In industrial scenarios, decomposition methods play a pivotal role in extracting fault information from intense background noise, which is essential for mitigating operational downtime risks. However, the performance of such decomposition methods is highly dependent on critical parameters, and inappropriate parameter tuning can significantly degrade diagnostic accuracy in practical applications. Feature mode decomposition (FMD) is widely used in fault diagnosis due to its adaptive decomposition capability; nevertheless, the unreasonable parameters setting in FMD method, lead to a wrong decomposition result. This article introduces an innovative adaptive FMD fault diagnosis approach, designed to eliminate the need for manual parameter tuning. By leveraging spectral difference preprocessing and precise parameter estimation, the method effectively achieves fault feature extraction. Simulation and experimental validation results demonstrate that the method outperforms up-to-date decomposition methods in terms of noise suppression and fault feature extraction. This adaptive FMD approach provides a robust solution for mechanical health monitoring in complex industrial environments, contributing to improved operational reliability and reduced maintenance costs.
HengAZhangSTanA CC, et al. Rotating machinery prognostics: state of the art, challenges and opportunities. Mech Syst Signal Pr2009; 23(3): 724–739.
2.
LiangPFYuZZWangB, et al. Fault transfer diagnosis of rolling bearings across multiple working conditions via subdomain adaptation and improved vision transformer network. Adv Eng Inform2023; 57: 102075.
3.
ChenZXHeCBLiuY B, et al. Incipient fault feature extraction of rolling bearing based on optimized singular spectrum decomposition. IEEE Sens J2021; 21(18): 20362–20374.
4.
WangBLeiYGLINP, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE T Reliab2020; 69(1): 401–412.
5.
ZhuHXJiangHKYaoRH, et al. Rolling bearing incipient fault feature extraction using impulse-enhanced sparse time-frequency representation. Meas Sci Technol2023; 34(10): 105124.
6.
WangZYYaoLGCaiYW, et al. Mahalanobis semi-supervised mapping and beetle antennae search based support vector machine for wind turbine rolling bearings fault diagnosis. Renew Energ2020; 155: 1312–1327.
7.
HouBCWangDXiaTB, et al. Difference mode decomposition for adaptive signal decomposition. Mech Syst Signal Pr2023; 191: 110203.
8.
WangYZWuJHYuZY, et al. A structurally re-parameterized convolution neural network-based method for gearbox fault diagnosis in edge computing scenarios. Eng Appl Artif Intel2023; 126: 107091.
9.
GuoJCLiuYYangRG, et al. Ensemble difference mode decomposition based on transmission path elimination technology for rotating machinery fault diagnosis. Mech Syst Signal Pr2024; 212: 111330.
10.
ShaoHDZhouXDLinJ, et al. Few-shot cross-domain fault diagnosis of bearing driven by Task-supervised ANIL. IEEE Internet Things2024; 11(13): 22892–22902.
11.
ZhaoMJiaXD.A novel strategy for signal denoising using reweighted SVD and its applications to weak fault feature enhancement of rotating machinery. Mech Syst Signal Pr2017; 94: 129–147.
12.
YanSShaoHDWangJ, et al. LiConvFormer: a lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attention. Expert Syst Appl2024; 237: 121338.
13.
HanCKLuWCuiLL, et al. Improved shift-invariant sparse parsing of mechanical fault based on feature atom. IEEE T Instrum Meast2024; 73: 6504412.
14.
GuoJCLiuYLiJH, et al. Rotating machinery fault detection using a new version of intrinsic time-scale decomposition. IEEE Sens J2023; 24(2): 1905–1918.
15.
LuJTJiaBLiSM, et al. A noise reduction method of rolling bearing based on empirical wavelet transform and adaptive time frequency peak filtering. Meas Sci Technol2023; 34(12): 125146.
16.
GeYZhangFSRenY.Adaptive fault diagnosis method for rotating machinery with unknown faults under multiple working conditions. J Manuf Syst2022; 63: 177–184.
17.
LiYChenGMasSC, et al. Bearing fault diagnosis method based on complete center frequency distribution feature. Struct Health Monit2023; 22(6): 4100–4116.
18.
ZhouJYangYWangP, et al. Multivariate local fluctuation mode decomposition and its application to gear fault diagnosis. Measurement2023; 214: 112769.
19.
LiuFChengJSHuNQ, et al. A novel random spectral similar component decomposition method and its application to gear fault diagnosis. Mech Syst Signal Pr2023; 208: 111032.
20.
LiuJYXieFQZhangQ, et al. A multisensory time-frequency features fusion method for rotating machinery fault diagnosis under nonstationary case. J Intell Manuf2023; 35(7): 3197–3217.
21.
JinHLinJHChenXQ, et al. Modal parameters identification method based on symplectic geometry model decomposition. Shock Vib2019; 2019: 5018732.
22.
GuJPengYXLuH, et al. An optimized variational mode decomposition method and its application in vibration signal analysis of bearings. Struct Health Monit2022; 21(5): 2386–2407.
23.
MiaoYHZhangBYLiCH, et al. Feature mode decomposition: new decomposition theory for rotating machinery fault diagnosis. IEEE T Ind Electron2022; 70(2): 1949–1960.
24.
YanXAYanWJXuYD, et al. Machinery multi-sensor fault diagnosis based on adaptive multivariate feature mode decomposition and multi-attention fusion residual convolutional neural network. Mech Syst Signal Pr2023; 202: 110664.
25.
YanXAJiaMP.Bearing fault diagnosis via a parameter-optimized feature mode decomposition. Measurement2022; 203: 112016.
26.
LiZPZhouZTZhouXY.A sensor-based modified FMD method to identify fault feature for mechanical fault diagnosis of ship-borne antennae. IEEE Access2023; 11: 40018–40028.
27.
HuangSXWangXPLiCF, et al. Data decomposition method combining permutation entropy and spectral substitution with ensemble empirical mode decomposition. Measurement2023; 139: 438–453.
28.
LiHWangTYZhangFB, et al. FMDPgram: an improvement of FMD for rotating machinery fault diagnosis. IEEE T Ind Inform2025; 21(8): 6398–6409.
29.
HeXZZhouXQLiJL, et al. Adaptive feature mode decomposition: a fault-oriented vibration signal decomposition method for identification of multiple localized faults in rotating machinery. Nonlinear Dynam2023; 111(17): 16237–16270.
GuJXWangZHKuenJ, et al. Recent advances in convolutional neural networks. Pattern Recongn2018; 77: 354–377.
32.
IbrahimRShafiqMO.Explainable convolutional neural networks: A taxonomy, review, and future directions. Acm Comput Surv2023; 55(10): 206.
33.
RichardsonNSchaefferHTranG.SRMD: Sparse random mode decomposition. Com Appl Math Comput2024; 6(2): 879–906.
34.
GuoJCLiuYYangRG, et al. Differgram: A convex optimization-based method for extracting optimal frequency band for fault diagnosis of rotating machinery. Expert Syst Appl2024; 245: 123051.
35.
ChenXWFengZP.Order spectrum analysis enhanced by surrogate test and Vold-Kalman filtering for rotating machinery fault diagnosis under time-varying speed conditions. Mech Syst Signal Pr2021; 154: 107585.
36.
TangMLiaoYXLuoF, et al. A Novel Method for Fault Diagnosis of Rotating Machinery. Entropy-switz2022; 24(5): 681.
37.
YinNMengZGuanY, et al. An adaptive multiple time domain synchronous averaging method and its application in vibration signal feature enhancement. Meas Sci Technol2022; 33(5): 055004.
38.
LiuZLPengDDZuoMJ, et al. Improved Hilbert-Huang transform with soft sifting stopping criterion and its application to fault diagnosis of wheelset bearings. ISA T2022; 125: 426–444.
39.
ChengJYangYWuZT, et al. Fault diagnosis ramanujan fourier mode decomposition and its application in gear. IEEE T Ind Inform2022; 18(9): 6079–6088.
40.
LiuHXiangJW.Kernel regression residual decomposition-based synchroextracting transform to detect faults in mechanical systems. ISA T2019; 87: 251–26.
41.
MengLJXiangJWWangYX, et al. A hybrid fault diagnosis method using morphological filter-translation invariant wavelet and improved ensemble empirical mode decomposition. Mech Syst Signal Pr2015; 50: 101–115.
