摘要
随着载人登月等航天任务的困难与挑战不断增加,对新型航天器研制的技术要求也越来越高,传统的经验模型和计算流体动力学(CFD)技术在复杂工况下存在局限性。针对多推进器压力预测在复杂工况下准确性和稳定性不足的问题,提出一种基于Transformer模型的压力预测方法。引入Transformer模型,对多推进器压力数据进行建模,通过稳健性分析和参数调校,提升模型预测准确性和稳定性,与LSTM方法相比,该方法在压力预测准确度上提高了16%。对改进下一代航天器的健康管理(PHM)技术,能够提升推进系统的设计和优化效率,增强航天器在复杂任务环境中的可靠性和安全性。
Addressing the issue of insufficient accuracy and stability in predicting pressure for multi-thruster systems under complex operating conditions,a pressure prediction method based on the transformer model was proposed.As challenges in space missions such as manned lunar exploration increase,the demand for advanced spacecraft development technologies rises accordingly.Traditional empirical models and computational fluid dynamics(CFD)face limitations in complex scenarios.This study introduced the Transformer model to model the pressure data of multiple thrusters.Through robustness analysis and parameter tuning,the accuracy and stability of the model s predictions were enhanced.Compared with the LSTM method,the proposed method in this study improved the accuracy of pressure prediction by 16%.This pressure prediction method had significant implications for improving the next-generation Prognostics and Health Management(PHM)technology of spacecraft and enhancing the efficiency of propulsion system design and optimization.It also had the potential to enhance the reliability and safety of spacecraft in complex mission environments.
作者
贾茹
JIA Ru(Institute of Spacecraft System Engineering,Beijing 100094,China)
出处
《探测与控制学报》
北大核心
2025年第3期127-134,共8页
Journal of Detection & Control
