A rotor bearing fault diagnosis method based on the Improved Flow Direction Algorithm (IFDA) optimized by the Variational Mode Extraction (VME) and the Continuous Wavelet Transform (CWT) - Multi Scale Hybrid Attention Network (MHAN) is proposed to address complex working environment problems, difficulty in identifying fault features due to the noise interference, and a low accuracy in fault diagnosis caused by the single information dimension of model input data and the insufficient feature extraction ability of the model. Firstly, this method uses weighted envelope spectral kurtosis as the fitness function and optimizes the center frequency and penalty factor of the VME using the IFDA. Input the optimal parameter combination into the VME to extract fault characteristic sensitive signals. Then, the one-dimension vibration signal is processed using the CWT to generate the time-frequency image data with significant fault features, which is used as the model input. And propose using the multi-scale mixed attention (MHA) for the feature extraction of data. Build a CWT-MHAN model to achieve fault diagnosis of the rotor bearing system. The experimental results show that the IFDA-VME can effectively extract fault feature-sensitive signals from signals contaminated by the strong noise, and its average feature energy ratio is significantly higher than other algorithms. The CWT-MHAN model can achieve single and composite fault diagnosis of rotor bearing systems and demonstrate a high diagnostic accuracy.
YuYXuJZhangM, et al. Comparative analysis of wavelet analysis and wavelet packet analysis in bearing fault diagnosis. Coal Mine Mac. 2019; 40(12): 170–173.
2.
HuangNEShenZLongSR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Royal Soc London. Series A: Math Phys Eng Sci. 1998; 454(1971): 903–995. https://doi.org/10.1098/rspa.1998.0193
3.
WuZHuangNE. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal. 2009; 1(01): 1–41. https://doi.org/10.1142/s1793536909000047
4.
YehJRShiehJSHuangNE. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method. Adv Adapt Data Anal. 2010; 2(02): 135–156. https://doi.org/10.1142/s1793536910000422
GaoYZhangJ. Bearing fault diagnosis based on EMD and FastICA. Machinery Design & Manufacture. 2024; 06: 48–52.
7.
LiuZDingKLinH, et al. A novel impact feature extraction method based on EMD and sparse decomposition for gear local fault diagnosis. Machines. 2022; 10(4): 242. https://doi.org/10.3390/machines10040242
8.
DaiTZhangYZhangK, et al. The research progress of empirical mode decomposition and mode mixing elimination. Appl Elec Tech. 2019; 45(3): 7–12.
9.
ZhaoYFanYLiH, et al. Rolling bearing composite fault diagnosis method based on EEMD fusion feature. J Mech Sci Technol. 2022; 36(9): 4563–4570. https://doi.org/10.1007/s12206-022-0819-x
10.
LyuSZENGYLIX, et al. Fault diagnosis of pump units based on EEMD and LCTDBO-BP. J Drain Irr Mach Eng. 2025; 43(1): 38–44.
11.
QinNWangTHuangD, et al. An open-switch fault diagnosis method for single-phase PWM rectifier based on CEEMD-DNN. Int J Control Autom Syst. 2023; 21(10): 3430–3442. https://doi.org/10.1007/s12555-021-0905-3
12.
ChenGYanCMengJ, et al. Improved VMD-FRFT based on initial center frequency for early fault diagnosis of rolling element bearing. Meas Sci Technol. 2021; 32(11): 115024. https://doi.org/10.1088/1361-6501/ac1613
YangYLiuHHanL, et al. A feature extraction method using VMD and improved envelope spectrum entropy for rolling bearing fault diagnosis. IEEE Sens J. 2023; 23(4): 3848–3858. https://doi.org/10.1109/jsen.2022.3232707
15.
NazariMSakhaeiNazariM, et al. Variational mode extraction: a new efficient method to derive respiratory signals from ECG. IEEE J Biomed Health Inform. 2017; 22(4): 1059–1067. https://doi.org/10.1109/JBHI.2017.2734074
16.
YangLWuYWangJ, et al. Research on recurrent neural network. J Comput Appl. 2018; 38(S2): 1–6+26.
17.
LiSLiCHuJ, et al. A research review on fault diagnosis of mechanical equipment based on deep belief network. Mod Manuf Eng. 2020; 10: 156–162+142.
18.
