摘要
针对行星探测器进入段着陆过程中存在干扰影响着陆精度的问题,提出一种基于径向基(Radial Basis Function,RBF)神经网络的分数阶滑模控制方法。基于滑模控制设计探测器进入段轨迹跟踪控制方法,引入分数阶微积分缓解滑模控制产生的抖振,利用RBF神经网络对大气密度不确定干扰进行估计补偿,将该方法应用于火星着陆场景仿真。仿真结果表明:该控制方法能够在未知大气密度不确定干扰下,对探测器着陆轨迹进行精确跟踪,使得行星探测器高精度的到达开伞点,实现行星探测器稳定着陆。
A fractional order sliding mode control method based on Radial Basis Function(RBF)neural network is proposed to solve the landing accuracy being affected by the interference during the landing process of planetary probe.Based on sliding mode control,a trajectory tracking control method for the entry phase of the probe is designed.Fractional calculus is introduced to alleviate the chattering caused by sliding mode control.RBF neural network is used to estimate and compensate the atmospheric density uncertainty.The method is applied to Mars landing scene simulation.The simulation results show that the proposed control method can accurately track the landing trajectory of the probe under the interference of unknown atmospheric density and uncertainty,so that the planetary probe can reach the parachute opening point with high accuracy and achieve stable landing of the planetary probe.
作者
范存礼
戴娟
刘海涛
苏中
朱翠
徐文婷
Fan Cunli;Dai Juan;Liu Haitao;Su Zhong;Zhu Cui;Xu Wenting(University of Beijing Information Science&Technology Beijing Key Laboratory of High Dynamic Navigation Technology,Beijing 100192,China;Key Laboratory of Modern Measurement&Control Technology,Ministry of Education,Beijing 100192,China;School of Automation,Beijing Information Science&Technology University,Beijing 100192,China;School of Information and Communication Engineering,Beijing Information Science&Technology University,Beijing 100101,China;School of Mathematics and Statistics,Hefei Normal University,Hefei 230601,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2021年第11期2697-2703,共7页
Journal of System Simulation
基金
国家自然科学基金(61703040,61603047)
北京信息科技大学师资补充与支持计划(2019-2021,5029011103)
北京信息科技大学科研水平提高重点研究培育项目(2121YJPY221)
高动态导航技术北京市重点实验室(HDN2019001)
合肥师范学院省级科研平台专项项目(2020PT27)。
关键词
行星着陆
轨迹跟踪
径向基神经网络
分数阶微积分
滑模控制
planetary landing
trajectory tracking
radial basis function neural network
fractional calculus
sliding mode control