基于有色噪声自回归建模的惯性/卫星交互多模型滤波导航算法  

Interacting Multiple Model Filter Algorithm of the Inertial/GPS Integrated System Based on the Colored Noise Regression Modeling

作　　者：赖际舟[1,2] 柳敏[1,2] 李志敏[1,2] 刘建业[1,2] 

机构地区：[1]江苏省物联网与控制技术重点实验室,南京210016 [2]南京航空航天大学自动化学院导航研究中心,南京210016

出　　处：《导航定位与授时》2015年第6期19-24,共6页Navigation Positioning and Timing

基　　金：国家自然科学基金项目(61174197;61428303)

摘　　要：针对卫星量测噪声为有色噪声导致惯性/卫星组合导航系统滤波精度降低的问题,提出了一种基于有色噪声自回归建模的自适应交互多模型滤波算法。建立了有色噪声自回归模型,通过量测残差序列获取拟合模型系数,从而对称扩展得到系数模型集;并构建了交互多模型滤波框架,实现不同模型滤波器之间的数据融合。仿真结果表明,相比于传统卡尔曼滤波算法,该方法能有效改善有色噪声对滤波带来的影响并提高组合导航系统定位精度,具有较好的工程应用参考价值。Aiming at the problem that the filtering precision would degrade when the satellite measurement noise is the colored noise, a method of adaptive interacting multiple model filter algorithm based on the colored noise regression modeling is proposed. The regression model of the colored noise is established, and the fitting model coefficient is obtained from the measuring residual sequence which can be symmetric extended to be a coefficient model set. Interactive multiple model filtering framework is built to realize data fusion between different model filter. The simulation results show that the method can effectively reduce the impact of the colored noise to the filter, and improve the positioning accuracy of the integrated navigation system, so it has a great value of engineering reference.

关 键 词：组合导航 多模型滤波 量测扩增 有色噪声 卫星定位系统 

分 类 号：V249.3[航空宇航科学与技术—飞行器设计]