Research of the Method of Determining k Value in VMD based on Kurtosis
In Variational Mode Decomposition（ VMD）,k belongs to the custom variable,the decomposition result will be different with the change of k,k directly affects the accuracy of the result,which too large or too small will affect the results. Basis on the question above,a method of determining k by kurtos...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2018-01-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2018.08.030 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In Variational Mode Decomposition（ VMD）,k belongs to the custom variable,the decomposition result will be different with the change of k,k directly affects the accuracy of the result,which too large or too small will affect the results. Basis on the question above,a method of determining k by kurtosis is proposed. Selecting an integer value of k between 2 and n,every k kurtosis of the maximum correlation coefficient is calculated,and the variation curve of kurtosis is plotted. If the kurtosis of the curve has no peak and monotonically increases,calculating the kurtosis of k is n+1,repeat the steps above. The maximum kurtosis is used as the criterion of optimization,when the kurtosis is maximum,the k is the best. The feasibility of the method is verified by the actual fault signal,a new thinking of the research for VMD is proposed. |
|---|---|
| ISSN: | 1004-2539 |