中国空间科学技术

中国空间科学技术

• 论文 •    下一篇

基于WP-LSTM-Attention的空心阴极时变温控下的寿命预测方法

蔡昂1，陈琳英2，*，宋仁旺1，石慧1，李婧3   

  1. 1.太原科技大学 电子信息工程学院，太原030024
    2.太原科技大学 应用科学学院，太原030024
    3.兰州空间技术物理研究所，兰州730000
  • 收稿日期:2025-05-15 修回日期:2025-08-08 录用日期:2025-08-13 发布日期:2026-01-13

A RUL prediction method for time-varying temperature control of hollow cathode based on WP-LSTM-Attention

CAI Ang1，CHEN Linying2，*，SONG Renwang1，SHI Hui1，LI Jing3   

  1. 1.Taiyuan University of Technology School of Electronic Information Engineering，Taiyuan 030024，China
    2.Taiyuan University of Technology School of Applied Sciences，Taiyuan 030024，China
    3.Lanzhou Institute of Space Technology Physics，Lanzhou 730000，China
  • Received:2025-05-15 Revision received:2025-08-08 Accepted:2025-08-13 Online:2026-01-13

PDF (PC)

0

摘要： 针对传统物理模型的方法难以有效捕捉复杂工况下的非线性、时变性退化问题，提出一种基于WPLSTMAttention的空心阴极时变温控下的剩余使用寿命（Remaining Useful Life,RUL）预测方法。首先，基于空心阴极的发射体蒸发失效机理，建立非线性时变维纳过程（Wiener Process,WP）模型；其次，采用长短时记忆（Long Short-Term Memory,LSTM）神经网络提取多源时间序列特征，通过温控下的多头注意力机制（Multi-Head Attention Mechanism，MHAM）分配退化敏感特征的权重，进而预测Wiener模型参数及退化趋势，并通过联合损失函数优化参数反向传播，实现物理-数据双驱动更新；最后，根据首达时间的概念，推导出剩余使用寿命的概率密度函数（Probability Density Function,PDF）。结果表明：较于单一物理或数据驱动模型，所提模型的均方根误差和平均绝对误差分别降低了22.81%和18.11%，验证了该模型在少样本场景下对LaB6空心阴极寿命预测的有效性和准确性。结论表明，通过将物理模型与数据驱动融合方法能更好的提高模型的预测精度和鲁棒性，为LaB6空心阴极寿命预测提供了新的方法路径和技术支撑。

关键词: 空心阴极, 剩余寿命预测, 长短时记忆神经网络, 多头注意力机制, 维纳过程

Abstract: Addresses the challenge of traditional physical models inadequately capturing nonlinear and time-varying degradation under complex operating conditions. A WP-LSTM-Attention method for predicting the Remaining Useful Life (RUL) of hollow cathodes under time-varying temperature control was developed. Firstly, A nonlinear time-varying Wiener Process (WP) model was established based on the hollow cathode’s emitter evaporation failure mechanism. Secondly, Long Short-Term Memory (LSTM) neural networks were employed to extract multi-source time-series features. The Multi-Head Attention Mechanism(MHAM) under temperature control was utilized to assign weights to degradation-sensitive features, enabling prediction of Wiener model parameters and degradation trends. Optimized parameter back propagation through a joint loss function achieved physics-data dual-driven updates. Finally, The Probability Density Function (PDF) of the RUL was derived using the first hitting time concept. The results demonstrated that, compared to single physical or data-driven models, the proposed model achieved a 22.81% reduction in Root Mean Square Error (RMSE) and an 18.11% reduction in Mean Absolute Error (MAE). These results validated the model’s effectiveness and accuracy for LaB6 hollow cathode life prediction in few-sample scenarios. The conclusion demonstrates that integrating physics with data-driven approaches significantly enhances prediction accuracy and robustness. This research provides a novel methodological pathway and technical support for lifetime prediction of LaB6 hollow cathodes.

Key words: hollow cathode, remaining useful life prediction, long short-term memory neural networks, multi-head attention mechanism, Wiener process