Rolling bearings are crucial components in the fields of mechanical, civil, and aerospace engineering. They sometimes work under various operating conditions, which makes it harder to distinguish faults from normal signals. Nuisance attribute projection (NAP) is a technique that has been widely used in audio and image recognition to eliminate interference information in the extracted feature space. In constructing the weighted matrix of NAP, the setting of the weighted value represents the degree of interference between the feature vectors. The interference is either taken into consideration in whole, or not considered at all, which will inevitably lead to information loss. In our work, an entropy-weighted NAP (EWNAP) is proposed to deal with such “bipolar problem” in constructing the weighted matrix. The eigenvalues of covariance matrix of collected signals contain dynamical information, and the fuzzy entropy is adopted to evaluate the dispersion degree of these eigenvalues. After normalization, these entropy values are used to express the weight relationship in the weighted matrix of EWNAP. The features processed by EWNAP can be used as samples and combined with neural network to achieve fault diagnosis of rolling bearings. Furthermore, a fault diagnosis approach with insufficient data is demonstrated to validate the effectiveness of the proposed scheme. In the case studies, Case Western Reserve University bearing database and data collected from the bearing fault simulation bench are used. These case studies show that the proposed EWNAP alleviates the interference caused by various operating conditions, and the comparative analysis confirms that the proposed method works better than the conventional methods.
LiuXBoLHeX, et al.Application of correlation matching for automatic bearing fault diagnosis. J Sound Vibration2012; 331(26): 5838–5852.
2.
LvYYuanRSongG. Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing. Mech Systems Signal Process2016; 81: 219–234.
3.
HengAZhangSTanACC, et al.Rotating machinery prognostics: state of the art, challenges and opportunities. Mech Systems Signal Process2009; 23(3): 724–739.
4.
TharwatAGaberTIbrahimA, et al.Linear discriminant analysis: a detailed tutorial. AI Communications2017; 30(2): 169–190.
MaJYuanY. Dimension reduction of image deep feature using PCA. J Vis Commun Image Representation2019; 63: 102578.
7.
BroRSmildeAK. Principal component analysis. Anal Methods2014; 6(9): 2812–2831.
8.
HatchAOKajarekarSStolckeA. Within-class covariance normalization for SVM-based speaker recognition. In: Ninth international conference on spoken language processing, Pittsburgh, PA, September 17–21, 2006, 2006.
9.
AhmadKSThosarASNirmalJH, et al.A unique approach in text independent speaker recognition using MFCC feature sets and probabilistic neural network. In: 2015 Eighth International Conference on Advances in Pattern Recognition, Kolkata, India, 4–7 Jan. 2015,. IEEE; 2015, pp. 1–6.
10.
LiuHZhangJChengY, et al.Fault diagnosis of gearbox using empirical mode decomposition and multi-fractal detrended cross-correlation analysis. J Sound Vibration2016; 385: 350–371.
11.
JinXZhaoMChowTWS, et al.Motor bearing fault diagnosis using trace ratio linear discriminant analysis. IEEE Transactions Industrial Electronics2013; 61(5): 2441–2451.
12.
LuJPlataniotisKNVenetsanopoulosAN. Face recognition using kernel direct discriminant analysis algorithms. IEEE Transactions Neural Networks2003; 14(1): 117–126.
13.
HeQKongFYanR. Subspace-based gearbox condition monitoring by kernel principal component analysis. Mech Systems Signal Process2007; 21(4): 1755–1772.
14.
OuyangALiuYPeiS, et al.A hybrid improved kernel LDA and PNN algorithm for efficient face recognition. Neurocomputing2020; 393: 214–222.
15.
KimKIFranzMOSchölkopfB. Iterative kernel principal component analysis for image modeling. IEEE transactions Pattern Analysis Machine Intelligence2005; 27(9): 1351–1366.
16.
PrietoMDCirrincioneGEspinosaAG, et al.Bearing fault detection by a novel condition-monitoring scheme based on statistical-time features and neural networks. IEEE Transactions Industrial Electronics2013; 60(8): 3398–3407.
17.
DingXHeQLuoN. A fusion feature and its improvement based on locality preserving projections for rolling element bearing fault classification. J Sound Vibration2015; 335: 367–383.
18.
YuWTengXLiuC. Face recognition using discriminant locality preserving projections. Image Vision Computing2006; 24(3): 239–248.
19.
LiFWangJTangB, et al.Life grade recognition method based on supervised uncorrelated orthogonal locality preserving projection and K-nearest neighbor classifier. Neurocomputing2014; 138: 271–282.
20.
YuJ. Bearing performance degradation assessment using locality preserving projections and Gaussian mixture models. Mech Systems Signal Process2011; 25(7): 2573–2588.
21.
SunCZhangZHeZ, et al.Manifold learning-based subspace distance for machinery damage assessment. Mech Systems Signal Process2016; 70-71: 637–649.
22.
HuangWChengJYangY. Rolling bearing fault diagnosis and performance degradation assessment under variable operation conditions based on nuisance attribute projection. Mech Systems Signal Process2019; 114: 165–188.
23.
CampbellWMSturimDEReynoldsDA, et al.SVM based speaker verification using a GMM Supervector kernel and NAP variability compensation. 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, Toulouse, France, Toulouse, France, 14–19 May 2006; 1: 1.
24.
VesnicerBMihelicF. The likelihood ratio decision criterion for nuisance attribute projection in GMM speaker verification. EURASIP J Adv Signal Process2008; 2008(1): 1–11.
25.
ZhaoXDongYYangH, et al.Nonlinear kernel nuisance attribute projection for speaker verification. In: 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, 31 March–4 April 2008. IEEE; 2008, pp. 4125–4128.
