Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM
Aiming at the non-stationary and nonlinearity characteristics of reciprocating compressor vibration signal,a fault diagnosis method for bearing fault of reciprocating compressor based on LMD multiscale entropy and SVM is proposed.To improve the envelope approximation accuracy of local mean and envel...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2015-01-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2015.02.029 |
| _version_ | 1826882212524457984 |
|---|---|
| author | Yang Songshan Zhou Hao Zhao Haiyang Wang Jindong |
| author_facet | Yang Songshan Zhou Hao Zhao Haiyang Wang Jindong |
| author_sort | Yang Songshan |
| collection | DOAJ |
| description | Aiming at the non-stationary and nonlinearity characteristics of reciprocating compressor vibration signal,a fault diagnosis method for bearing fault of reciprocating compressor based on LMD multiscale entropy and SVM is proposed.To improve the envelope approximation accuracy of local mean and envelope estimation,cubic Hermite interpolation method is used to construct envelope curves between extreme points according to the excellent characteristic of shape preservation.The vibration signals in each state are decomposed into a series of PF components with the improved LMD method,and the PF components which contain the main information of fault state are chosen according to the relative coefficient.By using the multiscale entropy,the quantitative description of the PF components is carried out,and the optimized scale factor is selected based on the maximum of average distances between different states,so the eigenvectors which have the best divisibility are extracted.The SVM is taken as pattern classifier,the type of bearing clearance fault is diagnosed,and the superiority of this method is verified by comparing the eigenvectors extracted by LMD and sample entropy and LMD and approximate entropy method. |
| first_indexed | 2024-03-13T09:24:22Z |
| format | Article |
| id | doaj.art-96f09d3289ff464bbda59d528abcd289 |
| institution | Directory Open Access Journal |
| issn | 1004-2539 |
| language | zho |
| last_indexed | 2025-02-17T03:05:02Z |
| publishDate | 2015-01-01 |
| publisher | Editorial Office of Journal of Mechanical Transmission |
| record_format | Article |
| series | Jixie chuandong |
| spelling | doaj.art-96f09d3289ff464bbda59d528abcd2892025-01-10T14:12:34ZzhoEditorial Office of Journal of Mechanical TransmissionJixie chuandong1004-25392015-01-013911912329915488Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVMYang SongshanZhou HaoZhao HaiyangWang JindongAiming at the non-stationary and nonlinearity characteristics of reciprocating compressor vibration signal,a fault diagnosis method for bearing fault of reciprocating compressor based on LMD multiscale entropy and SVM is proposed.To improve the envelope approximation accuracy of local mean and envelope estimation,cubic Hermite interpolation method is used to construct envelope curves between extreme points according to the excellent characteristic of shape preservation.The vibration signals in each state are decomposed into a series of PF components with the improved LMD method,and the PF components which contain the main information of fault state are chosen according to the relative coefficient.By using the multiscale entropy,the quantitative description of the PF components is carried out,and the optimized scale factor is selected based on the maximum of average distances between different states,so the eigenvectors which have the best divisibility are extracted.The SVM is taken as pattern classifier,the type of bearing clearance fault is diagnosed,and the superiority of this method is verified by comparing the eigenvectors extracted by LMD and sample entropy and LMD and approximate entropy method.http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2015.02.029Reciprocating compressorLMDMultiscale entropyBearingFault diagnosis |
| spellingShingle | Yang Songshan Zhou Hao Zhao Haiyang Wang Jindong Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM Jixie chuandong Reciprocating compressor LMD Multiscale entropy Bearing Fault diagnosis |
| title | Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM |
| title_full | Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM |
| title_fullStr | Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM |
| title_full_unstemmed | Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM |
| title_short | Fault Diagnosis Method for the Bearing of Reciprocating Compressor based on LMD Multiscale Entropy and SVM |
| title_sort | fault diagnosis method for the bearing of reciprocating compressor based on lmd multiscale entropy and svm |
| topic | Reciprocating compressor LMD Multiscale entropy Bearing Fault diagnosis |
| url | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2015.02.029 |
| work_keys_str_mv | AT yangsongshan faultdiagnosismethodforthebearingofreciprocatingcompressorbasedonlmdmultiscaleentropyandsvm AT zhouhao faultdiagnosismethodforthebearingofreciprocatingcompressorbasedonlmdmultiscaleentropyandsvm AT zhaohaiyang faultdiagnosismethodforthebearingofreciprocatingcompressorbasedonlmdmultiscaleentropyandsvm AT wangjindong faultdiagnosismethodforthebearingofreciprocatingcompressorbasedonlmdmultiscaleentropyandsvm |