Health assessment of bearings is a critical task in the maintenance of rotating machinery. The complex operating conditions of rolling bearings pose significant challenges to full-life health assessment. In this study, a health assessment method based on vibration and oil debris information is proposed. First, an oil debris sensor was designed to collect oil debris images. Then, a health stage segmentation algorithm is proposed to determine the fault time of early and late-stage faults. Also, a two-dimensional fusion algorithm with a dynamic weighting mechanism is proposed. Relevant vibration standards are employed to further validate the effectiveness of the health assessment. To demonstrate the superiority of the fusion decision approach, novel health assessment methods are also introduced for comparison. The results indicate that the proposed method effectively accounts for both early and late-stage faults, avoids the impact of data fluctuations, and consistently outputs early warning information that aligns more closely with the actual remaining life. The proposed method shows considerable potential for full-life health monitoring of rolling bearings in rotating machinery.
ChenXLuSWangH, et al. Bearing remaining useful life prediction using client selection and personalized aggregation enhancement in federated learning. IEEE Internet Things J2024; 11(24): 40888–40896. https://doi.org/10.1109/JIOT.2024.3456906
2.
ZhangKLiBHuangQ, et al. A reliability assessment method for rolling bearings under variable speed and variable load conditions. Measurement2025; 253: 117571. https://doi.org/10.1016/j.measurement.2025.117571
3.
WanXSunWChenK, et al. State degradation evaluation and early fault identification of wind turbine bearings. Fuel2022; 311: 122348. https://doi.org/10.1016/j.fuel.2021.122348
4.
ZhangKWangJShiH, et al. A variable working condition rolling bearing fault diagnosis method based on improved triplet loss algorithm. Int J Control Autom Syst2023, 21(4): 1361–1372. https://doi.org/10.1007/s12555-021-0975-2
5.
ZhuKZhouSChenL, et al. Rolling bearing fault diagnosis under variable working conditions using deep convolutional fuzzy system. Trans Instit Meas Control2024; 46(5): 845–857. https://doi.org/10.1177/01423312231184932
6.
ZhaoCLiangHShanY, et al. Bearing fault diagnosis method based on comprehensive information divergence and improved BP-AdaBoost algorithm. Struct Health Monit2023; 22(5): 3047–3064. https://doi.org/10.1177/14759217221140645
7.
ChenQDongXTuG, et al. TFN: an interpretable neural network with time-frequency transform embedded for intelligent fault diagnosis. Mech Syst Signal Process2024; 207: 110952. https://doi.org/10.1016/j.ymssp.2023.110952
8.
LiXYuSLeiY, et al. Intelligent machinery fault diagnosis with event-based camera. IEEE Trans Ind Inform2023; 20(1): 380–389. https://doi.org/10.1109/TII.2023.3262854
9.
YuGHuangXLinT, et al. A non-linear time–frequency tool for machinery fault diagnosis under varying speed condition. Mech Syst Signal Process2023; 186: 109849. https://doi.org/10.1016/j.ymssp.2022.109849
10.
FengZDuanXLinR, et al. Angle-time cyclostation-arity-gram for rolling bearing fault diagnosis under time-varying speed conditions. Mech Syst Signal Process2025; 241: 113446. https://doi.org/10.1016/j.ymssp.2025.113446
11.
IunusovaEGonzalezMKSzipkaK, et al. Early fault diagnosis in rolling element bearings: comparative analysis of a knowledge-based and a data-driven approach. J Intell Manuf2024; 35(5): 2327–2347. https://doi.org/10.1007/s10845-023-02151-y
12.
MattarAHASayedHYounesYK, et al. Experimental verification and nonlinear dynamic response analysis of a rolling element bearing with localized defects. J Fail Anal Prevent2022; 22(4): 1753–1770. https://doi.org/10.1007/s11668-022-01466-x
13.
WangPYangYMaH, et al. Vibration characteristics of rotor-bearing system with angular misalignment and cage fracture: simulation and experiment. Mech Syst Signal Process2023; 182: 109545. https://doi.org/10.1016/j.ymssp.2022.109545
14.
ShanZWangZYangJ, et al. Novel time frequency mode decomposition and information fusion for bearing fault diagnosis under varying-speed condition. IEEE Trans Instrum Meas2023; 72: 1–10. https://doi.org/10.1109/TIM.2023.3260275
15.
Sateesh KumarPAmarnathMKamarapuSK, et al. A study of surface fatigue wear and influence of contaminated lubricant in journal bearing system using tribological and vibration analyses. Proc IMechE, Part E: J Process Mechanical Engineering2024; 239(6): 3622–3636. https://doi.org/10.1177/09544089241233119
16.
