The empirical wavelet transform (EWT) method has shown a broad application prospect in the fault diagnosis of rotating machinery. However, it has the problem that the number of modes needs to be preset, and the spectrum segmentation is unreasonable under strong noise. To this end, this paper proposes a modal decomposition method of adaptively constructing empirical wavelet filter banks, which is named adaptive empirical wavelet filter banks (AEWFMD). Firstly, the spectrum trend line is constructed by calculating the energy mean of the Stockwell Transform spectrum along the frequency slice. Secondly, the proposed optimized fault feature energy ratio (OFCER) is used as the objective function, and the smoothing window of the order-statistic filtering is optimized to obtain the optimal spectral line. Then, taking the position of the minimum point of the optimal spectral line as the boundary, it divides the spectrum scientifically and adaptively constructs the empirical wavelet filter bank to reconstruct the modal components. Finally, the optimal modal component is selected based on the OFCER index, and its normalized envelope spectrum analysis is performed. Simulation and experimental results show that AEWFMD can adaptively determine the segmentation boundary and the number of modes. Compared with EWT, empirical Fourier decomposition (EFD), and Feature Mode decomposition (FMD) methods, AEWFMD performs better in single and compound fault feature extraction, which provides a new path for bearing fault diagnosis in engineering practice.
ZhouCXingLZouW, et al. EMGGDFuRDE: enhancive multiscale generalized Gaussian distribution fuzzy Renyi dispersion entropy and its application in wind turbines fault diagnosis. Mech Syst Signal Process2025; 231:112636. https://doi.org/10.1016/j.ymssp.2025.112636
2.
SongLJinYLinT, et al. Remaining useful life prediction method based on the spatiotemporal graph and GCN nested parallel route model. IEEE Trans Instrum Meas2024; 73: 1–12. https://doi.org/10.1109/TIM.2024.3370801
3.
LvSLiuSLiH, et al. A hybrid method combining Lévy process and neural network for predicting remaining useful life of rotating machinery. Adv Eng Inform2024; 61: 102490. https://doi.org/10.1016/j.aei.2024.102490
4.
FanCPengYShenY, et al. Variable scale multilayer perceptron for helicopter transmission system vibration data abnormity beyond efficient recovery. Eng Appl Artif Intell2024; 133: 108184. https://doi.org/10.1016/j.engappai.2024.108184
5.
CaoWMengZLiJ, et al. A bearing fault diagnosis method for unknown operating conditions based on differentiated feature extraction. ISA Trans2025; 156: 468–478. https://doi.org/10.1016/j.isatra.2024.10.024
6.
LiSPengYShenY, et al. Rolling bearing fault diagnosis under data imbalance and variable speed based on adaptive clustering weighted oversampling. Reliab Eng Syst Saf2024; 244: 109938. https://doi.org/10.1016/j.ress.2024.109938
7.
WangRJiangHZhuK, et al. A deep feature enhanced reinforcement learning method for rolling bearing fault diagnosis. Adv Eng Inform2022; 54: 101750. https://doi.org/10.1016/j.aei.2022.101750
8.
MengZWangYLiuJ, et al. Velocity-matching extraction demodulation transform for nonstationary signal analysis of rolling bearings. IEEE Trans Instrum Meas2025; 74: 1–11. https://doi.org/10.1109/TIM.2024.3509535
9.
SunWMengZLiuJ, et al. A novel compound fault diagnosis for rolling bearing based on sparse harmonic feature mode decomposition and enhanced spectral amplitude modulation. Mech Syst Signal Process2025; 239: 113343. https://doi.org/10.1016/j.ymssp.2025.113343
10.
QinYZhaoLChenY, et al. Learnable wavelet-driven physically interpretable networks for bearing fault diagnosis under variable speed. Mech Syst Signal Process2025; 237: 113121. https://doi.org/10.1016/j.ymssp.2025.113121
11.
FangCChangQHuX, et al. A digital twin-enabled domain adaptation network for cross-space fault diagnosis of roller bearings. Mech Syst Signal Process2025; 236: 113053. https://doi.org/10.1016/j.ymssp.2025.113053
12.
MahelaOPKhanBAlhelouHH, et al. Power quality assessment and event detection in distribution network with wind energy penetration using Stockwell Transform and fuzzy clustering. IEEE Trans Ind Inf2020; 16: 6922–6932. https://doi.org/10.1109/TII.2020.2971709
13.
