Rolling bearings are crucial parts of railway vehicles in the field of transportation engineering. The multivariate signals collected by multiple sensors reflect system’s dynamic characteristic comprehensively. The synchronous decomposition of the multivariate signal contributes to achieving accurate diagnosis. This paper conducts machinery multi-sensor fault diagnosis via multivariate intrinsic multiscale entropy (MIME) analysis and weighted nuisance attribute projection (WNAP). MIME analysis refers to the feature extraction of multivariate band-limited intrinsic mode functions (BLIMFs) by improved multiscale sample entropy (IMSE). Multivariate variational mode decomposition (MVMD) is applied to decompose multivariate signals into multivariate BLIMFs. IMSE is employed to quantitatively extract dynamical features of multivariate BLIMFs, to obtain feature matrices. The interferences caused by various operating conditions are eliminated by the proposed WNAP. The comparative analysis shows that the proposed machinery multi-sensor fault diagnosis approach using MIME analysis and WNAP achieves optimal diagnosis results, with diagnosis accuracy all over 98% statistically.
AhrabianALooneyDStankovićL, et al. (2015) Synchrosqueezing-based time-frequency analysis of multivariate data. Signal Processing106: 331–341.
2.
AlcarazRRietaJJ (2010) A review on sample entropy applications for the non-invasive analysis of atrial fibrillation electrocardiograms. Biomedical Signal Processing and Control5(1): 1–14.
3.
BettaGPietrosantoA (2000) Instrument fault detection and isolation: state of the art and new research trends. IEEE Transactions on Instrumentation and Measurement49(1): 100–107.
4.
BhattacharyyaAPachoriRB (2017) A multivariate approach for patient-specific EEG seizure detection using empirical wavelet transform. IEEE Transactions on Biomedical Engineering64(9): 2003–2015.
5.
CampbellWMSturimDEReynoldsDA, et al. (2006b) SVM based speaker verification using a GMM supervector kernel and NAP variability compensation In: 2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings. Toulouse, France. IEEE, p. I-97-I–100.
6.
ChenXXuXLiuA, et al. (2018) The use of multivariate EMD and CCA for denoising muscle artifacts from few-channel EEG recordings. IEEE Transactions on Instrumentation and Measurement67(2): 359–370.
7.
DingXHeQLuoN (2015) A fusion feature and its improvement based on locality preserving projections for rolling element bearing fault classification. Journal of Sound and Vibration335: 367–383.
8.
HuangWChengJYangY (2019) Rolling bearing fault diagnosis and performance degradation assessment under variable operation conditions based on nuisance attribute projection. Mechanical Systems and Signal Processing114: 165–188.
9.
JiangHChenJDongG (2016) Hidden Markov model and nuisance attribute projection based bearing performance degradation assessment. Mechanical Systems and Signal Processing72-73: 184–205.
10.
LeiYLinJHeZ, et al. (2013) A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing35(1-2): 108–126.
11.
LeiYYangBJiangX, et al. (2020) Applications of machine learning to machine fault diagnosis: a review and roadmap. Mechanical Systems and Signal Processing138: 106587.
12.
LiYFengKLiangX, et al. (2019) A fault diagnosis method for planetary gearboxes under non-stationary working conditions using improved Vold-Kalman filter and multi-scale sample entropy. Journal of Sound and Vibration439: 271–286.
13.
LiuHHanM (2014) A fault diagnosis method based on local mean decomposition and multi-scale entropy for roller bearings. Mechanism and Machine Theory75: 67–78.
14.
LvYYuanRSongG (2016) Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing. Mechanical Systems and Signal Processing81: 219–234.
15.
LvYYuanRWangT, et al. (2018) Health degradation monitoring and early fault diagnosis of a rolling bearing based on CEEMDAN and improved MMSE. Materials11(6): 1009.
16.
LvSLvYYuanR, et al. (2022) High-order synchroextracting transform for characterizing signals with strong AM-FM features and its application in mechanical fault diagnosis. Mechanical Systems and Signal Processing172: 108959.
17.
MahajanRMorshedBI (2015) Unsupervised eye blink artifact denoising of EEG data with modified multiscale sample entropy, Kurtosis, and wavelet-ICA. IEEE Journal of Biomedical and Health Informatics19(1): 158–165.
18.
MatejkaP (2009) Phonotactic and Acoustic Language Recognition. PhD thesis. Brno University of Technology, VUT.
19.
RehmanNAftabH (2019) Multivariate variational mode decomposition. IEEE Transactions on Signal Processing67(23): 6039–6052.
20.
RehmanNMandicDP (2010a) Empirical mode decomposition for trivariate signals. IEEE Transactions on Signal Processing58(3): 1059–1068.
21.
RehmanNMandicDP (2010b) Multivariate empirical mode decomposition. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences466(2117): 1291–1302.
22.
RehmanNMandicDP (2011) Filter bank property of multivariate empirical mode decomposition. IEEE Transactions on Signal Processing59(5): 2421–2426.
23.
ShikkenawisGMitraSK (2016) 2D orthogonal locality preserving projection for image denoising. IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society25(1): 262–273.
StrucVVesnicerBMihelicF, et al. (2010) Removing illumination artifacts from face images using the nuisance attribute projection. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, IEEE, 846–849.
26.
SunWChenJLiJ (2007) Decision tree and PCA-based fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing21(3): 1300–1317.
27.
VesnicerBMiheličF (2008) The likelihood ratio decision criterion for nuisance attribute projection in GMM speaker verification. EURASIP Journal on Applied Signal Processing2008(1): 786431.
28.
YuWZhaoC (2018) Sparse exponential discriminant analysis and its application to fault diagnosis. IEEE Transactions on Industrial Electronics65(7): 5931–5940.
29.
YuanRLvYKongQ, et al. (2019) Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network. Smart Materials and Structures28(12): 125001.
30.
ZhangHYangS (2016) Inclusion measure for typical hesitant fuzzy sets, the relative similarity measure and fuzzy entropy. Soft Computing20(4): 1277–1287.
31.
ZhangXMiaoQZhangH, et al. (2018) A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery. Mechanical Systems and Signal Processing108: 58–72.
32.
ZhaoXDongYYangH, et al. (2008) Nonlinear kernel nuisance attribute projection for speaker verification. In: 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, NV, USA, IEEE, 4125–4128.
33.
ZhaoCSunJLinS, et al. (2022) Rolling mill bearings fault diagnosis based on improved multivariate variational mode decomposition and multivariate composite multiscale weighted permutation entropy. Measurement195: 111190.
