The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit
later.
We apologize for any inconvenience caused
A blind source extraction method and its application to rolling bearing′s fault diagnosis
Author(s): WA NG Hong-chao, CHEN Jin, DONG Guang-ming
Pages: 755-
762
Year: 2014
Issue:
5
Journal: Journal of Vibration Engineering
Keyword: fault diagnosis; blind source extraction; rolling bearings; constrained independent component analysis;
Abstract: When fault arises in the rolling bearing it usually takes on cyclical characteristics .Firstly ,the desired source signal is extracted coarsely and the weight separation matrix W^is obtained by the proposed algorithm using the estimated fundamental period of the desired fault signal .Then ,the fixed-point algorithm is applied to the observed signals using W^as its initial weight matrix and more accurate desired source signal is derived .The proposed method has the following advantages over the con-strained independent component analysis (CICA):it neither need to estimate the fundamental period τof the desired source ac-curately nor need to construct the reference signal precisely which is otherwise for the CICA method .Besides ,the proposed method has a higher accuracy over the recent BSE methods .At last ,the above stated advantages of the proposed method are verified through simulation and the fault diagnosis test of rolling bearings .
Citations
No citation information