基于量子遗传算法的RBF神经网络智能滤波组合导航算法
|
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.
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.
引文
[1] 高扬,高逦,乌萌,等.GPS/IMU/DMI组合导航方法研究[J].西北工业大学学报,2018:2.
[2] 金红新,杨涛,王小刚,等.多传感器信息融合理论在无人机相对导航中的应用[J].国防科技大学学报,2017(5):90-95.
[3] Nourmohammadi H,Keighobadi J.Fuzzy adaptive integration scheme for low-cost SINS/GPS navigation system[J].Mechanical Systems & Signal Processing,2018,99:434-449.
[4] Jiang J,Yu F,Lan H,et al.Instantaneous observability of tightly coupled SINS/GPS during maneuvers[J].Sensors,2016,16(6):765.
[5] Lim J,Shin M,Hwang W.Variants of extended Kalman filtering approaches for Bayesian tracking[J].International Journal of Robust & Nonlinear Control,2017,27(2):319-346.
[6] Huang Y,Zhang Y,Xu B,et al.A new adaptive extended kalman filter for cooperative localization[J].IEEE Transactions on Aerospace & Electronic Systems,2018,54(1):353-368.
[7] 高宗余,李德胜.神经网络在MEMS-IMU/GPS组合导航中的应用研究[J].传感技术学报,2009,22(9):1356-1360.
[8] 陈建勇,王树宗.基于RBF神经网络的组合导航融合算法[J].数据采集与处理,2006,21(2):198-202.
[9] 高运广,王仕成,刘志国,等.一种基于遗传RBF神经网络的智能容错滤波算法[J].宇航学报,2011,32(8):1 715-1 721.
[10] Sarra S A,Cogar S.An examination of evaluation algorithms for the RBF method[J].Engineering Analysis with Boundary Elements,2017,75:36-45.
[11] Oliveira L L D,Freitas A A,Tinós R.Multi-objective genetic algorithms in the study of the genetic code's adaptability[J].Information Sciences,2017,425C:48-61.
[12] Saitoh A,Rahimi R,Nakahara M.A quantum genetic algorithm with quantum crossover and mutation operations[J].Quantum Information Processing,2014,13(3):737-755.
[13] Alam T,Raza Z.Quantum genetic algorithm based scheduler for batch of precedence constrained jobs on heterogeneous computing systems[J].Journal of Systems & Software,2017,135(1):126-142.
[14] Zhang B,Chu H,Sun T,et al.Error prediction for SINS/GPS after GPS outage based on hybrid KF-UKF[J].Mathematical Problems in Engineering,2015(4):1-9.
[15] 黄显林,李明明,卢鸿谦,等.非线性地磁/GPS/SINS组合导航方法[J].哈尔滨工程大学学报,2010,31(10):1 340-1 347.
[16] Hu S,Xu S,Wang D,et al.Optimization algorithm for kalman filter exploiting the numerical characteristics of SINS/GPS integrated navigation systems[J].Sensors,2015,15(11):28 402-28 420.
[17] Gong X,Qin T.Airborne earth observation positioning and orientation by SINS/GPS integration using CD R-T-S smoothing[J].Journal of Navigation,2014,67(2):211-225.
[2] 金红新,杨涛,王小刚,等.多传感器信息融合理论在无人机相对导航中的应用[J].国防科技大学学报,2017(5):90-95.
[3] Nourmohammadi H,Keighobadi J.Fuzzy adaptive integration scheme for low-cost SINS/GPS navigation system[J].Mechanical Systems & Signal Processing,2018,99:434-449.
[4] Jiang J,Yu F,Lan H,et al.Instantaneous observability of tightly coupled SINS/GPS during maneuvers[J].Sensors,2016,16(6):765.
[5] Lim J,Shin M,Hwang W.Variants of extended Kalman filtering approaches for Bayesian tracking[J].International Journal of Robust & Nonlinear Control,2017,27(2):319-346.
[6] Huang Y,Zhang Y,Xu B,et al.A new adaptive extended kalman filter for cooperative localization[J].IEEE Transactions on Aerospace & Electronic Systems,2018,54(1):353-368.
[7] 高宗余,李德胜.神经网络在MEMS-IMU/GPS组合导航中的应用研究[J].传感技术学报,2009,22(9):1356-1360.
[8] 陈建勇,王树宗.基于RBF神经网络的组合导航融合算法[J].数据采集与处理,2006,21(2):198-202.
[9] 高运广,王仕成,刘志国,等.一种基于遗传RBF神经网络的智能容错滤波算法[J].宇航学报,2011,32(8):1 715-1 721.
[10] Sarra S A,Cogar S.An examination of evaluation algorithms for the RBF method[J].Engineering Analysis with Boundary Elements,2017,75:36-45.
[11] Oliveira L L D,Freitas A A,Tinós R.Multi-objective genetic algorithms in the study of the genetic code's adaptability[J].Information Sciences,2017,425C:48-61.
[12] Saitoh A,Rahimi R,Nakahara M.A quantum genetic algorithm with quantum crossover and mutation operations[J].Quantum Information Processing,2014,13(3):737-755.
[13] Alam T,Raza Z.Quantum genetic algorithm based scheduler for batch of precedence constrained jobs on heterogeneous computing systems[J].Journal of Systems & Software,2017,135(1):126-142.
[14] Zhang B,Chu H,Sun T,et al.Error prediction for SINS/GPS after GPS outage based on hybrid KF-UKF[J].Mathematical Problems in Engineering,2015(4):1-9.
[15] 黄显林,李明明,卢鸿谦,等.非线性地磁/GPS/SINS组合导航方法[J].哈尔滨工程大学学报,2010,31(10):1 340-1 347.
[16] Hu S,Xu S,Wang D,et al.Optimization algorithm for kalman filter exploiting the numerical characteristics of SINS/GPS integrated navigation systems[J].Sensors,2015,15(11):28 402-28 420.
[17] Gong X,Qin T.Airborne earth observation positioning and orientation by SINS/GPS integration using CD R-T-S smoothing[J].Journal of Navigation,2014,67(2):211-225.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |