Simulation models incorporating fault mechanisms can acquire sufficient samples with rich fault information, providing an effective solution to deep learning-driven bearing fault diagnosis in case of sample scarcity. However, the simulation models in the previous studies are mainly designed for constant speed conditions and cannot generate effective source data aligning with the variable speed conditions. Moreover, the fault impacts of bearing exhibit time-varying characteristics under variable speed conditions, causing the obstacle of the fault feature representation of the deep learning model. Therefore, this article investigates an analytical fault simulation model-driven unsupervised fault diagnosis of rolling bearing under time-varying speeds. The simulation model can customize high-quality data that match the specific variable speed conditions. The proposed network can extract robust discriminable feature representation by designing multiscale enhanced temporal convolution transformer network and enables the feature alignment of the target and simulation samples under a pseudolabel guided domain adaptation training strategy. The effectiveness and superiority of the proposed method in addressing the bottleneck problems of bearing unsupervised fault diagnosis under variable speed conditions, including condition matching data generation and time-varying feature representation, is demonstrated using two different bearing datasets.
MiaoYLiCZhangBLinJ.Application of a coarse-to-fine minimum entropy deconvolution method for rotating machines fault detection. Mech Syst Signal Process2023; 198: 110431.
2.
YiCLiSHuangTXiaoHJiangY.On a prediction method for remaining useful life of rolling bearings via VMD-based dispersion entropy and GAN. IEEE Sens J2023; 23(22): 27744–27756.
3.
TaYLiYCaiW, et al. Adaptive staged remaining useful life prediction method based on multi-sensor and multi-feature fusion. Reliab Eng Syst Saf2023; 231: 109033.
4.
MiaoYZhangBLiCLinJZhangD.Feature mode decomposition: new decomposition theory for rotating machinery fault diagnosis. IEEE Trans Ind Electron2023; 70(2): 1949–1960.
5.
PangBNazariMTangG.Recursive variational mode extraction and its application in rolling bearing fault diagnosis. Mech Syst Signal Process2022; 165: 108321.
6.
WangZYangJGuoY.Unknown fault feature extraction of rolling bearings under variable speed conditions based on statistical complexity measures. Mech Syst Signal Process2022; 172: 108964.
7.
JiangXLiXWangQSongQLiuJZhuZ.Multi-sensor data fusion-enabled semi-supervised optimal temperature-guided PCL framework for machinery fault diagnosis. Inform Fusion2024; 101: 102005.
8.
WangZHeXYangBLiN.Subdomain adaptation transfer learning network for fault diagnosis of roller bearings. IEEE Trans Ind Electron2022; 69(8): 8430–8439.
9.
DingCHuangWShenCJiangXWangJZhuZ.Synchroextracting frequency synchronous chirplet transform for fault diagnosis of rotating machinery under varying speed conditions. Struct Health Monitor2024; 23(3): 1403–1422.
10.
BaoWTuXHuYLiF.Envelope spectrum L-Kurtosis and its application for fault detection of rolling element bearings. IEEE Trans Instrum Meas2020; 69(5): 1993–2002.
11.
YuanJSongZJiangHZhaoQZengQWeiY.The Msegram: a useful multichannel feature synchronous extraction tool for detecting rolling bearing faults. Mech Syst Signal Process2023; 187: 109923.
12.
YangNWangZCaiWLiY.Data regeneration based on multiple degradation processes for remaining useful life estimation. Reliab Eng Syst Saf2023; 229: 108867.
13.
LuFTongQFengZWanQ.Unbalanced bearing fault diagnosis under various speeds based on spectrum alignment and deep transfer convolution neural network. IEEE Trans Ind Inform2023; 19(7): 8295–8306.
14.
JiaFLeiYGuoLLinJXingS.A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines. Neurocomputing2018; 272: 619–628.
15.
AnZLiSWangJJiangX.A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network. ISA Trans2020; 100: 155–170.
16.
MingYShaoHCaiBLiuB.Rgfc-Forest: an enhanced deep forest method towards small-sample fault diagnosis of electromechanical system. Expert Syst Appl2023; 238: 122178.
17.
HeCShiHLiJ.IDSN: a one-stage interpretable and differentiable STFT domain adaptation network for traction motor of high-speed trains cross-machine diagnosis. Mech Syst Signal Process2023; 205: 110846.
18.
PengJShaoHXiaoYCaiBLiuB.Industrial surface defect detection and localization using multi-scale information focusing and enhancement GANomaly. Expert Syst Appl2024; 238: 122361.
19.
ZhangYJiJ CRenZ, et al. Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing. Reliab Eng Syst Saf2023; 234: 109186.
20.
DongYLiYZhengHWangRXuM.A new dynamic model and transfer learning based intelligent fault diagnosis framework for rolling element bearings race faults: solving the small sample problem. ISA Trans2022; 121: 327–348.
21.
XiaoYShaoHHanSHuoZWanJ.Novel joint transfer network for unsupervised bearing fault diagnosis from simulation domain to experimental domain. IEEE/ASME Trans Mechatron2022; 27(6): 5254–5263.
22.
LouYKumarAXiangJ.Machinery fault diagnosis based on domain adaptation to bridge the gap between simulation and measured signals. IEEE Trans Instrum Meas2022; 71: 1–9.
