Rotating machinery fault diagnostics has received a lot of attention in recent years. As a result, there has been an increase in research interest in rotating machine intelligent fault detection, especially when using measurement from multi-sensors. However, an accurate fault diagnosis is still challenged based on nonlinear and non-stationary vibration signals. On the other hand, not enough research has been done on structural information fusion from multi-sensor measurement due to the complexity of spatial–temporal correlation. This paper explores the use of vibration signals in multi-sensor measurement fusion for rotating machinery fault diagnostics, and a method using a cross-attention-based dual-branch graph neural network (CA-GNN) is proposed. First, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is used to decompose vibration signals. Variational mode decomposition is then used to further deconstruct the highest-frequency subsequence after its parameters have been optimized using the whale optimization algorithm. Next, we build the CA-GNN, which contains two space branches for high- and low-frequency signals after initially creating the graph using multiple sensor data sets. Information across both branches for high- and low-frequency components can then be efficiently fused. Lastly, two experimental scenarios are used to illustrate the suggested technique and assess its viability and accuracy for rotating machinery fault diagnosis. Results indicate that the proposed method can diagnose rotating machinery health issues with an average accuracy of up to 99%, indicating that the method’s performance can fulfill real-world requirements.
LiHWangWHuangP, et al. Fault diagnosis of rolling bearing using symmetrized dot pattern and density-based clustering. Measurement2020; 152: 107293.
2.
KibreteFEngida WoldemichaelDShimels GebremedhenH.Multi-Sensor data fusion in intelligent fault diagnosis of rotating machines: a comprehensive review. Measurement2024; 232; 114658.
3.
SunYLiS-YWangX.Bearing fault diagnosis based on EMD and improved Chebyshev distance in SDP image. Measurement2021; 176: 109100.
4.
ZhaoXZYeBY.Similarity of signal processing effect between Hankel matrix-based SVD and wavelet transform and its mechanism analysis. Mech Syst Signal Process2009; 23(4): 1062–1075.
5.
QiaoZJPanZR.SVD principle analysis and fault diagnosis for bearings based on the correlation coefficient. Meas Sci Technol2015; 26(8): 085014.
6.
ZhaoMJiaXD.A novel strategy for signal denoising using reweighted SVD and its applications to weak fault feature enhancement of rotating machinery. Mech Syst Signal Process2017; 94: 129–147.
7.
PengZChuF-I.Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mech Syst Signal Process2004; 18: 199–221.
8.
LinJQuL.Feature extraction based on morlet wavelet and its application for mechanical fault diagnosis. J Sound Vib2000; 234: 135–148.
9.
AmeidTMenacerATalhaouiH, et al. Discrete wavelet transform and energy eigen value for rotor bars fault detection in variable speed field-oriented control of induction motor drive. ISA Trans2018; 79: 217–231.
10.
XuYGDengYJZhaoJY, et al. A novel rolling bearing fault diagnosis method based on empirical wavelet transform and spectral trend. IEEE Trans Instrum Meas2020; 69(6): 2891–2904.
11.
HanBLiCSZhouYQ, et al. Second-order multisynchrosqueezing wavelet transform for bearing fault detection. J Vib Eng Technol2022; 10(4): 1541–1559.
12.
WangSYTianJLiangP, et al. Single and simultaneous fault diagnosis of gearbox via wavelet transform and improved deep residual network under imbalanced data. Eng Appl Artif Intell2024; 133: 108146.
13.
LiuDDCuiLLChengWD.A review on deep learning in planetary gearbox health state recognition: methods, applications, and dataset publication. Meas Sci Technol2024; 35(1): 012002.
14.
YuKLinTRTanJW.A bearing fault diagnosis technique based on singular values of EEMD spatial condition matrix and Gath-Geva clustering. Appl Acoust2017; 121: 33–45.
15.
LiHLiuTWuX, et al. Application of EEMD and improved frequency band entropy in bearing fault feature extraction. ISA Trans2019; 88: 170–185.
16.
LiHLiuTWuX, et al. Research on test bench bearing fault diagnosis of improved EEMD based on improved adaptive resonance technology. Measurement2021; 185: 109986.
17.
DamineYBessousNMegherbiAC, et al. Early bearing fault detection using EEMD and three-sigma rule denoising method. Mechanika2023; 29(4): 302–308.
18.
ZhangYYZhangYLiH, et al. Semi-supervised diagnosis method for coupling faults of key rotating components based on EEMD-KPCA under cross working conditions. Meas Sci Technol2024; 35(2): 25014.
19.
HanTLiuQNZhangL, et al. Fault feature extraction of low speed roller bearing based on Teager energy operator and CEEMD. Measurement2019; 138: 400–408.
20.
LuYFXieRLiangSY.CEEMD-assisted kernel support vector machines for bearing diagnosis. Int J Adv Manuf Technol2020; 106(7–8): 3063–3070.
21.
ZhongTQuJFFangXY, et al. The intermittent fault diagnosis of analog circuits based on EEMD-DBN. Neurocomputing2021; 436: 74–91.
