期刊文献+

基于预设性能神经网络的智能鲁棒交会任务规划

Intelligent Robust Rendezvous Mission Planning Based on Prescribed Performance Neural Networks
下载PDF
导出
摘要 针对航天器空间交会过程中存在不确定性因素影响交会精度的问题,研究了一种基于长短时记忆(Long-Short Term Memory,LSTM)与预设性能控制(Prescribed Performance Control,PPC)理论的交会任务智能规划方法。建立了航天器交会相对运动模型,通过LSTM对非合作目标交会任务中的相对运动模型不确定因素进行辨识;采用PPC理论进行航天器交会任务规划,提高不确定性因素条件下的交会精度,通过仿真验证了方法的有效性。 To solve the problem of uncertainties affecting the accuracy of spacecraft’s space rendezvous mission,a rendezvous mission intelligent planning method based on Long-Short Term Memory(LSTM)and Prescribed Performance Control(PPC)theory is studied.Firstly,the relative motion model of spacecraft rendezvous is established.Then,the uncertain factors in the relative motion model of uncooperative targets in rendezvous task are identified through LSTM.Furthermore,the mission planning of spacecraft rendezvous is carried out by using the PPC to realize high-precision rendezvous under the condition of uncertainties.Finally,the effectiveness of the method is verified by simulation.
作者 靳锴 何文志 宗茂 李思男 JIN Kai;HE Wenzhi;ZONG Mao;LI Sinan(The 54th Research Institute of CETC,Shijiazhuang 050081,China;Key Laboratory of Hebei Province on Unmanned System Intelligent Telemetry & Telecontrol Information Technology,Shijiazhuang 050081,China)
出处 《无线电工程》 北大核心 2022年第7期1166-1171,共6页 Radio Engineering
基金 国家自然科学基金(62103446)。
关键词 非合作目标 不确定因素 预设性能控制 长短时记忆 交会任务规划 uncooperative targets uncertain factors PPC LSTM rendezvous mission planning
  • 相关文献

参考文献4

二级参考文献65

  • 1李德毅,刘常昱,杜鹢,韩旭.不确定性人工智能[J].软件学报,2004,15(11):1583-1594. 被引量:405
  • 2魏蛟龙,岑朝辉.基于蚁群算法的区域覆盖卫星星座优化设计[J].通信学报,2006,27(8):62-66. 被引量:16
  • 3Knight F H. Risk, uncertainty and profit[M]. New York: Hart, Schaffner and Marx, 1921: 55-58. 被引量:1
  • 4Bankes S C. Tools and techniques for developing policies for complex and uncertain systems[J]. Proc of the National Academy of Sciences of the United States of America, 2002, 99(S 3): 7263-7266. 被引量:1
  • 5Van der Pas J, Walker W E, Marchau V, et al. Exploratory MCDA for handling deep uncertainties: The case of intelligent speed adaptation implementation[J]. J of Multi-Criteria Decision Analysis, 2010, 17(1/2): 1-23. 被引量:1
  • 6Kwakkel J H, Walker W E, Marchau V A W J. From predictive modeling to exploratory modeling: How to use non-predictive models for decision making under deep uncertainty[C]. Proc of the 25th Mini-EURO Conf on Uncertainty and Robustness in Planning and Decision Making. Portugal, 2010: 1-10. 被引量:1
  • 7Agusdinata D B. Exploratory modeling and analysis: A promising method to deal with deep uncertainty[D]. Delft: Department of Policy and Management, Delft University of Technology, 2008. 被引量:1
  • 8Pruyt E, Kwakkel J, Yucel G, et al. Energy transitions towards sustainability: A staged exploration of complexity and deep uncertainty[C]. Proc of the 29th Int Conf on the System Dynamics Society. Washington, 2011: 1-26. 被引量:1
  • 9Kwakkel J H, Pruyt E. Exploratory modeling and analysis: An approach for model-based foresight under deep uncertainty[J]. Technological Forecasting and Social Change, 2013, 80(3): 419-431. 被引量:1
  • 10Lempert R J, Popper S W, Bankes S C. Shaping the next one hundred years: New methods for quantitative, longterm policy analysis[M]. Santa Monica: Rand Publishing, 2003: 39-66. 被引量:1

共引文献24

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部