| 基于时间序列分析的自适应联邦滤波算法 |
| |
| 引用本文： | 袁赣南,袁克非,张红伟,李宁.基于时间序列分析的自适应联邦滤波算法[J].中国惯性技术学报,2011(6). |
| |
| 作者姓名： | 袁赣南 袁克非 张红伟 李宁 |
| |
| 作者单位： | 哈尔滨工程大学自动化学院; |
| |
| 基金项目： | 国家自然科学基金(61001154) |
| |
| 摘 要： | 以信息源的视角审视联邦滤波信息分配系数的问题,提出基于时间序列分析的自适应联邦滤波算法。通过引入导航传感器历史数据作为信息基础,以自回归滑动平均模型对其进行分析,使信息分配系数与导航传感器工作状态和环境状态相适应,提高系统性能。将此算法应用于组合导航系统,通过仿真实验对比,新的算法比经典联邦滤波算法定位精度提高40%,比其他的自适应联邦滤波算法位置误差标准差、速度误差标准差分别平均提高19.74%和30.67%,说明该算法具有良好性能。
|
| 关 键 词： | 自适应联邦滤波 信息分配系数 自回归滑动平均模型 组合导航 |
Self-adaptive federated filter based on time series analysis |
| |
| YUAN Gan-nan,YUAN Ke-fei,ZHANG Hong-wei,LI Ning.Self-adaptive federated filter based on time series analysis[J].Journal of Chinese Inertial Technology,2011(6). |
| |
| Authors: | YUAN Gan-nan YUAN Ke-fei ZHANG Hong-wei LI Ning |
| |
| Institution: | YUAN Gan-nan,YUAN Ke-fei,ZHANG Hong-wei,LI Ning(College of Automation,Harbin Engineering University,Harbin 150001,China) |
| |
| Abstract: | From the perspective of information source,the problem of information sharing coefficient is studied,and a new adaptive federated filter algorithm based on autoregressive moving-average(ARMA) model is proposed in this paper.The history data of navigation sensors are considered and analyzed by ARMA model,thus the information sharing coefficient can be adjusted according to the working status and circumstances.The proposed method is implemented in the integrated navigation system,and simulations are performed... |
| |
| Keywords: | self-adaptive federated filter information sharing coefficient autoregressive moving-average model integrated navigation |
| 本文献已被 CNKI 等数据库收录！ |
|
