Hybrid temporal convolutional network with feature enhancement and adaptive threshold for the prediction of bearing remaining useful life under noise interference
Restricted accessResearch articleFirst published online 2026
Hybrid temporal convolutional network with feature enhancement and adaptive threshold for the prediction of bearing remaining useful life under noise interference
Due to its broad receptive field and ability to eliminate future information leakage, the temporal convolutional network (TCN) has been widely used in the remaining useful life (RUL) estimation of bearings. However, the predictive capability of TCN is constrained by the distortion during degraded feature acquisition and the loss during feature extraction. To address these issues, a hybrid TCN with feature enhancement and adaptive threshold (HTCN-FA) is proposed. Firstly, a plug-and-play resilient nonlinear blind deconvolution (RNBD)-net subnetwork without reliance on prior knowledge is designed to enhance the representation of degraded features. Secondly, a theoretically rigorous and interpretable metric, harmonic distribution clarity, is introduced to monitor the operational condition of bearings. Thirdly, TCN blocks with adaptive thresholds and hybrid branches are employed to avoid the loss of degraded characteristics. Finally, datasets from twelve bearings under three working conditions are employed to validate the prediction and generalization performance of the proposed HTCN-FA. The results demonstrate that the proposed HTCN-FA outperforms existing methods in fault monitoring and RUL prediction while exhibiting superior noise adaptability.
ZhouJQinYChenD, et al. Remaining useful life prediction of bearings by a new reinforced memory GRU network. Adv Eng Inform2022; 53: 101682.
2.
LiuRDingXLiuS, et al. Knowledge-informed FIR-based cross-category filtering framework for interpretable machinery fault diagnosis under small samples. Reliab Eng Syst Saf2025; 254: 110610.
3.
LiuSFanL. An adaptive prediction approach for rolling bearing remaining useful life based on multistage model with three-source variability. Reliab Eng Syst Saf2022; 218: 108182.
4.
ShiHSongZBaiX, et al. A novel digital twin model for dynamical updating and real-time mapping of local defect extension in rolling bearings. Mech Syst Signal Process2023; 193: 110255.
5.
GuptaMWadhvaniRRasoolA. A real-time adaptive model for bearing fault classification and remaining useful life estimation using deep neural network. Knowl Based Syst2023; 259: 110070.
6.
WangHLiaoHMaX, et al. Remaining useful life prediction and optimal maintenance time determination for a single unit using isotonic regression and gamma process model. Reliab Eng Syst Saf2021; 210: 107504.
7.
GeRZhaiQWangH, et al. Wiener degradation models with scale-mixture normal distributed measurement errors for RUL prediction. Mech Syst Signal Process2022; 173: 109029.
8.
LuHBarzegarVNemaniVP, et al. Joint training of a predictor network and a generative adversarial network for time series forecasting: a case study of bearing prognostics. Expert Syst Appl2022; 203: 117415.
9.
YiCLiSHuangT, et al. On a prediction method for remaining useful life of rolling bearings via VMD-based dispersion entropy and GAN. IEEE Sens J2023: 27744–27756.
10.
LiJDingWMaoW, et al. Causal dilated convolution-based residual DenseNet with channel attention for RUL prediction of rolling bearings. Measurement2024; 235: 115012.
11.
DingWLiJMaoW, et al. Rolling bearing remaining useful life prediction based on dilated causal convolutional DenseNet and an exponential model. Reliab Eng Syst Saf2023; 232: 109072.
12.
XiangSLiPHuangY, et al. Single gated RNN with differential weighted information storage mechanism and its application to machine RUL prediction. Reliab Eng Syst Saf2024; 242: 109741.
13.
LiLJianQ. Remaining useful life prediction of wind turbine main-bearing based on LSTM optimized network. IEEE Sens J2024: 21143–21156.
14.
HanTLiuCYangW, et al. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults. Knowl Based Syst2019; 165: 474–487.
15.
ZhongTQinCShiG, et al. A residual denoising and multiscale attention-based weighted domain adaptation network for tunnel boring machine main bearing fault diagnosis. Sci China Technol Sci2024; 67(8): 2594–2618.
16.
LuPSongBXuL. Multi-condition bearing fault diagnosis based on one-dimensional convolutional neural network. J Shandong Univ Sci Technol2023; 42(5): 88–96.
