Wavelet domain principal feature analysis for spindle health diagnosis

Structural Health Monitoring - Tập 10 Số 6 - Trang 631-642 - 2011
Ruqiang Yan1, Robert X. Gao2
1School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
2Department of Mechanical Engineering, University of Connecticut, Storrs, CT, 06269, USA#TAB#

Tóm tắt

This article introduces a hybrid signal processing technique for spindle health monitoring and diagnosis, through the integration of wavelet packet transform and principal feature analysis. Vibration signals measured from a spindle test system with different defect conditions are first decomposed into multiple sub-frequency bands by means of the wavelet packet transform. Statistical parameters such as energy and Kurtosis of these sub-frequency bands are then calculated. Subsequently, Principal Feature Analysis, which is an extension of the Principal Component Analysis, is performed on the statistical parameters to aid in the selection of the most representative features, which can be distinctively separated from each other, as inputs to a diagnostic classifier. Experimental analysis of sensor data measured from the spindle test system has verified the effectiveness of the developed technique.

Từ khóa


Tài liệu tham khảo

10.1016/0301-679X(84)90076-8

10.1006/mssp.2000.1304

10.1006/mssp.2001.1416

10.1016/j.triboint.2008.06.013

10.1177/1475921703036049

10.1177/147592103039917

10.1177/1475921706067741

10.1016/j.engstruct.2006.10.013

10.1177/1475921707081968

10.1177/107754639700300102

10.1006/mssp.2001.1410

10.1016/j.ymssp.2005.08.032

10.1177/1475921705049762

10.1016/j.jsv.2006.01.037

10.1177/147592103039835

10.1117/12.539914

10.1109/TIM.2004.834070

Mallat SG, 1999, A wavelet tour of signal processing

10.1137/1.9780898719727

10.1016/j.jsv.2007.01.001

Gao R, 2007, In: The 6th International Workshop on Structural Health Monitoring, 598

10.1016/S0098-1354(01)00683-4

10.1177/1475921703002002005

10.1006/mssp.2000.1315

10.1016/j.ymssp.2008.03.010

10.1007/978-1-4757-1904-8

Duda R, 2001, Pattern classification

10.1016/S0888-3270(03)00077-3

10.1016/S0963-8695(01)00044-5

10.1016/j.ymssp.2004.06.001

10.1243/0954406971521845

10.1006/mssp.1997.0102

10.1177/1475921707081110

10.1177/1475921704045628

10.1006/mssp.1997.0090

10.1177/095440620121500907