一种色噪声下的自适应Kalman跟踪滤波器  

An Adaptive Kalman Tracking Filter with Colored Noises

作　　者：孙强[1,2] 惠晓滨[1] 黄鹤[3] 

机构地区：[1]空军工程大学,陕西西安710038 [2]空军装备部,北京100843 [3]西北工业大学,陕西西安710072

出　　处：《火力与指挥控制》2011年第3期49-51,共3页Fire Control & Command Control

基　　金：国家自然科学基金资助项目(60372085)

摘　　要：有色噪声干扰情况下非线性系统的状态估计是许多实际工程需要解决的问题。该文章针对传统Kalman滤波器噪声统计特性未知时,受色噪声的影响精度严重降低,甚至出现发散等现象,设计了一种基于神经模糊网络的自适应的Kalman滤波跟踪器。该滤波器通过利用神经模糊网络作为误差估计器,估计出Kalman滤波器的估计误差,从而对Kalman滤波跟踪器的预测结果进行修正,得到更优的预测值。计算机仿真结果表明,该算法可以克服传统算法的局限性,有效地防止滤波器发散,缩小实际的滤波误差,提高滤波精度,实现对跟踪结果的在线改进。Estimation in nonlinear system with Colored Noises is problem in many projects.The traditional Kalman Filter is still deficient in tracking targets in the nonlinear systems with colored noises.An adaptive Kalman tracking algorithm based on neuro-fuzzy network is proposed in the paper.The estimation error is obtained online to modify the filtered result with neuro-fuzzy network as the estimator.The analysis of simulation results indicates preliminarily that our better tracking algorithm does restrain colored noise and improve that tracking accuracy.At same time it can reduce error of traditional algorithm and improve the tracking accuracy of the system online.

关 键 词：KALMAN滤波 跟踪精度 神经模糊网络 计算机仿真 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]