The sensitivity of various features that are characteristics of machine health may vary significantly under different working conditions. Thus, it is critical to devise a systematic feature selection (FS) approach that provides a useful and automatic guidance on choosing the most effective features for machine health assessment. This article proposes a locality preserving projections (LPP)-based FS approach. Different from principal component analysis (PCA) that aims to discover the global structure of the Euclidean space, LPP can find a good linear embedding that preserves local structure information. This may enable LPP to find more meaningful low-dimensional information hidden in the high-dimensional observations compared with PCA. The LPP-based FS approach is based on unsupervised learning technique, which does not need too much prior knowledge to improve its utility in real-world applications. The effectiveness of the proposed approach was evaluated experimentally on bearing test-beds. A novel machine health assessment indication, Gaussian mixture model-based Mahalanobis distance is proposed to provide a comprehensible indication for quantifying machine health state. The proposed approach has shown to provide the better performance with reduced feature inputs than using all original candidate features. The experimental results indicate its potential applications as an effective tool for machine health assessment.
QiuH.LeeJ.LinJ.YuG.–Robust performance degradation assessment methods for enhanced rolling element bearing prognostics. Adv. Eng. Inf, 2003, 17, 127–140.
2.
WilliamsT.RiabdeneiraX.BillingtonS.KurfessT.–Rolling element bearing diagnostics in run-to-failure lifetime testing. Mech. Syst. Sig. Process, 2001, 15(5), 979–993.
3.
JardineA. K. S.LinD.BanjevicD.–A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Sig. Process, 2006, 20, 1483–1510.
4.
GuaF.YesilyurtbI.LiaY.HarrisaG.BallA.–An investigation of the effects of measurement noise in the use of instantaneous angular speed for machine diagnosis. Mech. Syst. Sig. Process, 2006, 20, 1444–1460.
5.
Sasi, A. B., Payne, B., Gu, F., and Ball, A. D. The exploration of instantaneous angular speed for condition monitoring of electric motors. In Proceeding of the 14th International Congress on Condition monitoring and diagnostic engineering management, 4–6 September 2001, Manchester, UK, pp. 311–318.
6.
LiY.GuF.HarrisG.BallA.BennettN.TravisK.BennettN.TravisK.–The measurement of instantaneous angular speed. Mech. Syst. Sig. Process, 2005, 19, 786–805.
JacksonJ. E.A user’s guide to principal components, 1991 (Wiley, New York).
9.
TenenbaumJ.SilvaD. D.LangfordJ.–A global geometric framework for nonlinear dimensionality reduction. Science, 2000, 290(5500), 2319–2323.
10.
RoweisS.SaulL.–Nonlinear dimensionality reduction by locally linear embedding. Science, 2000, 290(5500), 2323–2326.
11.
BelkinM.NiyogiP.–Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 2003, 15(6), 1373–1396.
12.
He, X. F. and Niyogi, P. Locality preserving projections. In Proceedings of the Conference on Advances in neural information processing systems, 8–13 December 2003, Vancouver, Canada, MIT Press, Cambridge, MA, 2004.
13.
XiF.SunQ.KrishnappaG.–Bearing diagnostics based on pattern recognition of statistical parameters. J. Vib. Control, 2000, 6(3), 75–92.
14.
ShaoY.NezuK.–Prognostics of remaining bearing life using neural networks. Proc. IMechE, Part C: J. Mechanical Engineering Science, 2000, 214, 217–230.
15.
YanJ.LeeJ.–Degradation assessment and fault modes classification using logistic regression. ASME J. Manufact. Sci. Eng., 2005, 127, 912–914.
16.
PanY. N.ChenJ.LiX. L.–Spectral entropy: a complementary index for rolling element bearing performance degradation assessment. Proc. IMechE, Part C: J. Mechanical Engineering Science, 2009, 223(5), 1223–1231.
17.
LiaoL.LeeJ.–A novel method for machine performance degradation assessment based on fixed cycle features test. J. Sound Vib, 2009, 326(3–5), 894–908.
18.
HonarvarF.MartinH.–New statistical moments for diagnostics of rolling element bearings. ASME J. Manufact. Sci. Eng., 1997, 119(3), 425–432.
19.
HarrisT.Rolling bearing analysis, 3rd edition, 1991 (Wiley, New York).
20.
RandallR. B.AntoniJ.ChobsaardS.–The relationship between spectral correlation and envelope analysis in the diagnostics of bearing faults and other cyclostationary machine signals. Mech. Syst. Sig. Process, 2001, 15, 945–962.
21.
Haasnoot, R. A. and Mansfield, N. J. Effect of vibration envelope on relative sensation of vibration on a steering wheel. In The 38th United Kingdom Conference on Human response to vibration, Institute of Naval Medicine, Alverstoke, Gosport, PO12 2DL, England, 17–19 September 2003, pp. 13–24.
22.
GebraeelN.LawleyM.LiuR.ParmeshwaranV.–Residual life predictions from vibration-based degradation signals: a neural network approach. IEEE Trans. Indus. Elect, 2004, 51, 694–700.
23.
DaubechiesI.–Orthonormal bases of compact supported wavelets. Commun. Pure Appl. Math., 1988, XLI, 909–996.
24.
MoriK.KasashimaN.YoshiokaT.UenoY.–Prediction of spalling on a ball bearing by applying the discrete wavelet transform to vibration signals. Wear, 1996, 195, 162–168.
25.
LouX.LoparoK. A.–Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mech. Syst. Sig. Process, 2004, 18, 1077–1095.
26.
PengZ. K.ChuF. L.–Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mech. Syst. Sig. Process, 2004, 18, 199–221.
27.
HuangN. E.ShenZ.LongS. R.WuM. C.ShihH. H.ZhengQ.YenN. C.TungC. C.LiuH. H.–The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. A, 1998, 454, 903–995.
28.
RaiV. K.MohantyA. R.–Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert Huang transform. Mech. Syst. Sig. Process, 2007, 21(6), 2607–2615.
29.
YuD.ChengJ.YangY.–Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings. Mech. Syst. Sig. Process, 2005, 19(2), 259–270.
30.
PengZ. K.TseP. W.ChuF. L.–A comparison study of improved Hilbert–Huang transform and wavelet transform: application to fault diagnosis for rolling bearing. Chem. Syst. Sig. Process, 2005, 19(5), 974–988.
31.
WuZ.HuangN. E.–Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv. Adapt. Data Anal., 2009, 1(1), 11–41.
32.
LeiY.HeZ.ZiY.–Application of the EEMD method to rotor fault diagnosis of rotating machinery. Mech. Syst. Sig. Process, 2009, 23, 1327–1338.
33.
HuangR.XiL.XiL.LiuC. R.QiuH.LeeJ.–Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech. Syst. Sig. Process, 2007, 21, 193–207.
34.
DempsterA.LairdN.RubinD.–Maximum likelihood estimation from incomplete data via the EM algorithm. J. Roy. Stat. Soc., 1977, 30(B), 1–38.
35.
Lee, J., Qiu, H., Yu, G., Lin, J., and Rexnord Technical Services. Bearing Data Set, IMS, University of Cincinnati. NASA Ames Prognostics Data Repository, available from http://ti.arc.nasa.gov/project/prognostic-data-repository (NASA Ames, Moffett Field, CA, 2009).
36.
HaykinS.Neural networks: a comprehensive foundation, 2nd edition, (Prentice-Hall, New Jersey, Englewood Cliffs).
