An integrated method based on refined composite multivariate hierarchical permutation entropy and random forest and its application in rotating machinery
Restricted accessResearch articleFirst published online February, 2020
An integrated method based on refined composite multivariate hierarchical permutation entropy and random forest and its application in rotating machinery
Fault feature extraction of rotating machinery is crucial and challenging due to its nonlinear and nonstationary characteristics. In order to resolve this difficulty, a quality nonlinear fault feature extraction method is required. Hierarchical permutation entropy has been proven to be a promising nonlinear feature extraction method for fault diagnosis of rotating machinery. Compared with multiscale permutation entropy, hierarchical permutation entropy considers the fault information hidden in both high frequency and low frequency components. However, hierarchical permutation entropy still has some shortcomings, such as poor statistical stability for short time series and inability of analyzing multichannel signals. To address such disadvantages, this paper proposes a new entropy method, called refined composite multivariate hierarchical permutation entropy. Refined composite multivariate hierarchical permutation entropy can extract rich fault information hidden in multichannel signals synchronously. Based on refined composite multivariate hierarchical permutation entropy and random forest, a novel fault diagnosis framework is proposed in this paper. The effectiveness of the proposed method is validated using experimental and simulated signals. The results demonstrate that the proposed method outperforms multivariate multiscale fuzzy entropy, refined composite multivariate multiscale fuzzy entropy, multivariate multiscale sample entropy, multivariate multiscale permutation entropy, multivariate hierarchical permutation entropy, and composite multivariate hierarchical permutation entropy in recognizing the different faults of rotating machinery.
AcharyaURHagiwaraYKohJEW, et al. (2018) Entropies for automated detection of coronary artery disease using ECG signals: a review. Biocybernetics and Biomedical Engineering38: 373–384.
2.
AhmedMUMandicDP (2011) Multivariate multiscale entropy: a tool for complexity analysis of multichannel data. Physical Review E84(6): 061918.
AzizWArifM (2005) Multiscale permutation entropy of physiological time series. In: 9th international multitopic conference (IEEE INMIC), Karachi, Pakistan, 24–25 December 2005, pp. 1–6. New York, USA: IEEE.
5.
BandtCPompeB (2002) Permutation entropy: a natural complexity measure for time series. Physical Review Letters88(17): 174102.
6.
CaoYTungWWGaoJB, et al. (2004) Detecting dynamical changes in time series using the permutation entropy. Physical Review E70(4): 046217.
7.
ChenJLiZPanJ, et al. (2016) Wavelet transform based on inner product in fault diagnosis of rotating machinery: a review. Mechanical Systems and Signal Processing70: 1–35.
8.
El-MongyHHYounesYK (2018) Vibration analysis of a multi-fault transient rotor passing through sub-critical resonances. Journal of Vibration and Control24(14): 2986–3009.
9.
FengZZhangDZuoMJ (2017) Adaptive mode decomposition methods and their applications in signal analysis for machinery fault diagnosis: a review with examples. IEEE Access5: 24301–24331.
10.
FengZZuoM (2012) Vibration signal models for fault diagnosis of planetary gearboxes. Journal of Sound and Vibration331(22): 4918–4939.
11.
GaoYVilleccoFLiM, et al. (2017) Multi-scale permutation entropy based on improved LMD and HMM for rolling bearing diagnosis. Entropy19(4): 176.
12.
GenuerRPoggiJMTuleau-MalotC (2010) Variable selection using random forests. Pattern Recognition Letters31(14): 2225–2236.
13.
HanTJiangDZhaoQ, et al. (2018) Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery. Transactions of the Institute of Measurement and Control40(8): 2681–2693.
14.
JiangYPengCKXuY (2011) Hierarchical entropy analysis for biological signals. Journal of Computational and Applied Mathematics236(5): 728–742.
15.
KoskoB (1986) Fuzzy entropy and conditioning. Information Sciences40(2): 165–174.
16.
LeiYZuoMJ (2009) Gear crack level identification based on weighted K nearest neighbor classification algorithm. Mechanical Systems and Signal Processing23(5): 1535–1547.
17.
LiYLiGYangY, et al. (2018) A fault diagnosis scheme for planetary gearboxes using adaptive multi-scale morphology filter and modified hierarchical permutation entropy. Mechanical Systems and Signal Processing105: 319–337.
18.
LiYXuMLiangX, et al. (2017) Application of bandwidth EMD and adaptive multiscale morphology analysis for incipient fault diagnosis of rolling bearings. IEEE Transactions on Industrial Electronics64(8): 6506–6517.
19.
LiYXuMWangR, et al. (2016) A fault diagnosis scheme for rolling bearing based on local mean decomposition and improved multiscale fuzzy entropy. Journal of Sound and Vibration360: 277–299.
