Currently, the monitoring of the health status of mechanical systems is becoming more and more critical, and the actual monitoring data is massive and high-dimensional, and these data are characterized mainly by imbalance. To solve the problem of low fault recognition rate caused by data imbalance, this article proposed a novel local and non-local information balanced neighborhood graph embedding interpretable deep autoencoder (LGBNGEDAE) method for rotating machinery fault diagnosis. Specifically, the local and non-local neighborhood information graph is embedded into the original objective function of the deep autoencoder to smooth the manifold structure of the data in LGBNEDSAE, which endows the deep learning model with better data learning capability and robustness of feature extraction as well as more reasonable network interpretability, making it more suitable for feature learning and classification of unbalanced data. Further, the method’s excellent fault diagnosis capability and generalization performance are verified on two opposed experimental cases of gearboxes. Compared with other deep learning architectures and shallow learning models, the method performs better in the face of unbalanced datasets.
ZhaoXJiaM.A novel unsupervised deep learning network for intelligent fault diagnosis of rotating machinery. Struct Health Monit2019; 19: 1745–1763.
2.
AzamfarMSinghJBravo-ImazI, et al. Multisensor data fusion for gearbox fault diagnosis using 2-D convolutional neural network and motor current signature analysis. Mech Syst Signal Process2020; 144: 1–18.
3.
LeeJWuFZhaoW, et al. Prognostics and health management design for rotary machinery systems: reviews, methodology and applications. Mech Syst Signal Process2014; 42: 314–334.
4.
ShiMZhaoRWuY, et al. Fault diagnosis of rotor based on local-global balanced orthogonal discriminant projection. Measurement2020; 168: 108320.
5.
ZhaoXJiaM.A novel deep fuzzy clustering neural network model and its application in fault recognition of rolling bearing. Meas Sci Technol2018; 29: 1–21.
6.
ChengHTaoWLiuC, et al. A novel method of composite multiscale weighted permutation entropy and machine learning for fault complex system fault diagnosis. Measurement2020; 158: 107748.
7.
WuYZhaoRJinW, et al. Intelligent fault diagnosis of rolling bearings using a semi-supervised convolutional neural network. Appl Intell2021; 51: 2144–2160.
8.
LiuZCaoHChenX, et al. Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings. Neurocomputing2013; 99: 399–410.
9.
LiXLiXMaH.Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery. Mech Syst Signal Process2020; 143: 106825.
10.
GanMWangCZhuC.Multiple-domain manifold for feature extraction in machinery fault diagnosis. Measurement2015; 75: 76–91.
11.
YaoBZhenPWuL, et al. Rolling element bearing fault diagnosis using improved manifold learning. IEEE Access2017; 5: 6027–6035.
12.
GunerkarRJalanABelgamwarS.Fault diagnosis of rolling element bearing based on artificial neural network. J Mech Sci Technol2019; 33: 505–511.
13.
ShaoKFuWTanJ, et al. Coordinated approach fusing time-shift multiscale dispersion entropy and vibrational Harris hawks optimization-based SVM for fault diagnosis of rolling bearing. Measurement2020; 173: 108580.
14.
ZhaoXJiaM.Fault diagnosis of rolling bearing based on feature reduction with global-local margin fisher analysis. Neurocomputing2018; 315: 447–464.
15.
WangZYaoLCaiY.Rolling bearing fault diagnosis using generalized refined composite multiscale sample entropy and optimized support vector machine. Measurement2020; 156: 107574.
16.
HuoZZhangYJomboG, et al. Adaptive multiscale weighted permutation entropy for rolling bearing fault diagnosis. IEEE Access2020; 8: 87529–87540.
17.
WangHPengMYuY, et al. Fault identification and diagnosis based on KPCA and similarity clustering for nuclear power plants. Ann Nucl Energy2021; 150: 107786.
18.
MaPZhangHFanW, et al. Fault diagnosis using an improved fusion feature based on manifold learning for wind turbine transmission system. Journal of Vibroengineering2019; 21: 1859–1874.
19.
ZhaoTZhangXWangS. GraphSMOTE: imbalanced node classification on graphs with graph neural networks. In: WSDM, 21: proceedings of the 14th ACM international conference on web search and data mining, Virtual Event, Israel, 2021.
20.
ArunCLakshmiC. Genetic algorithm-based oversampling approach to prune the class imbalance issue in software defect prediction. Soft Computing2021; 25: 1–16.
ZhangYLiXLiangG, et al. Imbalanced data fault diagnosis of rotating machinery using synthetic oversampling and feature learning. J Manuf Syst2018; 48: 34–50.
23.
WuZLinWJiY.An integrated ensemble learning model for imbalanced fault diagnostics and prognostics. IEEE Access2018; 6: 8394–8402.
24.
WeiJHuangHYaoL, et al. New imbalanced bearing fault diagnosis method based on Sample-characteristic Oversampling TechniquE (SCOTE) and multi-class LS-SVM. Appl Soft Comput2021; 101: 1–25.
