Method of assessing the state of a rolling bearing based on the relative compensation distance of multiple-domain features and locally linear embedding
A novel method is proposed for rolling bearing performance degradation assessment.
•
Sensitive IMFs of improved EEMD are combined with SVD to extract time-frequency features.
•
Multi-domain feature vectors were constructed to characterize fault information more completely.
•
LLE effectively eliminates correlation and redundancy of vibration signal features.
•
As an assessment index the proposed relative compensation distance is more effective.
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.