LiZLiJAnB, et al. The design method for surface texture of sliding friction pairs based on machine learning under mixed lubrication. Tribol Int2024; 194: 109563. https://doi.org/10.1016/j.triboint.2024.109563
PanYLiangBYangL, et al. Spatial-temporal modeling of oil condition monitoring: a review. Reliab Eng Syst Saf2024; 248: 110182. https://doi.org/10.1016/j.ress.2024.110182
19.
LiuZLiuYZuoH, et al. Oil debris and viscosity monitoring using optical measurement based on response surface methodology. Measurement2022; 195: 111152. https://doi.org/10.1016/j.measurement.2022.111152
20.
GongTYangJLouL, et al. A robust vibration frequency sensing method based on phase fusion of multiple RFID tags under nonuniform sampling. IEEE Sens J2025; 25(23): 43165–43175. https://doi.org/10.1109/JSEN.2025.3622151
21.
ZhaoHShuMAiZ, et al. A highly sensitive triboelectric vibration sensor for machinery condition monitoring. Adv Energy Mater2022; 12(37): 2201132. https://doi.org/10.1002/aenm.202270154
22.
WangLYuJWangP, et al. Intelligent online sensing of lubricating oil debris via dual-electrode oil-driven triboelectric nanogenerator. Chem Eng J2025; 503: 158413. https://doi.org/10.1016/j.cej.2024.158413
23.
HongJBaiCChengY, et al. Dual-coil micro-impedance resonance oil contaminant detection sensor based on microfluidic chip. Sens Actuat A Phys2022; 345: 113754. https://doi.org/10.1016/j.sna.2022.113754
24.
LiYYuCXueB, et al. A double lock-in amplifier circuit for complex domain signal detection of particles in oil. IEEE Trans Instrum Meas2022; 71: 1–10. https://doi.org/10.1109/TIM.2021.3130926
ZhangCMousaviAAMasriSF, et al. Vibration feature extraction using signal processing techniques for structural health monitoring: a review. Mech Syst Signal Process2022; 177: 109175. https://doi.org/10.1016/j.ymssp.2022.109175
27.
WangHLiuZPengD, et al. Attention-guided joint learning CNN with noise robustness for bearing fault diagnosis and vibration signal denoising. ISA Trans2022; 128: 470–484. https://doi.org/10.1016/j.isatra.2021.11.028
28.
JiaLChowTWSYuanY. GTFE-net: a Gramian time frequency enhancement CNN for bearing fault diagnosis. Eng Appl Artif Intell2023; 119: 105794. https://doi.org/10.1016/j.engappai.2022.105794
29.
PengYWuTWangS, et al. Wear state identification using dynamic features of wear debris for on-line purpose. Wear2017; 376–377: 1885–1891. https://doi.org/10.1016/j.wear.2017.01.012
30.
WangCWuDLiR, et al. The size and material identification of metal wear particles in lubricating oil based on EMD and SVM. Measurement2026; 258: 119065. https://doi.org/10.1016/j.measurement.2025.119065
31.
FanSZhangTGuoX, et al. FFWR-Net: a feature fusion wear particle recognition network for wear particle classification. J Mech Sci Technol2021; 35(4): 1699–1710. https://doi.org/10.1007/s12206-021-0333-6
32.
LiuZZuoHBaiF, et al. Intelligent classification of online wear particle in lubricating oil using optical direct imaging method and convolutional neural network for rotating machinery. Tribol Int2023; 189: 109015.
33.
ChengLLiYXuG, et al. Enhanced hierarchical grey entropy and dynamic fusion particle filter for rolling bearing degradation trend prediction. Struct Health Monit2025. Advance online publication. https://doi.org/10.1177/14759217251396967
34.
KumaraswamidhasLLahaS. Bearing degradation assessment and remaining useful life estimation based on Kullback-Leibler divergence and Gaussian processes regression. Measurement2021; 174: 108948. https://doi.org/10.1016/j.measurement.2020.108948
35.
MengJYanCChenG, et al. Health indicator of bearing constructed by rms-CUMSUM and GRRMD-CUMSUM with multifeatures of envelope spectrum. IEEE Trans Instrum Meas2021; 70: 1–16. https://doi.org/10.1109/TIM.2021.3054000
36.
NiQJiJFengK. Data-driven prognostic scheme for bearings based on a novel health indicator and gated recurrent unit network. IEEE Trans Ind Inform2023; 19(2): 1301–1311. https://doi.org/10.1109/TII.2022.3169465
37.
LiQLiangCYanC, et al. Performance degradation assessment of mechanical system based on dual adaptive drift coefficient state-space model with autocorrelation prediction error correction. Mech Syst Signal Process2026; 244: 113804. https://doi.org/10.1016/j.ymssp.2025.113804
KumarAGhoshSK. Size distribution analysis of wear debris generated in HEMM engine oil for reliability assessment: a statistical approach. Measurement2019; 131: 412–418. https://doi.org/10.1016/j.measurement.2018.09.012
40.
