NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals

NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals

This paper focuses on the fault diagnosis for NC machine tools and puts forward a fault diagnosis method based on kernel principal component analysis (KPCA) and k-nearest neighbor (kNN). A data-dependent KPCA based on covariance matrix of sample data is designed to overcome the subjectivity in param...

Full description

Bibliographic Details
Main Authors: Zhou Yuqing, Sun Bingtao, Li Fengping, Song Wenlei
Format: Article
Language:English
Published: Hindawi Limited 2015-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2015/139217
id doaj-22c86e70dbff4053897585369dcfdd76
record_format Article
spelling doaj-22c86e70dbff4053897585369dcfdd762020-11-24T23:46:43ZengHindawi LimitedShock and Vibration1070-96221875-92032015-01-01201510.1155/2015/139217139217NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration SignalsZhou Yuqing0Sun Bingtao1Li Fengping2Song Wenlei3College of Mechanical Engineering of Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical Engineering of Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical Engineering of Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical Engineering of Wenzhou University, Wenzhou 325035, ChinaThis paper focuses on the fault diagnosis for NC machine tools and puts forward a fault diagnosis method based on kernel principal component analysis (KPCA) and k-nearest neighbor (kNN). A data-dependent KPCA based on covariance matrix of sample data is designed to overcome the subjectivity in parameter selection of kernel function and is used to transform original high-dimensional data into low-dimensional manifold feature space with the intrinsic dimensionality. The kNN method is modified to adapt the fault diagnosis of tools that can determine thresholds of multifault classes and is applied to detect potential faults. An experimental analysis in NC milling machine tools is developed; the testing result shows that the proposed method is outperforming compared to the other two methods in tool fault diagnosis.http://dx.doi.org/10.1155/2015/139217
collection DOAJ
language English
format Article
sources DOAJ
author Zhou Yuqing
Sun Bingtao
Li Fengping
Song Wenlei
spellingShingle Zhou Yuqing
Sun Bingtao
Li Fengping
Song Wenlei
NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals
Shock and Vibration
author_facet Zhou Yuqing
Sun Bingtao
Li Fengping
Song Wenlei
author_sort Zhou Yuqing
title NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals
title_short NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals
title_full NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals
title_fullStr NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals
title_full_unstemmed NC Machine Tools Fault Diagnosis Based on Kernel PCA and k-Nearest Neighbor Using Vibration Signals
title_sort nc machine tools fault diagnosis based on kernel pca and k-nearest neighbor using vibration signals
publisher Hindawi Limited
series Shock and Vibration
issn 1070-9622
1875-9203
publishDate 2015-01-01
description This paper focuses on the fault diagnosis for NC machine tools and puts forward a fault diagnosis method based on kernel principal component analysis (KPCA) and k-nearest neighbor (kNN). A data-dependent KPCA based on covariance matrix of sample data is designed to overcome the subjectivity in parameter selection of kernel function and is used to transform original high-dimensional data into low-dimensional manifold feature space with the intrinsic dimensionality. The kNN method is modified to adapt the fault diagnosis of tools that can determine thresholds of multifault classes and is applied to detect potential faults. An experimental analysis in NC milling machine tools is developed; the testing result shows that the proposed method is outperforming compared to the other two methods in tool fault diagnosis.
url http://dx.doi.org/10.1155/2015/139217
work_keys_str_mv AT zhouyuqing ncmachinetoolsfaultdiagnosisbasedonkernelpcaandknearestneighborusingvibrationsignals
AT sunbingtao ncmachinetoolsfaultdiagnosisbasedonkernelpcaandknearestneighborusingvibrationsignals
AT lifengping ncmachinetoolsfaultdiagnosisbasedonkernelpcaandknearestneighborusingvibrationsignals
AT songwenlei ncmachinetoolsfaultdiagnosisbasedonkernelpcaandknearestneighborusingvibrationsignals
_version_ 1725492646887030784

Similar Items