Condition monitoring and diagnosis of a bearing are very important for any rotating machine as it governs the safety while the machine is in operating condition. To construct a feature vector selection of suitable signal processing techniques is a challenge for vibration-based condition monitoring techniques. In the methodology proposed, Short Time Fourier Transform (STFT), Walsh Hadamard Transform (WHT) and Variable Mode Decomposition (VMD) are used to generate 2-D time-frequency spectrograms from the various fault conditions of bearing. When Deep learning techniques apply for fault diagnosis, a large amount of dataset is required for training of machine learning model. To overcome this issue single image Generative Adversarial Network (SinGAN) as a data augmentation technique, utilized for generating additional 2-D time-frequency spectrograms from various fault conditions of ball bearing. To detect fault severity, four deep learning algorithms, ResNet 34, ResNet50, VGG16, and MobileNetV2 are used as a classifier. Experiments are conducted on a rolling bearing dataset provided by the bearing data center of Case Western Reserve University (CWRU) for validating the utility of methodology proposed. Results show that the proposed methodology enables to detect fault severity level with high classification accuracy.
ZhangDEntezamiMStewartE, et al. Adaptive fault feature extraction from wayside acoustic signals from train bearings. J Sound Vib2018; 425: 221–238.
2.
VakhariaVGuptaVKKankarPK.Ball bearing fault diagnosis using supervised and unsupervised machine learning methods. Int J Acoust Vib2015; 20: 244–250.
3.
HeDWangXLiS, et al. Identification of multiple faults in rotating machinery based on minimum entropy deconvolution combined with spectral kurtosis. Mech Syst Signal Process2016; 81: 235–249.
4.
LiuHWangXLuC.Rolling bearing fault diagnosis based on LCD–TEO and multifractal detrended fluctuation analysis. Mech Syst Signal Process2015; 60-61: 273–288.
5.
BoškoskiPGašperinMPetelinD, et al. Bearing fault prognostics using Rényi entropy based features and Gaussian process models. Mech Syst Signal Process2015; 52-53: 327–337.
6.
VakhariaVGuptaVKankarPK.A multiscale permutation entropy based approach to select wavelet for fault diagnosis of ball bearings. J Vib Control2015; 21: 3123–3131.
7.
Manjurul IslamMMKimJ-M.Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector machines. Reliab Eng Syst Saf2019; 184: 55–66.
8.
DaveVSinghSVakhariaV.Diagnosis of bearing faults using multi fusion signal processing techniques and mutual information. Indian J Eng Mater Sci2020; 11: 878–888.
9.
GlowaczA.Fault diagnosis of electric impact drills using thermal imaging. Measurement2021; 171: 108815.
10.
ZhangSZhangSWangB, et al. Deep learning algorithms for bearing fault diagnostics – a comprehensive review. IEEE Access2020; 8: 29857–29881.
11.
WangJZhuangJDuanL, et al. A multi-scale convolution neural network for featureless fault diagnosis. In: 2016international symposium on flexible automation (ISFA). Cleveland, OH, USA: IEEE, pp.65–70.
12.
GuoXChenLShenC.Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis. Measurement2016; 93: 490–502.
13.
MaPZhangHFanW, et al. A novel bearing fault diagnosis method based on 2D image representation and transfer learning-convolutional neural network. Meas Sci Technol2019; 30: 055402.
14.
WangHC.Blind source extraction of rolling bearings’ multi-type faults based on self-learned sparse atomics. Proc IMechE, Part C: J Mechanical Engineering Science2019; 233: 4531–4542.
15.
ZairMRahmouneCBenazzouzD.Multi-fault diagnosis of rolling bearing using fuzzy entropy of empirical mode decomposition, principal component analysis, and SOM neural network. Proc IMechE, Part C: J Mechanical Engineering Science2019; 233: 3317–3328.
16.
DengFDingHYangS, et al. An improved deep residual network with multiscale feature fusion for rotating machinery fault diagnosis. Meas Sci Technol2021; 32: 024002.
