FEATURE EXTRACTION METHOD OF SOUND SIGNAL TO ROLLING BEARING BASED ON BLIND SOURCE SEPARATION AND MORLET WAVELET
It is a new method of sound signal testing and analysis,but the SNR is too low,so we raise a feature extraction method of sound signal to rolling bearing based on blind source separation and adaptive Morlet wavelet. Firstly,the wavelet packet is used to change the single channel of the voice signal...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Strength
2018-01-01
|
| Series: | Jixie qiangdu |
| Subjects: | |
| Online Access: | http://www.jxqd.net.cn/thesisDetails#10.16579/j.issn.1001.9669.2018.03.004 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | It is a new method of sound signal testing and analysis,but the SNR is too low,so we raise a feature extraction method of sound signal to rolling bearing based on blind source separation and adaptive Morlet wavelet. Firstly,the wavelet packet is used to change the single channel of the voice signal separated into two virtual channels,then using BSS to extract the source of signal. Minimum Shannon entropy is used to optimize the Morlet wavelet shape factor,in order to match with the impact component. Then,an abrupt information detection method based on the transitional stage of singular curve of wavelet coefficient matrix is used to choose the appropriate scale for the wavelet transformation. Finally,the fault feature of the signal can be extracted using this method. The experimental results shows that the method could extract sound signal fault feature more effectively. |
|---|---|
| ISSN: | 1001-9669 |