Repetitive transients excited by local damage to rotating machinery are often submerged in severe background noise. Extracting repetitive fault transients under noise interference is key to bearing failure detection and damage tracking. Variational multiharmonic duality mode pursuit is an effective tool for accurately extracting repetitive fault transients and eliminating irrelevant noise. However, its input parameters typically require manual configuration, and its performance is significantly influenced by these settings. To handle the above problem, this article proposes a dual-domain filtering approach named enhanced spectral structure-guided variational model (ESSGVM) for bearing failure detection. First, according to the frequency component differences in the spectrum, the spectral structure-guided variational mode extraction is introduced to decompose the vibration signal without introducing prior parameters. Then, the optimal mode is selected by a novel blind feature indicator which takes into account both the impulsiveness and periodicity of transients feature. To further strengthen the transients feature and suppress in-band interference, adaptive variational multiharmonic duality mode pursuit is performed to refine repetitive fault transients from the enhanced signal while maintaining transient amplitude. A synergistic combination of dual-domain filtering enables precise spectrum separation and accurate transient extraction, significantly improving fault feature clarity and detection accuracy. Simulations and experiments showcase the superior ability of the ESSGVM to detect bearing failure.
RaiAUpadhyaySH.A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol Int2016; 96: 289–306.
2.
LiuHYuanRLvY, et al. Multivariate phase space warping-based degradation tracking and remaining useful life prediction of rolling bearings. IEEE Trans Reliab2024; 73(3): 1592–1605.
3.
YuanRLvYWangT, et al. Looseness monitoring of multiple M1 bolt joints using multivariate intrinsic multiscale entropy analysis and Lorentz signal-enhanced piezoelectric active sensing. Struct Health Monit2022; 21: 2851–2873.
4.
LeiYLiNGuoL, et al. Machinery health prognostics: a systematic review from data acquisition to RUL prediction. Mech Syst Signal Process2018; 104: 799–834.
5.
YuanRLvYLuZ, et al. Robust fault diagnosis of rolling bearing via phase space reconstruction of intrinsic mode functions and neural network under various operating conditions. Struct Health Monit2022; 22: 846–864.
6.
WangHSunWSunW, et al. A novel tool condition monitoring based on Gramian angular field and comparative learning. Int J Hydromechatronics2023; 6: 93–107.
7.
XiCYangJLiangX, et al. An improved gated convolutional neural network for rolling bearing fault diagnosis with imbalanced data. Int J Hydromechatronics2023; 6: 108–132.
8.
VashishthaGChauhanSSehriM, et al. A roadmap to fault diagnosis of industrial machines via machine learning: a brief review. Measurement2025; 242: 116216.
9.
AntoniJ.The spectral kurtosis: a useful tool for characterising non-stationary signals. Mech Syst Signal Process2006; 20: 282–307.
10.
AntoniJ.The infogram: entropic evidence of the signature of repetitive transients. Mech Syst Signal Process2016; 74: 73–94.
11.
MoshrefzadehAFasanaA.The Autogram: an effective approach for selecting the optimal demodulation band in rolling element bearings diagnosis. Mech Syst Signal Process2018; 105: 294–318.
12.
ZhangKChenPYangM, et al. The Harmogram: a periodic impulses detection method and its application in bearing fault diagnosis. Mech Syst Signal Process2022; 165: 108374.
13.
MiaoYZhangBLinJ, et al. A review on the application of blind deconvolution in machinery fault diagnosis. Mech Syst Signal Process2022; 163: 108202.
14.
ZhangZHuangWLiaoY, et al. Bearing fault diagnosis via generalized logarithm sparse regularization. Mech Syst Signal Process2022; 167: 108576.
15.
QiuTHuangWZhangZ, et al. A new approach for sparse optimization with Moreau envelope to extract bearing fault feature. Mech Syst Signal Process2024; 216: 111493.
16.
VashishthaGChauhanSZimrozR.Fault detection of the rotating machines through optimized orthogonal matching pursuit by golden jackal optimization. Struct Health Monit2025.
17.
PengZZhikePShiqianC.Review of signal decomposition theory and its applications in machine fault diagnosis. J Mech Eng2020; 56: 91–107.
18.
HuangRXiaJZhangB, et al. Compound fault diagnosis for rotating machinery: state-of-the-art, challenges, and opportunities. J Dyn Monit Diagn2023; 2(1): 13–29.
19.
HelmDTimuskM.Wavelet denoising applied to hardware redundant systems for rolling element bearing fault detection. J Dyn Monit Diagn2023; 2: 133–143.
20.
LvYYuanRSongG.Multivariate empirical mode decomposition and its application to fault diagnosis of rolling bearing. Mech Syst Signal Process2016; 81: 219–234.
21.
BerroucheYVashishthaGChauhanS, et al. Local damage detection in rolling element bearings based on a single ensemble empirical mode decomposition. Knowl Based Syst2024; 301: 112265.
22.
LiXMaJWangX, et al. An improved local mean decomposition method based on improved composite interpolation envelope and its application in bearing fault feature extraction. ISA Trans2020; 97: 365–383.
23.
WangLLiuZ.An improved local characteristic-scale decomposition to restrict end effects, mode mixing and its application to extract incipient bearing fault signal. Mech Syst Signal Process2021; 156: 107657.
24.
WangDZhaoYYiC, et al. Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings. Mech Syst Signal Process2018; 101: 292–308.
25.
ZhaoQWangJYinJ, et al. Peak envelope spectrum Fourier decomposition method and its application in fault diagnosis of rolling bearings. Measurement2022; 198: 111450.
26.
MiaoYZhangBLiC, et al. Feature mode decomposition: new decomposition theory for rotating machinery fault diagnosis. IEEE Trans Ind Electron2023; 70: 1949–1960.