ZhangYMHuangZXiaY. An improved multi-taper S-Transform method to estimate evolutionary spectrum and time-varying coherence of nonstationary processes. Mech Syst Sig Process2023; 198:110386. https://doi.org/10.1016/j.ymssp.2023.110386
14.
ZhangJYangDRenWX, et al. Time-varying characteristics analysis of vehicle-bridge interaction system based on modified S-transform reassignment technique. Mech Syst Sig Process2021; 160: 107807. https://doi.org/10.1016/j.ymssp.2021.107807
15.
YingWLiYNomanK, et al. Stockwell transform spectral amplitude modulation method for rotating machinery fault diagnosis. Mech Syst Signal Process2025; 223: 111884. https://doi.org/10.1016/j.ymssp.2024.111884
16.
LiuYXiangHJiangZ, et al. Second-order transient-extracting S transform for fault feature extraction in rolling bearings. Reliab Eng Syst Saf2023; 230: 108955. https://doi.org/10.1016/j.ress.2022.108955
17.
XieSXiaoLHuangH, et al. Attention-augmented stockwell transform and convolutional neural network framework for electroencephalogram-based multi-class classification of Frontotemporal Dementia. Inform Fusion2025; 123: 103267. https://doi.org/10.1016/j.inffus.2025.103267
18.
XiaoFWuMSongK, et al. Diagnosis of distribution network fault using multiresolution S-transform and modified convolution neural network. Int J Electr Power Energy Syst2024; 162: 110294. https://doi.org/10.1016/j.ijepes.2024.110294
19.
ShiLZhangZYangY, et al. A method for food origin identification and ingredient content prediction based on S-transform and multi-task deep learning. J Food Compos Anal2025; 147: 108123. https://doi.org/10.1016/j.jfca.2025.108123
20.
LuoJJShaoHDLinJ, et al. Meta-learning with elastic prototypical network for fault transfer diagnosis of bearings under unstable speeds. Reliab Eng Syst Saf2024; 245: 110001. https://doi.org/10.1016/j.ress.2024.110001
21.
JiangXXLiXGWangQ, et al. Multi-sensor data fusion-enabled semi-supervised optimal temperature-guided PCL framework for machinery fault diagnosis. Informat Fusion2024; 101: 16. https://doi.org/10.1016/j.inffus.2023.102005
22.
ZhaoDZCuiLLLiuDD. Bearing weak fault feature extraction under time-varying speed conditions based on frequency matching demodulation transform. IEEE ASME Trans Mechatron2023; 28(3): 1627–1637. https://doi.org/10.1109/TMECH.2022.3215545
23.
HuangNEShenZLongSR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond Ser A1998; 454. https://doi.org/10.1098/rspa.1998.0193
24.
WuZHuangNE. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Data Sci Adapt Anal2011; 1: 1–41. https://doi.org/10.1142/S1793536909000047
25.
YehJRShiehJSHuangNE. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method. Adv Data Sci Adapt Anal2010; 2(2): 135–156. https://doi.org/10.1142/S1793536910000422
26.
TorresMEColominasMASchlotthauerG, et al. A complete ensemble empirical mode decomposition with adaptive noise. In: 2011 IEEE international conference on acoustic, speech and signal processing (ICASSP), Prague Congress Center, Prague, Czech Republic, 22–27 May 2011, vol. 2, no. 1, pp. 4144–4147. IEEE.
27.
YingWMZhengJDPanHY, et al. Permutation entropy-based improved uniform phase empirical mode decomposition for mechanical fault diagnosis. Digital Signal Process2021; 117: 103167. https://doi.org/10.1016/j.dsp.2021.103167
NazariMSakhaeiSM. Variational mode extraction: a new efficient method to derive respiratory signals from ECG. IEEE J Biomed Health Inf2018; 22(4): 1059–1067. https://doi.org/10.1109/JBHI.2017.2734074
30.
PanHYYangYLiX, et al. Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis. Mech Syst Signal Process2019; 114: 189–211. https://doi.org/10.1016/j.ymssp.2018.05.019
31.
PanHYZhangYChengJ, et al. Symplectic geometry transformation-based periodic segment method: algorithm and applications. IEEE Trans Instrum Meas2023; 72: 1–8. https://doi.org/10.1109/TIM.2023.3271006
32.
ChengJYangYWuXW, et al. Symplectic Ramanujan mode decomposition and its application to compound fault diagnosis of bearings. ISA Trans2022; 129:495–503. https://doi.org/10.1016/j.isatra.2021.12.013
33.
