Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor
Tool fault diagnosis in numerical control (NC) machines plays a significant role in ensuring manufacturing quality. However, current methods of tool fault diagnosis lack accuracy. Therefore, in the present paper, a fault diagnosis method was proposed based on stationary subspace analysis (SSA) and l...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/7/4/346 |
| _version_ | 1818989199786770432 |
|---|---|
| author | Chen Gao Wei Xue Yan Ren Yuqing Zhou |
| author_facet | Chen Gao Wei Xue Yan Ren Yuqing Zhou |
| author_sort | Chen Gao |
| collection | DOAJ |
| description | Tool fault diagnosis in numerical control (NC) machines plays a significant role in ensuring manufacturing quality. However, current methods of tool fault diagnosis lack accuracy. Therefore, in the present paper, a fault diagnosis method was proposed based on stationary subspace analysis (SSA) and least squares support vector machine (LS-SVM) using only a single sensor. First, SSA was used to extract stationary and non-stationary sources from multi-dimensional signals without the need for independency and without prior information of the source signals, after the dimensionality of the vibration signal observed by a single sensor was expanded by phase space reconstruction technique. Subsequently, 10 dimensionless parameters in the time-frequency domain for non-stationary sources were calculated to generate samples to train the LS-SVM. Finally, the measured vibration signals from tools of an unknown state and their non-stationary sources were separated by SSA to serve as test samples for the trained SVM. The experimental validation demonstrated that the proposed method has better diagnosis accuracy than three previous methods based on LS-SVM alone, Principal component analysis and LS-SVM or on SSA and Linear discriminant analysis. |
| first_indexed | 2024-12-20T19:34:41Z |
| format | Article |
| id | doaj.art-0bc994599c9a47fa8aaeeaf7fcb850c3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-20T19:34:41Z |
| publishDate | 2017-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-0bc994599c9a47fa8aaeeaf7fcb850c32022-12-21T19:28:41ZengMDPI AGApplied Sciences2076-34172017-03-017434610.3390/app7040346app7040346Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single SensorChen Gao0Wei Xue1Yan Ren2Yuqing Zhou3College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaTool fault diagnosis in numerical control (NC) machines plays a significant role in ensuring manufacturing quality. However, current methods of tool fault diagnosis lack accuracy. Therefore, in the present paper, a fault diagnosis method was proposed based on stationary subspace analysis (SSA) and least squares support vector machine (LS-SVM) using only a single sensor. First, SSA was used to extract stationary and non-stationary sources from multi-dimensional signals without the need for independency and without prior information of the source signals, after the dimensionality of the vibration signal observed by a single sensor was expanded by phase space reconstruction technique. Subsequently, 10 dimensionless parameters in the time-frequency domain for non-stationary sources were calculated to generate samples to train the LS-SVM. Finally, the measured vibration signals from tools of an unknown state and their non-stationary sources were separated by SSA to serve as test samples for the trained SVM. The experimental validation demonstrated that the proposed method has better diagnosis accuracy than three previous methods based on LS-SVM alone, Principal component analysis and LS-SVM or on SSA and Linear discriminant analysis.http://www.mdpi.com/2076-3417/7/4/346stationary subspace analysisleast squares support vector machineNC machinetool fault diagnosis |
| spellingShingle | Chen Gao Wei Xue Yan Ren Yuqing Zhou Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor Applied Sciences stationary subspace analysis least squares support vector machine NC machine tool fault diagnosis |
| title | Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor |
| title_full | Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor |
| title_fullStr | Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor |
| title_full_unstemmed | Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor |
| title_short | Numerical Control Machine Tool Fault Diagnosis Using Hybrid Stationary Subspace Analysis and Least Squares Support Vector Machine with a Single Sensor |
| title_sort | numerical control machine tool fault diagnosis using hybrid stationary subspace analysis and least squares support vector machine with a single sensor |
| topic | stationary subspace analysis least squares support vector machine NC machine tool fault diagnosis |
| url | http://www.mdpi.com/2076-3417/7/4/346 |
| work_keys_str_mv | AT chengao numericalcontrolmachinetoolfaultdiagnosisusinghybridstationarysubspaceanalysisandleastsquaressupportvectormachinewithasinglesensor AT weixue numericalcontrolmachinetoolfaultdiagnosisusinghybridstationarysubspaceanalysisandleastsquaressupportvectormachinewithasinglesensor AT yanren numericalcontrolmachinetoolfaultdiagnosisusinghybridstationarysubspaceanalysisandleastsquaressupportvectormachinewithasinglesensor AT yuqingzhou numericalcontrolmachinetoolfaultdiagnosisusinghybridstationarysubspaceanalysisandleastsquaressupportvectormachinewithasinglesensor |