Intelligent fault diagnosis of rotating machinery under variable working conditions based on deep transfer learning with fusion of local and global time–frequency features
Restricted accessResearch articleFirst published online July, 2024
Intelligent fault diagnosis of rotating machinery under variable working conditions based on deep transfer learning with fusion of local and global time–frequency features
With the development of deep learning methods, the data-driven fault diagnosis methods have attracted a great deal of interest. However, as for the data-driven fault diagnosis methods, technology has to overcome various difficulties in the practical industrial scenarios, such as variable working conditions, insufficient effective samples, and environmental noise interference. Combining with the time–frequency analysis of vibration signals, a domain adaptation fault diagnosis model based on ResNet and Transformer (DAFDMRT) is proposed in this work, aiming to solve the problems encountered by current rotating machinery fault diagnosis methods in the field of application. Firstly, the vibration signal is processed by wavelet packet transform and the time–frequency information grayscale maps is constructed. Next, a deep fusion feature extraction network combining ResNet and Transformer encoder, is designed for the extraction and fusion of the local and global features of multi-scale time–frequency information. Finally, the multi-kernel maximum mean discrepancy is applied to measure and minimize the distribution difference between the deep features of source and target domain, thereby improving the diagnostic performance of the diagnosis model in variable working conditions. In this work, comparative experiments are conducted as for bearing and gearbox datasets under variable working conditions. The results indicate that DAFDMRT can show excellent performances in terms of fault diagnosis and generalization ability.
DingYJiaMMiaoQ, et al. 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.
2.
ZhangLZhangHCaiG.The multiclass fault diagnosis of wind turbine bearing based on multisource signal fusion and deep learning generative model. IEEE Trans Instrum Meas2022; 71: 1–12.
3.
XuYYanXSunB, et al. Deep coupled visual perceptual networks for motor fault diagnosis under nonstationary conditions. IEEE/ASME Trans Mechatron2022; 27(6): 4840–4850.
4.
ZhaoZLiuPGaoJ.Model-based fault diagnosis methods for systems with stochastic process -a survey. Neurocomputing2022; 513(7): 137–152.
5.
SoheilFHassanAAbdolrezaO.Incipient fault detection of helical gearbox based on variational mode decomposition and time synchronous averaging. Struct Health Monit2023; 22(2): 1494–1512.
6.
ChenMShaoHDouH, et al. Data augmentation and intelligent fault diagnosis of planetary gearbox using ILoF-GAN under extremely limited samples. IEEE Trans Reliab2022; 173: 1–9.
7.
WangJFuPJiS, et al. A light weight multisensory fusion model for induction motor fault diagnosis. IEEE/ASME Trans Mechatron2022; 27(6): 4932–4941.
8.
WangHXuJSunC, et al. Intelligent fault diagnosis for planetary gearbox using time-frequency representation and deep reinforcement learning. IEEE/ASME Trans Mechatron2021; 27(2): 985–998.
9.
ZhangSWangRSiY, et al. An improved convolutional neural network for three-phase inverter fault diagnosis. IEEE Trans Instrum Meas2022; 71: 1–15.
10.
TangHLiaoZChenP, et al. A robust deep learning network for low-speed machinery fault diagnosis based on multi-kernel and RPCA. IEEE/ASME Trans Mechatron2022; 27(3): 1522–1532.
11.
YuanRLvYLuZ, et al. Industrial fault diagnosis based on diverse variable weighted ensemble learning. Struct Health Monit2023; 22(2): 846–864.
12.
WangJLiTSunC, et al. Improved spiking neural network for intershaft bearing fault diagnosis. J Manuf Syst2022; 65: 208–219.
13.
YangJBaoWLiuY.Class metric regularized deep belief network with sparse representation for fault diagnosis. Int J Intell Syst2022; 37(9): 5996–6022.
14.
YanSShaoHXiaoY, et al. Hybrid robust convolutional autoencoder for unsupervised anomaly detection of machine tools under noises. Rob Comput Integr Manuf2023; 79: 102441.
15.
PangXXueXJiangW, et al. An investigation into fault diagnosis of planetary gearboxes using a bispectrum convolutional neural network. IEEE/ASME Trans Mechatron2020; 26(4): 2027–2037.
16.
ShenFHuiYYanR, et al. A new penalty domain selection machine enabled transfer learning for gearbox fault recognition. IEEE Trans Ind Electron2020; 67(10): 8743–8754.
17.
ZhouTHanTDroguettE.Towards trustworthy machine fault diagnosis: a probabilistic bayesian deep learning framework. Reliab Eng Syst Saf2022; 224(14): 108525.
18.
YuXLiangZWangY, et al. A wavelet packet transform-based deep feature transfer learning method for bearing fault diagnosis under different working conditions. Measurement2022; 201: 111597.
19.
LuNXiaoHSunY, et al. A new method for intelligent fault diagnosis of machines based on unsupervised domain adaptation. Neurocomputing2021; 427: 96–109.
20.
ZhouYDongYZhouH, et al. Deep dynamic adaptive transfer network for rolling bearing fault diagnosis with considering cross-machine instance. IEEE Trans Instrum Meas2021; 70: 1–11.
21.
XiaYShenCWangD, et al. Moment matching-based intraclass multisource domain adaptation network for bearing fault diagnosis. Mech Syst Signal Process2022; 168: 108697.
22.
QianQQinYLuoJ, et al. Deep discriminative transfer learning network for cross-machine fault diagnosis. J Manuf Syst2023; 186: 109884.
