摘要
组合导航中标准卡尔曼滤波和扩展卡尔曼滤波存在容错性和鲁棒性不足,处理非线性信号能力较弱的缺点.提出了基于量子遗传算法的RBF神经网络的智能滤波组合导航算法,通过RBF神经网络调节卡尔曼滤波增益,而神经网络参数由量子遗传算法进行调整优化.对捷联惯导系统(SINS)/全球卫星定位系统(GPS)组合导航系统进行了仿真实验,结果表明:该算法提高了导航定位的精度、鲁棒性和可靠性.
Standard Kalman filtering and extended Kalman filtering in integrated navigation have shortcomings of fault tolerance and robustness,and their abilities processing nonlinear signal are weak.In this paper,an integrated navigation intelligent filtering algorithm based on RBF neural network by quantum genetic algorithm(QGA)is proposed,which regulates the Kalman filter gain through the RBF neural network,and the neural network parameters are adjusted and optimized by the quantum genetic algorithm.Then the simulation experiments of SINS/GPS integrated navigation system show that the quantum genetic RBF neural network algorithm improves the accuracy,robustness and reliability of navigation positioning.
作者
李云飞
李广飞
杨勇
谢康
代飞
曹涌
LI Yun-fei;LI Guang-fei;YANG Yong;XIE Kang;DAI Fei;CAO Yong(Wenshan Power Supply Bureau of Yunnan Power Grid Limited Liability,Wenshan 663000,China;School of Big Data and Intelligence Engineering,Southwest Forestry University,Kunming 650224,China)
出处
《云南大学学报（自然科学版）》
CAS
CSCD
北大核心
2019年第A01期21-26,共6页
Journal of Yunnan University(Natural Sciences Edition)
基金
国家自然科学基金(61462095,61702442)
云南省自然科学基金(2016FB102,2018FB105)
关键词
量子遗传算法
RBF神经网络
组合导航
quantum genetic algorithm
RBF neural network
Integrated navigation
作者简介
李云飞(1979-),男,云南人,高级工程师,主要从事电力调度自动化与信息化研究工作;通信作者:曹涌(1982-),男,博士,副教授,主要从事通信和网络优化研究.E-mail:cn_caoyong@126.com.