17.
JoshuvaASugumaranV.A lazy learning approach for condition monitoring of wind turbine blade using vibration signals and histogram features. Measurement2020; 152: 107295.
18.
GangadharNKumarHNarendranathS, et al. Condition monitoring of single point cutting tools based on machine learning approach. Int J Acoust Vib2018; 23: 131–137.
AlShormanOIrfanMSaadN, et al. A review of artificial intelligence methods for condition monitoring and fault diagnosis of rolling element bearings for induction motor. Shock Vib2020; 2020: 1–20.
GoodfellowIJPouget-AbadieJMirzaM, et al. Generative adversarial networks. ArXiv14062661 Cs stat. http://arxiv.org/abs/1406.2661 (2014, accessed 19 December 2020).
24.
WangJHanBBaoH, et al. Data augment method for machine fault diagnosis using conditional generative adversarial networks. Proc IMechE, Part J: J Engineering Tribology2020; 234: 2719–2727.
25.
HuangNChenQCaiG, et al. Fault diagnosis of bearing in wind turbine gearbox under actual operating conditions driven by limited data with noise labels. IEEE Trans Instrum Meas2021; 70: 1–10.
26.
ShaoSWangPYanR.Generative adversarial networks for data augmentation in machine fault diagnosis. Comput Ind2019; 106: 85–93.
27.
GaoXDengFYueX.Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty. Neurocomputing2020; 396: 487–494.
28.
LiQChenLShenC, et al. Enhanced generative adversarial networks for fault diagnosis of rotating machinery with imbalanced data. Meas Sci Technol2019; 30: 115005.
29.
BeauchampKG.Applications of walsh and related functions: with an introduction to sequency theory. London: Academic Press, 1984.
30.
FinoA.Unified matrix treatment of the fast Walsh-Hadamard transform. IEEE Trans Comput1976; C–25: 1142–1146.
31.
DragomiretskiyKZossoD.Variational mode decomposition. IEEE Trans SIGNAL Process2014; 62: 14.
32.
GuedidiAGuettafACardosoAJM.Bearing faults classification based on variational mode decomposition and artificial neural network. Piscataway, NJ: IEEE, 2019.
33.
DeyNBorahSBaboR, et al. Social network analytics. Amsterdam: Elsevier, 2019.
34.
HeKZhangXRenS, et al. Deep residual learning for image recognition. ArXiv151203385 Cs. http://arxiv.org/abs/1512.03385 (2015, accessed 21 December 2020).
35.
Kankar PK, Sharma SC and Harsha SP. Fault diagnosis of ball bearings using continuous wavelet transform. Applied Soft Computing 2011; 11: 2300–2312
36.
SimonyanKZissermanA. Very deep convolutional networks for large-scale image recognition. ArXiv14091556 Cs, http://arxiv.org/abs/1409.1556 (2015, accessed 21 December 2020).
37.
SandlerMHowardAZhuM, et al. MobileNetV2: inverted residuals and linear bottlenecks. In: 2018.IEEE/CVF conference on computer vision and pattern recognition. Salt Lake City, UT: IEEE, pp.4510–4520.
38.
ShuklaRKankarPKPachoriRB.Automated bearing fault classification based on discrete wavelet transform method. Life Cycle Reliab Saf Eng2021; 10: 99–111.
39.
ZhaoBYuanQ.Improved generative adversarial network for vibration-based fault diagnosis with imbalanced data. Meas J Int Meas Confed2021; 169: 108522.
40.
ChenZMauricioALiW, et al. A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks. Mech Syst Signal Process2020; 140: 106683.
41.
ZhouQLiYTianY, et al. A novel method based on nonlinear auto-regression neural network and convolutional neural network for imbalanced fault diagnosis of rotating machinery. Meas J Int Meas Confed2020; 161: 107880.
42.
LiuHYaoDYangJ, et al. Lightweight convolutional neural network and its application in rolling bearing fault diagnosis under variable working conditions. Sens Switz2019; 19: 1–20.