17.
SunHXiaMHuY, et al. A new sorting feature-based temporal convolutional network for remaining useful life prediction of rotating machinery. Comput Electr Eng2021; 95: 107413.
18.
LiFChengYTangB, et al. Multi-layer gated temporal convolution network for residual useful life prediction of rotating machinery. Mech Syst Signal Process2021; 155: 107600.
19.
ZhangQLiuQYeQ. An attention-based temporal convolutional network method for predicting remaining useful life of aero-engine. Eng Appl Artif Intell2024; 127: 107241.
20.
ZhaoCZhangLZhongM. Fault diagnosis of fan gear box based on cyclic convolution generation adversarial network. J Shandong Univ Sci Technol2024; 43(1): 109–118.
21.
MiaoYLiCZhangB, et al. Application of a coarse-to-fine minimum entropy deconvolution method for rotating machines fault detection. Mech Syst Signal Process2023; 198: 110431.
22.
ZhangZWangJLiS, et al. Fast nonlinear blind deconvolution for rotating machinery fault diagnosis. Mech Syst Signal Process2023; 187: 109918.
23.
MarianiSRenduQUrbaniM, et al. Causal dilated convolutional neural networks for automatic inspection of ultrasonic signals in non-destructive evaluation and structural health monitoring. Mech Syst Signal Process2021; 157: 107748.
24.
SongBLuPXuL. Inverter switch tube open circuit fault diagnosis based on deep autoencoder network. J Shandong Univ Sci Technol2023; 42(6): 117–128.
25.
ChangYChenJLiuY, et al. Temporal convolution-based sorting feature repeat-explore network combining with multi-band information for remaining useful life estimation of equipment. Knowl Based Syst2022; 249: 108958.
26.
MaHHanBWangJ, et al. Resilient fast nonlinear blind deconvolution with uniform initialization for the bearing fault diagnosis. Struct Health Monit2024: 2978–3001.
27.
ShiHMiaoYLiC, et al. A novel bearing intelligent fault diagnosis method based on spectrum sparse deep deconvolution. Eng Appl Artif Intell2024; 133: 108102.
28.
WangYDengLZhengL, et al. Temporal convolutional network with soft thresholding and attention mechanism for machinery prognostics. J Manuf Syst2021; 60: 512–526.
29.
HeKZhangXRenS, et al. (2016). Identity mappings in deep residual networks. In: LeibeB.MatasJ.SebeN.WellingM. (eds) Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science(), vol 9908. Cham: Springer. https://doi.org/10.1007/978-3-319-46493-0_38
30.
GuoJWangZLiH, et al. A hybrid prognosis scheme for rolling bearings based on a novel health indicator and nonlinear Wiener process. Reliab Eng Syst Saf2024; 245: 110014.
31.
YangNWangZCaiW, et al. Data regeneration based on multiple degradation processes for remaining useful life estimation. Reliab Eng Syst Saf2023; 229: 108867.
32.
ZhangJTianJYanP, et al. Multi-hop graph pooling adversarial network for cross-domain remaining useful life prediction: a distributed federated learning perspective. Reliab Eng Syst Saf2024; 244: 109950.
33.
HuangC-GHuangH-ZLiY-F, et al. A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing. J Manuf Syst2021; 61: 757–772.
34.
WangLCaoHFuY. A bearing prognosis framework based on deep wavelet extreme learning machine and particle filtering. Appl Soft Comput2022; 131: 109763.
35.
KongWLiH. Remaining useful life prediction of rolling bearing under limited data based on adaptive time-series feature window and multi-step ahead strategy. Appl Soft Comput2022; 129: 109630.
36.
LiuRDingXZhangY, et al. Variable-scale evolutionary adaptive mode denoising in the application of gearbox early fault diagnosis. Mech Syst Signal Process2023; 185: 109773.
37.
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.
38.
GongFMaPZhangH, et al. Rolling bearings remaining useful life estimation using digital twin and physics-informed methods with uncertainty quantification. Eng Appl Artif Intell2025; 154: 111070.
39.
ZouWLuZHuZ, et al. Remaining useful life estimation of bearing using deep multiscale window-based transformer. IEEE Trans Instrum Meas2023; 72: 1–11.
