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.
McFaddenPSmithJ. Vibration monitoring of rolling element bearings by the high frequency resonance technique – a review. Tribol Int1984; 17(1): 3–10.
2.
HoDRandallRB. Optimization of bearing diagnostic techniques using simulated and actual bearing fault signals. Mech Syst Signal Pr2000; 14(5): 763–788.
3.
WangW. Early detection of gear tooth cracking using the resonance demodulation technique. Mech Syst Signal Pr2001; 15(5): 887–903.
4.
YanRGaoR. Multi-scale enveloping spectrogram for vibration analysis in bearing defect diagnosis. Tribol Int2009; 42(2): 293–302.
5.
WangW. An evaluation of some emerging techniques for gear fault detection. Struct Health Monit2003; 2(3): 225–242.
6.
SekharAS. Identification of a crack in a rotor system using a model-based wavelet approach. Struct Health Monit2003; 2(4): 293–308.
7.
Reda TahaMMNoureldinALyceroJLBacaTJ. Wavelet transform for structural health monitoring: a compendium of uses and features. Struct Health Monit2006; 5(3): 267–295.
8.
PakrashiVBasuBO’ConnorA. Structural damage detection and calibration using wavelet-kurtosis techniques. Eng Struct2007; 22(9): 2097–2108.
9.
BasuBNagarajaiahSChakrabortyA. On-line identification of linear time varying stiffness of structural systems by wavelet analysis. Struct Health Monit2008; 7(1): 21–36.
10.
LiuBLingSFMengQ. Machinery diagnosis based on wavelet packets. J Vib Control1997; 3: 5–17.
11.
AltmannJMathewJ. Multiple band-pass autoregressive demodulation for rolling-element bearing fault diagnosis. Mech Syst Signal Pr2001; 15: 963–977.
12.
FanXZuoMJ. Gearbox fault detection using Hilbert and wavelet packet transform. Mech Syst Signal Pr2006; 20: 966–982.
13.
ShindeAHouZ. A wavelet packet based sifting process and its application for structural health monitoring. Struct Health Monit2005; 4(2): 153–170.
14.
ChakrabortyABasuBMitraM. Identification of modal parameters of linear MDOF system using wavelet packets. J Sound Vib2006; 25(3–5): 827–837.
15.
SuZChangCC. Structural degradation monitoring using covariance-driven wavelet packet signature. Struct Health Monit2003; 2(4): 309–325.
16.
YanRGaoR. Harmonic wavelet packet transform for on-line system health diagnosis. In: SPIE International Symposium on Sensors and Smart Structures Technologies for Civil, Mechanical and Aerospace Systems2004San Diego, CA, 512–522.
17.
MalhiAGaoR. PCA-based feature selection scheme for machine defect classification. IEEE T Instrum Meas2004; 53(6): 1517–1525.
18.
Cohen I. Automatic facial expression recognition from video sequences using temporal information. MS Thesis, University of Illinois at Urbana Champaign, 2000.
19.
Liu G, Zhang J, Wang W and McMillan L. Human motion estimation from a reduced marker set. In: Proceedings of the 2006 Symposium on Interactive 3D Graphics and Games, Redwood Shores, CA, 2006, pp.35–42.
20.
MallatSG. A wavelet tour of signal processing, London: Academic Press, 1999.
21.
ChuiCK. Wavelet: A mathematical tool for signal analysis, Philadelphia, PA: Society for Industrial and Applied Mathematics, 1997.
22.
OcakRLoparoKADiscenzoFM. Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling: A method for bearing prognostics. J Sound Vib2007; 302: 951–961.
23.
GaoRYanR. Wavelet packet transform-based hybrid signal processing for machine health monitoring and diagnosis. In: The 6th International Workshop on Structural Health Monitoring2007Stanford, CA, 598–605.
24.
KanoMHasebeSHashimotoI. A new multivariate statistical process monitoring method using principal component analysis. Comput Chem Eng2001; 25(7–8): 1103–1113.
25.
De BoePGolinvalJC. Principal component analysis of a piezo-sensor array for damage localization. Struct Health Monit2003; 2(2): 137–144.
26.
BaydarNChenQBallAKrugerU. Detection of incipient tooth defect in helical gears using multivariate statistics. Mech Syst Signal Pr2001; 15: 303–321.
27.
HeQYanRKongFDuR. Machine condition monitoring using principle component representation. Mech Syst Signal Pr2009; 23(2): 446–466.
28.
JolliffeIT. Principal component analysis, New York Inc: Springer-Verlag, 1986.
Yan R. Base wavelet selection criteria for non-stationary vibration analysis in bearing health diagnosis. PhD Dissertation, University of Massachusetts, Amherst, 2007.
31.
LouXLoparoKA. Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mech Syst Signal Process2004; 18: 1077–1095.
32.
NikolaouNGAntoniadisIA. Rolling element bearing fault diagnosis using wavelet packets. NDT&E Int2002; 35: 197–205.
33.
ZhangSMathewJMaLSunY. Best basis-based intelligent machine fault diagnosis. Mech Syst Signal Process2005; 19: 357–370.
34.
McCormickACNandiAK. Classification of the rotating machine condition using artificial neural networks. Proc Inst Mech Eng C1997; 211: 439–450.
35.
StaszewskiWJWordenKTomlinsonGR. Time-frequency analysis in gearbox fault detection using wigner-ville distribution and pattern recognition. Mech Syst Signal Process1997; 11(5): 673–692.
36.
Gao R, Wang C, Yan R and Malhi A. A neural network approach to bearing health assessment. In: Proceedings of IEEE World Congress on Computation Intelligence, Vancouver, BC, Canada, 2006, pp.1878–1885.
37.
NiuGSonJDWidodoAYangBSHwangDHKangDS. A comparison of classifier performance for fault diagnosis of induction motor using multi-type signals. Struct Health Monit2007; 6(3): 215–229.
38.
YangBSHanTAnJLKimHCAhnBH. A condition classification system for reciprocating compressors. Struct Health Monit2004; 3(3): 277–284.
39.
PayaBAEsatIIBadiMNM. Artificial neural network based fault diagnosis of rotating machinery using wavelet transforms as a preprocessor. Mech Syst Signal Pr1997; 11(5): 751–765.
40.
JackLBNandiAK. Support vector machines for detection and characterization of rolling element bearing faults. Proc Inst Mech Eng C2001; 215: 1065–1074.
