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.