25.
ChenRZhuJHuX, et al. Fault diagnosis method of rolling bearing based on multiple classifier ensemble of the weighted and balanced distribution adaptation under limited sample imbalance. ISA Trans2021; 114: 434–443.
26.
LanYHanXZongW, et al. Two-step fault diagnosis framework for rolling element bearings with imbalanced data based on GSA-WELM and GSA-ELM. Proc IMechE, Part C: J Mechanical Engineering Science2018; 232: 2937–2947.
27.
Razavi-FarRFarajzadeh-ZanjaniMSaifM.An integrated class-imbalance learning scheme for diagnosing bearing defects in induction motors. IEEE Trans Ind Inf2017; 13: 2758–2769.
28.
Razavi-FarRFarajzadeh-ZanjaniMSaifM, et al. A hybrid ensemble scheme for diagnosing new class defects under non-stationary and class imbalance conditions. In: 2017 international conference on sensing, diagnostics, prognostics, and control (SDPC), Shanghai(CN), 2017, vol. 74, pp. 355–360.
29.
JiaFLeiYLuN, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization. Mech Syst Signal Process2018; 110: 349–367.
30.
ShaoHXiaMWanJ, et al. Modified stacked auto-encoder using adaptive morlet wavelet for intelligent fault diagnosis of rotating machinery. IEEE/ASME Trans Mechatron2021; 99: 1–10.
31.
ShaoHJiangHWangF, et al. Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet. ISA Trans2017; 69: 187–201.
32.
ZhaoXYaoJDengW, et al. Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network. IEEE Trans Neural Networks Learn Syst. Epub ahead of print 5January2022. DOI: 10.1109/TNNLS.2021.3135877.
LeiYJiaFLinJ, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Trans Ind Electron2016; 63: 3137–3147.
35.
HintonGSalakhutdinovR.Reducing the dimensionality of data with neural networks. Science2006; 313: 504–507.
36.
ShaoHDingZChengJ, et al. Intelligent fault diagnosis among different rotating machines using novel stacked transfer auto-encoder optimized by PSO. ISA Trans2020; 105: 308–319.
37.
HintonGDengLYuD, et al. Deep Neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag2012; 29: 82–97.
38.
MengGCongWZhuC.Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings. Mech Syst Signal Process2016; 72–73: 92–104.
39.
QianWLiS.A novel class imbalance-robust network for bearing fault diagnosis utilizing raw vibration signals. Measurement2020; 156: 107567.
40.
WuZGuoYLinW, et al. A weighted deep representation learning model for imbalanced fault diagnosis in cyber-physical systems. Sensors2018; 18: 1096.
41.
SunWShaoSZhaoR, et al. A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Measurement2016; 89: 171–178.
42.
LiJLiXHeD, et al. A Novel method for early gear pitting fault diagnosis using stacked SAE and GBRBM. Sensors2019; 19: 758.
43.
ChenXJiAChengG.A novel deep feature learning method based on the fused-stacked AEs for planetary gear fault diagnosis. Energies2019; 12: 4522.
44.
LiJLiXHeD, et al. Unsupervised rotating machinery fault diagnosis method based on integrated SAE–DBN and a binary processor. J Intell Manuf2020; 31: 1899–1916.
45.
ShaoHJiangHWangF, et al. An enhancement deep feature fusion method for rotating machinery fault diagnosis. Knowledge Based Syst2017; 119: 200–220.
46.
SandryhailaAMouraJ.Big data analysis with signal processing on graphs: representation and processing of massive data sets with irregular structure. IEEE Signal Process Mag2014; 31: 80–90.
47.
MarwanNDongesJZouY, et al. Complex network approach for recurrence analysis of time series. Phys Lett A2009; 373: 4246–4254.
48.
LacasaLLuqueBBallesterosF, et al. From time series to complex networks: the visibility graph. Proc Natl Acad Sci2008; 105: 4972–4975.
49.
QiaoLZhangLChenS, et al. Data-driven graph construction and graph learning: a review. Neurocomputing2018; 312: 336–351.
50.
GaoYMangCYuD.Semi-supervised graph convolutional network and its application in intelligent fault diagnosis of rotating machinery. Measurement2021; 186: 110084.
51.
SunKZhangJZhangC, et al. Generalized extreme learning machine autoencoder and a new deep neural network. Neurocomputing2016; 230: 374–381.
52.
GeHSunWZhaoM, et al. Stacked denoising extreme learning machine autoencoder based on graph embedding for feature representation. IEEE Access2019; 7: 13433–13444.
53.
LiYLekamalageCLiuT, et al. Learning representations with local and global geometries preserved for machine fault diagnosis. IEEE Trans Ind Electron2019; 63: 2360–2370.
54.
YanSDongXZhangB, et al. Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell2007; 29: 40–51.
55.
ShaoHJiangHZhaoH, et al. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis. Mech Syst Signal Process2017; 95: 187–204.