MaoWFengWLiuY, et al. A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mech Syst Signal Process. 2021; 150: 107233. https://doi.org/10.1016/j.ymssp.2020.107233
19.
WangZZhangZQinJ, et al. Review of mechanical fault diagnosis technology based on convolutional neural network. J Comput Appl. 2022; 42(04): 1036–1043.
20.
HuangTZhangQTangX, et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems. Artif Intell Rev. 2022; 55(2): 1289–1315. https://doi.org/10.1007/s10462-021-09993-z
21.
ZhaoJZhaoZYangS, et al. Rolling bearing fault diagnosis based on residual connection and 1D-CNN. J Vib Shock. 2021; 40(10): 1–6.
22.
XieFWangGWangL, et al. Fault diagnosis method of gearbox based on STFT and 2DCNN-SVM. Noise and Vibration Control. 2024; 44(04): 103–109.
23.
YuanJHanTTangJ, et al. An approach to intelligent fault diagnosis of rolling BearingUsing wavelet time-frequency representations and CNN. Mach Des Res. 2017; 33(02): 93–97.
24.
LiuYanCLiuY, et al.Multiscale residual antinoise network via interpretable dynamic recalibration mechanism for rolling bearing fault diagnosis with few samples. IEEE Sens J2023; 23(24): 31425–31439. https://doi.org/10.1109/jsen.2023.3328007
25.
HuangHuangHu, et al. UDDGN: domain-independent compact boundary learning method for universal diagnosis domain generation. IEEE Trans Instrum Meas. 2025; 74.
26.
Huang, Hu, Wang, et al. OAIFAN: a noise-robust discriminative feature unification framework for cross-speed fault transfer diagnosis. IEEE Trans Instrum Meas. 2025; 74.
Wang, Xu, Yan, et al. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN. IEEE Trans Instrum Meas. 2019; 69(5): 2377–2389.
29.
LiuZhaoSZhangZ, et al. ECG signal delineation based on multi-scale channel attention convolutional neural network. International conference on image, vision and intelligent systems. Singapore: Springer Nature, 2023, pp. 465–478.
30.
GongBDuX. Research on analog circuit fault diagnosis based on CBAM-CNN. In: 2021 IEEE International Conference on Electronic Technology, Communication and Information (ICETCI).IEEE, 2021, pp. 258–261.
31.
WangZHanHZhuJ, et al. A fault diagnosis method for aviation high-speed bearings driven by multi-head attention. J Vib Shock. 2023; 42(04): 295–305.
32.
TianAZhangYMaC, et al. Noise-robust machinery fault diagnosis based on self-attention mechanism in wavelet domain. Measurement. 2023; 207: 112327. https://doi.org/10.1016/j.measurement.2022.112327
33.
KaramiHAnarakiMVFarzinS, et al. Flow Direction Algorithm (FDA): a novel optimization approach for solving optimization problems. Comput Ind Eng. 2021; 156: 107224. https://doi.org/10.1016/j.cie.2021.107224
TaoHZhangD, et al. Early fault diagnosis of rolling bearings based on ParametricOptimized VMD-MCKD. Noise Vib Control. 2024; 44(06): 156–164.
36.
WooSParkJLeeJ Y, et al.Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV). ECVA,2018, pp. 3–19.
37.
Guo, Lu, Hou, et al. Segnext: rethinking convolutional attention design for semantic segmentation. Adv Neural Inf Process Syst. 2022; 35: 1140–1156.
38.
HuJShenLSunG. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition.IEEE, 2018, pp. 7132–7141.
39.
WangQWuBZhuP, et al.ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.IEEE, 2020, pp. 11534–11542.
YangXS. Firefly algorithms for multimodal optimization. International symposium on stochastic algorithms. Springer Berlin Heidelberg, 2009, pp. 169–178.
LiangKZhaoMLinJ, et al. Maximum average kurtosis deconvolution and its application for the impulsive fault feature enhancement of rotating machinery. Mech Syst Signal Process. 2021; 149: 107323. https://doi.org/10.1016/j.ymssp.2020.107323
46.
DengLiuQDengY, et al.An improved method to construct basic probability assignment based on the confusion matrix for classification problem. Inf Sci2016; 340: 250–261. https://doi.org/10.1016/j.ins.2016.01.033
