The hollow cathode, as the core component of an ion thruster system, plays a critical role in ignition and sustaining discharge for the thruster. However, its functional structural components gradually degrade during prolonged operation, ultimately leading to system failure. In order to effectively enhance the reliability of ion propulsion systems and mitigate operational risks, a digital twin-assisted residual temporal convolutional network-bidirectional gated recurrent unit-attention (ResTCN-BiGRU-Attention) model was proposed for predicting RUL (remaining useful life) of lanthanum hexaboride (LaB6) hollow cathodes. First, the working mechanism of hollow cathodes was analyzed, and a dynamic simulation model was constructed using digital twin technology to obtain simulated data. Then, a subdomain adaptation mechanism was introduced to achieve residual correction by minimizing the discrepancy of fine-grained features between the simulated and real domains. Finally, the ResTCN-BiGRU-Attention model was applied for the RUL prediction of hollow cathodes.The results demonstrate that the proposed model achieves superior performance in four evaluation metrics, with the mean squared error, root mean squared error, mean absolute error, and coefficient of determination reaching 0.055, 0.234 7, 0.151 4, and 0.987 38, respectively. It is concluded that the model exhibits excellent prediction accuracy and generalizability, providing a valuable reference for the design of long-life hollow cathodes.
CHEN Lin-ying, ZHANG Yan-qin, SHI Hui, SONG Ren-wang, LI Jing.
Remaining Useful Life Prediction of Hollow Cathodes Based on Digital Twin and ResTCN-BiGRU-Attention Model[J].
Science Technology and Engineering, 2026, 26(26): 11501-11513 DOI:10.12404/j.issn.1671-1815.2505697
子域自适应是域自适应的一个细粒度分支,如图4所示。其核心思想是:在源域和目标域整体分布对齐的基础上,进一步对同一类别对应的子域进行条件分布对齐,从而减少同类样本在不同域之间的分布差异。把源域和目标域分别拆成c个子域,对每个子域对计算局部最大平均差异(local maximum mean discrepancy,LMMD),LMMD表达式为
ZhangTianping, ZhangXue’er. Application practices and realizations of the ion electric propulsion on spacecraft[J]. Vacuum and Cryogenics, 2019, 25(2): 73-81.
GuoNing, JiangHaocheng, GuZuo. Life prediction of hollow cathode in ion thruster[J]. Vacuum, 2009, 46(4): 83-85.
[9]
WangW, LeiY, YanT, et al. Residual convolution long short-term memory network for machines remaining useful life prediction and uncertainty quantification[J]. Journal of Dynamics, Monitoring and Diagnostics, 2022, 1(1): 2-8.
[10]
LinJ, ShaoH D, ZhouX D, et al. Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signals[J]. Expert Systems with Applications, 2023, 230: 120696.
[11]
ChenX, ShaoH, XiaoY, et al. Collaborative fault diagnosis of rotating machinery via dual adversarial guided unsupervised multi-domain adaptation network[J]. Mechanical Systems and Signal Processing, 2023, 198: 110427.
[12]
RenZ, LinT, FengK, et al. A systematic review on imbalanced learning methods in intelligent fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-35.
WanYu, QiJinping, ZhangRu, et al. Research on prediction of coal and gas outburst based on over-sampling SVM[J]. Science Technology and Engineering, 2021, 21(28): 12080-12087.
SunJiajia, LiChengli, ChangDexian, et al. A data augmentation method for intrusion detection imbalance problem using generative adversarial networks[J]. Science Technology and Engineering, 2022, 22(18): 7965-7971.
[17]
LiuS W, JiangH K, et al. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis[J]. Measurement, 2021, 168: 108371.
[18]
LiW, ZhangX, ShaoH D, et al. Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework[J]. Advanced Engineering Informatics, 2022, 52: 101552.
[19]
ZhaoX L, YaoJ Y, DengW X, et al. Normalized conditional variational auto-encoder with adaptive focal loss for imbalanced fault diagnosis of bearing-rotor system[J]. Mechanical Systems and Signal Processing, 2022, 170: 108826.
[20]
PengY Z, WangY, ShaoY M. A novel bearing imbalance Fault-diagnosis method based on a Wasserstein conditional generative adversarial network[J]. Measurement, 2022, 192: 110924.
