Generally, the health conditions of rotating machinery are complicated and changeable. Meanwhile, its fault labeled information is mostly unknown. Therefore, it is man-sized to automatically capture the useful fault labeled information from the monitoring raw vibration signals. That is to say, the intelligent unsupervised learning approach has a significant influence on fault diagnosis of rotating machinery. In this study, a span-new unsupervised deep learning network can be constructed based on the proposed feature extractor (L12 sparse filtering (L12SF)) and the designed clustering extractor (Weighted Euclidean Affinity Propagation) for resolving the issue that the acquisition of fault sample labeled information is burdensome, yet costly. Naturally, the novel intelligent fault diagnosis method of rotating machinery based on unsupervised deep learning network is first presented in this study. Thereinto, the proposed unsupervised deep learning network consists of two layers of unsupervised feature extractor (L12SF) and one layer of unsupervised clustering (Weighted Euclidean Affinity Propagation). L12SF can improve the regularization performance of sparse filtering, and Weighted Euclidean Affinity Propagation can get rid of the traditional Euclidean distance in affinity propagation that cannot highlight the contribution of different features in fault clustering. To make a long story short, the frequency spectrum signals are first entered into the constructed unsupervised deep learning network for fault feature representation; afterward, the unsupervised feature learning and unsupervised fault classification of rotating machinery can be implemented. The superiority of the proposed algorithms and method is validated by two cases of rolling bearing fault dataset. Ultimately, the proposed unsupervised fault diagnosis method can provide a theoretical basis for the development of intelligent unsupervised fault diagnosis technology for rotating machinery.
LeeJWuFZhaoW, et al. Prognostics and health management design for rotary machinery systems—reviews, methodology and applications. Mech Syst Signal Pr2014; 42(1–2): 314–334.
2.
ReubenLCKMbaD. Bearing time-to-failure estimation using spectral analysis features. Struct Health Monit2014; 13(2): 219–230.
3.
ChenXChengGShanX, et al. Research of weak fault feature information extraction of planetary gear based on ensemble empirical mode decomposition and adaptive stochastic resonance. Measurement2015; 73: 55–67.
4.
YuKLinTRTanJ.A bearing fault and severity diagnostic technique using adaptive deep belief networks and Dempster–Shafer theory. Struct Health Monit. Epub ahead of print 15 April 2019. DOI: 10.1177/1475921719841690.
5.
CuiLHuangJZhangF.Quantitative and localization diagnosis of a defective ball bearing based on vertical–horizontal synchronization signal analysis. IEEE T Ind Electron2017; 64: 8695–8705.
6.
YanXJiaMZhaoZ.A novel intelligent detection method for rolling bearing based on IVMD and instantaneous energy distribution-permutation entropy. Measurement2018; 130: 435–447.
7.
CuiLHuangJZhangF, et al. HVSRMS localization formula and localization law: localization diagnosis of a ball bearing outer ring fault. Mech Syst Signal Pr2019; 120: 608–629.
8.
San MartinGDroguettELMeruaneV, et al. Deep variational auto-encoders: a promising tool for dimensionality reduction and ball bearing elements fault diagnosis. Struct Health Monit2019; 18(4): 1092–1128.
9.
JiaFLeiYLuN, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization. Mech Syst Signal Pr2018; 110: 349–367.
10.
LuoSChengJZengM, et al. An intelligent fault diagnosis model for rotating machinery based on multi-scale higher order singular spectrum analysis and GA-VPMCD. Measurement2016; 87: 38–50.
11.
LeiYJiaFLinJ, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE T Ind Electron2016; 63(5): 3137–3147.
12.
RaiAUpadhyaySH.Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering. Mech Syst Signal Pr2017; 93: 16–29.
13.
LiJZhangYXieP.A new adaptive cascaded stochastic resonance method for impact features extraction in gear fault diagnosis. Measurement2016; 91: 499–508.
14.
LeiYLinJZuoMJ, et al. Condition monitoring and fault diagnosis of planetary gearboxes: a review. Measurement2014; 48(1): 292–305.
15.
TangXZhuangLCaiJ, et al. Multi-fault classification based on support vector machine trained by chaos particle swarm optimization. Knowl-Based Syst2010; 23(5): 486–490.
YangYLiaoYMengG, et al. A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis. Expert Syst Appl2011; 38(9): 11311–11320.
18.
DuMDingSJiaH.Study on density peaks clustering based on k-nearest neighbors and principal component analysis. Knowl-Based Syst2016; 99: 135–145.
19.
SahuAApleyDWRungerGC.Feature selection for noisy variation patterns using kernel principal component analysis. Knowl-Based Syst2014; 72(1): 37–47.
20.
LinFYehCCLeeMY.The use of hybrid manifold learning and support vector machines in the prediction of business failure. Knowl-Based Syst2011; 24(1): 95–101.
21.
LiangLLiuFLiM, et al. Feature selection for machine fault diagnosis using clustering of non-negation matrix factorization. Measurement2016; 94: 295–305.
