Recently, deep learning has been a predominantly used technique for intelligent fault diagnosis of industrial machines. It has accomplished satisfactory performance as well. However, noise is present in a real-life industrial working environment, and the operational load also constantly changes. This work proposes a Time-Frequency Fusion Network (TFFNet) for intelligent fault diagnosis. It is robust convolutional neural network based deep-learning algorithm and eliminates the signal processing required for denoising. The success of the developed model is verified in the presence of real-time noisy conditions and under a load-varying environment. The proposed model attained 99.98% accuracy in a noisy environment and 98.6% average accuracy under six cases of domain shift. Finally, the results are compared with past studies using accuracy as a performance indicator.
Ben AliJFnaiechNSaidiL, et al. (2015) Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals. Applied Acoustics89: 16–27.
2.
AmarouayacheIIESaadiMNGuersiN, et al. (2020) Bearing fault diagnostics using eemd processing and convolutional neural network methods. The International Journal of Advanced Manufacturing Technology107: 4077–4095.
3.
AwrejcewiczJKryskoVMitskievichS, et al. (2021) Principal component analysis in the linear theory of vibrations: continuous mechanical systems driven by different kinds of external noise. Proceedings of the Institution of Mechanical Engineers - Part C: Journal of Mechanical Engineering Science235(1): 48–62.
4.
BuchaiahSShakyaP (2022a) Automatic incipient fault detection and health state assessment of rolling element bearings using pruned exact linear time method. Journal of Vibration and Control29: 10775463221131843.
5.
BuchaiahSShakyaP (2022b) Bearing fault diagnosis and prognosis using data fusion based feature extraction and feature selection. Measurement188: 110506.
CheCWangHNiX, et al. (2020) Intelligent fault diagnosis method of rolling bearing based on stacked denoising autoencoder and convolutional neural network. Industrial Lubrication and Tribology72(7): 947–953.
8.
ChenHYLeeCH (2020) Vibration signals analysis by explainable artificial intelligence (XAI) approach: application on bearing faults diagnosis. IEEE Access8: 134246–134256.
9.
ChoudharyAMianTFatimaS (2021) Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images. Measurement176: 109196.
10.
DhamandeLSChaudhariMB (2018) Compound gear-bearing fault feature extraction using statistical features based on time-frequency method. Measurement125: 63–77.
11.
GaoYLiuXHuangH, et al. (2021) A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems. ISA Transactions108: 356–366.
12.
GlorotXBordesABengioY (2011) Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. Fort Lauderdale, FL, USA: JMLR Workshop and Conference Proceedings, 315–323.
13.
GuYKZhouXQYuDP, et al. (2018) Fault diagnosis method of rolling bearing using principal component analysis and support vector machine. Journal of Mechanical Science and Technology32: 5079–5088.
14.
GuoLGaoHHuangH, et al. (2016) Multifeatures fusion and nonlinear dimension reduction for intelligent bearing condition monitoring. Shock and Vibration2016: 4632562.
15.
HwangDHYounYWSunJH, et al. (2015) Support vector machine based bearing fault diagnosis for induction motors using vibration signals. Journal of Electrical Engineering and Technology10(4): 1558–1565.
16.
IoffeSSzegedyC (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning. Lille, France: PMLR, 448–456.
17.
JiaFLeiYLinJ, et al. (2016) Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing72-73: 303–315.
18.
JiangWWangCZouJ, et al. (2021) Application of deep learning in fault diagnosis of rotating machinery. Processes9(6): 919.
19.
JinZHanQZhangK, et al. (2020) An intelligent fault diagnosis method of rolling bearings based on Welch power spectrum transformation with radial basis function neural network. Journal of Vibration and Control26(9-10): 629–642.
20.
KamatPSugandhiR (2020) Bibliometric Analysis of Bearing Fault Detection Using Artificial Intelligence. Library Philosophy and Practice (e-journal), 1–21. Available at: https://digitalcommons.unl.edu/libphilprac/4350
21.
LiSHuangJ (2020) Non-Gaussian noise induced stochastic resonance in FitzHugh–Nagumo neural system with time delay. AIP Advances10(2): 025310.
22.
LiSLiuGTangX, et al. (2017) An ensemble deep convolutional neural network model with improved ds evidence fusion for bearing fault diagnosis. Sensors17(8): 1729.
23.
MaLDingYWangZ, et al. (2021) An interpretable data augmentation scheme for machine fault diagnosis based on a sparsity-constrained generative adversarial network. Expert Systems with Applications182: 115234.
24.
MishraSKShakyaPBabureddyV, et al. (2021) An approach to improve high-frequency resonance technique for bearing fault diagnosis. Measurement178: 109318.
25.
MovsessianAGarcía CavaDTcherniakD (2021) An artificial neural network methodology for damage detection: demonstration on an operating wind turbine blade. Mechanical Systems and Signal Processing159: 107766.
26.
PatelAShakyaP (2021) Spur gear crack modelling and analysis under variable speed conditions using variational mode decomposition. Mechanism and Machine Theory164: 104357.
27.
PeetersCGuillaumePHelsenJ (2016) Vibration-based bearing fault detection on experimental wind turbine gearbox data. PHM Society European Conference3(1). doi: 10.36001/phme.2016.v3i1.1620.
28.
ShaoHJiangHLiX, et al. (2018) Rolling bearing fault detection using continuous deep belief network with locally linear embedding. Computers in Industry96: 27–39.
29.
ShenSLuHSadoughiM, et al. (2021) A physics-informed deep learning approach for bearing fault detection. Engineering Applications of Artificial Intelligence103: 104295.
30.
ShengS (2016) Wind Turbine Gearbox Reliability Database, Condition Monitoring, and Operation and Maintenance Research Update. Golden, CO, USA: National Renewable Energy Lab.(NREL). Technical report.
31.
SrivastavaNHintonGKrizhevskyA, et al. (2014) Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research15(1): 1929–1958.
32.
Van der MaatenLHintonG (2008) Visualizing data using t-SNE. Journal of Machine Learning Research9(11): 2579–2605.
33.
VermaNKGuptaVKSharmaM, et al. (2013) Intelligent condition based monitoring of rotating machines using sparse auto-encoders. In: 2013 IEEE Conference on Prognostics and Health Management (PHM). Gaithersburg, MD, USA: IEEE, 1–7.
34.
WoolfP (2009) Chemical Process Dynamics and Controls. Open Textbook Library. Ann Arbor, MI, USA: University of Michigan Engineering Controls Group.
35.
YuGLiCZhangJ (2013) A new statistical modeling and detection method for rolling element bearing faults based on alpha–stable distribution. Mechanical Systems and Signal Processing41(1-2): 155–175.
36.
ŻakGTeuerleMWyłomańskaA, et al. (2017) Measures of dependence for alpha-stable distributed processes and its application to diagnostics of local damage in presence of impulsive noise. Shock and Vibration2017: 1963769.
37.
ZhangWPengGLiC, et al. (2017) A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors17(2): 425.
38.
ZhangWLiCPengG, et al. (2018) A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical Systems and Signal Processing100: 439–453.
