A fault diagnosis approach for roller bearings based on EMD method and AR model

The main purpose of this paper is to propose a new fault feature extraction approach based on empirical mode decomposition (EMD) method and autoregressive (AR) model for roller bearings. AR model is an effective approach to extract the fault feature of the vibration signals and the fault pattern can...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mechanical systems and signal processing 2006-02, Vol.20 (2), p.350-362
Hauptverfasser: Junsheng, Cheng, Dejie, Yu, Yu, Yang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 362
container_issue 2
container_start_page 350
container_title Mechanical systems and signal processing
container_volume 20
creator Junsheng, Cheng
Dejie, Yu
Yu, Yang
description The main purpose of this paper is to propose a new fault feature extraction approach based on empirical mode decomposition (EMD) method and autoregressive (AR) model for roller bearings. AR model is an effective approach to extract the fault feature of the vibration signals and the fault pattern can be identified directly by the extracted fault features without establishing the mathematical model and studying the fault mechanism of the system. However, AR model can only be applied to stationary signals, while the fault vibration signals of a roller bearing are non-stationary. Aiming at this problem, in this paper, the EMD method is used as a pretreatment to decompose the non-stationary vibration signal of a roller bearing into a number of intrinsic mode function (IMF) components which are stationary, then the AR model of each IMF component can be established. The AR parameters and the remnant's variance of the AR models of each IMF components are regarded as the feature vectors. The Mahalanobis distance criterion function is used to identify the condition and fault pattern of a roller bearing. Experimental analysis results show that the roller bearing fault features can be extracted by the proposed approach effectively.
doi_str_mv 10.1016/j.ymssp.2004.11.002
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_29254752</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0888327004001736</els_id><sourcerecordid>29254752</sourcerecordid><originalsourceid>FETCH-LOGICAL-c364t-5eca5e75849e73cb04642ea91af6439a0b60010ba29cf3aef084b7d9f912793</originalsourceid><addsrcrecordid>eNp9kE1v1DAQhi0EEkvhF3DxBW4JY8eJ4wOHVSkfUlEl4G5NnHHrVRIvnmyl_ntSthI3TnN53ndmHiHeKqgVqO7DoX6YmY-1BjC1UjWAfiZ2ClxXKa2652IHfd9XjbbwUrxiPgCAM9DtxM1eRjxNqxwT3i6ZE0s8HkvGcCdjLrLkaaIiB8KSlluWAzKNMi_y6vsnOdN6l0eJyyj3P-ScR5peixcRJ6Y3T_NC_Px89evya3V98-Xb5f66Ck1n1qqlgC3ZtjeObBMGMJ3RhE5h7EzjEIYOQMGA2oXYIEXozWBHF53S1jUX4v25dbv094l49XPiQNOEC-UTe-10a2yrN7A5g6Fk5kLRH0uasTx4Bf5RnT_4v-r8ozqvlN_Ubal3T_XIAadYcAmJ_0Vt27bK2o37eOZo-_Q-UfEcEi2BxlQorH7M6b97_gAZ34S9</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>29254752</pqid></control><display><type>article</type><title>A fault diagnosis approach for roller bearings based on EMD method and AR model</title><source>Elsevier ScienceDirect Journals</source><creator>Junsheng, Cheng ; Dejie, Yu ; Yu, Yang</creator><creatorcontrib>Junsheng, Cheng ; Dejie, Yu ; Yu, Yang</creatorcontrib><description>The main purpose of this paper is to propose a new fault feature extraction approach based on empirical mode decomposition (EMD) method and autoregressive (AR) model for roller bearings. AR model is an effective approach to extract the fault feature of the vibration signals and the fault pattern can be identified directly by the extracted fault features without establishing the mathematical model and studying the fault mechanism of the system. However, AR model can only be applied to stationary signals, while the fault vibration signals of a roller bearing are non-stationary. Aiming at this problem, in this paper, the EMD method is used as a pretreatment to decompose the non-stationary vibration signal of a roller bearing into a number of intrinsic mode function (IMF) components which are stationary, then the AR model of each IMF component can be established. The AR parameters and the remnant's variance of the AR models of each IMF components are regarded as the feature vectors. The Mahalanobis distance criterion function is used to identify the condition and fault pattern of a roller bearing. Experimental analysis results show that the roller bearing fault features can be extracted by the proposed approach effectively.