23.
YuKFuQMaHLinTLiX.Simulation data driven weakly supervised adversarial domain adaptation approach for intelligent cross-machine fault diagnosis. Struct Health Monitor2021; 20(4): 2182–2198.
24.
PangBLiuQSunZXuZHaoZ.Time-frequency supervised contrastive learning via pseudo-labeling: an unsupervised domain adaptation network for rolling bearing fault diagnosis under time-varying speeds. Adv Eng Inform2024; 59: 102304.
25.
LuNXiaoHSunYHanMWangY.A new method for intelligent fault diagnosis of machines based on unsupervised domain adaptation. Neurocomputing2021; 427: 96–109.
26.
YanSShaoHWangJZhengXLiuB.LiConvFormer: a lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention. Expert Syst Appl2024; 237: 121338.
27.
DaiZLiuHLeQ VTanM.CoAtNet: marrying convolution and attention for all data sizes. arXiv2021; 2021: abs/2106.04803.
28.
FangHDengJBaiY, et al. CLFormer: a lightweight transformer based on convolutional embedding and linear self-attention with strong robustness for bearing fault diagnosis under limited sample conditions. IEEE Trans Instrum Meas2022; 71: 1–8.
29.
DingYJiaMMiaoQCaoY.A novel time–frequency Transformer based on self–attention mechanism and its application in fault diagnosis of rolling bearings. Mech Syst Signal Process2022; 168: 108616.
30.
McFaddenPDSmithJD.Vibration monitoring of rolling element bearings by the high-frequency resonance technique—a review. Tribol Int1984; 17(1): 3–10.
31.
McFaddenPDSmithJD.The vibration produced by multiple point defects in a rolling element bearing. J Sound Vib1985; 98(2): 263–273.
32.
HoDRandallRBRandallRB.Optimisation of bearing diagnostic techniques using simulated and actual bearing fault signals. Mech Syst Signal Process2000; 14: 763–788.
33.
AntoniJRandallRB.Differential diagnosis of gear and bearing faults. J Vib Acoust2002; 124(2): 165–171.
34.
D’EliaGCocconcelliMMucchiE.An algorithm for the simulation of faulted bearings in non-stationary conditions. Meccanica2017; 53(4–5): 1147–1166.
35.
LiFWangLWangDWuJZhaoH.An adaptive multiscale fully convolutional network for bearing fault diagnosis under noisy environments. Measurement2023; 216: 112993.
36.
DengFBiYLiuYYangS.Remaining useful life prediction of machinery: a new multiscale temporal convolutional network framework. IEEE Trans Instrum Meas2022; 71: 1–13.
37.
WuXZhangSZhouQYangZZhaoCLateckiLJ.Entropy minimization versus diversity maximization for domain adaptation. IEEE Trans Neural Netw Learn Syst2023; 34(6): 2896–2907.
38.
ZhangYRenZZhouSYuT.Adversarial domain adaptation with classifier alignment for cross-domain intelligent fault diagnosis of multiple source domains. Meas Sci Technol2021; 32(3): 035102.
39.
ThuanNDHongHS.HUST bearing: a practical dataset for ball bearing fault diagnosis. BMC Res Notes2023; 16(1): 138.
40.
BuzzoniMD’EliaGCocconcelliM.A tool for validating and benchmarking signal processing techniques applied to machine diagnosis. Mech Syst Signal Process2020; 139: 106618.
41.
JiaZLinYWangJYangKLiuTZhangX (eds). MMCNN: a multi-branch multi-scale convolutional neural network for motor imagery classification. Machine Learning and Knowledge Discovery in Databases, 2021, pp. 736–751.
42.
WangHLiuZPengDQinY.Understanding and learning discriminant features based on multiattention 1DCNN for wheelset bearing fault diagnosis. IEEE Trans Ind Inform2020; 16(9): 5735–5745.
43.
YuXZhaoZZhangX, et al. Conditional adversarial domain adaptation with discrimination embedding for locomotive fault diagnosis. IEEE Trans Instrum Meas2020; 70: 1–12.
44.
TaoHChengLQiuJStojanovicV.Few shot cross equipment fault diagnosis method based on parameter optimization and feature mertic. Meas Sci Technol2022; 33(11): 115005.
45.
HanTLiuCYangWJiangD.A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults. Knowl Based Syst2019; 165: 474–487.
46.
LiuRWangFYangBQinS J.Multiscale Kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions. IEEE Trans Ind Inform2020; 16(6): 3797–3806.
47.
LiangPWangBJiangGLiNZhangL.Unsupervised fault diagnosis of wind turbine bearing via a deep residual deformable convolution network based on subdomain adaptation under time-varying speeds. Eng Appl Artif Intell2023; 118: 105656.
48.
ChenJWangCWangBZhouZ.A visualized classification method via t-distributed stochastic neighbor embedding and various diagnostic parameters for planetary gearbox fault identification from raw mechanical data. Sens Actuat A Phys2018; 284: 52–65.
49.
HanSShaoHChengJYangXCaiB.Convformer-NSE: a novel end-to-end gearbox fault diagnosis framework under heavy noise using joint global and local information. IEEE/ASME Trans Mechatron2023; 28(1): 340–349.
