Accurately predicting the remaining useful life (RUL) of a bearing is crucial in the prognostics and reliability management of machinery. Owing to the cost of wind power operation and maintenance and commercial barriers, collecting early failure samples of gearbox bearings is costly. Accordingly, the prediction of the RUL of bearings with few samples remains a challenging problem. To address this challenge, a two-stage method based on DWRNet and MGAU is proposed to predict the RUL of bearings with few samples. First, a bearing’s health indicator (HI) is constructed using a dynamic weighted residual network (DWRNet), which utilizes a dynamic weighted residual block to fully extract the fault feature of the bearing. Then, a meta-gated adaptive unit (MGAU) neural network is implemented to predict RUL of bearings with few samples via a gated adaptive unit and multi-task learning. Finally, the prediction ability of the proposed method is verified using a dataset of bearings.
CaoLZhangHMengZ, et al. (2023) A parallel GRU with dual-stage attention mechanism model integrating uncertainty quantification for probabilistic RUL prediction of wind turbine bearings. Reliability Engineering & System Safety235: 109197. DOI: 10.1016/j.ress.2023.109197.
2.
ChengHKongXWangQ, et al. (2022) The two-stage RUL prediction across operation conditions using deep transfer learning and insufficient degradation data. Reliability Engineering & System Safety225: 108581. DOI: 10.1016/j.ress.2022.108581.
3.
GuoLLiNJiaF, et al. (2017) A recurrent neural network based health indicator for remaining useful life prediction of bearings. Neurocomputing240: 98–109. DOI: 10.1016/j.neucom.2017.02.045.
4.
JiangKLiZZhouY, et al. (2022) Transient waveform matching based on ascending multi-wavelets for diagnostics and prognostics of bearing deterioration. ISA Transactions120: 330–341. DOI: 10.1016/j.isatra.2021.03.016.
5.
JiangWWuJZhuH, et al. (2023) Paired ensemble and group knowledge measurement for health evaluation of wind turbine gearbox under compound fault scenarios. Journal of Manufacturing Systems70: 382–394. DOI: 10.1016/j.jmsy.2023.08.004.
6.
KrügerJGCBrittoAde SBarddalJP (2023) An explainable machine learning approach for student dropout prediction. Expert Systems with Applications233: 120933. DOI: 10.1016/j.eswa.2023.120933.
7.
KumarAParkashCTangH, et al. (2023) Intelligent framework for degradation monitoring, defect identification and estimation of remaining useful life (RUL) of bearing. Advanced Engineering Informatics58: 102206. DOI: 10.1016/j.aei.2023.102206.
8.
LiXTengWPengD, et al. (2023) Feature fusion model based health indicator construction and self-constraint state-space estimator for remaining useful life prediction of bearings in wind turbines. Reliability Engineering & System Safety233: 109124. DOI: 10.1016/j.ress.2023.109124.
9.
PanTChenJYeZ, et al. (2022) A multi-head attention network with adaptive meta-transfer learning for RUL prediction of rocket engines. Reliability Engineering & System Safety225: 108610. DOI: 10.1016/j.ress.2022.108610.
10.
PanTZhangSLiF, et al. (2023) A meta network pruning framework for remaining useful life prediction of rocket engine bearings with temporal distribution discrepancy. Mechanical Systems and Signal Processing195: 110271. DOI: 10.1016/j.ymssp.2023.110271.
11.
PangTYuTSongB (2023) RUL prediction for bivariate degradation process considering individual differences. Measurement: Journal of the International Measurement Confederation218: 113156. DOI: 10.1016/j.measurement.2023.113156.
12.
QiaoLZhangYWangQ (2023) Fault detection in wind turbine generators using a meta-learning-based convolutional neural network. Mechanical Systems and Signal Processing200: 110528. DOI: 10.1016/j.ymssp.2023.110528.
13.
QinYYangJZhouJ, et al. (2023) A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL prediction. Advanced Engineering Informatics56: 101973. DOI: 10.1016/j.aei.2023.101973.
14.
ShenYTangBLiB, et al. (2022) Remaining useful life prediction of rolling bearing based on multi-head attention embedded Bi-LSTM network. Measurement: Journal of the International Measurement Confederation202: 111803. DOI: 10.1016/j.measurement.2022.111803.
15.
TangDGongMTianL, et al. (2022) Health indicator construction of high-speed rotating bearings in aerospace CMG based on physics-inspired machine-learning approach. IEEE Transactions on Instrumentation and Measurement71: 1–11. DOI: 10.1109/TIM.2022.3208253.
16.
TianJJiangYZhangJ, et al. (2023) A novel transfer ensemble learning framework for remaining useful life prediction under multiple working conditions. IEEE Transactions on Instrumentation and Measurement72: 1–11. DOI: 10.1109/TIM.2023.3273676.
17.
Velasco-GallegoCLazakisI (2023) Mar-RUL: a remaining useful life prediction approach for fault prognostics of marine machinery. Applied Ocean Research140: 103735. DOI: 10.1016/j.apor.2023.103735.
18.
YangLLiaoYDuanR, et al. (2023a) A bidirectional recursive gated dual attention unit based RUL prediction approach. Engineering Applications of Artificial Intelligence120: 105885. DOI: 10.1016/j.engappai.2023.105885.
19.
YangQTangBLiQ, et al. (2023b) Dual-frequency enhanced attention network for aircraft engine remaining useful life prediction. ISA Transactions141: 167–183. DOI: 10.1016/j.isatra.2023.06.020.
20.
YuXTangBDengL (2023) Fault diagnosis of rotating machinery based on graph weighted reinforcement networks under small samples and strong noise. Mechanical Systems and Signal Processing186: 109848. DOI: 10.1016/j.ymssp.2022.109848.
21.
ZhangJLiXTianJ, et al. (2023a) A variational local weighted deep sub-domain adaptation network for remaining useful life prediction facing cross-domain condition. Reliability Engineering & System Safety231: 108986. DOI: 10.1016/j.ress.2022.108986.
22.
ZhangJTianJLiM, et al. (2023b) A parallel hybrid neural network with integration of spatial and temporal features for remaining useful life prediction in prognostics. IEEE Transactions on Instrumentation and Measurement72: 1–12. DOI: 10.1109/TIM.2022.3227956.
23.
ZhaoYZhangGHuW, et al. (2023) Meta-learning based voltage control strategy for emergency faults of active distribution networks. Applied Energy349: 121399. DOI: 10.1016/j.apenergy.2023.121399.
24.
ZhuJJiangQShenY, et al. (2023a) Res-HSA: residual hybrid network with self-attention mechanism for RUL prediction of rotating machinery. Engineering Applications of Artificial Intelligence124: 106491. DOI: 10.1016/j.engappai.2023.106491.
25.
ZhuYWuJLiuX, et al. (2023b) Hybrid scheme through read-first-LSTM encoder-decoder and broad learning system for bearings degradation monitoring and remaining useful life estimation. Advanced Engineering Informatics56: 102014. DOI: 10.1016/j.aei.2023.102014.
26.
ZuoTZhangKZhengQ, et al. (2023) A hybrid attention-based multi-wavelet coefficient fusion method in RUL prognosis of rolling bearings. Reliability Engineering & System Safety237: 109337. DOI: 10.1016/j.ress.2023.109337.