</description><identifier>ISSN: 0888-3270</identifier><identifier>EISSN: 1096-1216</identifier><identifier>DOI: 10.1016/j.ymssp.2004.11.002</identifier><language>eng</language><publisher>London: Elsevier Ltd</publisher><subject>Applied sciences ; AR model ; Distance criterion function ; Drives ; EMD method ; Exact sciences and technology ; Fault diagnosis ; Fundamental areas of phenomenology (including applications) ; Gears ; Industrial metrology. Testing ; Measurement and testing methods ; Mechanical engineering. Machine design ; Physics ; Roller bearings ; Solid mechanics ; Structural and continuum mechanics</subject><ispartof>Mechanical systems and signal processing, 2006-02, Vol.20 (2), p.350-362</ispartof><rights>2004 Elsevier Ltd</rights><rights>2006 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c364t-5eca5e75849e73cb04642ea91af6439a0b60010ba29cf3aef084b7d9f912793</citedby><cites>FETCH-LOGICAL-c364t-5eca5e75849e73cb04642ea91af6439a0b60010ba29cf3aef084b7d9f912793</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0888327004001736$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3536,27903,27904,65309</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=17555177$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Junsheng, Cheng</creatorcontrib><creatorcontrib>Dejie, Yu</creatorcontrib><creatorcontrib>Yu, Yang</creatorcontrib><title>A fault diagnosis approach for roller bearings based on EMD method and AR model</title><title>Mechanical systems and signal processing</title><description>The main purpose of this paper is to propose a new fault feature extraction approach based on empirical mode decomposition (EMD) method and autoregressive (AR) model for roller bearings. AR model is an effective approach to extract the fault feature of the vibration signals and the fault pattern can be identified directly by the extracted fault features without establishing the mathematical model and studying the fault mechanism of the system. However, AR model can only be applied to stationary signals, while the fault vibration signals of a roller bearing are non-stationary. Aiming at this problem, in this paper, the EMD method is used as a pretreatment to decompose the non-stationary vibration signal of a roller bearing into a number of intrinsic mode function (IMF) components which are stationary, then the AR model of each IMF component can be established. The AR parameters and the remnant's variance of the AR models of each IMF components are regarded as the feature vectors. The Mahalanobis distance criterion function is used to identify the condition and fault pattern of a roller bearing. Experimental analysis results show that the roller bearing fault features can be extracted by the proposed approach effectively.</description><subject>Applied sciences</subject><subject>AR model</subject><subject>Distance criterion function</subject><subject>Drives</subject><subject>EMD method</subject><subject>Exact sciences and technology</subject><subject>Fault diagnosis</subject><subject>Fundamental areas of phenomenology (including applications)</subject><subject>Gears</subject><subject>Industrial metrology. Testing</subject><subject>Measurement and testing methods</subject><subject>Mechanical engineering. Machine design</subject><subject>Physics</subject><subject>Roller bearings</subject><subject>Solid mechanics</subject><subject>Structural and continuum mechanics</subject><issn>0888-3270</issn><issn>1096-1216</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2006</creationdate><recordtype>article</recordtype><recordid>eNp9kE1v1DAQhi0EEkvhF3DxBW4JY8eJ4wOHVSkfUlEl4G5NnHHrVRIvnmyl_ntSthI3TnN53ndmHiHeKqgVqO7DoX6YmY-1BjC1UjWAfiZ2ClxXKa2652IHfd9XjbbwUrxiPgCAM9DtxM1eRjxNqxwT3i6ZE0s8HkvGcCdjLrLkaaIiB8KSlluWAzKNMi_y6vsnOdN6l0eJyyj3P-ScR5peixcRJ6Y3T_NC_Px89evya3V98-Xb5f66Ck1n1qqlgC3ZtjeObBMGMJ3RhE5h7EzjEIYOQMGA2oXYIEXozWBHF53S1jUX4v25dbv094l49XPiQNOEC-UTe-10a2yrN7A5g6Fk5kLRH0uasTx4Bf5RnT_4v-r8ozqvlN_Ubal3T_XIAadYcAmJ_0Vt27bK2o37eOZo-_Q-UfEcEi2BxlQorH7M6b97_gAZ34S9</recordid><startdate>20060201</startdate><enddate>20060201</enddate><creator>Junsheng, Cheng</creator><creator>Dejie, Yu</creator><creator>Yu, Yang</creator><general>Elsevier Ltd</general><general>Elsevier</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20060201</creationdate><title>A