26.
MachlicaLZajícZ. Factor analysis and nuisance attribute projection revisited. In: Proceedings of ICSPL 2012: 13th Annual Conference of the International Speech Communication Association 2012, Portland, OR, 9–13 September 2012: 1570–1573.
27.
JiangHChenJDongG. Hidden Markov model and nuisance attribute projection based bearing performance degradation assessment. Mech Systems Signal Process2016; 72: 184–205.
28.
JiangHChenJDongG, et al.An intelligent performance degradation assessment method for bearings. J Vibration Control2017; 23(18): 3023–3040.
29.
JiangHChenJDongG. Nuisance attribute projection based channel compensation technique and its application in bearing performance degradation assessment. In: COMADEM, Lancashire, UK, 10–13 July 2017, pp. 488.
30.
JiangHYuanJZhaoQ, et al.A robust performance degradation modeling approach based on Student’s T-HMM and nuisance attribute projection. IEEE Access2020; 8: 49629–49644.
31.
MaHLiSAnZ. A fault diagnosis approach for rolling bearing based on convolutional neural network and nuisance attribute projection under various speed conditions. Applied Sciences2019; 9(8): 1603.
32.
GandhiJGopinathRKumarCS. Nuisance attribute projection for system independent fault diagnosis of synchronous generator. In: WISPNET, Chennai, India, 22–24 March 2017, IEEE, 2017, pp. 544–549.
33.
GandhiJGopinathRKumarCS. System independent fault diagnosis for synchronous generator. Int J Prognostics Health Management2017; 8(2): 11
34.
GopinathRKumarCSRamachandranKI, et al.Intelligent fault diagnosis of synchronous generators. Expert Systems Applications2016; 45: 142–149.
35.
GopinathRKumarCSRamachandranRI. Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques. Int J Prognostics Health Management2018; 9(2): 11.
36.
ŠtrucVVesnicerBMiheličF, et al.Removing illumination artifacts from face images using the nuisance attribute projection. In: Proceedings of the 2010 IEEE International Conference on Acoustics Speech and Signal Processing, Dallas, TX, 14–19 March 2010. IEEE; 2010, pp. 846–849.
37.
AcePRMatejkaPAceVPR, et al.Phonotactic and acoustic language recognition. Brno, Czechia: Brno University of Technology, 2008.
38.
ZhangHYangS. Inclusion measure for typical hesitant fuzzy sets, the relative similarity measure and fuzzy entropy. Soft Comput2016; 20(4): 1277–1287.
39.
ZhengJChengJYangY. A rolling bearing fault diagnosis approach based on LCD and fuzzy entropy. Mechanism Machine Theory2013; 70: 441–453.
40.
DengWZhangSZhaoH, et al.A novel fault diagnosis method based on integrating empirical wavelet transform and fuzzy entropy for motor bearing. IEEE Access2018; 6: 35042–35056.
41.
YuanRLvYLiH, et al.Robust fault diagnosis of rolling bearings using multivariate intrinsic multiscale entropy analysis and neural network under varying operating conditions. IEEE Access2019; 7: 130804–130819.
42.
BinGFGaoJJLiXJ, et al.Early fault diagnosis of rotating machinery based on wavelet packets-Empirical mode decomposition feature extraction and neural network. Mech Systems Signal Process2012; 27: 696–711.
43.
ZhangZWangYWangK. Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network. J Intelligent Manufacturing2013; 24(6): 1213–1227.
44.
SuLZhaZLuX, et al.Using BP network for ultrasonic inspection of flip chip solder joints. Mech Systems Signal Process2013; 34(1–2): 183–190.
45.
LvYYuanRWangT, et al.Health degradation monitoring and early fault diagnosis of a rolling bearing based on CEEMDAN and improved MMSE. Materials2018; 11(6): 1009.
46.
YuanRLvYKongQ, et al.Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network. Smart Materials Structures2019; 28(12): 125001.
47.
LeiYHeZZiY. A new approach to intelligent fault diagnosis of rotating machinery. Expert Systems Applications2008; 35(4): 1593–1600.
48.
HuangNEShenZLongSR, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings the Royal Society London. Series A: Mathematical, Physical Engineering Sciences1998; 454: 903–995.
49.
ReadyMSReadyDMDevendiranS, et al.Bearing fault diagnosis using empirical mode decomposition, entropy based features and data mining techniques. Materials Today: Proceedings2018; 5(5): 11460–11475.
50.
LiXDaiKWangZ, et al.Lithium-ion batteries fault diagnostic for electric vehicles using sample entropy analysis method. J Energy Storage2020; 27: 101121.
51.
SharmaVPareyA. Gearbox fault diagnosis using RMS based probability density function and entropy measures for fluctuating speed conditions. Structural Health Monitoring2017; 16(6): 682–695.
52.
XYZhongCHZhaoHJ Dong. et al.Rolling Bearing Fault Diagnosis Using Sample Entropy and 1.5 Dimension Spectrum Based on EMD, Applied Mechanics Materials2013; 278–280: 1027–1031.
53.
SmithWARandallRB. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study. Mech Systems Signal Process2015; 64–65: 100–131.
54.
McDonaldGLZhaoQZuoMJ. Maximum correlated Kurtosis deconvolution and application on gear tooth chip fault detection. Mech Systems Signal Process2012; 33: 237–255.
55.
SolomonoffACampbellWMQuillenC. Nuisance attribute projection. Netherlands: Speech Communication, 2007, pp. 1–73.
56.
LiJYaoXWangX, et al.Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis. Measurement2020; 153: 107419.