[21]
LinZ Y, GoyalP, GirshickR, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017(99): 2999-3007.
[22]
LuoJ Q, XuS X, WangH Y, et al. Improving GBDT performa-nce on imbalanced datasets: an empirical study of class-balanced loss functions[J]. Neurocomputing, 2025, 634: 129896.
[23]
FernandoK, TsokosC. Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(7): 2940-2951.
[24]
JiaF, LeiY G, LinJ, et al. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization[J]. Mechanical Systems and Signal Processing, 2018, 110: 349-367.
[25]
HeZ Y, ShaoH D, et al. Support tensor machine with dynamic penalty factors and its application to the fault diagnosis of rotating machinery with unbalanced data[J]. Mechanical Systems and Signal Processing, 2020, 141: 106441.
[26]
YuY X, WangH, LiY, et al. Pareto-optimal adaptive loss resi-dual shrinkage network for imbalanced fault diagnostics of machines[J]. IEEE Transactions on Industrial Informatics, 2022, 18(4): 2233-2243.
[27]
RenZ J, ZhuY S, LiuZ L, et al. Adaptive cost-sensitive learning: improving the convergence of intelligent diagnosis models under imbalanced data[J]. Knowledge-Based Systems, 2022, 241: 108-296.
[28]
LiuH, LiuZ Y, JiaW Q, et al. A novel imbalanced data classification method based on weakly supervised learning for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2022, 18(3): 1583-1593.
XieKan, YiXiaolong, LiangFuwen, et al. Experimental investigation on relationship between hollow cathode and discharge oscillation in hall thruster[J]. Journal of Solid Rocket Technology, 2022, 45(3): 484-490.
SunMingming, GuZuo, GuoNing, et al. Simulation and analysis of thermal characteristics of hollow cathode in ion thruster[J]. High Power Laser and Particle Beams, 2010, 22(5): 1149-1152.
YangWei, ZhangTianping, FengJie, et al. Experimental investigation on performance of hollow cathode with graphite keeper[J]. Vacuum and Cryogenics, 2017, 23(2): 87-91.
YangWei, ShiKai, GuZengjie, et al. Discharge voltage fluctuation phenomenon and its generation mechanism in LaB6 hollow cathode[J]. Science Technology and Engineering, 2020, 20(33): 13914-13918.
[39]
HsiehJ H, HuangY L, HuangP H, et al. Investigation of anode diameter and keeper geometry influence on open-end emitter heaterless hollowcathode discharge[J]. Vacuum, 2024, 229: 113504.
[40]
TianF, MiaoL, XiaQ M, et al. A global model for evaluating discharge characteristics and performance of hollow cathodes[J]. Chinese Journal of Aeronautics, 2024, 37(9): 72-84.
XieKan, ZhangTianping, WuZhiwen, et al. A review of sputtering erosion mechanism in discharge cathode for ion thrusters[J]. Journal of Vacuum Science and Technology, 2014, 34(5): 461-468.
GuoNing, JiangHaocheng, GaoJun, et al. Analysis of failure modes in hollow cathodes for ion thrusters[J]. Vacuum and Cryogenics, 2005, 11(4): 239-242.
[45]
TaoF, ZhangM, LiuY, et al. Digital twin driven prognostics and health management for complex equipment[J]. CIRP Annals-Manufacturing Technology, 2018, 67(1): 169-172.
[46]
KeF, JiJ, ZhangY, et al. Digital twin-driven intelligent assessment of gear surface degradation[J]. Mechanical Systems and Signal Processing, 2023, 186: 109896.
[47]
CuiL, WangX, LiuD, et al. An adaptive sparse graph learning method based on digital twin dictionary for remaining useful life prediction of rolling element bearings[J]. IEEE Transactions on Industrial Informatics, 2024, 20(9): 10892-10900.
[48]
KangT W, MoY. A comprehensive digital twin framework for building environment monitoring with emphasis on real-time data connectivity and predictability[J]. Developments in the Built Environment, 2024(17): 100309.
TaoFei, MaXin, QiQinglin, et al. Theory and key technologies of digital twin connection and interaction[J]. Computer Integrated Manufacturing System, 2023, 29(1): 1-10.