22.
YangCYWuTY.Diagnostics of gear deterioration using EEMD approach and PCA process. Measurement2015; 61: 75–87.
23.
HeXCaiDYanS, et al. Neighborhood preserving embedding. In: Proceedings of the 10th IEEE international conference on computer vision, Beijing, China, 17–21 October 2005, pp. 1208–1213. New York: IEEE.
24.
BachmannCMAinsworthTLFusinaRA.Exploiting manifold geometry in hyperspectral imagery. IEEE T Geosci Remote2005; 43(3): 441–454.
25.
TangBSongTLiF, et al. Fault diagnosis for a wind turbine transmission system based on manifold learning and Shannon wavelet support vector machine. Renew Energ2014; 62(3): 1–9.
26.
XueXZhouJ.A hybrid fault diagnosis approach based on mixed-domain state features for rotating machinery. ISA T2017; 66: 284–295.
27.
LeiYHeZZiY, et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique. Mech Syst Signal Pr2008; 22(2): 419–435.
28.
HintonGESalakhutdinovRR.Reducing the dimensionality of data with neural networks. Science2006; 313(5786): 504–507.
29.
HintonGEDengLYuD, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Proc Mag2012; 29(6): 82–97.
30.
KrizhevskyASutskeverIHintonGE.ImageNet classification with deep convolutional neural networks. Adv Neur In2012; 25: 1097–1105.
31.
HuangRXiLLiX, et al. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods. Mech Syst Signal Pr2007; 21(1): 193–207.
32.
TamilselvanPWangP.Failure diagnosis using deep belief learning based health state classification. Reliab Eng Syst Safe2013; 115(7): 124–135.
33.
TranVTAlThobianiFBallA.An approach to fault diagnosis of reciprocating compressor valves using Teager–Kaiser energy operator and deep belief networks. Expert Syst Appl2014; 41(9): 4113–4122.
34.
ShaoHJiangHZhangH, et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network. IEEE T Ind Electron2018; 65(3): 2727–2736.
35.
JiaFLeiYLinJ, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Syst Signal Pr2016; 72–73: 303–315.
36.
HaidongSHongkaiJKeZ, et al. A novel tracking deep wavelet auto-encoder method for intelligent fault diagnosis of electric locomotive bearings. Mech Syst Signal Pr2018; 110: 193–209.
37.
ZhangZLiJZhuR. Deep neural network for face recognition based on sparse autoencoder. In: Proceedings of the 8th international congress on image and signal processing, Shenyang, China, 14–16 October 2015, pp. 594–598. New York: IEEE.
38.
SunWShaoSZhaoR, et al. A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Measurement2016; 89: 171–178.
39.
NgiamJKohPWChenZ, et al. Sparse filtering. In: Proceedings of the 24th international conference on neural information processing systems, Granada, 12–15 December 2011, pp. 1125–1133. Red Hook, NY: Curran Associates, Inc.
40.
ZhaoCFengZ.Application of multi-domain sparse features for fault identification of planetary gearbox. Measurement2017; 104: 169–179.
41.
BezdekJCEhrlichRFullW.FCM: the fuzzy c-means clustering algorithm. Comput Geosci1984; 10(2–3): 191–203.
42.
DemetgulMYildizKTaskinS, et al. Fault diagnosis on material handling system using feature selection and data mining techniques. Measurement2014; 55(9): 15–24.
43.
YuKLinTRTanJW.A bearing fault diagnosis technique based on singular values of EEMD spatial condition matrix and Gath-Geva clustering. Appl Acoust2017; 121: 33–45.
44.
FreyBJDueckD.Clustering by passing messages between data points. Science2007; 315(5814): 972–976.
45.
ZhengW-DWangHQianY, et al. Pattern recognition of partial discharge in GIS based on the adaptive affinity propagation clustering algorithm. High Volt Apparat2013; 49: 50–55.
46.
ZhangXWangWNørvågK, et al. K-AP: generating specified K clusters by efficient affinity propagation. In: Proceedings of the IEEE international conference on data mining, Sydney, NSW, Australia, 13–17 December 2010, pp. 1187–1192. New York: IEEE.
47.
WeiZWangYHeS, et al. A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection. Knowl-Based Syst2017; 116: 1–12.
48.
LiFZuradaJMWuW.Smooth group L 1/2 regularization for input layer of feedforward neural networks. Neurocomputing2018; 314: 109–119.
49.
ZhaoXJiaM.Fault diagnosis of rolling bearing based on feature reduction with global-local margin Fisher analysis. Neurocomputing2018; 315: 447–464.
50.
ChenFTangBChenR.A novel fault diagnosis model for gearbox based on wavelet support vector machine with immune genetic algorithm. Measurement2013; 46(1): 220–232.
DingXHeQLuoN.A fusion feature and its improvement based on locality preserving projections for rolling element bearing fault classification. J Sound Vib2015; 335: 367–383.