22.
GaoSZLiTCZhangYM, et al. Fault diagnosis method of rolling bearings based on adaptive modified CEEMD and 1DCNN model. ISA Trans2023; 140: 309–330.
23.
XiaoyunGKunpengFZehengZ, et al. Multiple fault diagnosis for rolling bearings method employing CEEMD-GCN based on horizontal visibility graph. Meas Sci Technol2023; 34(3): 035022.
24.
FuLWangSChenR, et al. Intelligent fault diagnosis of rolling bearings based on an improved empirical wavelet transform and ResNet under variable conditions. IEEE Sens J2023; 23(23): 29097–29108.
25.
ChengHCZhangYMLuWJ, et al. A bearing fault diagnosis method based on VMD-SVD and fuzzy clustering. Int J Pattern Recognit Artif Intell2019; 33(12): 1950018.
26.
YuMYGuoGHFangMH, et al. Intershaft bearing compound faults identification by using VMD and a new index: the activity parameter in Hjorth parameters. Nonlinear Dyn2022; 110(3): 2657–2672.
27.
WangSQFengZG.Multi-sensor fusion rolling bearing intelligent fault diagnosis based on VMD and ultra-lightweight GoogLeNet in industrial environments. Digit Signal Process2024; 145: 104306.
28.
GuJPengYXLuH, et al. A novel fault diagnosis method of rotating machinery via VMD, CWT and improved CNN. Measurement2022; 200: 111635.
29.
HeDQZouXYJinZZ, et al. Intelligent fault diagnosis of train bearing based on ISTOA-VMD and SE-WDCNN. J Vib Control2023; 30(15–16): 3572–3583.
30.
LiJXLiuZWQiuM, et al. Fault diagnosis model of rolling bearing based on parameter adaptive VMD algorithm and Sparrow Search Algorithm-Based PNN. Eksploat Niezawodn2023; 25(2): 163547.
31.
LiMXYanCLiuW, et al. Fault diagnosis model of rolling bearing based on parameter adaptive AVMD algorithm. Appl Intell2023; 53(3): 3150–3165.
32.
LiuHHHanMH.A fault diagnosis method based on local mean decomposition and multi-scale entropy for roller bearings. Mech Mach Theory2014; 75: 67–78.
33.
LiuZWHeZJGuoW, et al. A hybrid fault diagnosis method based on second generation wavelet de-noising and local mean decomposition for rotating machinery. ISA Trans2016; 61: 211–220.
34.
LiYBLiangXHYangYT, et al. Early Fault Diagnosis of Rotating Machinery by Combining Differential Rational Spline-Based LMD and K-L Divergence. IEEE Trans Instrum Meas2017; 66(11): 3077–3090.
35.
WangCGanMZhuCA.Fault feature extraction of rolling element bearings based on wavelet packet transform and sparse representation theory. J Intell Manuf2018; 29(4): 937–951.
36.
SunRBYangZBZhaiZ, et al. Sparse representation based on parametric impulsive dictionary design for bearing fault diagnosis. Mech Syst Signal Process2019; 122: 737–753.
37.
AnBTWangSBYanRQ, et al. Adaptive robust noise modeling of sparse representation for bearing fault diagnosis. IEEE Trans Instrum Meas2021; 70: 1.
38.
MiaoMQSunYHYuJB.Deep sparse representation network for feature learning of vibration signals and its application in gearbox fault diagnosis. Knowl Based Syst2022; 240: 108116.
39.
ZhangCLQiangYHouW, et al. High-fidelity fault signature extraction of rolling bearings via nonconvex regularized sparse representation enhanced by flexible analytical wavelet transform. Struct Health Monit2024; 23(5): 2869–2891.
40.
HuYBaoWJTuXT, et al. An adaptive spectral kurtosis method and its application to fault detection of rolling element bearings. IEEE Trans Instrum Meas2020; 69(3): 739–750.
41.
HashimSShakyaP.A spectral kurtosis based blind deconvolution approach for spur gear fault diagnosis. ISA Trans2023; 142: 492–500.
42.
LiPHDangJJiaR, et al. Research on wind turbine composite fault decoupling and slight fault extraction based on continuous spectral kurtosis deconvolution. J Vib Eng Technol2024; 12(3): 2975–2986.
43.
SunJYanCWenJ.Intelligent Bearing fault diagnosis method combining compressed data acquisition and deep learning. IEEE Trans Instrum Meas2018; 67: 185–195.
44.
HeZShaoHWangP, et al. Deep transfer multi-wavelet auto-encoder for intelligent fault diagnosis of gearbox with few target training samples. Knowl Based Syst2020; 191: 105313.
45.
XuFHuangZYangF, et al. Constructing a health indicator for roller bearings by using a stacked auto-encoder with an exponential function to eliminate concussion. Appl Soft Comput2020; 89: 106119.
46.
ZhuHChengJZhangC, et al. Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings. Appl Soft Comput2020; 88: 106060.