27.
ChauhanSVashishthaGKumarR, et al. An adaptive feature mode decomposition based on a novel health indicator for bearing fault diagnosis. Measurement2024; 226: 114191.
28.
DragomiretskiyKZossoD.Variational mode decomposition. IEEE Trans Signal Process2014; 62: 531–544.
29.
ZhangXMiaoQZhangH, et al. A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery. Mech Syst Signal Process2018; 108: 58–72.
30.
MiaoYZhaoMLinJ.Identification of mechanical compound-fault based on the improved parameter-adaptive variational mode decomposition. ISA Trans2019; 84: 82–95.
31.
LiJChengXLiQ, et al. Adaptive energy-constrained variational mode decomposition based on spectrum segmentation and its application in fault detection of rolling bearing. Signal Process2021; 183: 108025.
32.
HuangYLinJLiuZ, et al. A modified scale-space guiding variational mode decomposition for high-speed railway bearing fault diagnosis. J Sound Vib2019; 444: 216–234.
33.
JiangXWangJShenC, et al. An adaptive and efficient variational mode decomposition and its application for bearing fault diagnosis. Struct Health Monit2020; 20: 2708–2725.
34.
NazariMSakhaeiSMNazariM, et al. Variational mode extraction: a new efficient method to derive respiratory signals from ECG. IEEE J Biomed Health Inform2018; 22: 1059–1067.
35.
JiangTZhangQZhangJ, et al. Variational multi-harmonic duality mode pursuit method for extracting repetitive transient components from vibration signals. Measurement2023; 225: 113987.
36.
LiCLiuYLiuZ, et al. A new fault diagnosis method for wheelset-bearing system based on VME convergence tendency diagram. Meas Sci Technol2023; 34: 085107.
37.
WangXJiangXSongQ, et al. Spectral structure inducing efficient variational model for enhancing bearing fault feature. Signal Process2024; 216: 109304.
38.
SaidiLBen AliJBenbouzidM, et al. The use of SESK as a trend parameter for localized bearing fault diagnosis in induction machines. ISA Trans2016; 63: 436–447.
39.
LiJYaoXWangH, et al. Periodic impulses extraction based on improved adaptive VMD and sparse code shrinkage denoising and its application in rotating machinery fault diagnosis. Mech Syst Signal Process2019; 126: 568–589.
40.
WangLLiuZCaoH, et al. Subband averaging kurtogram with dual-tree complex wavelet packet transform for rotating machinery fault diagnosis. Mech Syst Signal Process2020; 142: 106755.
41.
MiaoYWangJZhangB, et al. Practical framework of Gini index in the application of machinery fault feature extraction. Mech Syst Signal Process2022; 165: 108333.
42.
WangD.Spectral L2/L1 norm: a new perspective for spectral kurtosis for characterizing non-stationary signals. Mech Syst Signal Process2018; 104: 290–293.
43.
ZhaoMJiaX.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.
44.
ChengJYangYHuN, et al. A noise reduction method based on adaptive weighted symplectic geometry decomposition and its application in early gear fault diagnosis. Mech Syst Signal Process2021; 149: 107351.
45.
ZhengKYaoDShiY, et al. An adaptive group sparse feature decomposition method in frequency domain for rolling bearing fault diagnosis. ISA Trans2023; 138: 562–581.
46.
ChenYMaoZHouX, et al. Noise-robust adaptive feature mode decomposition method for accurate feature extraction in rotating machinery fault diagnosis. Mech Syst Signal Process2024; 211: 111213.
47.
ZhangXZhangZWangJ, et al. Reweighted-Kurtogram with sub-bands rearranged and ensemble dual-tree complex wavelet packet transform for bearing fault diagnosis. Struct Health Monit2022; 21: 2951–2967.
48.
YaoRJiangHLiX, et al. Bearing incipient fault feature extraction using adaptive period matching enhanced sparse representation. Mech Syst Signal Process2022; 166.
49.
ZhaoZWuSQiaoB, et al. Enhanced sparse period-group lasso for bearing fault diagnosis. IEEE Trans Ind Electron2019; 66: 2143–2153.
50.
ZhangCLiuYWanF, et al. Adaptive filtering enhanced windowed correlated kurtosis for multiple faults diagnosis of locomotive bearings. ISA Trans2020; 101: 421–429.
51.
LvYZhangQYuanR, et al. Local lowest-rank dynamic mode decomposition for transient feature extraction of rolling bearings. ISA Trans2023; 133: 539–558.
52.
PangBNazariMSunZ, et al. An optimized variational mode extraction method for rolling bearing fault diagnosis. Struct Health Monit2021; 21: 558–570.
53.
BorghesaniPPennacchiPChattertonS.The relationship between kurtosis- and envelope-based indexes for the diagnostic of rolling element bearings. Mech Syst Signal Process2014; 43: 25–43.
54.
DaiJSoHC.Group-sparsity learning approach for bearing fault diagnosis. IEEE Trans Ind Inform2022; 18: 4566–4576.
55.
ZhouWFengZXuYF, et al. Empirical Fourier decomposition: an accurate signal decomposition method for nonlinear and non-stationary time series analysis, Mech Syst Signal Process2022; 163: 108155.
56.
JiangXWangJShiJ, et al. A coarse-to-fine decomposing strategy of VMD for extraction of weak repetitive transients in fault diagnosis of rotating machines. Mech Syst Signal Process2019; 116: 668–692.
57.
JunYTaoYANNaipengLI, et al. XJTU-SY rolling element bearing accelerated life test datasets: a tutorial. J Mech Eng2019; 55: 1–6.
58.
ChenBSongDZhangW, et al. A novel spectral coherence-based envelope spectrum for railway axle-box bearing damage identification. Struct Health Monit2022; 22: 879–896.