ChenGLiKYuanK, et al. Identifying change point in dynamic bearing degradation process: a retrospective approach based on visibility graph modeling. Eng Appl Artif Intell2025; 156: 110988. https://doi.org/10.1016/j.engappai.2025.110988
41.
MengWWangYZhangX, et al. Prediction of fault evolution and remaining useful life for rolling bearings with spalling fatigue using digital twin technology. Appl Intell2023; 53(23): 28611–28626. https://doi.org/10.1007/s10489-023-05010-8
42.
CaoYDingYJiaM, et al. A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings. Reliab Eng Syst Saf2021; 215: 107813. https://doi.org/10.1016/j.ress.2021.107813
43.
WangYHouDXuD, et al. Prediction of rolling bearing performance degradation based on SAE and TCN-attention models. J Mech Sci Technol2023; 37(4): 1567–1583.
44.
SinitsinVIbryaevaOSakovskayaV, et al. Intelligent bearing fault diagnosis method combining mixed input and hybrid CNN-MLP model. Mech Syst Signal Process2022; 180: 109454. https://doi.org/10.1016/j.ymssp.2022.109454
45.
YanRZhouZShangZ, et al. Knowledge driven machine learning towards interpretable intelligent prognostics and health management: review and case study. Chin J Mech Eng2025; 38(1): 5. https://doi.org/10.1186/s10033-024-01173-8
46.
JiangLChenJCaoH, et al. A novel bearing fault diagnosis method using a hybrid tcn-transformer architecture: a deep learning approach. J Mech Sci Technol2025; 39(7): 3821–3834. https://doi.org/10.1007/s12206-025-0607-5
47.
MishraRKChoudharyAFatimaS, et al. A systematic review on advancement and challenges in multi-fault diagnosis of rotating machines. Eng Appl Artif Intell2025; 156: 111306. https://doi.org/10.1016/j.engappai.2025.111306
48.
XuKKongXWangQ, et al. A bearing fault diagnosis method without fault data in new working condition combined dynamic model with deep learning. Adv Eng Inform2022; 54: 101795. https://doi.org/10.1016/j.aei.2022.101795
49.
KeshunYZengweiLYingkuiG. A performance-interpretable intelligent fusion of sound and vibration signals for bearing fault diagnosis via dynamic CAME. Nonlinear Dyn2024; 112(23): 20903–20940. https://doi.org/10.1007/s11071-024-10157-1
50.
KangXWangDShaoY, et al. An efficient hybrid multi-station TDOA and single-station aoa localization method. IEEE Trans Wirel Commun2023; 22(8): 5657–5670. https://doi.org/10.1109/TWC.2023.3235753
51.
SongJLiFZhaoJ, et al. PMSLM demagnetization fault detection based on multisensor signal fusion and enhanced graph neural network. IEEE Trans Transp Electrif2025; 11(5): 12428–12440. https://doi.org/10.1109/TTE.2025.3590405
52.
LiQYanCChenG, et al. Remaining useful life prediction of rolling bearings based on risk assessment and degradation state coefficient. ISA Trans2022; 129: 413–428. https://doi.org/10.1016/j.isatra.2022.01.031
53.
BettaharTChemseddineRBenazzouzD. Faults’ diagnosis of time-varying rotational speed machinery based on vibration and acoustic signals features extraction, and machine learning methods. J Vib Eng Technol2022; 11: 2333–2347. https://doi.org/10.1007/s42417-022-00705-7
54.
WuGYanNChoiK-N, et al. A two-step vibration-sound signal fusion method for weak fault feature detection in rolling bearing systems. Adv Mech Eng2021; 13(12): 16878140211067155. https://doi.org/10.1177/16878140211067155
55.
ShiHLiYBaiX, et al. A two-stage sound-vibration signal fusion method for weak fault detection in rolling bearing systems. Mech Syst Signal Process2022; 172: 109012. https://doi.org/10.1016/j.ymssp.2022.109012
56.
LoutasTHRouliasDPaulyE, et al. The combined use of vibration, acoustic emission and oil debris on-line monitoring towards a more effective condition monitoring of rotating machinery. Mech Syst Signal Process2011; 25(4): 1339–1352. https://doi.org/10.1016/j.ymssp.2010.11.007
57.
LuanXZhaoJShaY, et al. Rolling bearing state monitoring method based on fusion of multichannel vibration signals with oil debris information. Struct Health Monit2025. https://doi.org/10.1177/14759217241301305
58.
BiswasRKMajumdarMCBasuSK. Vibration and oil analysis by ferrography for condition monitoring. J Inst Eng India Ser C2013; 94(3): 267–274. https://doi.org/10.1007/s40032-013-0079-8
59.
EstevesPJSeriacopiVDe MacêdoMCS, et al. Combined effect of abrasive particle size distribution and ball material on the wear coefficient in micro-scale abrasive wear tests. Wear2021; 476: 203639. https://doi.org/10.1016/j.wear.2021.203639
