Effective fault diagnosis is critical for the safe and efficient operation of rotating machinery in nuclear facilities. This paper proposes a deep learning-based approach that integrates multi-domain signal analysis and transfer learning to classify rotor conditions as either healthy or faulty. Vibration signals are transformed into 2D images and processed using pretrained models: ResNet50, GoogleNet, and a custom Deep Convolutional Neural Network (DCNN). Signal transforms, including the Fast Fourier Transform (FFT), Fractional Fourier Transform, Short-Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT), and Fractional Wavelet Synchrosqueezing Transform, are applied to enhance feature representation. ResNet50 achieved up to 100% accuracy on the primary dataset and over 99% on the secondary dataset. GoogleNet and DCNN also demonstrated excellent performance, achieving accuracies of up to 100% in specific domains. Additionally, transfer learning using YamNet enabled effective sound-based classification of vibration signals. These results show that using advanced signal processing together with deep learning can lead to very accurate and quick fault detection in important safety situations.
AhmedHOANandiAK. Vibration image representations for fault diagnosis of rotating machines: a review. Machines2022; 10(12): 1113.
2.
AhmedHNandiAK. Condition monitoring with vibration signals: compressive sampling and learning algorithms for rotating machines. Hoboken, NJ, USA: John Wiley & Sons, 2020.
3.
AhmedHWongMNandiA. Intelligent condition monitoring method for bearing faults from highly compressed measurements using sparse over-complete features. Mech Syst Signal Process2018; 99: 459–477.
4.
AhmedHOANandiAK. Three-stage hybrid fault diagnosis for rolling bearings with compressively sampled data and subspace learning techniques. IEEE Trans Ind Electron2019; 66: 5516–5524.
5.
QuYHeDYoonJ, et al.Gearbox tooth cut fault diagnostics using acoustic emission and vibration sensors—a comparative study. Sensors (Peterb, NH)2014; 14: 1372–1393.
6.
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: 106861.
7.
Resendiz-OchoaESaucedo-DorantesJJBenitez-RangelJP, et al.Novel methodology for condition monitoring of gear wear using supervised learning and infrared thermography. Appl Sci2020; 10: 506.
8.
AhmedHOWongMDNandiAK. Classification of bearing faults combining compressive sampling, laplacian score, and support vector machine. In Proceedings of the IECON 2017—43rd Annual Conference of the IEEE Industrial Electronics Society. Beijing, China: IEEE, 2017, pp. 8053–8058.
9.
AhmedHOWongMDNandiAK. Effects of deep neural network parameters on classification of bearing faults. In Proceedings of the IECON 2016—42nd Annual Conference of the IEEE Industrial Electronics Society 2016. Florence, Italy: IEEE, 2016, pp. 6329–6334.
10.
SeeraMWongMLDNandiAK. Classification of ball bearing faults using a hybrid intelligent model. Appl Soft Comput2017; 57: 427–435.
11.
ZhangLNandiAK. Fault classification using genetic programming. Mech Syst Signal Process2007; 21: 1273–1284.
12.
JackLBNandiAK. Support vector machines for detection and characterization of rolling element bearing faults. Proc Inst Mech Eng Part C J. Mech. Eng. Sci2001; 215: 1065–1074.
13.
NayanaBRGeethanjaliP. Analysis of statistical time-domain features effectiveness in identification of bearing faults from vibration signal. IEEE Sens J2017; 17: 5618–5625.
14.
SreejithBVermaAKSrividyaA. Fault diagnosis of rolling element bearing using time-domain features and neural networks. InProceedings of the IEEE Region 10 and the Third International Conference on Industrial and Information Systems. Kharagpur, India: IEEE, 2008, Vol. 8, pp. 1–6.
15.
BouguerriouNHaritopoulosMCapdessusC, et al.Novel cyclostationarity-based blind source separation algorithm using second order statistical properties: theory and application to the bearing defect diagnosis. Mech Syst Signal Process2005; 19: 1260–1281.
16.
ElashaFMbaDRuiz-CarcelC. A comparative study of adaptive filters in detecting a naturally degraded bearing within a gearbox. Mech Syst Signal Process2016; 3: 1–8.
17.
AyazE. Autoregressive modeling approach of vibration data for bearing fault diagnosis in electric motors. J. Vibroeng2014; 16: 2130–2138.
