Rolling bearings are critical components in rotating machinery and play a vital role in industrial production. However, due to complex working conditions and high operational loads, the risk of bearing failure increases significantly. Accurately predicting the remaining useful life (RUL) of rolling bearings is essential for enhancing the reliability and safety of industrial equipment. To address the challenges in accurately determination of the First Prediction Time (FPT) under weak early-stage faults and the insufficient utilization of temporal information in existing methods, this study proposes the following improvements: First, the data preprocessing procedure is optimized by introducing a frequency-energy ratio-based method for FPT determination, enabling precise identification of incipient weak faults. Second, a synthetic time-frequency graph is innovatively constructed to comprehensively capture the evolutionary trends of time-frequency features. Finally, a parallel deep learning architecture is designed to separately extract temporal and feature information from the bearing degradation process, followed by deep fusion for accurate RUL prediction. Experimental validation conducted on the XJTU-SY bearing dataset demonstrates that the proposed parallel model significantly enhances the accuracy of life prediction.
MiJHLiuLZhuangYH, et al. A synthetic feature processing method for remaining useful life prediction of rolling bearings. IEEE Trans Reliab2023; 72(1): 125–136.
2.
JiangGDuanZZhaoQ, et al. Remaining useful life prediction of rolling bearings based on TCN-MSA. Meas Sci Technol2023; 35(2): 025125.
3.
ZhangJ-XHuC-HHeX, et al. A novel lifetime estimation method for two-phase degrading systems. IEEE Trans Reliab2019; 68(2): 689–709.
4.
SunJZuoHWangW, et al. Application of a state space modeling technique to system prognostics based on a health index for condition-based maintenance. Mech Syst Signal Proc2012; 28: 585–596.
5.
MaMMaoZ.Deep-convolution-based LSTM network for remaining useful life prediction. IEEE Trans Indus Inform2020; 17(3): 1658–1667.
6.
LeeJWuFZhaoW, et al. Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications. Mech Syst Signal Proc2014; 42(1–2): 314–334.
7.
WangHXuJYanR, et al. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN. IEEE Trans Instrum Meas2019; 69(5): 2377–2389.
8.
DuanRZhouJZLiuJ, et al. A performance degradation prediction approach for turbo-generator bearing considering complex working conditions based on clustering indicator and self-optimized deep learning model. Meas Sci Technol2021; 32(6): 065103.
9.
HintonGEOsinderoSTehY-W.A fast learning algorithm for deep belief nets. Neural Comput2006; 18(7): 1527–1554.
10.
PeiHHuCHSiXS, et al. Review of machine learning-based remaining life prediction methods for equipment. J Mech Eng2019; 55(8): 1–13.
11.
SuHXiangLHuA, et al. A novel method based on meta-learning for bearing fault diagnosis with small sample learning under different working conditions. Mech Syst Signal Proc2022; 169: 108765.
12.
WangGXiangJ.Remain useful life prediction of rolling bearings based on exponential model optimized by gradient method. Measurement2021; 176(4): 109161.
13.
YujingWShidaWShouqiangK, et al. Health index construction and remaining useful life prediction of rolling bearings. In: IEEE international conference on electronic measurement & instruments (ICEMI), Changsha, China, 2019, pp. 1241–1247.
14.
LiNLeiYLinJ, et al. An improved exponential model for predicting remaining useful life of rolling element bearings. IEEE Trans Indus Electron2015; 62(12): 7762–7773.
15.
AhmadWKhanSAIslamMMM, et al. A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models. Reliab Eng Syst Saf2019; 184: 67–76.
16.
CuiLWangXWangH, et al. Research on remaining useful life prediction of rolling element bearings based on time-varying Kalman filter. IEEE Trans Instrum Meas2019; 69(6): 2858–2867.
17.
DeutschJHeD.Using deep learning-based approach to predict remaining useful life of rotating components. IEEE Trans Syst Man Cybern Syst2017; 48(1): 11–20.
18.
ZhouSXiaoMBartosP, et al. Remaining useful life prediction and fault diagnosis of rolling bearings based on short-time Fourier transform and convolutional neural network. Shock Vibr2020; 2020(1): 8857307.
19.
YooYBaekJ-G.A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network. Appl Sci2018; 8(7): 1102.
20.
XiangSQinYZhuC, et al. Long short-term memory neural network with weight amplification and its application into gear remaining useful life prediction. Eng Appl Artif Intell2020; 91: 103587.
21.
ShenYZTangBLiB, et al. Remaining useful life prediction of rolling bearing based on multi-head attention embedded Bi-LSTM network. Measurement2022; 202: 111803.
22.
KumarAParkashCZhouYQ, et al. Entropy-based domain adaption strategy for predicting remaining useful life of rolling element bearing. Eng Appl Artif Intell2024; 133: 108575.
23.
SchmidhuberJ.Deep learning in neural networks: an overview. Neural Netw2015; 61: 85–117.
24.
LiuZLiuYBaiF, et al. An oil wear particle identification method based on Wasserstein generative adversarial network and improved CNN using a custom-built optical imaging sensor. Measurement2024; 232: 114663.
25.
NieLXuSZhangL, et al. Remaining useful life prediction of Aeroengines based on multi-head attention mechanism. Machines2022; 10(7): 552.
26.
ZangYYuZXuK, et al. Data-driven fiber model based on the deep neural network with multi-head attention mechanism. Opt Express2022; 30(26): 46626–46648.
27.
ZhengSRistovskiKFarahatA, et al. Long short-term memory network for remaining useful life estimation. In: 2017 IEEE international conference on prognostics and health management (ICPHM), Dallas, TX, USA, 19–21 June 2017, pp. 88–95.
28.
SidhuRKKumarRRanaPS.Long short-term memory neural network-based multi-level model for smart irrigation. Modern Phys Lett B2020; 34(36): 205418.
29.
XiangLWangPYangX, et al. Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism. Measurement2021; 175: 109094.
30.
YanTWangDHouB, et al. Generic framework for integration of first prediction time detection with machine degradation modelling from frequency domain. IEEE Trans Reliab2021; 71(4): 1464–1476.
31.
HelmiHForouzantabarA.Rolling bearing fault detection of electric motor using time domain and frequency domain features extraction and ANFIS. IET Electr Power Appl2019; 13(5): 662–669.
32.
DeutschJHeD.Using deep learning based approaches for bearing remaining useful life prediction. Ann Conf Progn Health Manag Soc2016; 8(1): 1–7.
33.
WangWLuY.Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model. IOP Conf Ser Mater Sci Eng2018; 324: 012049.
34.
LeiYGHanTYWangB.Data set interpretation of XJTU-SY rolling bearing accelerated life test. J Mech Eng2019; 55(16): 1–6.