GuoJCSiZTXiangJW. Cycle kurtosis entropy guided symplectic geometry mode decomposition for detecting faults in rotating machinery. ISA Trans2023; 138: 546–561. https://doi.org/10.1016/j.isatra.2023.03.026
34.
LiSQYanCFHouYF, et al. Compound fault diagnosis method for rolling bearings based on enhanced MED and adaptive periodized symplectic geometry mode decomposition. Struct Health Monit2025: 1: 31. https://doi.org/10.1177/14759217251314703
WangDZhaoYYiC, et al. Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings. Mech Syst Signal Process2018; 101: 292–308. https://doi.org/10.1016/j.ymssp.2017.08.038
37.
PanJChenJIZiYY, et al. Mono-component feature extraction for mechanical fault diagnosis using modified empirical wavelet transform via data-driven adaptive Fourier spectrum segment. Mech Syst Signal Process2016; 72: 160–183. https://doi.org/10.1016/j.ymssp.2015.10.017
38.
LuoZJLiuTYanSZ, et al. Revised empirical wavelet transform based on auto-regressive power spectrum and its application to the mode decomposition of deployable structure. J Sound Vib2018; 431: 70–87. https://doi.org/10.1016/j.jsv.2018.06.001
39.
HuYLiFLiH, et al. An enhanced empirical wavelet transform for noisy and non-stationary signal processing. Digit Signal Process2017; 60: 220–229. https://doi.org/10.1016/j.dsp.2016.09.012
40.
XuYGDengYJZhaoJY, et al. A novel rolling bearing fault diagnosis method based on empirical wavelet transform and spectral trend. IEEE Trans Instrum Meas2019; 69(6): 2891–2904. https://doi.org/10.1109/TIM.2019.2928534
41.
ZhouWFengZXuYF, et al. Empirical Fourier decomposition: an accurate signal decomposition method for nonlinear and non-stationary time series analysis. Mech Syst Sig Process2022; 163: 108155. https://doi.org/10.1016/j.ymssp.2021.108155
42.
MiaoYHZhangBLiC, et al. Feature mode decomposition: new decomposition theory for rotating machinery fault diagnosis. IEEE Trans Ind Electron2022; 70(2): 1949–1960. https://doi.org/10.1109/TIE.2022.3156156
43.
StockwellRGMansinhaLLoweRP. Localization of the complex spectrum: the S transform. IEEE Trans Signal Process1996; 44(4): 998–1001. https://doi.org/10.1109/78.492555
LuZYanXWangZ, et al. Compound fault diagnosis of rolling bearings based on AVMD and IMOMEDA. Meas Sci Technol2024; 35: 066124. https://doi.org/10.1088/1361-6501/ad34f0
46.
YuMDuJXuX, et al. A multi-strategy enhanced dung Beetle optimization for real-world engineering problems and UAV path planning. Alex Eng J2025; 15: 1432. https://doi.org/10.1007/s10462-025-11235-5
47.
ChengYWangSChenB, et al. An improved envelope spectrum via candidate fault frequency optimizationgram for bearing fault diagnosis. J Sound Vibr2022; 523: 116746. https://doi.org/10.1016/j.jsv.2022.116746
48.
GaoCLiuSZhangX. A new method of adaptive Fourier modal decomposition and its application to rolling bearing fault diagnosis. Struct Health Monit. Epub ahead of print 2025. https://doi.org/10.1177/14759217251347534
49.
WangHYanCZhaoY, et al. SEACKgram: a targeted method of optimal demodulation-band selection for compound faults diagnosis of rolling bearing. Struct Health Monit2024; 24(1): 223–242. https://doi.org/10.1177/14759217241235337
50.
LiSYanCHouY, et al. Isolation and identification of rolling bearing compound faults based on adaptive periodized singular spectrum analysis and Rényi entropy. Meas Sci Technol2024; 35(6): 066102. https://doi.org/10.1088/1361-6501/ad2bca
51.
QiuHLeeJLinJ, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics. J Sound Vibr2006; 289: 1066–1090. https://doi.org/10.1016/j.jsv.2005.03.007
52.
PangBZhangHChengTS, et al. Spectral variational mode extraction and its application in fault detection of rolling bearing. Struct Health Monit2023; 22(16): 449–471. https://doi.org/10.1177/14759217221098670
53.
ChengYWangZChenB, et al. An improved complementary ensemble empirical mode decomposition with adaptive noise and its application to rolling element bearing fault diagnosis. ISA Trans2019; 91: 218–234. https://doi.org/10.1016/j.isatra.2019.01.038