23.
XiaoYShaoHHanS, et al. Novel joint transfer network for unsupervised bearing fault diagnosis from simulation domain to experimental domain. IEEE-ASME Trans Mechatron2022; 27(6): 5254–5263.
24.
ZhengHYangYYinJ, et al. Deep domain generalization combining a priori diagnosis knowledge toward cross-domain fault diagnosis of rolling bearing. IEEE Trans Instrum Meas2021; 70: 1–11.
25.
LiXZhangWMaH, et al. Partial transfer learning in machinery cross-domain fault diagnostics using class-weighted adversarial networks. Neural Network2020; 129: 313–322.
26.
CaiFZhanMChaiQ, et al. Fault diagnosis of DAB converters based on ResNet with adaptive threshold denoising. IEEE Trans Instrum Meas2022; 71: 1–10.
27.
HeKZhangCRenS, et al. Deep residual learning for image recognition. In: Computer vision and pattern recognition (CVPR), Las Vegas, NV, USA. pp. 770–778.
28.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: Neural Information processing systems (NIPS), Long Beach, CA, USA, vol. 30, p. 03762.
29.
DevlinJChangMLeeK, et al. Bert: pre-training of deep bidirectional transformers for language understanding. In: The North American chapter of the association for computational linguistics (NAACL), Minneapolis, MN, USA.
30.
DosovitskiyABeyerLKolesnikovA, et al. An image is worth 16x16 words: transformers for image recognition at scale. In: International conference on learning representations (ICLR). (online).
31.
TayYTranVDehghaniM, et al. Transformer memory as a differentiable search index. Adv Neural Inf Process Syst2022; 35: 21831–21843.
32.
HanKWangYChenH, et al. A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell2022; 2(4): 12556.
33.
GrettonABorgwardtMRaschB, et al. A kernel two-sample test. J Mach Learning Res2012; 13(1): 723–773.
34.
GrettonASejdinovicDStrathmannH, et al. Optimal kernel choice for large-scale two-sample tests. In: Advances in neural information processing systems (NIPS), Lake Tahoe, CA, USA.
35.
BhavsarKVakhariaVChaudhariR, et al. A comparative study to predict bearing degradation using discrete wavelet transform (DWT), tabular generative adversarial networks (TGAN) and machine learning models. Machines2022; 10(3): 176–193.
36.
SilikANooriMAltabeyW, et al. Optimum wavelet selection for nonparametric analysis toward structural health monitoring for processing big data from sensor network: a comparative study. Struct Health Monit2022; 21(3): 803–825.
37.
YuKWangXChengY.A post-processing method for time-reassigned multisynchrosqueezing transform and its application in processing the strong frequency-varying signal. IEEE Trans Instrum Meas2021; 70: 1–11.
38.
GulatiAQinJChiuC, et al. Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:200508100, 2020.
39.
DingYJiaM.Convolutional transformer: an enhanced attention mechanism architecture for remaining useful life estimation of bearings. IEEE Trans Instrum Meas2022; 71: 1–10.
40.
YuXWangYLiangZ, et al. An adaptive domain adaptation method for rolling bearings’ fault diagnosis fusing deep convolution and self-attention networks. IEEE Trans Instrum Meas2023; 72: 1–14.
41.
PanSTsangIKwokJ, et al. Domain adaptation via transfer component analysis. IEEE Trans Neural Networks2011; 22(74): 199–210.
42.
LongMWangJDingG, et al. Transfer feature learning with joint distribution adaptation. In: IEEE international conference on computer vision (ICCV), Sydney, NSW, Australia, vol. 52, pp. 2200–2207.
43.
SunBSaenkoK.Deep CORAL: correlation alignment for deep domain adaptation. In: European conference on computer vision (ECCV), Amsterdam, Netherlands, vol. 9915, pp. 443–450.
44.
YanHDingYLiP, et al. Mind the class weight bias: weighted maximum mean discrepancy for unsupervised domain adaptation. In: Computer vision and pattern recognition (CVPR), Honolulu, HI, USA, vol. 36, pp. 945–954.
45.
TzengEHoffmanJSaenkoK, et al. Adversarial discriminative domain adaptation. In: Computer vision and pattern recognition (CVPR), Honolulu, HI, USA. vol. 42, pp. 2962–2971.
46.
ShaoSStephenMYanR, et al. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inf2019; 15(4): 2446–2455.
JhaRSwamiP.Fault diagnosis and severity analysis of rolling bearings using vibration image texture enhancement and multiclass support vector machines. Appl Acoust2021; 182: 108243.
49.
SutharVVakhariaVPatelV, et al. Detection of compound faults in ball bearings using multiscale-SinGAN, heat transfer search optimization, and extreme learning machine. Machines2022; 11(1): 29.
50.
IkhlefBRahmouneCToufikB, et al. Gearboxes fault detection under operation varying condition based on MODWPT, ant colony optimization algorithm and random forest classifier. Adv Mech Eng2021; 13(8): 16878140211043004.
51.
HeJLiXChenY, et al. Deep transfer learning method based on 1d-CNN for bearing fault diagnosis. Shock Vibr2021; 2021: 1–16.
52.
WangXShenCXiaM, et al. Multi-scale deep intra-class transfer learning for bearing fault diagnosis. Reliab Eng Syst Saf2020; 202: 107050.
53.
QianWLiSWangJ.A new transfer learning method and its application on rotating machine fault diagnosis under variant working conditions. IEEE Access2018; 6: 69907–69917.
