Bearing Fault Classification Based on Conditional Random Field
Condition monitoring of rolling element bearing is paramount for predicting the lifetime and performing effective maintenance of the mechanical equipment. To overcome the drawbacks of the hidden Markov model (HMM) and improve the diagnosis accuracy, conditional random field (CRF) model based classif...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.3233/SAV-130770 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832552264651243520 |
|---|---|
| author | Guofeng Wang Xiaoliang Feng Chang Liu |
| author_facet | Guofeng Wang Xiaoliang Feng Chang Liu |
| author_sort | Guofeng Wang |
| collection | DOAJ |
| description | Condition monitoring of rolling element bearing is paramount for predicting the lifetime and performing effective maintenance of the mechanical equipment. To overcome the drawbacks of the hidden Markov model (HMM) and improve the diagnosis accuracy, conditional random field (CRF) model based classifier is proposed. In this model, the feature vectors sequences and the fault categories are linked by an undirected graphical model in which their relationship is represented by a global conditional probability distribution. In comparison with the HMM, the main advantage of the CRF model is that it can depict the temporal dynamic information between the observation sequences and state sequences without assuming the independence of the input feature vectors. Therefore, the interrelationship between the adjacent observation vectors can also be depicted and integrated into the model, which makes the classifier more robust and accurate than the HMM. To evaluate the effectiveness of the proposed method, four kinds of bearing vibration signals which correspond to normal, inner race pit, outer race pit and roller pit respectively are collected from the test rig. And the CRF and HMM models are built respectively to perform fault classification by taking the sub band energy features of wavelet packet decomposition (WPD) as the observation sequences. Moreover, K-fold cross validation method is adopted to improve the evaluation accuracy of the classifier. The analysis and comparison under different fold times show that the accuracy rate of classification using the CRF model is higher than the HMM. This method brings some new lights on the accurate classification of the bearing faults. |
| format | Article |
| id | doaj-art-e7e357894b8d4214a24be11576dfc11c |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-e7e357894b8d4214a24be11576dfc11c2025-02-03T05:59:16ZengWileyShock and Vibration1070-96221875-92032013-01-0120459160010.3233/SAV-130770Bearing Fault Classification Based on Conditional Random FieldGuofeng Wang0Xiaoliang Feng1Chang Liu2Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin, ChinaKey Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin, ChinaKey Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin, ChinaCondition monitoring of rolling element bearing is paramount for predicting the lifetime and performing effective maintenance of the mechanical equipment. To overcome the drawbacks of the hidden Markov model (HMM) and improve the diagnosis accuracy, conditional random field (CRF) model based classifier is proposed. In this model, the feature vectors sequences and the fault categories are linked by an undirected graphical model in which their relationship is represented by a global conditional probability distribution. In comparison with the HMM, the main advantage of the CRF model is that it can depict the temporal dynamic information between the observation sequences and state sequences without assuming the independence of the input feature vectors. Therefore, the interrelationship between the adjacent observation vectors can also be depicted and integrated into the model, which makes the classifier more robust and accurate than the HMM. To evaluate the effectiveness of the proposed method, four kinds of bearing vibration signals which correspond to normal, inner race pit, outer race pit and roller pit respectively are collected from the test rig. And the CRF and HMM models are built respectively to perform fault classification by taking the sub band energy features of wavelet packet decomposition (WPD) as the observation sequences. Moreover, K-fold cross validation method is adopted to improve the evaluation accuracy of the classifier. The analysis and comparison under different fold times show that the accuracy rate of classification using the CRF model is higher than the HMM. This method brings some new lights on the accurate classification of the bearing faults.http://dx.doi.org/10.3233/SAV-130770 |
| spellingShingle | Guofeng Wang Xiaoliang Feng Chang Liu Bearing Fault Classification Based on Conditional Random Field Shock and Vibration |
| title | Bearing Fault Classification Based on Conditional Random Field |
| title_full | Bearing Fault Classification Based on Conditional Random Field |
| title_fullStr | Bearing Fault Classification Based on Conditional Random Field |
| title_full_unstemmed | Bearing Fault Classification Based on Conditional Random Field |
| title_short | Bearing Fault Classification Based on Conditional Random Field |
| title_sort | bearing fault classification based on conditional random field |
| url | http://dx.doi.org/10.3233/SAV-130770 |
| work_keys_str_mv | AT guofengwang bearingfaultclassificationbasedonconditionalrandomfield AT xiaoliangfeng bearingfaultclassificationbasedonconditionalrandomfield AT changliu bearingfaultclassificationbasedonconditionalrandomfield |