47.
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.
48.
RenZGuoJ.Fault diagnosis using signal processing and deep learning-based image pattern recognition. Technisches Messen2024; 91(2): 129–138.
49.
ChoudharyAMishraRKFatimaS, et al. Multi-input CNN based vibro-acoustic fusion for accurate fault diagnosis of induction motor. Eng Appl Artif Intell2023; 120: 105872.
50.
ZhangWLiCPengG, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mech Syst Signal Process2018; 100: 439–453.
51.
MaMSunCChenXF.Discriminative deep belief networks with ant colony optimization for health status assessment of machine. IEEE Trans Instrum Meas2017; 66(12): 3115–3125.
52.
WangYLPanZFYuanXF, et al. A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network. ISA Trans2020; 96: 457–467.
53.
YanXALiuYJiaMP.Multiscale cascading deep belief network for fault identification of rotating machinery under various working conditions. Knowl Based Syst2020; 193: 105484.
54.
AnZLiSWangJ, et al. A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network. ISA Trans2020; 100: 155–170.
55.
ZhangY-HZhouTHuangX, et al. Fault diagnosis of rotating machinery based on recurrent neural networks. Measurement2021; 171(3): 108774.
56.
AnYZhangKLiuQ, et al. Rolling bearing fault diagnosis method base on periodic sparse attention and LSTM. IEEE Sens J202; 22: 12044–12053.
57.
ChenYJRaoMFengK, et al. Physics-Informed LSTM hyperparameters selection for gearbox fault detection. Mech Syst Signal Process2022; 171: 108907.
58.
AnYYZhangKChaiY, et al. Gaussian mixture variational-based transformer domain adaptation fault diagnosis method and its application in bearing fault diagnosis. IEEE Trans Ind Inform2024; 20(1): 615–625.
59.
ZhouYZhengHXHuangX, et al. Graph neural networks: taxonomy, advances, and trends. ACM Trans Intell Syst Technol2022; 13(1): 15.
60.
ZhouJCuiGZhangZ, et al. Graph neural networks: a review of methods and applications. AI Open2020; 1: 57–81.
61.
WangZWuZYLiXQ, et al. Attention-aware temporal-spatial graph neural network with multi-sensor information fusion for fault diagnosis. Knowl Based Syst2023; 278: 110891.
62.
LiTFZhouZLiSN, et al. The emerging graph neural networks for intelligent fault diagnostics and prognostics: a guideline and a benchmark study. Mech Syst Signal Process2022; 168: 108653.
63.
XiaMLiTXuL, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE/ASME Trans Mechatron2018; 23: 101–110.
64.
MaMSunCChenX.Deep coupling autoencoder for fault diagnosis with multimodal sensory data. IEEE Trans Ind Inform2018; 14: 1137–1145.
65.
HeYTangH-SRenY, et al. A deep multi-signal fusion adversarial model based transfer learning and residual network for axial piston pump fault diagnosis. Measurement2022; 192(2): 110889.
66.
WangLCaoHYeZ, et al. DVGTformer: a dual-view graph Transformer to fuse multi-sensor signals for remaining useful life prediction. Mech Syst Signal Process2024; 207(1–2): 110935.
67.
SongLHWangCFanJS, et al. Elastic structural analysis based on graph neural network without labeled data. Comput Aided Civil Infrastruct Eng2023; 38(10): 1307–1323.
68.
ParisiFRuggieriSLovreglioR, et al. On the use of mechanics-informed models to structural engineering systems: application of graph neural networks for structural analysis. Structures2024; 59: 105712.
69.
YangYGLiTFSunC, et al. Graph attention U-Net to fuse multi-sensor signals for long-tailed distribution fault diagnosis. Eng Appl Artif Intell2023; 126: 106927.
70.
LiCYMoLKwohCK, et al. Noise-robust multi-view graph neural network for fault diagnosis of rotating machinery. Mech Syst Signal Process2025; 224: 112025.
71.
PoongadanSLineeshMC.Non-linear time series prediction using improved CEEMDAN, SVD and LSTM. Neural Process Lett2024; 56(4): 164.
72.
LiuZKLvKLZhengC, et al. A fault diagnosis method for rolling element bearings based on ICEEMDAN and Bayesian network. J Mech Sci Technol2022; 36(5): 2201–2212.
73.
ColominasMASchlotthauerGTorresME.Improved complete ensemble EMD: a suitable tool for biomedical signal processing. Biomed Signal Process Control2014; 14: 19–29.
74.
MirjaliliSMLewisA.The whale optimization algorithm. Adv Eng Softw2016; 95: 51–67.
75.
ShaoSYMcAleerSYanRQ, et al. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inform2019; 15(4): 2446–2455.
76.
RezazadehNPerfettoDde OliveiraM, et al. A fine-tuning deep learning framework to palliate data distribution shift effects in rotary machine fault detection. Struct Health Monit. Epub ahead of print 30November2024. DOI: 10.1177/14759217241295951.
