基于声信号分析的齿轮故障诊断方法_杨德斌.pdf

0 4 Vol.0 No.4 2008 4 Journal of University of Science and Technology Beijing Apr.2008 杨德斌　杨聚星　阳建宏　章立军 , 100083 　　, ., ., . 　;;;; + 　TH 165 .3;TN 911.7 Method of gear fault diagnosis based on acoustic signal analysis YAN GDebin, YAN GJux ing, YAN GJianhong, ZHAN G Lij un School of Mechanical Engineering, University of Science and Technology eijing, eijing 100083, China ABSTRACT　Due to the noise disturbance from surrounding equipments and environment in gear fault diagnosis based on acoustic sig- nal analysis, a novel method combined with independent component analysis and auto-correlation w as proposed.Independent compo- nent analysis w asused to separate characteristic signaland interference signal.And then auto-correlation was used to extract the peri- odic component of characteristic signal.Experimental resultsindicate that the proposed approach could reduce strong background noise and extract fault feature form gear acoustic signal. KEY WORDS　gear;fault diagnosis;acoustic signal;independent component analysis;auto-correlation 　　, 1　 ,, ., [3-8] (independent component , , analysis, ICA) [1] . , , , ,、,、 . . N , , s (t )(j =1,2, …,N ).j ,, , M (MN ) , .: [2] ., N x (t )= [a s (t )] 　i=1, 2, …,M (1) , i ∑ ij j j =1 , , a s (t) i ij j . .(1): . x (t)=As (t) (2)