Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR
The vibration signals are usually characterized by nonstationary, nonlinearity, and high frequency shocks, and the redundant features degrade the performance of fault diagnosis methods. To deal with the problem, a novel fault diagnosis approach for rotating machinery is presented by combining improv...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Shock and Vibration |
| Online Access: | http://dx.doi.org/10.1155/2018/4526970 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547428001120256 |
|---|---|
| author | Xiaoguang Zhang Zhenyue Song Dandan Li Wei Zhang Zhike Zhao Yingying Chen |
| author_facet | Xiaoguang Zhang Zhenyue Song Dandan Li Wei Zhang Zhike Zhao Yingying Chen |
| author_sort | Xiaoguang Zhang |
| collection | DOAJ |
| description | The vibration signals are usually characterized by nonstationary, nonlinearity, and high frequency shocks, and the redundant features degrade the performance of fault diagnosis methods. To deal with the problem, a novel fault diagnosis approach for rotating machinery is presented by combining improved local mean decomposition (LMD) with support vector machine–recursive feature elimination with minimum redundancy maximum relevance (SVM-RFE-MRMR). Firstly, an improved LMD method is developed to decompose vibration signals into a subset of amplitude modulation/frequency modulation (AM-FM) product functions (PFs). Then, time and frequency domain features are extracted from the selected PFs, and the complicated faults can be thus identified efficiently. Due to degradation of fault diagnosis methods resulting from redundant features, a novel feature selection method combining SVM-RFE with MRMR is proposed to select salient features, improving the performance of fault diagnosis approach. Experimental results on reducer platform demonstrate that the proposed method is capable of revealing the relations between the features and faults and providing insights into fault mechanism. |
| format | Article |
| id | doaj-art-510234c9816c4bf48e12ec7c23e98871 |
| institution | Kabale University |
| issn | 1070-9622 1875-9203 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Shock and Vibration |
| spelling | doaj-art-510234c9816c4bf48e12ec7c23e988712025-02-03T06:44:39ZengWileyShock and Vibration1070-96221875-92032018-01-01201810.1155/2018/45269704526970Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMRXiaoguang Zhang0Zhenyue Song1Dandan Li2Wei Zhang3Zhike Zhao4Yingying Chen5School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, ChinaSchool of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, ChinaThe vibration signals are usually characterized by nonstationary, nonlinearity, and high frequency shocks, and the redundant features degrade the performance of fault diagnosis methods. To deal with the problem, a novel fault diagnosis approach for rotating machinery is presented by combining improved local mean decomposition (LMD) with support vector machine–recursive feature elimination with minimum redundancy maximum relevance (SVM-RFE-MRMR). Firstly, an improved LMD method is developed to decompose vibration signals into a subset of amplitude modulation/frequency modulation (AM-FM) product functions (PFs). Then, time and frequency domain features are extracted from the selected PFs, and the complicated faults can be thus identified efficiently. Due to degradation of fault diagnosis methods resulting from redundant features, a novel feature selection method combining SVM-RFE with MRMR is proposed to select salient features, improving the performance of fault diagnosis approach. Experimental results on reducer platform demonstrate that the proposed method is capable of revealing the relations between the features and faults and providing insights into fault mechanism.http://dx.doi.org/10.1155/2018/4526970 |
| spellingShingle | Xiaoguang Zhang Zhenyue Song Dandan Li Wei Zhang Zhike Zhao Yingying Chen Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR Shock and Vibration |
| title | Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR |
| title_full | Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR |
| title_fullStr | Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR |
| title_full_unstemmed | Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR |
| title_short | Fault Diagnosis for Reducer via Improved LMD and SVM-RFE-MRMR |
| title_sort | fault diagnosis for reducer via improved lmd and svm rfe mrmr |
| url | http://dx.doi.org/10.1155/2018/4526970 |
| work_keys_str_mv | AT xiaoguangzhang faultdiagnosisforreducerviaimprovedlmdandsvmrfemrmr AT zhenyuesong faultdiagnosisforreducerviaimprovedlmdandsvmrfemrmr AT dandanli faultdiagnosisforreducerviaimprovedlmdandsvmrfemrmr AT weizhang faultdiagnosisforreducerviaimprovedlmdandsvmrfemrmr AT zhikezhao faultdiagnosisforreducerviaimprovedlmdandsvmrfemrmr AT yingyingchen faultdiagnosisforreducerviaimprovedlmdandsvmrfemrmr |