18.
LinHCYeYC. Reviews of bearing vibration measurement using fast Fourier transform and enhanced fast Fourier transform algorithms. Adv Mech Eng2019; 11: 1687814018816751.
19.
FarokhzadS. Vibration based fault detection of centrifugal pump by fast Fourier transform and adaptive neuro-fuzzy inference system. J Mech Eng Technol2013; 36: 82–87.
20.
de Jesus Romero-TroncosoR. Multirate signal processing to improve FFT-based analysis for detecting faults in induction motors. IEEE Trans Ind Inf2016; 13: 1291–1300.
21.
TianJMorilloCAzarianMH, et al.Motor bearing fault detection using spectral kurtosis-based feature extraction coupled with K-nearest neighbor distance analysis. IEEE Trans Ind Electron2015; 63: 1793–1803.
22.
AhmedHNandiAK. Compressive sampling and feature ranking framework for bearing fault classification with vibration signals. IEEE Access2018; 6: 44731–44746.
23.
WangYXiangJMarkertR, et al.Spectral kurtosis for fault detection, diagnosis and prognostics of rotating machines: a review with applications. Mech Syst Signal Process2016; 66-67: 679–698.
24.
ShakyaPDarpeAKKulkarniMS. Vibration-based fault diagnosis in rolling element bearings: ranking of various time, frequency and time-frequency domain data-based damage identi cation parameters. Int J Cond Monitor2013; 3: 53–62.
25.
WangLLiuZMiaoQ, et al.Time–frequency analysis based on ensemble local mean decomposition and fast kurtogram for rotating machinery fault diagnosis. Mech Syst Signal Process2018; 103: 60–75.
26.
YuJLvJ. Weak Fault feature extraction of rolling bearings using local mean decomposition-based multilayer hybrid denoising. IEEE Trans Instrum Meas2017; 66: 3148–3159.
27.
PandhareVSinghJLeeJ. Convolutional neural network based rolling-element bearing fault diagnosis for naturally occurring and progressing defects using time-frequency domain features. In Proceedings of the 2019 Prognostics and System Health Management Conference (PHM-Paris). Paris, France: IEEE, 2019, pp. 320–326.
28.
JiaFLeiYLinJ, et al.Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Syst Signal Process2016; 72–73: 303–315.
29.
AhmedHOANandiAK. Connected components-based colour image representations of vibrations for a two-stage fault diagnosis of roller bearings using convolutional neural networks. Chin J Mech Eng2021; 34: 37.
30.
LeiYYangBJiangX, et al.Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
31.
HouBWangDWangY, et al.Adaptive weighted signal preprocessing technique for machine health monitoring. IEEE Trans Instrum Meas2021; 70: 1–11.
32.
BhaktaKSikderNNahidAA, et al., Fault diagnosis of induction motor bearing using Cepstrum based preprocessing and ensemble learning algorithm. In: 2019 International conference on electrical, computer and communication engineering (ECCE). Piscataway: IEEE, 2019, pp. 1–6.
33.
FangHDengJZhaoB, et al.LEFE-Net: a lightweight efficient feature extraction network with strong robustness for bearing fault diagnosis. IEEE Trans Instrum Meas2021; 70: 1–11.
34.
LeeJQiuHYuG, et al.Rexnord Technical Services. Bearing data set. NASA ames prognostics data repository. Moffett Field, CA: NASA Ames Research Center, 2007.
35.
GoyalDPablaB. The vibration monitoring methods and signal processing techniques for structural health monitoring: a review. Arch Comput Methods Eng2016; 23: 585–594.
36.
BrighamEOMorrowRE. The fast Fourier transform. IEEE Spectr1967; 4: 63–70.
37.
RomanssiniMde AguirrePCCCompassi-SeveroL, et al.A review on vibration monitoring techniques for predictive maintenance of rotating machinery. Eng2023; 4: 1797–1817.
38.
PatilSSGaikwadJA. Vibration analysis of electrical rotating machines using FFT: a method of predictive maintenance. In Proceedings of the 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT). India: Tiruchengode, 2013, pp. 1–6.
39.
KhadersabAShivakumarS. Vibration analysis techniques for rotating machinery and its effect on bearing faults. Procedia Manuf2018; 20: 247–252.
40.
