您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2012, Vol. 42 ›› Issue (5): 12-17.

• 机器学习与数据挖掘 • 上一篇    下一篇

一种基于“当前”模型的改进卡尔曼滤波算法

兰义华,任浩征*,张勇,赵雪峰   

  1. 淮海工学院计算机工程学院, 江苏 连云港 222005
  • 收稿日期:2012-03-28 出版日期:2012-10-20 发布日期:2012-03-28
  • 通讯作者: 任浩征(1981- ),女,河北保定人,讲师,硕士,主要研究方向为图像处理与人工智能. E-mail: renhaozheng666@163.com
  • 作者简介:兰义华(1979- ),男,湖北仙桃人,讲师,博士,主要研究方向为图像处理与人工智能. E-mail: lanhua-2000@sina.com
  • 基金资助:
    国家自然科学基金资助项目(40806011);淮海工学院自然科学基金资助项目(Z2009013)

An improved Kalman filter algorithm based on the “current” model

LAN Yi-hua, REN Hao-zheng*, ZHANG Yong, ZHAO Xue-feng   

  1. School of Computer Engineering, Huaihai Institute of Technology, Lianyungang 222005, China
  • Received:2012-03-28 Online:2012-10-20 Published:2012-03-28

摘要: 针对“当前”模型中加速度上下限对卡尔曼算法造成的影响,提出了一种改进算法。该改进算法利用速度预测估计和速度滤波估计间的偏差进行加速度方差自适应调整,避免了加速度极限值对状态估计精度的影响。最后对具有不同加速度极限值参数的卡尔曼滤波算法进行了仿真,验证了加速度上下限对卡尔曼滤波算法精度有一定影响,并进一步对比了所提出的改进算法和基于“当前”模型的标准卡尔曼滤波算法的效果,结果表明改进算法的预测误差小,跟踪精度高。

关键词: “当前”模型;卡尔曼滤波, 自适应调整;状态估计

Abstract: An improved Kalman algorithm based on the “current” model was presented to avoid the influence of the acceleration limits. The difference between the velocity forecast estimate and the corrected velocity estimate was utilized to perform adaptive acceleration variance adjustment. The simulation of Kalman algorithms with different acceleration limit parameters proved that the performance of Kalman filter was influenced by the acceleration limits. In addition, the improved Kalman algorithm was compared with standard Kalman filter. The results showed that the proposed method forecast more accurately than the standard Kalman filter.

Key words: “current” model, Kalman filtering, adaptive adjust, state estimation

中图分类号: 

  • TN391
No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!