fault diagnosis approach for roller bearings based on EMD method and AR model</title><author>Junsheng, Cheng ; Dejie, Yu ; Yu, Yang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c364t-5eca5e75849e73cb04642ea91af6439a0b60010ba29cf3aef084b7d9f912793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Applied sciences</topic><topic>AR model</topic><topic>Distance criterion function</topic><topic>Drives</topic><topic>EMD method</topic><topic>Exact sciences and technology</topic><topic>Fault diagnosis</topic><topic>Fundamental areas of phenomenology (including applications)</topic><topic>Gears</topic><topic>Industrial metrology. Testing</topic><topic>Measurement and testing methods</topic><topic>Mechanical engineering. Machine design</topic><topic>Physics</topic><topic>Roller bearings</topic><topic>Solid mechanics</topic><topic>Structural and continuum mechanics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Junsheng, Cheng</creatorcontrib><creatorcontrib>Dejie, Yu</creatorcontrib><creatorcontrib>Yu, Yang</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Mechanical systems and signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Junsheng, Cheng</au><au>Dejie, Yu</au><au>Yu, Yang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A fault diagnosis approach for roller bearings based on EMD method and AR model</atitle><jtitle>Mechanical systems and signal processing</jtitle><date>2006-02-01</date><risdate>2006</risdate><volume>20</volume><issue>2</issue><spage>350</spage><epage>362</epage><pages>350-362</pages><issn>0888-3270</issn><eissn>1096-1216</eissn><abstract>The main purpose of this paper is to propose a new fault feature extraction approach based on empirical mode decomposition (EMD) method and autoregressive (AR) model for roller bearings. AR model is an effective approach to extract the fault feature of the vibration signals and the fault pattern can be identified directly by the extracted fault features without establishing the mathematical model and studying the fault mechanism of the system. However, AR model can only be applied to stationary signals, while the fault vibration signals of a roller bearing are non-stationary. Aiming at this problem, in this paper, the EMD method is used as a pretreatment to decompose the non-stationary vibration signal of a roller bearing into a number of intrinsic mode function (IMF) components which are stationary, then the AR model of each IMF component can be established. The AR parameters and the remnant's variance of the AR models of each IMF components are regarded as the feature vectors. The Mahalanobis distance criterion function is used to identify the condition and fault pattern of a roller bearing. Experimental analysis results show that the roller bearing fault features can be extracted by the proposed approach effectively.</abstract><cop>London</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.ymssp.2004.11.002</doi><tpages>13</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0888-3270
ispartof Mechanical systems and signal processing, 2006-02, Vol.20 (2), p.350-362
issn 0888-3270
1096-1216
language eng
recordid cdi_proquest_miscellaneous_29254752
source Elsevier ScienceDirect Journals
subjects Applied sciences
AR model
Distance criterion function
Drives
EMD method
Exact sciences and technology
Fault diagnosis
Fundamental areas of phenomenology (including applications)
Gears
Industrial metrology. Testing
Measurement and testing methods
Mechanical engineering. Machine design
Physics
Roller bearings
Solid mechanics
Structural and continuum mechanics
title A fault diagnosis approach for roller bearings based on EMD method and AR model
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T08%3A59%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20fault%20diagnosis%20approach%20for%20roller%20bearings%20based%20on%20EMD%20method%20and%20AR%20model&rft.jtitle=Mechanical%20systems%20and%20signal%20processing&rft.au=Junsheng,%20Cheng&rft.date=2006-02-01&rft.volume=20&rft.issue=2&rft.spage=350&rft.epage=362&rft.pages=350-362&rft.issn=0888-3270&rft.eissn=1096-1216&rft_id=info:doi/10.1016/j.ymssp.2004.11.002&rft_dat=%3Cproquest_cross%3E29254752%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=29254752&rft_id=info:pmid/&rft_els_id=S0888327004001736&rfr_iscdi=true