LinHCYeYCHuangBJ, et al.Bearing vibration detection and analysis using enhanced fast Fourier transform algorithm. Adv Mech Eng2016; 8: 1687814016675080.
41.
KumarBKDiwakarGSatynarayanaM. Determination of unbalance in rotating machine using vibration signature analysis. Int. J. Mod. Eng. Res2012; 2: 3415–3421.
42.
SaleemMADiwakarGSatyanarayanaM. Detection of unbalance in rotating machines using shaft deflection measurement during its operation. IOSR J Mech Civ Eng2012; 3: 8–20.
43.
de Sá Só MartinsDHCVianaDPde LimaAA, et al.Diagnostic and severity analysis of combined failures composed by imbalance and misalignment in rotating machines. Int J Adv Manuf Technol2021; 114: 3077–3092.
44.
BahriMAbdul KarimSA. Fractional Fourier transform: main properties and inequalities. Mathematics (Basel)2023; 11: 1234.
DaubechiesI. The wavelet transform, time-frequency localization and signal analysis. IEEE Trans Inf Theor1990; 36: 961–1005.
47.
BurrusCSGopinathRAGuoH, et al.Introduction to wavelets and wavelet transforms a primer. Hoboken, NJ, USA: Prentice Hall, 1998, p. 1.
48.
SaxenaMBannetOOGuptaM, et al.Bearing Fault monitoring using CWT based vibration signature. Procedia Eng2016; 144: 234–241.
49.
ShenCWangDKongF, et al.Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier. Measurement2013; 46: 1551–1564.
50.
ShiHChenJSiJ, et al.Fault diagnosis of rolling bearings based on a residual dilated pyramid network and full convolutional denoising autoencoder. Sensors (Peterb, NH)2020; 20: 5734.
51.
XuGLiuMJiangZ, et al.Bearing Fault diagnosis method based on deep convolutional neural network and random forest ensemble learning. Sensors (Peterb, NH)2019; 19: 1088.
52.
TangSYuanSZhuY, et al.An integrated deep learning method towards fault diagnosis of hydraulic axial piston pump. Sensors (Peterb, NH)2020; 20: 6576.
53.
NguyenVCHoangDTTranXT, et al.A bearing fault diagnosis method using multi-branch deep neural network. Machines2021; 9: 345.
54.
OberlinTMeignenSPerrierV. Second-order synchrosqueezing transform or invertible reassignment? Towards ideal time-frequency representations. IEEE Trans Signal Process2015; 63(5): 1335–1344.
55.
ShiJChenGZhaoY, et al.Synchrosqueezed fractional wavelet transform: a new high-resolution time-frequency representation. IEEE Trans Signal Process2023; 71: 264–278.
56.
MisraSKumarSSayyadS, et al.Fault detection in induction motor using time domain and spectral imaging-based transfer learning approach on vibration data. Sensors (Peterb, NH)2022; 22: 8210.
57.
SaadMHHashimaSElArabyWS, et al.Early diagnosis of COVID-19 images using optimal CNN hyperparameters. Diagnostics2023; 13(1): 76.
58.
DoSSongKDChungJW. Basics of deep learning: a radiologist’s guide to understanding published radiology articles on deep learning. Korean J Radiol2020; 21: 33–41.
59.
SayyadSKumarSBongaleA, et al.Estimating remaining useful life in machines using artificial intelligence: a scoping review. Libr Philos Pract2021; 2021: 1–26.
60.
ElArabyWSMadianAH. Performance comparison for COVID-19 chest X-ray images classification based on different CNNs. International Journal of Electrical Engineering and Computer Science2022; 4: 58–65.
61.
LuCWangYRagulskisM, et al.Fault diagnosis for rotating machinery: a method based on image processing. PLoS One2016; 11: e0164111.
62.
LiXZhangWDingQ, et al.Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation. J Intell Manuf2020; 31: 433–452.
63.
CuiWMengGWangA, et al.Application of rotating machinery fault diagnosis based on deep learning. Shock Vibrat2021; 1: 3083190.
64.
JiangWWangCZouJ, et al.Application of deep learning in fault diagnosis of rotating machinery. Processes2021; 9(6): 919.
65.
TamaBAVaniaMLeeS, et al.Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals. Artif Intell Rev2023; 56: 4667–4709.