20.
LiuRYangBZhangX, et al. (2016) Time-frequency atoms-driven support vector machine method for bearings incipient fault diagnosis. Mechanical Systems and Signal Processing75: 345–370.
21.
MorabitoFCLabateDLa ForestaF, et al. (2012) Multivariate multi-scale permutation entropy for complexity analysis of Alzheimer’s disease EEG. Entropy14(7): 1186–1202.
22.
PedregosaFVaroquauxG, GramfortA, et al. (2012) Scikit-learn: machine learning in Python. Journal of Machine Learning Research12(10): 2825–2830.
23.
RandallRBAntoniJ (2011) Rolling element bearing diagnostics—a tutorial. Mechanical Systems and Signal Processing25(2): 485–520.
24.
RichmanJSMoormanJR (2000) Physiological time-series analysis using approximate entropy and sample entropy. American Journal of Physiology-Heart and Circulatory Physiology278(6): H2039–H2049.
25.
SánchezRVLuceroPVásquezRE, et al. (2018) Feature ranking for multi-fault diagnosis of rotating machinery by using random forest and KNN. Journal of Intelligent & Fuzzy Systems34(6): 3463–3473.
26.
ShannonCE (1948) A mathematical theory of communication. Bell System Technical Journal27(3): 379–423.
27.
SmithWARandallRB (2015) Rolling element bearing diagnostics using the case western reserve university data: a benchmark study. Mechanical Systems and Signal Processing64–65: 100–131.
28.
WangDPeterWTTsuiKL (2013) An enhanced kurtogram method for fault diagnosis of rolling element bearings. Mechanical Systems and Signal Processing35(1–2): 176–199.
29.
WangLLiuZMiaoQ, et al. (2018a) Time-frequency analysis based on ensemble local mean decomposition and fast kurtogram for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing103: 60–75.
30.
WangTChuFFengZ (2018b) Meshing frequency modulation (MFM) index-based kurtogram for planet bearing fault detection. Journal of Sound and Vibration432: 437–453.
31.
WuSDWuCWLinSG, et al. (2014) Analysis of complex time series using refined composite multiscale entropy. Physics Letters A378(20): 1369–1374.
32.
WuSDWuPHWuCW, et al. (2012) Bearing fault diagnosis based on multiscale permutation entropy and support vector machine. Entropy14(8): 1343–1356.
33.
YanRLiuYGaoRX (2012) Permutation entropy: a nonlinear statistical measure for status characterization of rotary machines. Mechanical Systems and Signal Processing29: 474–484.
34.
YinYShangP (2017) Multivariate weighted multiscale permutation entropy for complex time series. Nonlinear Dynamics88(3): 1707–1722.
35.
YuJHeY (2018) Planetary gearbox fault diagnosis based on data-driven valued characteristic multigranulation model with incomplete diagnostic information. Journal of Sound and Vibration429: 63–77.
36.
YuanJWangYPengY, et al. (2017) Weak fault detection and health degradation monitoring using customized standard multiwavelets. Mechanical Systems and Signal Processing94: 384–399.
37.
ZhangMWangKSWeiD, et al. (2018) Amplitudes of characteristic frequencies for fault diagnosis of planetary gearbox. Journal of Sound and Vibration432: 119–132.
38.
ZhaoMLinJ (2018) Health assessment of rotating machinery using a rotary encoder. IEEE Transactions on Industrial Electronics65(3): 2548–2556.
39.
ZhengJChengJYangY (2014a) Multiscale permutation entropy based rolling bearing fault diagnosis. Shock and Vibration2014: 154291.
40.
ZhengJChengJYangY, et al. (2014b) A rolling bearing fault diagnosis method based on multi-scale fuzzy entropy and variable predictive model-based class discrimination. Mechanism and Machine Theory78: 187–200.
41.
ZhengJPanHChengJ (2017) Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines. Mechanical Systems and Signal Processing85: 746–759.
42.
ZhengJPanHYangS, et al. (2018) Generalized composite multiscale permutation entropy and Laplacian score based rolling bearing fault diagnosis. Mechanical Systems and Signal Processing99: 229–243.
43.
ZhengJTuDPanH, et al. (2017) A refined composite multivariate multiscale fuzzy entropy and Laplacian score-based fault diagnosis method for rolling bearings. Entropy19(11): 585.
44.
ZhuK (2018) Performance degradation assessment of rolling element bearings based on hierarchical entropy and general distance. Journal of Vibration and Control24(14): 3194–3205.
45.
ZhuKSongXXueD (2014) A roller bearing fault diagnosis method based on hierarchical entropy and support vector machine with particle swarm optimization algorithm. Measurement47: 669–675.
