ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692018-01-0140273230600542RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTIONXU QiongYanWU YinHuaIn order to solve interference of the neighborhood size of the linear local tangent space alignment（ LLTSA） when used in fault feature reduction,in this paper,a fault diagnosis method based on linear local tangent space alignment（ NALLTSA） for dimension reduction is proposed. Firstly,the high-dimensional fault feature of mechanical vibration signal are extracted. And then,the neighborhood adaptive linear local tangent space alignment with Parzen window density estimation is used to reduce the high-dimensional set to the low-dimensional compressed sensitive feature subset. Finally,the corresponding relationship between low-dimensional feature and fault classes are established by using support vector machine（ SVM）.Dimension reduction with NA-LLTSA can effectively increase the discrimination of fault feature,and furthermore,SVM can further improve fault diagnosis accuracy with its excellent pattern recognition capacity. Finally,the effectiveness of the proposed method was verified through the fault diagnosis experiment of rolling bearing.http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2018.01.005Fault diagnosisDimension reductionNeighborhood Adaptive linear local tangent space alignment（NA-LLTSA）Support vector machine（SVM） |
| spellingShingle | XU QiongYan WU YinHua RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION Jixie qiangdu Fault diagnosis Dimension reduction Neighborhood Adaptive linear local tangent space alignment（NA-LLTSA） Support vector machine（SVM） |
| title | RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION |
| title_full | RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION |
| title_fullStr | RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION |
| title_full_unstemmed | RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION |
| title_short | RESEARCH ON FAULT DIAGNOSIS METHOD BASED ON NEIGHBORHOOD ADAPTIVE LLTSA FOR DIMENSION REDUTION |
| title_sort | research on fault diagnosis method based on neighborhood adaptive lltsa for dimension redution |
| topic | Fault diagnosis Dimension reduction Neighborhood Adaptive linear local tangent space alignment（NA-LLTSA） Support vector machine（SVM） |
| url | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2018.01.005 |
| work_keys_str_mv | AT xuqiongyan researchonfaultdiagnosismethodbasedonneighborhoodadaptivelltsafordimensionredution AT wuyinhua researchonfaultdiagnosismethodbasedonneighborhoodadaptivelltsafordimensionredution |